Dr. rer. nat. Christian Schwartz

• A Comprehensive End-to-End Lag Model for Online and Cloud Video Gaming Metzger, Florian; Rafetseder, Albert; Schwartz, Christian in Proc. 5th ISCA/DEGA Workshop on Perceptual Quality of Systems (PQS 2016) (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  To further the knowledge of basic game mechanics and improve future video game Quality of Experience (QoE) studies we present a model and simulation for End-to-End (E2E) lag in networked and cloud computer games. E2E lag describes the latency between a user's action and the display of the action's results on the screen, thus providing both a basic measure for interactivity and a fundamental parameter to derived QoE metrics. In contrast to E2E lag models that focus on the network Round-Trip Time (RTT), the presented work also factors in the game's tickrate and framerate (and codec latencies in the case of cloud games). This reveals side effects that can entirely mask the network delay's contribution to the total lag, an important notion to consider for future game studies.

  @inproceedings{info3-inproceedings-2016-31, abstract = {To further the knowledge of basic game mechanics and improve future video game Quality of Experience (QoE) studies we present a model and simulation for End-to-End (E2E) lag in networked and cloud computer games. E2E lag describes the latency between a user's action and the display of the action's results on the screen, thus providing both a basic measure for interactivity and a fundamental parameter to derived QoE metrics. In contrast to E2E lag models that focus on the network Round-Trip Time (RTT), the presented work also factors in the game's tickrate and framerate (and codec latencies in the case of cloud games). This reveals side effects that can entirely mask the network delay's contribution to the total lag, an important notion to consider for future game studies.}, author = {Metzger, Florian and Rafetseder, Albert and Schwartz, Christian}, booktitle = {Proc. 5th ISCA/DEGA Workshop on Perceptual Quality of Systems (PQS 2016)}, keywords = {sys:hidden:inproceedings}, month = 8, title = {A Comprehensive End-to-End Lag Model for Online and Cloud Video Gaming}, year = 2016 }

  %0 Conference Paper %1 info3-inproceedings-2016-31 %A Metzger, Florian %A Rafetseder, Albert %A Schwartz, Christian %B Proc. 5th ISCA/DEGA Workshop on Perceptual Quality of Systems (PQS 2016) %D 2016 %T A Comprehensive End-to-End Lag Model for Online and Cloud Video Gaming %X To further the knowledge of basic game mechanics and improve future video game Quality of Experience (QoE) studies we present a model and simulation for End-to-End (E2E) lag in networked and cloud computer games. E2E lag describes the latency between a user's action and the display of the action's results on the screen, thus providing both a basic measure for interactivity and a fundamental parameter to derived QoE metrics. In contrast to E2E lag models that focus on the network Round-Trip Time (RTT), the presented work also factors in the game's tickrate and framerate (and codec latencies in the case of cloud games). This reveals side effects that can entirely mask the network delay's contribution to the total lag, an important notion to consider for future game studies.
• Games and frames: A strange tale of QoE studies Metzger, Florian; Rafetseder, Albert; Schwartz, Christian; Hoßfeld, Tobias in Eighth International Conference on Quality of Multimedia Experience (QoMEX) (2016).
  • [ BibTeX ]
  • [ EndNote ]
  @inproceedings{info3-inproceedings-2016-27, author = {Metzger, Florian and Rafetseder, Albert and Schwartz, Christian and Hoßfeld, Tobias}, booktitle = {Eighth International Conference on Quality of Multimedia Experience (QoMEX)}, keywords = {sys:hidden:inproceedings}, title = {Games and frames: A strange tale of QoE studies}, year = 2016 }

  %0 Conference Paper %1 info3-inproceedings-2016-27 %A Metzger, Florian %A Rafetseder, Albert %A Schwartz, Christian %A Hoßfeld, Tobias %B Eighth International Conference on Quality of Multimedia Experience (QoMEX) %D 2016 %T Games and frames: A strange tale of QoE studies
• Discrete-Time Analysis: Deriving the Distribution of the Number of Events in an Arbitrarily Distributed Interval Gebert, Steffen; Zinner, Thomas; Lange, Stanislav; Schwartz, Christian; Tran-Gia, Phuoc (2016).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @techreport{info3-techreport-2016-1, author = {Gebert, Steffen and Zinner, Thomas and Lange, Stanislav and Schwartz, Christian and Tran-Gia, Phuoc}, institution = {University of Wuerzburg}, keywords = {sys:hidden:techreport}, month = 6, number = 498, title = {Discrete-Time Analysis: Deriving the Distribution of the Number of Events in an Arbitrarily Distributed Interval}, year = 2016 }

  %0 Report %1 info3-techreport-2016-1 %A Gebert, Steffen %A Zinner, Thomas %A Lange, Stanislav %A Schwartz, Christian %A Tran-Gia, Phuoc %D 2016 %N 498 %T Discrete-Time Analysis: Deriving the Distribution of the Number of Events in an Arbitrarily Distributed Interval
• Assessing the Accuracy of Network Estimations in the DOTA 2 Game Client Hirth, Matthias; Allendorf, Fabian; Metzger, Florian; Schwartz, Christian in Workshop on Perceptual Quality of Systems (PQS) (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Online video games and the subjective quality of player inter- actions with them rely on good network conditions. Almost equally important is a good and timely knowledge of such conditions in order to take proper countermeasures to worsening conditions. To this end, many online video games include components for estimating the current network status. In this paper, we examine the accuracy of those estimations for the popular competitive multiplayer game DOTA 2. Our results show that the game client is capable of performing a good estimation of the delay and packet loss, but only after a rather large initial delay.

  @inproceedings{info3-inproceedings-2016-13, abstract = {Online video games and the subjective quality of player inter- actions with them rely on good network conditions. Almost equally important is a good and timely knowledge of such conditions in order to take proper countermeasures to worsening conditions. To this end, many online video games include components for estimating the current network status. In this paper, we examine the accuracy of those estimations for the popular competitive multiplayer game DOTA 2. Our results show that the game client is capable of performing a good estimation of the delay and packet loss, but only after a rather large initial delay.}, address = {Berlin, Germany}, author = {Hirth, Matthias and Allendorf, Fabian and Metzger, Florian and Schwartz, Christian}, booktitle = {Workshop on Perceptual Quality of Systems (PQS)}, keywords = {sys:hidden:inproceedings}, month = 8, title = {Assessing the Accuracy of Network Estimations in the DOTA 2 Game Client}, year = 2016 }

  %0 Conference Paper %1 info3-inproceedings-2016-13 %A Hirth, Matthias %A Allendorf, Fabian %A Metzger, Florian %A Schwartz, Christian %B Workshop on Perceptual Quality of Systems (PQS) %C Berlin, Germany %D 2016 %T Assessing the Accuracy of Network Estimations in the DOTA 2 Game Client %X Online video games and the subjective quality of player inter- actions with them rely on good network conditions. Almost equally important is a good and timely knowledge of such conditions in order to take proper countermeasures to worsening conditions. To this end, many online video games include components for estimating the current network status. In this paper, we examine the accuracy of those estimations for the popular competitive multiplayer game DOTA 2. Our results show that the game client is capable of performing a good estimation of the delay and packet loss, but only after a rather large initial delay.
• Performance Modeling of Softwarized Network Functions Using Discrete-Time Analysis Gebert, Steffen; Zinner, Thomas; Lange, Stanislav; Schwartz, Christian; Tran-Gia, Phuoc in 28th International Teletraffic Congress (ITC) (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  The softwarization of networks promises cost savings and better scalability of network functions by moving functionality from specialized devices into commercial off-the-shelf hardware. Generalized computing hardware offers many degrees for adjustment and tuning, which can affect performance and resource utilization. One of these adjustments are the interrupt mitigation techniques implemented by modern network interface cards and operating systems. Using these, an administrator can optimize either lower latencies or lower CPU overhead for processing of network traffic. In this work, an analytical model that allows computing relevant performance metrics like the packet processing time and the packet loss for generic virtualized network functions running on commodity hardware is developed. The applicability of the model is shown by comparing its outcome with measurements conducted in a local testbed. Based on this model, impact factors like the average packet interarrival time, the interarrival time distribution, and the duration of the interrupt aggregation interval are studied.

  @inproceedings{info3-inproceedings-2016-4, abstract = {The softwarization of networks promises cost savings and better scalability of network functions by moving functionality from specialized devices into commercial off-the-shelf hardware. Generalized computing hardware offers many degrees for adjustment and tuning, which can affect performance and resource utilization. One of these adjustments are the interrupt mitigation techniques implemented by modern network interface cards and operating systems. Using these, an administrator can optimize either lower latencies or lower CPU overhead for processing of network traffic. In this work, an analytical model that allows computing relevant performance metrics like the packet processing time and the packet loss for generic virtualized network functions running on commodity hardware is developed. The applicability of the model is shown by comparing its outcome with measurements conducted in a local testbed. Based on this model, impact factors like the average packet interarrival time, the interarrival time distribution, and the duration of the interrupt aggregation interval are studied.}, address = {Würzburg, Germany}, author = {Gebert, Steffen and Zinner, Thomas and Lange, Stanislav and Schwartz, Christian and Tran-Gia, Phuoc}, booktitle = {28th International Teletraffic Congress (ITC)}, keywords = {sendate}, month = 9, title = {Performance Modeling of Softwarized Network Functions Using Discrete-Time Analysis}, year = 2016 }

  %0 Conference Paper %1 info3-inproceedings-2016-4 %A Gebert, Steffen %A Zinner, Thomas %A Lange, Stanislav %A Schwartz, Christian %A Tran-Gia, Phuoc %B 28th International Teletraffic Congress (ITC) %C Würzburg, Germany %D 2016 %T Performance Modeling of Softwarized Network Functions Using Discrete-Time Analysis %X The softwarization of networks promises cost savings and better scalability of network functions by moving functionality from specialized devices into commercial off-the-shelf hardware. Generalized computing hardware offers many degrees for adjustment and tuning, which can affect performance and resource utilization. One of these adjustments are the interrupt mitigation techniques implemented by modern network interface cards and operating systems. Using these, an administrator can optimize either lower latencies or lower CPU overhead for processing of network traffic. In this work, an analytical model that allows computing relevant performance metrics like the packet processing time and the packet loss for generic virtualized network functions running on commodity hardware is developed. The applicability of the model is shown by comparing its outcome with measurements conducted in a local testbed. Based on this model, impact factors like the average packet interarrival time, the interarrival time distribution, and the duration of the interrupt aggregation interval are studied.
• Load Dynamics of a Multiplayer Online Battle Area and Simulative Assessment of Edge Server Placements Burger, Valentin; Frances Pajo, Jane; Sanchez, Odnan Ref; Seufert, Michael; Schwartz, Christian; Wamser, Florian; Davoli, Franco; Tran-Gia, Phuoc in ACM Multimedia Systems Conference (MMSys) (2016).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Free-to-play models, streaming of games and eSports are reasons for online gaming to grow in popularity recently. On the forefront are multiplayer online battle arenas, which gain high popularity by introducing a competitive format that is easy to access and requires cooperation and team play. These games highly rely on fast reaction of the players, which makes latency the key performance indicator of such applications. To obtain low latency, this paper proposes moving game servers close to players towards the edge of the network. The performance of such mechanism highly depends on the geographic distribution of players. By analyzing match histories and statistics, we develop models for the arrival process and location of game requests. This allows us to evaluate the performance of edge server resource migration policies in an event based simulation. Our results show that a high number of edge servers is preferable compared to few larger edge servers to reduce the latency of players. This supports approaches that allow deploying virtual server instances in the back-haul.

  @inproceedings{info3-inproceedings-2016-2, abstract = {Free-to-play models, streaming of games and eSports are reasons for online gaming to grow in popularity recently. On the forefront are multiplayer online battle arenas, which gain high popularity by introducing a competitive format that is easy to access and requires cooperation and team play. These games highly rely on fast reaction of the players, which makes latency the key performance indicator of such applications. To obtain low latency, this paper proposes moving game servers close to players towards the edge of the network. The performance of such mechanism highly depends on the geographic distribution of players. By analyzing match histories and statistics, we develop models for the arrival process and location of game requests. This allows us to evaluate the performance of edge server resource migration policies in an event based simulation. Our results show that a high number of edge servers is preferable compared to few larger edge servers to reduce the latency of players. This supports approaches that allow deploying virtual server instances in the back-haul.}, address = {Klagenfurt, Austria}, author = {Burger, Valentin and Frances Pajo, Jane and Sanchez, Odnan Ref and Seufert, Michael and Schwartz, Christian and Wamser, Florian and Davoli, Franco and Tran-Gia, Phuoc}, booktitle = {ACM Multimedia Systems Conference (MMSys)}, keywords = {can}, month = 5, title = {Load Dynamics of a Multiplayer Online Battle Area and Simulative Assessment of Edge Server Placements}, year = 2016 }

  %0 Conference Paper %1 info3-inproceedings-2016-2 %A Burger, Valentin %A Frances Pajo, Jane %A Sanchez, Odnan Ref %A Seufert, Michael %A Schwartz, Christian %A Wamser, Florian %A Davoli, Franco %A Tran-Gia, Phuoc %B ACM Multimedia Systems Conference (MMSys) %C Klagenfurt, Austria %D 2016 %T Load Dynamics of a Multiplayer Online Battle Area and Simulative Assessment of Edge Server Placements %X Free-to-play models, streaming of games and eSports are reasons for online gaming to grow in popularity recently. On the forefront are multiplayer online battle arenas, which gain high popularity by introducing a competitive format that is easy to access and requires cooperation and team play. These games highly rely on fast reaction of the players, which makes latency the key performance indicator of such applications. To obtain low latency, this paper proposes moving game servers close to players towards the edge of the network. The performance of such mechanism highly depends on the geographic distribution of players. By analyzing match histories and statistics, we develop models for the arrival process and location of game requests. This allows us to evaluate the performance of edge server resource migration policies in an event based simulation. Our results show that a high number of edge servers is preferable compared to few larger edge servers to reduce the latency of players. This supports approaches that allow deploying virtual server instances in the back-haul.
• Modeling and Evaluation of Multi-Stakeholder Scenarios in Communication Networks Schwartz, Christian PhD thesis, University of Wuerzburg. (2016, April).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @phdthesis{info3-dissertation-2016-1, author = {Schwartz, Christian}, keywords = {sys:hidden:supervisor:phuoc.tran-gia}, month = 4, school = {University of Wuerzburg}, title = {Modeling and Evaluation of Multi-Stakeholder Scenarios in Communication Networks}, year = 2016 }

  %0 Thesis %1 info3-dissertation-2016-1 %A Schwartz, Christian %D 2016 %T Modeling and Evaluation of Multi-Stakeholder Scenarios in Communication Networks

• Agile Management of Software Based Networks Gebert, Steffen; Schwartz, Christian; Zinner, Thomas; Tran-Gia, Phuoc (2015).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @techreport{info3-techreport-2015-267, author = {Gebert, Steffen and Schwartz, Christian and Zinner, Thomas and Tran-Gia, Phuoc}, institution = {University of Wuerzburg}, keywords = {sys:hidden:techreport}, month = 1, number = 493, title = {Agile Management of Software Based Networks}, year = 2015 }

  %0 Report %1 info3-techreport-2015-267 %A Gebert, Steffen %A Schwartz, Christian %A Zinner, Thomas %A Tran-Gia, Phuoc %D 2015 %N 493 %T Agile Management of Software Based Networks
• Crowdsourced Network Measurements: Benefits and Best Practices Hirth, Matthias; Hoßfeld, Tobias; Mellia, Marco; Schwartz, Christian; Lehrieder, Frank in Computer Networks Special Issue on Crowdsourcing (2015).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Network measurements are of high importance both for the operation of networks and for the design and evaluation of new management mechanisms. Therefore, several approaches exist for running network measurements, ranging from analyzing live traffic traces from campus or Internet Service Provider (ISP) networks to performing active measurements on distributed testbeds, e.g., PlanetLab, or involving volunteers. However, each method falls short, offering only a partial view of the network. For instance, the scope of passive traffic traces is limited to an ISP’s network and customers’ habits, whereas active measurements might be biased by the population or node location involved. To complement these techniques, we pro- pose to use (commercial) crowdsourcing platforms for network measurements. They permit a controllable, diverse and realistic view of the Internet and pro- vide better control than do measurements with voluntary participants. In this study, we compare crowdsourcing with traditional measurement techniques, describe possible pitfalls and limitations, and present best practices to overcome these issues. The contribution of this paper is a guideline for researchers to understand when and how to exploit crowdsourcing for network measurements.

  @article{info3-article-2015-135, abstract = {Network measurements are of high importance both for the operation of networks and for the design and evaluation of new management mechanisms. Therefore, several approaches exist for running network measurements, ranging from analyzing live traffic traces from campus or Internet Service Provider (ISP) networks to performing active measurements on distributed testbeds, e.g., PlanetLab, or involving volunteers. However, each method falls short, offering only a partial view of the network. For instance, the scope of passive traffic traces is limited to an ISP’s network and customers’ habits, whereas active measurements might be biased by the population or node location involved. To complement these techniques, we pro- pose to use (commercial) crowdsourcing platforms for network measurements. They permit a controllable, diverse and realistic view of the Internet and pro- vide better control than do measurements with voluntary participants. In this study, we compare crowdsourcing with traditional measurement techniques, describe possible pitfalls and limitations, and present best practices to overcome these issues. The contribution of this paper is a guideline for researchers to understand when and how to exploit crowdsourcing for network measurements.}, author = {Hirth, Matthias and Hoßfeld, Tobias and Mellia, Marco and Schwartz, Christian and Lehrieder, Frank}, journal = {Computer Networks Special Issue on Crowdsourcing}, keywords = {sys:hidden:article}, title = {Crowdsourced Network Measurements: Benefits and Best Practices}, year = 2015 }

  %0 Journal Article %1 info3-article-2015-135 %A Hirth, Matthias %A Hoßfeld, Tobias %A Mellia, Marco %A Schwartz, Christian %A Lehrieder, Frank %D 2015 %J Computer Networks Special Issue on Crowdsourcing %T Crowdsourced Network Measurements: Benefits and Best Practices %X Network measurements are of high importance both for the operation of networks and for the design and evaluation of new management mechanisms. Therefore, several approaches exist for running network measurements, ranging from analyzing live traffic traces from campus or Internet Service Provider (ISP) networks to performing active measurements on distributed testbeds, e.g., PlanetLab, or involving volunteers. However, each method falls short, offering only a partial view of the network. For instance, the scope of passive traffic traces is limited to an ISP’s network and customers’ habits, whereas active measurements might be biased by the population or node location involved. To complement these techniques, we pro- pose to use (commercial) crowdsourcing platforms for network measurements. They permit a controllable, diverse and realistic view of the Internet and pro- vide better control than do measurements with voluntary participants. In this study, we compare crowdsourcing with traditional measurement techniques, describe possible pitfalls and limitations, and present best practices to overcome these issues. The contribution of this paper is a guideline for researchers to understand when and how to exploit crowdsourcing for network measurements.
• To Each According to his Needs: Dimensioning Video Buffer for Specific User Profiles and Behavior Hoßfeld, Tobias; Moldovan, Christian; Schwartz, Christian in Third IFIP/IEEE International Workshop on Quality of Experience Centric Management (2015).
  • [ BibTeX ]
  • [ EndNote ]
  @inproceedings{info3-inproceedings-2015-35, address = {Ottawa, Canada}, author = {Hoßfeld, Tobias and Moldovan, Christian and Schwartz, Christian}, booktitle = {Third IFIP/IEEE International Workshop on Quality of Experience Centric Management}, keywords = {sys:hidden:inproceedings}, month = 5, title = {To Each According to his Needs: Dimensioning Video Buffer for Specific User Profiles and Behavior}, year = 2015 }

  %0 Conference Paper %1 info3-inproceedings-2015-35 %A Hoßfeld, Tobias %A Moldovan, Christian %A Schwartz, Christian %B Third IFIP/IEEE International Workshop on Quality of Experience Centric Management %C Ottawa, Canada %D 2015 %T To Each According to his Needs: Dimensioning Video Buffer for Specific User Profiles and Behavior
• Analyzing the Impact of Delay and Packet Loss on Google Docs Dinh-Xuan, Lam; Schwartz, Christian; Hirth, Matthias; Wamser, Florian; Truong Thu, Huong in 7th International Conference on Mobile Networks and Management (2015).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Software as a Service allows end users to use complex soft- ware directly from their browsers, transferring heavy computation to servers in the cloud. One use of this paradigm is word processing, former a classic use cases of Thin-Client computing. Similar to Thin-Client systems, the network parameters are an important influence factor for the cloud application performance. In this paper, we study Google Docs as an example for online word processing tools. We consider a traditional single user scenario as well as a collaborative scenario with two users working on one document simultaneously. We identify multiple relevant sub-processes per scenario as performance metrics and use a testbed to automatically evaluate the performance of Google Docs under varying network parameters. The main contributions of the paper are (1) the quantification of the impact of network parameters such as delay and packet loss on application performance metrics for both scenarios and (2) linear regression models to derive the application performance for giving network parameters.

  @inproceedings{info3-inproceedings-2015-522, abstract = {Software as a Service allows end users to use complex soft- ware directly from their browsers, transferring heavy computation to servers in the cloud. One use of this paradigm is word processing, former a classic use cases of Thin-Client computing. Similar to Thin-Client systems, the network parameters are an important influence factor for the cloud application performance. In this paper, we study Google Docs as an example for online word processing tools. We consider a traditional single user scenario as well as a collaborative scenario with two users working on one document simultaneously. We identify multiple relevant sub-processes per scenario as performance metrics and use a testbed to automatically evaluate the performance of Google Docs under varying network parameters. The main contributions of the paper are (1) the quantification of the impact of network parameters such as delay and packet loss on application performance metrics for both scenarios and (2) linear regression models to derive the application performance for giving network parameters.}, address = {Santander, Spain}, author = {Dinh-Xuan, Lam and Schwartz, Christian and Hirth, Matthias and Wamser, Florian and Truong Thu, Huong}, booktitle = {7th International Conference on Mobile Networks and Management}, keywords = {can}, month = 9, title = {Analyzing the Impact of Delay and Packet Loss on Google Docs}, year = 2015 }

  %0 Conference Paper %1 info3-inproceedings-2015-522 %A Dinh-Xuan, Lam %A Schwartz, Christian %A Hirth, Matthias %A Wamser, Florian %A Truong Thu, Huong %B 7th International Conference on Mobile Networks and Management %C Santander, Spain %D 2015 %T Analyzing the Impact of Delay and Packet Loss on Google Docs %X Software as a Service allows end users to use complex soft- ware directly from their browsers, transferring heavy computation to servers in the cloud. One use of this paradigm is word processing, former a classic use cases of Thin-Client computing. Similar to Thin-Client systems, the network parameters are an important influence factor for the cloud application performance. In this paper, we study Google Docs as an example for online word processing tools. We consider a traditional single user scenario as well as a collaborative scenario with two users working on one document simultaneously. We identify multiple relevant sub-processes per scenario as performance metrics and use a testbed to automatically evaluate the performance of Google Docs under varying network parameters. The main contributions of the paper are (1) the quantification of the impact of network parameters such as delay and packet loss on application performance metrics for both scenarios and (2) linear regression models to derive the application performance for giving network parameters.
• Modeling Crowdsourcing Platforms to Enable Workforce Dimensioning Schwartz, Christian; Borchert, Kathrin; Hirth, Matthias; Tran-Gia, Phuoc in International Telecommunication Networks and Applications Conference (2015).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Crowdsourcing platforms provide an easy and scalable access to human workforce that can, e.g., provide subjective judgements, tagging information, or even generate knowledge. In conjunction with machine clouds offering scalable access to computing resources, these human cloud provider offer numerous possibilities for creating new applications which would not have been possible a few years ago. However, in order to build sustainable services on top of this inter-cloud environment, scalability considerations have to be made. While cloud computing systems are already well studied in terms of dimensioning of the hardware resources, there still exists little work on the appropriate scaling of crowdsourcing platforms. This is especially challenging, as the complex interaction between all involved stakeholders, platform providers, workers and employers have to be considered. The contribution of this work is threefold. First we develop a model for common crowdsourcing platforms and implement the model using a simulative approach, which is validated with a comparison to an analytic M[X]/M/c − ∞ system. In a second step we evaluate inter-arrival times as well as campaign size distributions based on a dataset of a large commercial crowdsourcing platform to derive realistic model parameters and illustrate the differences to the analytic approximation. Finally, we perform a parameter study using the simulation model to derive guidelines for dimensioning crowdsourcing platforms, while considering relevant parameters for the involved stakeholders, i.e., the delay before work on a task begins and the work load of the workers.

  @inproceedings{info3-inproceedings-2015-529, abstract = {Crowdsourcing platforms provide an easy and scalable access to human workforce that can, e.g., provide subjective judgements, tagging information, or even generate knowledge. In conjunction with machine clouds offering scalable access to computing resources, these human cloud provider offer numerous possibilities for creating new applications which would not have been possible a few years ago. However, in order to build sustainable services on top of this inter-cloud environment, scalability considerations have to be made. While cloud computing systems are already well studied in terms of dimensioning of the hardware resources, there still exists little work on the appropriate scaling of crowdsourcing platforms. This is especially challenging, as the complex interaction between all involved stakeholders, platform providers, workers and employers have to be considered. The contribution of this work is threefold. First we develop a model for common crowdsourcing platforms and implement the model using a simulative approach, which is validated with a comparison to an analytic M[X]/M/c − ∞ system. In a second step we evaluate inter-arrival times as well as campaign size distributions based on a dataset of a large commercial crowdsourcing platform to derive realistic model parameters and illustrate the differences to the analytic approximation. Finally, we perform a parameter study using the simulation model to derive guidelines for dimensioning crowdsourcing platforms, while considering relevant parameters for the involved stakeholders, i.e., the delay before work on a task begins and the work load of the workers.}, address = {Sydney, Australia}, author = {Schwartz, Christian and Borchert, Kathrin and Hirth, Matthias and Tran-Gia, Phuoc}, booktitle = {International Telecommunication Networks and Applications Conference}, keywords = {crowdsourcing-design}, month = 11, title = {Modeling Crowdsourcing Platforms to Enable Workforce Dimensioning}, year = 2015 }

  %0 Conference Paper %1 info3-inproceedings-2015-529 %A Schwartz, Christian %A Borchert, Kathrin %A Hirth, Matthias %A Tran-Gia, Phuoc %B International Telecommunication Networks and Applications Conference %C Sydney, Australia %D 2015 %T Modeling Crowdsourcing Platforms to Enable Workforce Dimensioning %X Crowdsourcing platforms provide an easy and scalable access to human workforce that can, e.g., provide subjective judgements, tagging information, or even generate knowledge. In conjunction with machine clouds offering scalable access to computing resources, these human cloud provider offer numerous possibilities for creating new applications which would not have been possible a few years ago. However, in order to build sustainable services on top of this inter-cloud environment, scalability considerations have to be made. While cloud computing systems are already well studied in terms of dimensioning of the hardware resources, there still exists little work on the appropriate scaling of crowdsourcing platforms. This is especially challenging, as the complex interaction between all involved stakeholders, platform providers, workers and employers have to be considered. The contribution of this work is threefold. First we develop a model for common crowdsourcing platforms and implement the model using a simulative approach, which is validated with a comparison to an analytic M[X]/M/c − ∞ system. In a second step we evaluate inter-arrival times as well as campaign size distributions based on a dataset of a large commercial crowdsourcing platform to derive realistic model parameters and illustrate the differences to the analytic approximation. Finally, we perform a parameter study using the simulation model to derive guidelines for dimensioning crowdsourcing platforms, while considering relevant parameters for the involved stakeholders, i.e., the delay before work on a task begins and the work load of the workers.
• Continuously Delivering Your Network (Short Paper) Gebert, Steffen; Schwartz, Christian; Zinner, Thomas; Tran-Gia, Phuoc in IEEE/IFIP International Symposium on Integrated Network Management (IM) (2015).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Softwarization and cloudification of networks through software defined networking and network functions virtualisation promise a new degree of flexibility and agility. By moving logic from device firmware into software applications and applying software development mechanisms, innovation can be introduced with less effort. Concrete ways how to operate and orchestrate such systems are not yet defined. The process of making changes to a controller software or a virtualized network function in a production network without the risk of network disruption is not covered by literature. Complexity of systems brings the risk of unexpected side-effects and has so long been a show-stopper for administrators applying changes to networking devices. This paper suggests the adaption of the successful concept of continuous delivery into the software defined networking world. Test-driven development and automatic acceptance tests demonstrate that the software engineering community already found ways to ensure that changes do not break. Applied to network engineering, the adaption of continuous delivery can be seen as an enabler for risk-free and frequent changes in production infrastructure through push button deployments.

  @inproceedings{info3-inproceedings-2015-512, abstract = {Softwarization and cloudification of networks through software defined networking and network functions virtualisation promise a new degree of flexibility and agility. By moving logic from device firmware into software applications and applying software development mechanisms, innovation can be introduced with less effort. Concrete ways how to operate and orchestrate such systems are not yet defined. The process of making changes to a controller software or a virtualized network function in a production network without the risk of network disruption is not covered by literature. Complexity of systems brings the risk of unexpected side-effects and has so long been a show-stopper for administrators applying changes to networking devices. This paper suggests the adaption of the successful concept of continuous delivery into the software defined networking world. Test-driven development and automatic acceptance tests demonstrate that the software engineering community already found ways to ensure that changes do not break. Applied to network engineering, the adaption of continuous delivery can be seen as an enabler for risk-free and frequent changes in production infrastructure through push button deployments.}, address = {Ottawa, Canada}, author = {Gebert, Steffen and Schwartz, Christian and Zinner, Thomas and Tran-Gia, Phuoc}, booktitle = {IEEE/IFIP International Symposium on Integrated Network Management (IM)}, keywords = {saser-siegfried}, month = 5, title = {Continuously Delivering Your Network (Short Paper)}, year = 2015 }

  %0 Conference Paper %1 info3-inproceedings-2015-512 %A Gebert, Steffen %A Schwartz, Christian %A Zinner, Thomas %A Tran-Gia, Phuoc %B IEEE/IFIP International Symposium on Integrated Network Management (IM) %C Ottawa, Canada %D 2015 %T Continuously Delivering Your Network (Short Paper) %X Softwarization and cloudification of networks through software defined networking and network functions virtualisation promise a new degree of flexibility and agility. By moving logic from device firmware into software applications and applying software development mechanisms, innovation can be introduced with less effort. Concrete ways how to operate and orchestrate such systems are not yet defined. The process of making changes to a controller software or a virtualized network function in a production network without the risk of network disruption is not covered by literature. Complexity of systems brings the risk of unexpected side-effects and has so long been a show-stopper for administrators applying changes to networking devices. This paper suggests the adaption of the successful concept of continuous delivery into the software defined networking world. Test-driven development and automatic acceptance tests demonstrate that the software engineering community already found ways to ensure that changes do not break. Applied to network engineering, the adaption of continuous delivery can be seen as an enabler for risk-free and frequent changes in production infrastructure through push button deployments.
• Continuously Delivering Your Network Gebert, Steffen; Schwartz, Christian; Zinner, Thomas; Tran-Gia, Phuoc (2015, May).
  • [ BibTeX ]
  • [ EndNote ]
  @misc{info3-poster-2015-37, address = {Ottawa, Canada}, author = {Gebert, Steffen and Schwartz, Christian and Zinner, Thomas and Tran-Gia, Phuoc}, booktitle = {IEEE/IFIP International Symposium on Integrated Network Management (IM)}, keywords = {sys:hidden:poster}, month = 5, title = {Continuously Delivering Your Network}, year = 2015 }

  %0 Generic %1 info3-poster-2015-37 %A Gebert, Steffen %A Schwartz, Christian %A Zinner, Thomas %A Tran-Gia, Phuoc %B IEEE/IFIP International Symposium on Integrated Network Management (IM) %C Ottawa, Canada %D 2015 %T Continuously Delivering Your Network

• GTP-based Load Model and Virtualization Gain for a Mobile Network’s GGSN Metzger, Florian; Schwartz, Christian; Hoßfeld, Tobias in 5th International Conference on Communications and Electronics (2014).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Multiple outages in major mobile networks have been reported in the recent past. In fixed and datacenter networks, such capacity problems are solved by scaling out, i.e. purchasing additional hardware. In mobile networks this is not easily possible as network components are usually sold as sealed middleboxes. With the advances in server performance and SDN it has been suggested to virtualize these boxes. This also opens up opportunities to dimension according to current load and save energy by switching off parts of the infrastructure. Such suggestions immediately raise the question on the cost of virtualization. To answer this question, we introduce models for both a traditional as well as a virtualized GGSN. In addition, we provide distributions for the load experienced at the GGSN based on network measurements. With this at hand, we study the influence of different dimensioning parameters on important performance metrics, with special consideration for the impact of provisioning new instances for the virtual GGSN.

  @inproceedings{info3-inproceedings-2014-497, abstract = {Multiple outages in major mobile networks have been reported in the recent past. In fixed and datacenter networks, such capacity problems are solved by scaling out, i.e. purchasing additional hardware. In mobile networks this is not easily possible as network components are usually sold as sealed middleboxes. With the advances in server performance and SDN it has been suggested to virtualize these boxes. This also opens up opportunities to dimension according to current load and save energy by switching off parts of the infrastructure. Such suggestions immediately raise the question on the cost of virtualization. To answer this question, we introduce models for both a traditional as well as a virtualized GGSN. In addition, we provide distributions for the load experienced at the GGSN based on network measurements. With this at hand, we study the influence of different dimensioning parameters on important performance metrics, with special consideration for the impact of provisioning new instances for the virtual GGSN.}, address = {Da Nang, Vietnam}, author = {Metzger, Florian and Schwartz, Christian and Hoßfeld, Tobias}, booktitle = {5th International Conference on Communications and Electronics}, keywords = {sys:hidden:inproceedings}, month = 7, title = {GTP-based Load Model and Virtualization Gain for a Mobile Network's GGSN}, year = 2014 }

  %0 Conference Paper %1 info3-inproceedings-2014-497 %A Metzger, Florian %A Schwartz, Christian %A Hoßfeld, Tobias %B 5th International Conference on Communications and Electronics %C Da Nang, Vietnam %D 2014 %T GTP-based Load Model and Virtualization Gain for a Mobile Network's GGSN %X Multiple outages in major mobile networks have been reported in the recent past. In fixed and datacenter networks, such capacity problems are solved by scaling out, i.e. purchasing additional hardware. In mobile networks this is not easily possible as network components are usually sold as sealed middleboxes. With the advances in server performance and SDN it has been suggested to virtualize these boxes. This also opens up opportunities to dimension according to current load and save energy by switching off parts of the infrastructure. Such suggestions immediately raise the question on the cost of virtualization. To answer this question, we introduce models for both a traditional as well as a virtualized GGSN. In addition, we provide distributions for the load experienced at the GGSN based on network measurements. With this at hand, we study the influence of different dimensioning parameters on important performance metrics, with special consideration for the impact of provisioning new instances for the virtual GGSN.
• Predicting Result Quality in Crowdsourcing Using Application Layer Monitoring Hirth, Matthias; Scheuring, Sven; Hoßfeld, Tobias; Schwartz, Christian; Tran-Gia, Phuoc in 5th International Conference on Communications and Electronics (ICCE 2014) (2014).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Crowdsourcing has become a valuable tool for many business applications requiring to meet a certain quality of the results generated by the workers. Therefore, several quality assurance mechanisms have been developed which are partly deployed in commercial crowdsourcing platforms. However, these mechanisms usually impose additional work overhead for the worker, e.g. by adding test questions, or increase the costs for the employer, e.g. by replicating the task for majority decisions. In this work, we analyze the applicability of implicit measurements to objectively estimate the quality of the workers' results. First efforts in this area have already been made by investigating the impact of the task completion time. We extend this research by deploying an application layer monitoring (ALM), which enables monitoring the workers' interactions with our task interface on a much more detailed level. Based on an exemplary use case, we discuss a possible implementation and demonstrate the potential of the approach by predicting the quality of the workers' submission based on our monitoring results. This ALM provides a new way to identify low quality work as well as difficulties in fulfilling the formulated tasks in the domain of Crowdsourcing.

  @inproceedings{info3-inproceedings-2014-494, abstract = {Crowdsourcing has become a valuable tool for many business applications requiring to meet a certain quality of the results generated by the workers. Therefore, several quality assurance mechanisms have been developed which are partly deployed in commercial crowdsourcing platforms. However, these mechanisms usually impose additional work overhead for the worker, e.g. by adding test questions, or increase the costs for the employer, e.g. by replicating the task for majority decisions. In this work, we analyze the applicability of implicit measurements to objectively estimate the quality of the workers' results. First efforts in this area have already been made by investigating the impact of the task completion time. We extend this research by deploying an application layer monitoring (ALM), which enables monitoring the workers' interactions with our task interface on a much more detailed level. Based on an exemplary use case, we discuss a possible implementation and demonstrate the potential of the approach by predicting the quality of the workers' submission based on our monitoring results. This ALM provides a new way to identify low quality work as well as difficulties in fulfilling the formulated tasks in the domain of Crowdsourcing.}, address = {Da Nang, Vietnam}, author = {Hirth, Matthias and Scheuring, Sven and Hoßfeld, Tobias and Schwartz, Christian and Tran-Gia, Phuoc}, booktitle = {5th International Conference on Communications and Electronics (ICCE 2014)}, keywords = {crowdsourcing-design}, month = 7, title = {Predicting Result Quality in Crowdsourcing Using Application Layer Monitoring}, year = 2014 }

  %0 Conference Paper %1 info3-inproceedings-2014-494 %A Hirth, Matthias %A Scheuring, Sven %A Hoßfeld, Tobias %A Schwartz, Christian %A Tran-Gia, Phuoc %B 5th International Conference on Communications and Electronics (ICCE 2014) %C Da Nang, Vietnam %D 2014 %T Predicting Result Quality in Crowdsourcing Using Application Layer Monitoring %X Crowdsourcing has become a valuable tool for many business applications requiring to meet a certain quality of the results generated by the workers. Therefore, several quality assurance mechanisms have been developed which are partly deployed in commercial crowdsourcing platforms. However, these mechanisms usually impose additional work overhead for the worker, e.g. by adding test questions, or increase the costs for the employer, e.g. by replicating the task for majority decisions. In this work, we analyze the applicability of implicit measurements to objectively estimate the quality of the workers' results. First efforts in this area have already been made by investigating the impact of the task completion time. We extend this research by deploying an application layer monitoring (ALM), which enables monitoring the workers' interactions with our task interface on a much more detailed level. Based on an exemplary use case, we discuss a possible implementation and demonstrate the potential of the approach by predicting the quality of the workers' submission based on our monitoring results. This ALM provides a new way to identify low quality work as well as difficulties in fulfilling the formulated tasks in the domain of Crowdsourcing.
• Performance Model for Waiting Times in Cloud File Synchronization Services Schwartz, Christian; Hirth, Matthias; Hoßfeld, Tobias; Tran-Gia, Phuoc in 26th International Teletraffic Congress (ITC) (2014).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Over the last few years, the importance of cloud services for file synchronization has been increasing. With the release of network enabled cameras like Google Glass the trend of synchronizing new photos with the cloud has emerged as an important new use case for mobile networks. Multiple stakeholder are interested in optimizing this synchronization process according to different orthogonal metrics. The end user is interested in a fast synchronization of images as well as a low energy consumption of the client used for upload to the network. The network operator requires a low number of network connections per synchronization of a batch of images in order to reduce the signaling load of the mobile network. This paper answers the question if the goals of the stakeholders can be achieved by selecting an appropriate synchronization scheduling mechanism. Therefore, we first present a model for the waiting time of cloud file synchronization services. Second, we perform measurements on the popular Dropbox service to obtain parameters required in the model. Finally, we perform a parameter study over the considered mechanisms and parameters, suggest a preferable algorithm and identify trade-offs favorable for all stakeholders.

  @inproceedings{info3-inproceedings-2014-495, abstract = {Over the last few years, the importance of cloud services for file synchronization has been increasing. With the release of network enabled cameras like Google Glass the trend of synchronizing new photos with the cloud has emerged as an important new use case for mobile networks. Multiple stakeholder are interested in optimizing this synchronization process according to different orthogonal metrics. The end user is interested in a fast synchronization of images as well as a low energy consumption of the client used for upload to the network. The network operator requires a low number of network connections per synchronization of a batch of images in order to reduce the signaling load of the mobile network. This paper answers the question if the goals of the stakeholders can be achieved by selecting an appropriate synchronization scheduling mechanism. Therefore, we first present a model for the waiting time of cloud file synchronization services. Second, we perform measurements on the popular Dropbox service to obtain parameters required in the model. Finally, we perform a parameter study over the considered mechanisms and parameters, suggest a preferable algorithm and identify trade-offs favorable for all stakeholders.}, address = {Karlskrona, Sweden}, author = {Schwartz, Christian and Hirth, Matthias and Hoßfeld, Tobias and Tran-Gia, Phuoc}, booktitle = {26th International Teletraffic Congress (ITC)}, keywords = {smartenit}, month = 9, title = {Performance Model for Waiting Times in Cloud File Synchronization Services}, year = 2014 }

  %0 Conference Paper %1 info3-inproceedings-2014-495 %A Schwartz, Christian %A Hirth, Matthias %A Hoßfeld, Tobias %A Tran-Gia, Phuoc %B 26th International Teletraffic Congress (ITC) %C Karlskrona, Sweden %D 2014 %T Performance Model for Waiting Times in Cloud File Synchronization Services %X Over the last few years, the importance of cloud services for file synchronization has been increasing. With the release of network enabled cameras like Google Glass the trend of synchronizing new photos with the cloud has emerged as an important new use case for mobile networks. Multiple stakeholder are interested in optimizing this synchronization process according to different orthogonal metrics. The end user is interested in a fast synchronization of images as well as a low energy consumption of the client used for upload to the network. The network operator requires a low number of network connections per synchronization of a batch of images in order to reduce the signaling load of the mobile network. This paper answers the question if the goals of the stakeholders can be achieved by selecting an appropriate synchronization scheduling mechanism. Therefore, we first present a model for the waiting time of cloud file synchronization services. Second, we perform measurements on the popular Dropbox service to obtain parameters required in the model. Finally, we perform a parameter study over the considered mechanisms and parameters, suggest a preferable algorithm and identify trade-offs favorable for all stakeholders.
• Increasing the Coverage of Vantage Points in Distributed Active Network Measurements by Crowdsourcing Burger, Valentin; Hirth, Matthias; Schwartz, Christian; Hoßfeld, Tobias in Measurement, Modelling and Evaluation of Computing Systems (MMB 2014) (2014).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Internet video constitutes more than half of all consumer traffic. Most of the video traffic is delivered by content delivery networks (CDNs). The huge amount of traffic from video CDNs poses problems to access providers. To understand and monitor the impact of video traffic on access networks and the topology of CDNs, distributed active measurements are needed. Recently used measurement platforms are mainly hosted in National Research and Education Networks (NRENs). However, the view of these platforms on the CDN is very limited, since the coverage of NRENs is low in developing countries. Furthermore campus networks do not reflect the characteristics of end user access networks. We propose to use crowdsourcing to increase the coverage of vantage points in distributed active network measurements. In this study, we compare measurements of a global CDN conducted in PlanetLab with measurements assigned to workers of a crowdsourcing platform. Therewith, the coverage of vantage points and the sampled part of the global video CDN are analyzed. Our results show that the capability of PlanetLab to measure global CDNs is rather low, since the vast majority of requests is directed to the US. By using the crowdsourcing platform we obtain a diverse set of vantage points that reveals more than twice as many autonomous systems deploying video servers.

  @inproceedings{info3-inproceedings-2014-486, abstract = {Internet video constitutes more than half of all consumer traffic. Most of the video traffic is delivered by content delivery networks (CDNs). The huge amount of traffic from video CDNs poses problems to access providers. To understand and monitor the impact of video traffic on access networks and the topology of CDNs, distributed active measurements are needed. Recently used measurement platforms are mainly hosted in National Research and Education Networks (NRENs). However, the view of these platforms on the CDN is very limited, since the coverage of NRENs is low in developing countries. Furthermore campus networks do not reflect the characteristics of end user access networks. We propose to use crowdsourcing to increase the coverage of vantage points in distributed active network measurements. In this study, we compare measurements of a global CDN conducted in PlanetLab with measurements assigned to workers of a crowdsourcing platform. Therewith, the coverage of vantage points and the sampled part of the global video CDN are analyzed. Our results show that the capability of PlanetLab to measure global CDNs is rather low, since the vast majority of requests is directed to the US. By using the crowdsourcing platform we obtain a diverse set of vantage points that reveals more than twice as many autonomous systems deploying video servers.}, address = {Bamberg, Germany}, author = {Burger, Valentin and Hirth, Matthias and Schwartz, Christian and Hoßfeld, Tobias}, booktitle = {Measurement, Modelling and Evaluation of Computing Systems (MMB 2014)}, keywords = {smartenit}, month = 3, title = {Increasing the Coverage of Vantage Points in Distributed Active Network Measurements by Crowdsourcing}, year = 2014 }

  %0 Conference Paper %1 info3-inproceedings-2014-486 %A Burger, Valentin %A Hirth, Matthias %A Schwartz, Christian %A Hoßfeld, Tobias %B Measurement, Modelling and Evaluation of Computing Systems (MMB 2014) %C Bamberg, Germany %D 2014 %T Increasing the Coverage of Vantage Points in Distributed Active Network Measurements by Crowdsourcing %X Internet video constitutes more than half of all consumer traffic. Most of the video traffic is delivered by content delivery networks (CDNs). The huge amount of traffic from video CDNs poses problems to access providers. To understand and monitor the impact of video traffic on access networks and the topology of CDNs, distributed active measurements are needed. Recently used measurement platforms are mainly hosted in National Research and Education Networks (NRENs). However, the view of these platforms on the CDN is very limited, since the coverage of NRENs is low in developing countries. Furthermore campus networks do not reflect the characteristics of end user access networks. We propose to use crowdsourcing to increase the coverage of vantage points in distributed active network measurements. In this study, we compare measurements of a global CDN conducted in PlanetLab with measurements assigned to workers of a crowdsourcing platform. Therewith, the coverage of vantage points and the sampled part of the global video CDN are analyzed. Our results show that the capability of PlanetLab to measure global CDNs is rather low, since the vast majority of requests is directed to the US. By using the crowdsourcing platform we obtain a diverse set of vantage points that reveals more than twice as many autonomous systems deploying video servers.
• A new power profiling method and power scaling mechanism for energy-aware NetFPGA gigabit router Pham Ngoc, Nam; Nguyen Huu, Thanh; Vu Quang, Trong; Tran Hoang, Vu; Truong Thu, Huong; Tran-Gia, Phuoc; Schwartz, Christian in Computer Networks (2014).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  Today the ICT industry accounts for 2–4% of the worldwide carbon emissions that are estimated to double in a business-as-usual scenario by 2020. A remarkable part of the large energy volume consumed in the Internet today is due to the over-provisioning of network resources such as routers, switches and links to meet the stringent requirements on reliability. Therefore, performance and energy issues are important factors in designing gigabit routers for future networks. However, the design and prototyping of energy-efficient routers is challenging because of multiple reasons, such as the lack of power measurements from live networks and a good understanding of how the energy consumption varies under different traffic loads and switch/router configuration settings. Moreover, the exact energy saving level gained by adopting different energy-efficient techniques in different hardware prototypes is often poorly known. In this article, we first propose a measurement framework that is able to quantify and profile the detailed energy consumption of sub-components in the NetFPGA OpenFlow switch. We then propose a new power-scaling algorithm that can adapt the operational clock frequencies as well as the corresponding energy consumption of the FPGA core and the Ethernet ports to the actual traffic load. We propose a new energy profiling method, which allows studying the detailed power performance of network devices. Results show that our energy efficient solution obtains higher level of energy efficiency compared to some existing approaches as the upper and lower bounds of power consumption of the NetFPGA Openflow switch are proved to be 30% lower than ones of the commercial HP Enterprise switch. Moreover, the new switch architecture can save up to 97% of dynamic power consumption of the FPGA chip at lowest frequency mode.

  @article{info3-article-2014-133, abstract = {Today the ICT industry accounts for 2–4% of the worldwide carbon emissions that are estimated to double in a business-as-usual scenario by 2020. A remarkable part of the large energy volume consumed in the Internet today is due to the over-provisioning of network resources such as routers, switches and links to meet the stringent requirements on reliability. Therefore, performance and energy issues are important factors in designing gigabit routers for future networks. However, the design and prototyping of energy-efficient routers is challenging because of multiple reasons, such as the lack of power measurements from live networks and a good understanding of how the energy consumption varies under different traffic loads and switch/router configuration settings. Moreover, the exact energy saving level gained by adopting different energy-efficient techniques in different hardware prototypes is often poorly known. In this article, we first propose a measurement framework that is able to quantify and profile the detailed energy consumption of sub-components in the NetFPGA OpenFlow switch. We then propose a new power-scaling algorithm that can adapt the operational clock frequencies as well as the corresponding energy consumption of the FPGA core and the Ethernet ports to the actual traffic load. We propose a new energy profiling method, which allows studying the detailed power performance of network devices. Results show that our energy efficient solution obtains higher level of energy efficiency compared to some existing approaches as the upper and lower bounds of power consumption of the NetFPGA Openflow switch are proved to be 30% lower than ones of the commercial HP Enterprise switch. Moreover, the new switch architecture can save up to 97% of dynamic power consumption of the FPGA chip at lowest frequency mode.}, author = {Pham Ngoc, Nam and Nguyen Huu, Thanh and Vu Quang, Trong and Tran Hoang, Vu and Truong Thu, Huong and Tran-Gia, Phuoc and Schwartz, Christian}, journal = {Computer Networks}, keywords = {sys:hidden:article}, title = {A new power profiling method and power scaling mechanism for energy-aware NetFPGA gigabit router}, year = 2014 }

  %0 Journal Article %1 info3-article-2014-133 %A Pham Ngoc, Nam %A Nguyen Huu, Thanh %A Vu Quang, Trong %A Tran Hoang, Vu %A Truong Thu, Huong %A Tran-Gia, Phuoc %A Schwartz, Christian %D 2014 %J Computer Networks %T A new power profiling method and power scaling mechanism for energy-aware NetFPGA gigabit router %X Today the ICT industry accounts for 2–4% of the worldwide carbon emissions that are estimated to double in a business-as-usual scenario by 2020. A remarkable part of the large energy volume consumed in the Internet today is due to the over-provisioning of network resources such as routers, switches and links to meet the stringent requirements on reliability. Therefore, performance and energy issues are important factors in designing gigabit routers for future networks. However, the design and prototyping of energy-efficient routers is challenging because of multiple reasons, such as the lack of power measurements from live networks and a good understanding of how the energy consumption varies under different traffic loads and switch/router configuration settings. Moreover, the exact energy saving level gained by adopting different energy-efficient techniques in different hardware prototypes is often poorly known. In this article, we first propose a measurement framework that is able to quantify and profile the detailed energy consumption of sub-components in the NetFPGA OpenFlow switch. We then propose a new power-scaling algorithm that can adapt the operational clock frequencies as well as the corresponding energy consumption of the FPGA core and the Ethernet ports to the actual traffic load. We propose a new energy profiling method, which allows studying the detailed power performance of network devices. Results show that our energy efficient solution obtains higher level of energy efficiency compared to some existing approaches as the upper and lower bounds of power consumption of the NetFPGA Openflow switch are proved to be 30% lower than ones of the commercial HP Enterprise switch. Moreover, the new switch architecture can save up to 97% of dynamic power consumption of the FPGA chip at lowest frequency mode.

• Performance Analysis of the Trade-off Between Signalling Load and Power Consumption for Popular Smartphone Apps in 3G Networks Schwartz, Christian; Hoßfeld, Tobias; Lehrieder, Frank; Tran-Gia, Phuoc (2013).
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  @techreport{info3-techreport-2013-260, author = {Schwartz, Christian and Hoßfeld, Tobias and Lehrieder, Frank and Tran-Gia, Phuoc}, institution = {University of Wuerzburg}, keywords = {sys:hidden:techreport}, month = 1, number = 485, title = {Performance Analysis of the Trade-off Between Signalling Load and Power Consumption for Popular Smartphone Apps in 3G Networks}, year = 2013 }

  %0 Report %1 info3-techreport-2013-260 %A Schwartz, Christian %A Hoßfeld, Tobias %A Lehrieder, Frank %A Tran-Gia, Phuoc %D 2013 %N 485 %T Performance Analysis of the Trade-off Between Signalling Load and Power Consumption for Popular Smartphone Apps in 3G Networks
• Angry Apps: The Impact of Network Timer Selection on Power Consumption, Signalling Load, and Web QoE Schwartz, Christian; Hoßfeld, Tobias; Lehrieder, Frank; Tran-Gia, Phuoc in Journal of Computer Networks and Communications (2013). 1–22.
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  The popularity of smartphones and mobile applications has experienced a considerable growth during recent years and this growth is expected to continue in the future. Since smartphones have only very limited energy resources, battery efficiency is one of the deter- mining factors for a good user experience. Therefore, some smartphones tear down connec- tions to the mobile network soon after a completed data transmission to reduce the power consumption of their transmission unit. However, frequent connection re-establishments caused by apps which send or receive small amounts of data often lead to a heavy signalling load within the mobile network. One of the major contributions of this article is the investigation of the resulting trade-off between energy consumption at the smartphone and the generated signalling traffic in the mobile network. We explain that this trade-off can be controlled by the connection release timeout and study the impact of this parameter for a number of popular apps that cover a wide range of traffic characteristics in terms of bandwidth requirements and resulting signalling traffic. Finally, we study the impact of the timer settings on QoE for web traffic. This is an important aspect since connection establishments do not only lead to signalling traffic, but they also increase the load time of web pages.

  @article{info3-article-2013-108, abstract = {The popularity of smartphones and mobile applications has experienced a considerable growth during recent years and this growth is expected to continue in the future. Since smartphones have only very limited energy resources, battery efficiency is one of the deter- mining factors for a good user experience. Therefore, some smartphones tear down connec- tions to the mobile network soon after a completed data transmission to reduce the power consumption of their transmission unit. However, frequent connection re-establishments caused by apps which send or receive small amounts of data often lead to a heavy signalling load within the mobile network. One of the major contributions of this article is the investigation of the resulting trade-off between energy consumption at the smartphone and the generated signalling traffic in the mobile network. We explain that this trade-off can be controlled by the connection release timeout and study the impact of this parameter for a number of popular apps that cover a wide range of traffic characteristics in terms of bandwidth requirements and resulting signalling traffic. Finally, we study the impact of the timer settings on QoE for web traffic. This is an important aspect since connection establishments do not only lead to signalling traffic, but they also increase the load time of web pages.}, author = {Schwartz, Christian and Hoßfeld, Tobias and Lehrieder, Frank and Tran-Gia, Phuoc}, journal = {Journal of Computer Networks and Communications}, keywords = {sys:hidden:article}, month = 9, pages = {1 - 22}, title = {Angry Apps: The Impact of Network Timer Selection on Power Consumption, Signalling Load, and Web QoE}, year = 2013 }

  %0 Journal Article %1 info3-article-2013-108 %A Schwartz, Christian %A Hoßfeld, Tobias %A Lehrieder, Frank %A Tran-Gia, Phuoc %D 2013 %J Journal of Computer Networks and Communications %P 1 - 22 %T Angry Apps: The Impact of Network Timer Selection on Power Consumption, Signalling Load, and Web QoE %X The popularity of smartphones and mobile applications has experienced a considerable growth during recent years and this growth is expected to continue in the future. Since smartphones have only very limited energy resources, battery efficiency is one of the deter- mining factors for a good user experience. Therefore, some smartphones tear down connec- tions to the mobile network soon after a completed data transmission to reduce the power consumption of their transmission unit. However, frequent connection re-establishments caused by apps which send or receive small amounts of data often lead to a heavy signalling load within the mobile network. One of the major contributions of this article is the investigation of the resulting trade-off between energy consumption at the smartphone and the generated signalling traffic in the mobile network. We explain that this trade-off can be controlled by the connection release timeout and study the impact of this parameter for a number of popular apps that cover a wide range of traffic characteristics in terms of bandwidth requirements and resulting signalling traffic. Finally, we study the impact of the timer settings on QoE for web traffic. This is an important aspect since connection establishments do not only lead to signalling traffic, but they also increase the load time of web pages.
• Modeling and Experimenting Combined Smart Sleep and Power Scaling Algorithms in Energy-aware Data Center Networks. Nguyen, Huu-Thanh; Pham Ngoc, Nam; Truong, Thu-Huong; Tran Ngoc, Thuan; Nguyen Minh, Duong; Giang Nguyen, Van; Nguyen, Tai-Hung; Ngo Quynh, Thu; Hock, David; Schwartz, Christian in Simulation Modelling Practice and Theory (2013). 39
  • [ BibTeX ]
  • [ EndNote ]
  @article{info3-article-2013-118, author = {Nguyen, Huu-Thanh and Pham Ngoc, Nam and Truong, Thu-Huong and Tran Ngoc, Thuan and Nguyen Minh, Duong and Giang Nguyen, Van and Nguyen, Tai-Hung and Ngo Quynh, Thu and Hock, David and Schwartz, Christian}, journal = {Simulation Modelling Practice and Theory}, keywords = {sys:hidden:article}, month = 12, title = {Modeling and Experimenting Combined Smart Sleep and Power Scaling Algorithms in Energy-aware Data Center Networks.}, volume = 39, year = 2013 }

  %0 Journal Article %1 info3-article-2013-118 %A Nguyen, Huu-Thanh %A Pham Ngoc, Nam %A Truong, Thu-Huong %A Tran Ngoc, Thuan %A Nguyen Minh, Duong %A Giang Nguyen, Van %A Nguyen, Tai-Hung %A Ngo Quynh, Thu %A Hock, David %A Schwartz, Christian %D 2013 %J Simulation Modelling Practice and Theory %T Modeling and Experimenting Combined Smart Sleep and Power Scaling Algorithms in Energy-aware Data Center Networks. %V 39
• Smart-Phone Energy Consumption Vs. 3G Signaling Load: The Influence of Application Traffic Patterns Schwartz, Christian; Lehrieder, Frank; Wamser, Florian; Hoßfeld, Tobias; Tran-Gia, Phuoc in Tyrrhenian International Workshop 2013 on Digital Communications: Green ICT (2013).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  The high signaling load in today’s UMTS networks has recently lead to severe problems and network outages of several hours, so called Signaling Storms. The reason is that cer- tain network access patterns of popular smart-phone applications trigger frequent connection re-establishments, which are signaled to the network via the radio resource control (RRC) protocol. As a consequence of the network agnostic implementation of smart- phone applications, entities of the mobile network operator may experience overload, while energy consumption at the smart- phones is mutually determined. The aim of this work is to study the impact of traffic charac- teristics on the power consumption of the smart-phone and the signaling messages in the mobile network. For that purpose, we first develop a simple model for the RRC states of a smart-phone. Second, we estimate the resulting power drain and the signalling traffic of the smart-phone. Then, we investigate the applicability of our model by comparing analytical with simulation results for real-world smart-phone traffic measurements. Finally, we evaluate the effect of network parameter optimization on traffic with different statistical characteristics. Our counter-intuitive results show that in particular bursty traffic patterns are suitable for UMTS networks while periodic patterns may cause increased power consumption and signaling overload – in contrast to classical queueing systems.

  @inproceedings{info3-inproceedings-2013-481, abstract = {The high signaling load in today’s UMTS networks has recently lead to severe problems and network outages of several hours, so called Signaling Storms. The reason is that cer- tain network access patterns of popular smart-phone applications trigger frequent connection re-establishments, which are signaled to the network via the radio resource control (RRC) protocol. As a consequence of the network agnostic implementation of smart- phone applications, entities of the mobile network operator may experience overload, while energy consumption at the smart- phones is mutually determined. The aim of this work is to study the impact of traffic charac- teristics on the power consumption of the smart-phone and the signaling messages in the mobile network. For that purpose, we first develop a simple model for the RRC states of a smart-phone. Second, we estimate the resulting power drain and the signalling traffic of the smart-phone. Then, we investigate the applicability of our model by comparing analytical with simulation results for real-world smart-phone traffic measurements. Finally, we evaluate the effect of network parameter optimization on traffic with different statistical characteristics. Our counter-intuitive results show that in particular bursty traffic patterns are suitable for UMTS networks while periodic patterns may cause increased power consumption and signaling overload – in contrast to classical queueing systems.}, address = {Genova, Italy}, author = {Schwartz, Christian and Lehrieder, Frank and Wamser, Florian and Hoßfeld, Tobias and Tran-Gia, Phuoc}, booktitle = {Tyrrhenian International Workshop 2013 on Digital Communications: Green ICT}, keywords = {oekonet}, month = 9, title = {Smart-Phone Energy Consumption Vs. 3G Signaling Load: The Influence of Application Traffic Patterns}, year = 2013 }

  %0 Conference Paper %1 info3-inproceedings-2013-481 %A Schwartz, Christian %A Lehrieder, Frank %A Wamser, Florian %A Hoßfeld, Tobias %A Tran-Gia, Phuoc %B Tyrrhenian International Workshop 2013 on Digital Communications: Green ICT %C Genova, Italy %D 2013 %T Smart-Phone Energy Consumption Vs. 3G Signaling Load: The Influence of Application Traffic Patterns %X The high signaling load in today’s UMTS networks has recently lead to severe problems and network outages of several hours, so called Signaling Storms. The reason is that cer- tain network access patterns of popular smart-phone applications trigger frequent connection re-establishments, which are signaled to the network via the radio resource control (RRC) protocol. As a consequence of the network agnostic implementation of smart- phone applications, entities of the mobile network operator may experience overload, while energy consumption at the smart- phones is mutually determined. The aim of this work is to study the impact of traffic charac- teristics on the power consumption of the smart-phone and the signaling messages in the mobile network. For that purpose, we first develop a simple model for the RRC states of a smart-phone. Second, we estimate the resulting power drain and the signalling traffic of the smart-phone. Then, we investigate the applicability of our model by comparing analytical with simulation results for real-world smart-phone traffic measurements. Finally, we evaluate the effect of network parameter optimization on traffic with different statistical characteristics. Our counter-intuitive results show that in particular bursty traffic patterns are suitable for UMTS networks while periodic patterns may cause increased power consumption and signaling overload – in contrast to classical queueing systems.
• Trade-Offs for Video-Providers in LTE Networks: Smartphone Energy Consumption Vs Wasted Traffic Schwartz, Christian; Scheib, Marc; Hoßfeld, Tobias; Tran-Gia, Phuoc; Manuel Gimenez-Guzman, Jose in 22nd International Teletraffic Congress Specialist Seminar on Energy Efficient and Green Networking (2013).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Long Term Evolution (LTE) networks provide broadband Internet access to mobile users. One of the main use cases for LTE is a mobile video. When selecting a video transmis- sion mechanism, a video provider has to consider different and orthogonal metrics. The consumer expects a high video Quality of Experience (QoE) and a low energy consumption during download and playback. The video provider is interested in minimizing its resources and corresponding costs, like bandwidth and wasted traffic. Wasted traffic occurs if a user aborts and additional video data is already downloaded but not played out, consuming resources unnecessarily. This raises the questions 1) how a video provider delivers the video contents while reducing the operational costs and satisfying the customers demands 2) what is the influence of the customer abort behaviour. To answer these questions, we first study the influence of mechanism selection on energy consumption and wasted traffic. Second, we show that the different user models do not influence the wasted traffic significantly. Finally, we provide parameter se- lection guidelines for the Streaming mechanism, which are shown to satisfy better both the requirements of the video provider as well as those of the customer, to achieve Pareto optimal results with regard to the smartphone energy consumption and wasted traffic.

  @inproceedings{info3-inproceedings-2013-482, abstract = {Long Term Evolution (LTE) networks provide broadband Internet access to mobile users. One of the main use cases for LTE is a mobile video. When selecting a video transmis- sion mechanism, a video provider has to consider different and orthogonal metrics. The consumer expects a high video Quality of Experience (QoE) and a low energy consumption during download and playback. The video provider is interested in minimizing its resources and corresponding costs, like bandwidth and wasted traffic. Wasted traffic occurs if a user aborts and additional video data is already downloaded but not played out, consuming resources unnecessarily. This raises the questions 1) how a video provider delivers the video contents while reducing the operational costs and satisfying the customers demands 2) what is the influence of the customer abort behaviour. To answer these questions, we first study the influence of mechanism selection on energy consumption and wasted traffic. Second, we show that the different user models do not influence the wasted traffic significantly. Finally, we provide parameter se- lection guidelines for the Streaming mechanism, which are shown to satisfy better both the requirements of the video provider as well as those of the customer, to achieve Pareto optimal results with regard to the smartphone energy consumption and wasted traffic.}, address = {Christchurch, New Zealand}, author = {Schwartz, Christian and Scheib, Marc and Hoßfeld, Tobias and Tran-Gia, Phuoc and Manuel Gimenez-Guzman, Jose}, booktitle = {22nd International Teletraffic Congress Specialist Seminar on Energy Efficient and Green Networking}, keywords = {smartenit}, month = 11, title = {Trade-Offs for Video-Providers in LTE Networks: Smartphone Energy Consumption Vs Wasted Traffic}, year = 2013 }

  %0 Conference Paper %1 info3-inproceedings-2013-482 %A Schwartz, Christian %A Scheib, Marc %A Hoßfeld, Tobias %A Tran-Gia, Phuoc %A Manuel Gimenez-Guzman, Jose %B 22nd International Teletraffic Congress Specialist Seminar on Energy Efficient and Green Networking %C Christchurch, New Zealand %D 2013 %T Trade-Offs for Video-Providers in LTE Networks: Smartphone Energy Consumption Vs Wasted Traffic %X Long Term Evolution (LTE) networks provide broadband Internet access to mobile users. One of the main use cases for LTE is a mobile video. When selecting a video transmis- sion mechanism, a video provider has to consider different and orthogonal metrics. The consumer expects a high video Quality of Experience (QoE) and a low energy consumption during download and playback. The video provider is interested in minimizing its resources and corresponding costs, like bandwidth and wasted traffic. Wasted traffic occurs if a user aborts and additional video data is already downloaded but not played out, consuming resources unnecessarily. This raises the questions 1) how a video provider delivers the video contents while reducing the operational costs and satisfying the customers demands 2) what is the influence of the customer abort behaviour. To answer these questions, we first study the influence of mechanism selection on energy consumption and wasted traffic. Second, we show that the different user models do not influence the wasted traffic significantly. Finally, we provide parameter se- lection guidelines for the Streaming mechanism, which are shown to satisfy better both the requirements of the video provider as well as those of the customer, to achieve Pareto optimal results with regard to the smartphone energy consumption and wasted traffic.
• Inter-AS Traffic Characteristics of a Global Content Delivery Network Burger, Valentin; Hirth, Matthias; Schwartz, Christian; Hoßfeld, Tobias (2013, June 28).
  • [ BibTeX ]
  • [ EndNote ]
  @presentation{info3-talk-2013-469, address = {ITG 5.2.1 Fachgruppentreffen, Würzburg, Germany}, author = {Burger, Valentin and Hirth, Matthias and Schwartz, Christian and Hoßfeld, Tobias}, keywords = {sys:hidden:presentation}, month = 6, title = {Inter-AS Traffic Characteristics of a Global Content Delivery Network}, year = 2013 }

  %0 Generic %1 info3-talk-2013-469 %A Burger, Valentin %A Hirth, Matthias %A Schwartz, Christian %A Hoßfeld, Tobias %C ITG 5.2.1 Fachgruppentreffen, Würzburg, Germany %D 2013 %T Inter-AS Traffic Characteristics of a Global Content Delivery Network

• A Queuing Analysis of an Energy-Saving Mechanism in Data Centers Schwartz, Christian; Pries, Rastin; Tran-Gia, Phuoc in International Conference on Information Networking (ICOIN) (2012).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  The high energy costs for running a data center led to a rethinking towards an energy-efficient operation of a data center. Designed for supporting the expected peak traffic load, the goal of the data center provider such as Amazon or Google is now to dynamically adapt the number of offered resources according to the current traffic load. In this paper, we present a queuing theoretical model to evaluate the trade-off between waiting time and power consumption if only a subset of servers is active all the time and the remaining servers are enabled on demand. We develop a queuing model with thresholds to turn-on reserve servers when needed. Furthermore, the resulting system behavior under varying parameters and requirements for Pareto optimality are studied.

  @inproceedings{info3-inproceedings-2012-430, abstract = {The high energy costs for running a data center led to a rethinking towards an energy-efficient operation of a data center. Designed for supporting the expected peak traffic load, the goal of the data center provider such as Amazon or Google is now to dynamically adapt the number of offered resources according to the current traffic load. In this paper, we present a queuing theoretical model to evaluate the trade-off between waiting time and power consumption if only a subset of servers is active all the time and the remaining servers are enabled on demand. We develop a queuing model with thresholds to turn-on reserve servers when needed. Furthermore, the resulting system behavior under varying parameters and requirements for Pareto optimality are studied.}, address = {Bali, Indonesia}, author = {Schwartz, Christian and Pries, Rastin and Tran-Gia, Phuoc}, booktitle = {International Conference on Information Networking (ICOIN)}, keywords = {sys:hidden:inproceedings}, month = 2, title = {A Queuing Analysis of an Energy-Saving Mechanism in Data Centers}, year = 2012 }

  %0 Conference Paper %1 info3-inproceedings-2012-430 %A Schwartz, Christian %A Pries, Rastin %A Tran-Gia, Phuoc %B International Conference on Information Networking (ICOIN) %C Bali, Indonesia %D 2012 %T A Queuing Analysis of an Energy-Saving Mechanism in Data Centers %X The high energy costs for running a data center led to a rethinking towards an energy-efficient operation of a data center. Designed for supporting the expected peak traffic load, the goal of the data center provider such as Amazon or Google is now to dynamically adapt the number of offered resources according to the current traffic load. In this paper, we present a queuing theoretical model to evaluate the trade-off between waiting time and power consumption if only a subset of servers is active all the time and the remaining servers are enabled on demand. We develop a queuing model with thresholds to turn-on reserve servers when needed. Furthermore, the resulting system behavior under varying parameters and requirements for Pareto optimality are studied.

• Multipath Routing Slice Experiments in Federated Testbeds Zseby, Tanja; Zinner, Thomas; Tutschku, Kurt; Shavitt, Yuval; Tran-Gia, Phuoc; Schwartz, Christian; Rafetseder, Albert; Henke, Christian; Schmoll, Carsten in Future Internet Assembly (FIA) Book Future Internet: Achievements and Promising Technology, J. Domingue, A. Galis, A. Gavras, T. Zahariadis, D. Lambert, F. Cleary, P. Daras, S. Krco, H. Müller, M.-S. Li (eds.) (2011).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  The Internet today consist of many heterogeneous infras- tructures, owned and maintained by separate and potentially competing administrative authorities. On top of this a wide variety of applications has different requirements with regard to quality, reliability and security from the underlying networks. The number of stakeholders who partici- pate in provisioning of network and services is growing. More demanding applications (like eGovernment, eHealth, critical and emergency infras- tructures) are on the rise. Therefore we assume that these two basic characteristics, a) multiple authorities and b) applications with very di- verse demands, are likely to stay or even increase in the Internet of the future. In such an environment federation and virtualization of resources are key features that should be supported in a future Internet. The ability to form slices across domains that meet application specific requirements enables many of the desired features in future networks. In this paper, we present a Multipath Routing Slice experiment that we performed over multiple federated testbeds. We combined capabilities from different experimental facilities, since one single testbed did not offer all the required capabilities. This paper summarizes the conducted experiment, our experience with the usability of federated testbeds and our experience with the use of advanced measurement technologies within experimental facilities. We believe that this experiment provides a good example use case for the future Internet itself because we assume that the Internet will consist of multiple different infrastructures that have to be combined in application specific overlays or routing slices, very much like the experimental facilities we used in this experiment. We also assume that the growing demands will push towards a much better measurement instrumentation of the future Internet. The tools used in our experiment can provide a starting point for this.

  @incollection{info3-incollection-2011-15, abstract = {The Internet today consist of many heterogeneous infras- tructures, owned and maintained by separate and potentially competing administrative authorities. On top of this a wide variety of applications has different requirements with regard to quality, reliability and security from the underlying networks. The number of stakeholders who partici- pate in provisioning of network and services is growing. More demanding applications (like eGovernment, eHealth, critical and emergency infras- tructures) are on the rise. Therefore we assume that these two basic characteristics, a) multiple authorities and b) applications with very di- verse demands, are likely to stay or even increase in the Internet of the future. In such an environment federation and virtualization of resources are key features that should be supported in a future Internet. The ability to form slices across domains that meet application specific requirements enables many of the desired features in future networks. In this paper, we present a Multipath Routing Slice experiment that we performed over multiple federated testbeds. We combined capabilities from different experimental facilities, since one single testbed did not offer all the required capabilities. This paper summarizes the conducted experiment, our experience with the usability of federated testbeds and our experience with the use of advanced measurement technologies within experimental facilities. We believe that this experiment provides a good example use case for the future Internet itself because we assume that the Internet will consist of multiple different infrastructures that have to be combined in application specific overlays or routing slices, very much like the experimental facilities we used in this experiment. We also assume that the growing demands will push towards a much better measurement instrumentation of the future Internet. The tools used in our experiment can provide a starting point for this.}, author = {Zseby, Tanja and Zinner, Thomas and Tutschku, Kurt and Shavitt, Yuval and Tran-Gia, Phuoc and Schwartz, Christian and Rafetseder, Albert and Henke, Christian and Schmoll, Carsten}, booktitle = {Future Internet Assembly (FIA) Book Future Internet: Achievements and Promising Technology}, editor = {Domingue, John and Galis, Alex and Gavras, Anastasius and Zahariadis, Theodore and Lambert, Dave and Cleary, Frances and Daras, Patros and Krco, Srdjan and Müller, Henning and Li, Man-Sze}, keywords = {myown}, month = 5, publisher = {Springer}, title = {Multipath Routing Slice Experiments in Federated Testbeds}, year = 2011 }

  %0 Book Section %1 info3-incollection-2011-15 %A Zseby, Tanja %A Zinner, Thomas %A Tutschku, Kurt %A Shavitt, Yuval %A Tran-Gia, Phuoc %A Schwartz, Christian %A Rafetseder, Albert %A Henke, Christian %A Schmoll, Carsten %B Future Internet Assembly (FIA) Book Future Internet: Achievements and Promising Technology %D 2011 %E Domingue, John %E Galis, Alex %E Gavras, Anastasius %E Zahariadis, Theodore %E Lambert, Dave %E Cleary, Frances %E Daras, Patros %E Krco, Srdjan %E Müller, Henning %E Li, Man-Sze %I Springer %T Multipath Routing Slice Experiments in Federated Testbeds %X The Internet today consist of many heterogeneous infras- tructures, owned and maintained by separate and potentially competing administrative authorities. On top of this a wide variety of applications has different requirements with regard to quality, reliability and security from the underlying networks. The number of stakeholders who partici- pate in provisioning of network and services is growing. More demanding applications (like eGovernment, eHealth, critical and emergency infras- tructures) are on the rise. Therefore we assume that these two basic characteristics, a) multiple authorities and b) applications with very di- verse demands, are likely to stay or even increase in the Internet of the future. In such an environment federation and virtualization of resources are key features that should be supported in a future Internet. The ability to form slices across domains that meet application specific requirements enables many of the desired features in future networks. In this paper, we present a Multipath Routing Slice experiment that we performed over multiple federated testbeds. We combined capabilities from different experimental facilities, since one single testbed did not offer all the required capabilities. This paper summarizes the conducted experiment, our experience with the usability of federated testbeds and our experience with the use of advanced measurement technologies within experimental facilities. We believe that this experiment provides a good example use case for the future Internet itself because we assume that the Internet will consist of multiple different infrastructures that have to be combined in application specific overlays or routing slices, very much like the experimental facilities we used in this experiment. We also assume that the growing demands will push towards a much better measurement instrumentation of the future Internet. The tools used in our experiment can provide a starting point for this.
• ResiLyzer: Ein Werkzeug zur Analyse der Ausfallsicherheit in paketvermittelten Kommunikationsnetzen Hock, David; Hartmann, Matthias; Schwartz, Christian; Menth, Michael (2011, March).
  • [ BibTeX ]
  • [ EndNote ]
  @misc{info3-software-2011-4, address = {Kiel, Germany}, author = {Hock, David and Hartmann, Matthias and Schwartz, Christian and Menth, Michael}, booktitle = {PIK-Praxis der Informationsverarbeitung und Kommunikation}, keywords = {sys:hidden:software}, month = 3, title = {ResiLyzer: Ein Werkzeug zur Analyse der Ausfallsicherheit in paketvermittelten Kommunikationsnetzen}, year = 2011 }

  %0 Generic %1 info3-software-2011-4 %A Hock, David %A Hartmann, Matthias %A Schwartz, Christian %A Menth, Michael %B PIK-Praxis der Informationsverarbeitung und Kommunikation %C Kiel, Germany %D 2011 %T ResiLyzer: Ein Werkzeug zur Analyse der Ausfallsicherheit in paketvermittelten Kommunikationsnetzen
• ResiLyzer: Ein Werkzeug zur Analyse der Ausfallsicherheit in paketvermittelten Kommunikationsnetzen Hock, David; Hartmann, Matthias; Schwartz, Christian; Menth, Michael in PIK - Praxis der Informationsverarbeitung und Kommunikation (2011). 34 158–159.
  • [ BibTeX ]
  • [ EndNote ]
  @article{info3-article-2011-105, author = {Hock, David and Hartmann, Matthias and Schwartz, Christian and Menth, Michael}, journal = {PIK - Praxis der Informationsverarbeitung und Kommunikation}, keywords = {sys:hidden:article}, month = 8, pages = {158-159}, title = {ResiLyzer: Ein Werkzeug zur Analyse der Ausfallsicherheit in paketvermittelten Kommunikationsnetzen}, volume = 34, year = 2011 }

  %0 Journal Article %1 info3-article-2011-105 %A Hock, David %A Hartmann, Matthias %A Schwartz, Christian %A Menth, Michael %D 2011 %J PIK - Praxis der Informationsverarbeitung und Kommunikation %P 158-159 %T ResiLyzer: Ein Werkzeug zur Analyse der Ausfallsicherheit in paketvermittelten Kommunikationsnetzen %V 34

• ResiLyzer: A Tool for Resilience Analysis in Packet-Switched Communication Networks Hock, David; Menth, Michael; Hartmann, Matthias; Schwartz, Christian; Stezenbach, David in 15th International GI/ITG Conference on Measurement, Modelling and Evaluation of Computing Systems and Dependability and Fault Tolerance (MMB & DFT 2010) (2010).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  We present a tool for the analysis of fault-tolerance in packet-switched communication networks. Network elements like links or routers can fail or unexpected traffic surges may occur. They lead to service disruptions and degradations. Our tool quantifies these risks and presents a comprehensive digest of the results. We explain the core idea of the analysis and illustrate the tool.

  @inproceedings{info3-inproceedings-2010-365, abstract = {We present a tool for the analysis of fault-tolerance in packet-switched communication networks. Network elements like links or routers can fail or unexpected traffic surges may occur. They lead to service disruptions and degradations. Our tool quantifies these risks and presents a comprehensive digest of the results. We explain the core idea of the analysis and illustrate the tool.}, address = {Essen, Germany}, author = {Hock, David and Menth, Michael and Hartmann, Matthias and Schwartz, Christian and Stezenbach, David}, booktitle = {15th International GI/ITG Conference on Measurement, Modelling and Evaluation of Computing Systems and Dependability and Fault Tolerance (MMB & DFT 2010)}, keywords = {sys:hidden:inproceedings}, month = 3, title = {ResiLyzer: A Tool for Resilience Analysis in Packet-Switched Communication Networks}, year = 2010 }

  %0 Conference Paper %1 info3-inproceedings-2010-365 %A Hock, David %A Menth, Michael %A Hartmann, Matthias %A Schwartz, Christian %A Stezenbach, David %B 15th International GI/ITG Conference on Measurement, Modelling and Evaluation of Computing Systems and Dependability and Fault Tolerance (MMB & DFT 2010) %C Essen, Germany %D 2010 %T ResiLyzer: A Tool for Resilience Analysis in Packet-Switched Communication Networks %X We present a tool for the analysis of fault-tolerance in packet-switched communication networks. Network elements like links or routers can fail or unexpected traffic surges may occur. They lead to service disruptions and degradations. Our tool quantifies these risks and presents a comprehensive digest of the results. We explain the core idea of the analysis and illustrate the tool.
• Optimizing Unique Shortest Paths for Resilient Routing and Fast Reroute in IP-Based Networks Hock, David; Hartmann, Matthias; Menth, Michael; Schwartz, Christian in IEEE/IFIP Network Operations and Management Symposium (NOMS) (2010).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Intradomain routing in IP networks follows shortest paths according to administrative link costs. When several equalcost shortest paths exist, routers that use equal-cost multipath (ECMP) distribute the traffic over all of them. To produce singleshortest path (SSP) routing, a selection mechanism (tie-breaker) chooses just one of the equal-cost paths. Tie-breakers are poorly standardized and use information that may change over time, which makes SSP routing unpredictable. Therefore, link costs producing unique shortest paths (USP) are preferred. In this paper, we show that optimized SSP routing can lead to significantly higher link utilization than expected in case of non-deterministic tie-breakers. We investigate the impact of the allowed link cost range on the general availability of USP routing. We use a heuristic algorithm to generate link costs for USP routing and to minimize the maximum link utilization in networks with and without failures. Fast reroute (FRR) mechanisms can repair failures faster than conventional IP rerouting by pre-computing shortest backup paths around failed network elements. However, when multiple equal-cost paths exist, the backup path layout is unpredictable. We adapt our heuristic to optimize USP routing for IP-FRR using not-via addresses and MPLS-FRR with facility and oneto- one backup. Finally, we compare the performance of USP with various other routing schemes using realistic Rocketfuel topologies.

  @inproceedings{info3-inproceedings-2010-363, abstract = {Intradomain routing in IP networks follows shortest paths according to administrative link costs. When several equalcost shortest paths exist, routers that use equal-cost multipath (ECMP) distribute the traffic over all of them. To produce singleshortest path (SSP) routing, a selection mechanism (tie-breaker) chooses just one of the equal-cost paths. Tie-breakers are poorly standardized and use information that may change over time, which makes SSP routing unpredictable. Therefore, link costs producing unique shortest paths (USP) are preferred. In this paper, we show that optimized SSP routing can lead to significantly higher link utilization than expected in case of non-deterministic tie-breakers. We investigate the impact of the allowed link cost range on the general availability of USP routing. We use a heuristic algorithm to generate link costs for USP routing and to minimize the maximum link utilization in networks with and without failures. Fast reroute (FRR) mechanisms can repair failures faster than conventional IP rerouting by pre-computing shortest backup paths around failed network elements. However, when multiple equal-cost paths exist, the backup path layout is unpredictable. We adapt our heuristic to optimize USP routing for IP-FRR using not-via addresses and MPLS-FRR with facility and oneto- one backup. Finally, we compare the performance of USP with various other routing schemes using realistic Rocketfuel topologies.}, address = {Osaka, Japan}, author = {Hock, David and Hartmann, Matthias and Menth, Michael and Schwartz, Christian}, booktitle = {IEEE/IFIP Network Operations and Management Symposium (NOMS)}, keywords = {sys:hidden:inproceedings}, month = 4, title = {Optimizing Unique Shortest Paths for Resilient Routing and Fast Reroute in IP-Based Networks}, year = 2010 }

  %0 Conference Paper %1 info3-inproceedings-2010-363 %A Hock, David %A Hartmann, Matthias %A Menth, Michael %A Schwartz, Christian %B IEEE/IFIP Network Operations and Management Symposium (NOMS) %C Osaka, Japan %D 2010 %T Optimizing Unique Shortest Paths for Resilient Routing and Fast Reroute in IP-Based Networks %X Intradomain routing in IP networks follows shortest paths according to administrative link costs. When several equalcost shortest paths exist, routers that use equal-cost multipath (ECMP) distribute the traffic over all of them. To produce singleshortest path (SSP) routing, a selection mechanism (tie-breaker) chooses just one of the equal-cost paths. Tie-breakers are poorly standardized and use information that may change over time, which makes SSP routing unpredictable. Therefore, link costs producing unique shortest paths (USP) are preferred. In this paper, we show that optimized SSP routing can lead to significantly higher link utilization than expected in case of non-deterministic tie-breakers. We investigate the impact of the allowed link cost range on the general availability of USP routing. We use a heuristic algorithm to generate link costs for USP routing and to minimize the maximum link utilization in networks with and without failures. Fast reroute (FRR) mechanisms can repair failures faster than conventional IP rerouting by pre-computing shortest backup paths around failed network elements. However, when multiple equal-cost paths exist, the backup path layout is unpredictable. We adapt our heuristic to optimize USP routing for IP-FRR using not-via addresses and MPLS-FRR with facility and oneto- one backup. Finally, we compare the performance of USP with various other routing schemes using realistic Rocketfuel topologies.
• Effectiveness of Link Cost Optimization for IP Rerouting and IP Fast Reroute Hock, David; Hartmann, Matthias; Schwartz, Christian; Menth, Michael in 15th International GI/ITG Conference on Measurement, Modelling and Evaluation of Computing Systems and Dependability and Fault Tolerance (MMB & DFT 2010) (2010).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  In this paper, we bring together resilience analysis and routing optimization for IP-based intra-domain networks. When link, node, or multiple failures occur, traffic is rerouted which increases the link load on backup paths and possibly causes congestion. Resilience analysis detects the risk of overload situations a priori based on a large set of most likely failure scenarios. To counteract, the routing can be optimized and configured that such bottlenecks are avoided at least for a smaller set of failure scenarios. In this paper, we demonstrate the effectiveness of this routing optimization in IP networks. We use resilience analysis with suitable aggregate views on relative link loads. Furthermore, we compare conventional IP rerouting with IP fast reroute (IP-FRR) and show that IP-FRR can also significantly profit from routing optimization. This paper reviews major parts of previous publications and presents a new method to visualize and compare the resilience of different routing schemes.

  @inproceedings{info3-inproceedings-2010-364, abstract = {In this paper, we bring together resilience analysis and routing optimization for IP-based intra-domain networks. When link, node, or multiple failures occur, traffic is rerouted which increases the link load on backup paths and possibly causes congestion. Resilience analysis detects the risk of overload situations a priori based on a large set of most likely failure scenarios. To counteract, the routing can be optimized and configured that such bottlenecks are avoided at least for a smaller set of failure scenarios. In this paper, we demonstrate the effectiveness of this routing optimization in IP networks. We use resilience analysis with suitable aggregate views on relative link loads. Furthermore, we compare conventional IP rerouting with IP fast reroute (IP-FRR) and show that IP-FRR can also significantly profit from routing optimization. This paper reviews major parts of previous publications and presents a new method to visualize and compare the resilience of different routing schemes.}, address = {Essen, Germany}, author = {Hock, David and Hartmann, Matthias and Schwartz, Christian and Menth, Michael}, booktitle = {15th International GI/ITG Conference on Measurement, Modelling and Evaluation of Computing Systems and Dependability and Fault Tolerance (MMB & DFT 2010)}, keywords = {sys:hidden:inproceedings}, month = 3, title = {Effectiveness of Link Cost Optimization for IP Rerouting and IP Fast Reroute}, year = 2010 }

  %0 Conference Paper %1 info3-inproceedings-2010-364 %A Hock, David %A Hartmann, Matthias %A Schwartz, Christian %A Menth, Michael %B 15th International GI/ITG Conference on Measurement, Modelling and Evaluation of Computing Systems and Dependability and Fault Tolerance (MMB & DFT 2010) %C Essen, Germany %D 2010 %T Effectiveness of Link Cost Optimization for IP Rerouting and IP Fast Reroute %X In this paper, we bring together resilience analysis and routing optimization for IP-based intra-domain networks. When link, node, or multiple failures occur, traffic is rerouted which increases the link load on backup paths and possibly causes congestion. Resilience analysis detects the risk of overload situations a priori based on a large set of most likely failure scenarios. To counteract, the routing can be optimized and configured that such bottlenecks are avoided at least for a smaller set of failure scenarios. In this paper, we demonstrate the effectiveness of this routing optimization in IP networks. We use resilience analysis with suitable aggregate views on relative link loads. Furthermore, we compare conventional IP rerouting with IP fast reroute (IP-FRR) and show that IP-FRR can also significantly profit from routing optimization. This paper reviews major parts of previous publications and presents a new method to visualize and compare the resilience of different routing schemes.

• Objective Functions for Optimization of Resilient and Non-Resilient IP Routing Hartmann, Matthias; Hock, David; Menth, Michael; Schwartz, Christian in 7th International Workshop on the Design of Reliable Communication Networks (DRCN) (2009).
  • [ Abstract ]
  • [ BibTeX ]
  • [ EndNote ]
  • [ Download ]
  Intradomain routing in IP networks follows leastcost paths according to administrative link costs. Routing optimization modifies these values to minimize an objective function for a network with given link capacities and traffic matrix. An example for an objective function is the maximum utilization of all links under failure-free conditions or also after rerouting in case of network failures. Many papers have provided heuristic algorithms for routing optimization using different objective functions, but the investigation and comparison of various objective functions has not attracted much attention so far. In this work we present several objective functions for resilient IP routing. We also propose a new combined optimization approach which can simultaneously optimize different objective functions with almost no additional computation effort and describe new techniques to minimize overall computation time. The different objective functions and combinations thereof are then analyzed and compared experimentally.

  @inproceedings{info3-inproceedings-2009-358, abstract = {Intradomain routing in IP networks follows leastcost paths according to administrative link costs. Routing optimization modifies these values to minimize an objective function for a network with given link capacities and traffic matrix. An example for an objective function is the maximum utilization of all links under failure-free conditions or also after rerouting in case of network failures. Many papers have provided heuristic algorithms for routing optimization using different objective functions, but the investigation and comparison of various objective functions has not attracted much attention so far. In this work we present several objective functions for resilient IP routing. We also propose a new combined optimization approach which can simultaneously optimize different objective functions with almost no additional computation effort and describe new techniques to minimize overall computation time. The different objective functions and combinations thereof are then analyzed and compared experimentally.}, address = {Washington, D.C., USA}, author = {Hartmann, Matthias and Hock, David and Menth, Michael and Schwartz, Christian}, booktitle = {7th International Workshop on the Design of Reliable Communication Networks (DRCN)}, keywords = {sys:hidden:inproceedings}, month = 10, title = {Objective Functions for Optimization of Resilient and Non-Resilient IP Routing}, year = 2009 }

  %0 Conference Paper %1 info3-inproceedings-2009-358 %A Hartmann, Matthias %A Hock, David %A Menth, Michael %A Schwartz, Christian %B 7th International Workshop on the Design of Reliable Communication Networks (DRCN) %C Washington, D.C., USA %D 2009 %T Objective Functions for Optimization of Resilient and Non-Resilient IP Routing %X Intradomain routing in IP networks follows leastcost paths according to administrative link costs. Routing optimization modifies these values to minimize an objective function for a network with given link capacities and traffic matrix. An example for an objective function is the maximum utilization of all links under failure-free conditions or also after rerouting in case of network failures. Many papers have provided heuristic algorithms for routing optimization using different objective functions, but the investigation and comparison of various objective functions has not attracted much attention so far. In this work we present several objective functions for resilient IP routing. We also propose a new combined optimization approach which can simultaneously optimize different objective functions with almost no additional computation effort and describe new techniques to minimize overall computation time. The different objective functions and combinations thereof are then analyzed and compared experimentally.