Nikolas Wehner - Lehrstuhl für Informatik III

Telefon	(0931) 31-88150
Telefax	(0931) 31-86632
E-Mail	nikolas.wehner@uni-wuerzburg.de
Raum	A213a
Anschrift	Lehrstuhl für Informatik III Am Hubland D-97074 Würzburg

Contents: Overview | Publications | Teaching | Working Group | Projects

Research Interests

My research interests include the following topics:

Quality of Experience (QoE) of Internet applications
Measurement and analytics of (encrypted) network traffic
Artificial intelligence and machine learning for networks
Performance analysis and modeling of communication systems

Recent Publications

1.
Wehner, N., Seufert, A., Hoßfeld, T. & Seufert, M. A Tutorial on Data-Driven Quality of Experience Modeling with Explainable Artificial Intelligence. IEEE Communications Surveys & Tutorials (2025).
- [ BibTeX ]
- [ EndNote ]
@article{info3-article-2025-2, author = {Wehner, Nikolas and Seufert, Anika and Hoßfeld, Tobias and Seufert, Michael}, journal = {IEEE Communications Surveys & Tutorials}, keywords = {sys:hidden:article}, month = {06}, title = {A Tutorial on Data-Driven Quality of Experience Modeling with Explainable Artificial Intelligence}, year = 2025 }

%0 Journal Article %1 info3-article-2025-2 %A Wehner, Nikolas %A Seufert, Anika %A Hoßfeld, Tobias %A Seufert, Michael %D 2025 %J IEEE Communications Surveys & Tutorials %T A Tutorial on Data-Driven Quality of Experience Modeling with Explainable Artificial Intelligence
1.
Wehner, N. et al. Exploring the Application of Time Series Foundation Models to Network Monitoring Tasks. Computer Networks, Special Issue on Generative and Explainable AI for Internet Traffic and Network Architectures (2025).
- [ BibTeX ]
- [ EndNote ]
@article{info3-article-2025-1, author = {Wehner, Nikolas and Casas, Pedro and Dietz, Katharina and Geißler, Stefan and Hoßfeld, Tobias and Seufert, Michael}, journal = {Computer Networks, Special Issue on Generative and Explainable AI for Internet Traffic and Network Architectures}, keywords = {sys:hidden:article}, month = {05}, title = {Exploring the Application of Time Series Foundation Models to Network Monitoring Tasks}, year = 2025 }

%0 Journal Article %1 info3-article-2025-1 %A Wehner, Nikolas %A Casas, Pedro %A Dietz, Katharina %A Geißler, Stefan %A Hoßfeld, Tobias %A Seufert, Michael %D 2025 %J Computer Networks, Special Issue on Generative and Explainable AI for Internet Traffic and Network Architectures %T Exploring the Application of Time Series Foundation Models to Network Monitoring Tasks
1.
Wehner, N., Karagkioules, T., Halepovic, E., Simonovski, F. & Hoßfeld, T. To Cap or not to Cap: Bandwidth Capping Effects on Network Interactions and QoE of Competing Short Video Streams. in 16th ACM Multimedia Systems Conference (MMSys) (2025).
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Delivering popular short video streaming services like TikTok, Instagram Reels, or YouTube Shorts, poses substantial challenges for service providers and network operators. This is not only due to high download volumes but also due to high-volume pre-loading strategies that cause high bandwidth demand variations. These strategies, designed to reduce initial delays, can additionally lead to bandwidth excess when users swipe quickly through videos and consume only a fraction of downloaded content. This creates inefficiencies and unbalanced network resource utilization, particularly in competitive bandwidth environments. To address these challenges, we investigate the effectiveness of bandwidth capping in this paper, i.e., limiting the throughput of video flows in the network. We conduct measurement studies to analyze the impact of capping on network interactions and Quality of Experience (QoE) of three popular short video services in different scenarios. We find that capping substantially reduces download volume (15% - 45% median reduction) and bandwidth excess (18% - 52% mean reduction), while bandwidth utilization fairness improves. Meanwhile, QoE surprisingly remains nearly unaffected in most cases, with only minor statistical differences in a few scenarios.

@inproceedings{info3-inproceedings-2025-1, abstract = {Delivering popular short video streaming services like TikTok, Instagram Reels, or YouTube Shorts, poses substantial challenges for service providers and network operators. This is not only due to high download volumes but also due to high-volume pre-loading strategies that cause high bandwidth demand variations. These strategies, designed to reduce initial delays, can additionally lead to bandwidth excess when users swipe quickly through videos and consume only a fraction of downloaded content. This creates inefficiencies and unbalanced network resource utilization, particularly in competitive bandwidth environments. To address these challenges, we investigate the effectiveness of bandwidth capping in this paper, i.e., limiting the throughput of video flows in the network. We conduct measurement studies to analyze the impact of capping on network interactions and Quality of Experience (QoE) of three popular short video services in different scenarios. We find that capping substantially reduces download volume (15% - 45% median reduction) and bandwidth excess (18% - 52% mean reduction), while bandwidth utilization fairness improves. Meanwhile, QoE surprisingly remains nearly unaffected in most cases, with only minor statistical differences in a few scenarios.}, address = {Stellenbosch, South Africa}, author = {Wehner, Nikolas and Karagkioules, Theodoros and Halepovic, Emir and Simonovski, Filip and Hoßfeld, Tobias}, booktitle = {16th ACM Multimedia Systems Conference (MMSys)}, keywords = {sys:hidden:inproceedings}, month = {04}, title = {To Cap or not to Cap: Bandwidth Capping Effects on Network Interactions and QoE of Competing Short Video Streams}, year = 2025 }

%0 Conference Paper %1 info3-inproceedings-2025-1 %A Wehner, Nikolas %A Karagkioules, Theodoros %A Halepovic, Emir %A Simonovski, Filip %A Hoßfeld, Tobias %B 16th ACM Multimedia Systems Conference (MMSys) %C Stellenbosch, South Africa %D 2025 %T To Cap or not to Cap: Bandwidth Capping Effects on Network Interactions and QoE of Competing Short Video Streams %X Delivering popular short video streaming services like TikTok, Instagram Reels, or YouTube Shorts, poses substantial challenges for service providers and network operators. This is not only due to high download volumes but also due to high-volume pre-loading strategies that cause high bandwidth demand variations. These strategies, designed to reduce initial delays, can additionally lead to bandwidth excess when users swipe quickly through videos and consume only a fraction of downloaded content. This creates inefficiencies and unbalanced network resource utilization, particularly in competitive bandwidth environments. To address these challenges, we investigate the effectiveness of bandwidth capping in this paper, i.e., limiting the throughput of video flows in the network. We conduct measurement studies to analyze the impact of capping on network interactions and Quality of Experience (QoE) of three popular short video services in different scenarios. We find that capping substantially reduces download volume (15% - 45% median reduction) and bandwidth excess (18% - 52% mean reduction), while bandwidth utilization fairness improves. Meanwhile, QoE surprisingly remains nearly unaffected in most cases, with only minor statistical differences in a few scenarios.
1.
Dietz, K. et al. Agree to Disagree: Exploring Consensus of XAI Methods for ML-based NIDS. in 1st Workshop on Network Security Operations (NeSecOr) as part of CNSM’24 (2024).
- [ BibTeX ]
- [ EndNote ]
@inproceedings{info3-inproceedings-2024-8, address = {Prague, Czech Republic}, author = {Dietz, Katharina and Hajizadeh, Mehrdad and Schleicher, Johannes and Wehner, Nikolas and Geißler, Stefan and Casas, Pedro and Seufert, Michael and Hoßfeld, Tobias}, booktitle = {1st Workshop on Network Security Operations (NeSecOr) as part of CNSM'24}, keywords = {vipnano}, month = 10, title = {Agree to Disagree: Exploring Consensus of XAI Methods for ML-based NIDS}, year = 2024 }

%0 Conference Paper %1 info3-inproceedings-2024-8 %A Dietz, Katharina %A Hajizadeh, Mehrdad %A Schleicher, Johannes %A Wehner, Nikolas %A Geißler, Stefan %A Casas, Pedro %A Seufert, Michael %A Hoßfeld, Tobias %B 1st Workshop on Network Security Operations (NeSecOr) as part of CNSM'24 %C Prague, Czech Republic %D 2024 %T Agree to Disagree: Exploring Consensus of XAI Methods for ML-based NIDS
1.
Dietz, K. et al. Certainly Uncertain: Demystifying ML Uncertainty for Active Learning in Network Monitoring Tasks. in 20th International Conference on Network and Service Management (CNSM) (2024).
- [ BibTeX ]
- [ EndNote ]
@inproceedings{info3-inproceedings-2024-7, address = {Prague, Czech Republic}, author = {Dietz, Katharina and Hajizadeh, Mehrdad and Wehner, Nikolas and Geißler, Stefan and Casas, Pedro and Seufert, Michael and Hoßfeld, Tobias}, booktitle = {20th International Conference on Network and Service Management (CNSM)}, keywords = {vipnano}, month = 10, title = {Certainly Uncertain: Demystifying ML Uncertainty for Active Learning in Network Monitoring Tasks}, year = 2024 }

%0 Conference Paper %1 info3-inproceedings-2024-7 %A Dietz, Katharina %A Hajizadeh, Mehrdad %A Wehner, Nikolas %A Geißler, Stefan %A Casas, Pedro %A Seufert, Michael %A Hoßfeld, Tobias %B 20th International Conference on Network and Service Management (CNSM) %C Prague, Czech Republic %D 2024 %T Certainly Uncertain: Demystifying ML Uncertainty for Active Learning in Network Monitoring Tasks

A comprehensive list of all publications can be found here: Publications

Nikolas Wehner M. Sc.

Research Interests

Recent Publications

Bildnachweise