Publications

Video streaming has become an indispensable technology in people’s lives, while its usage keeps constantly increasing. The variability, instability and unpredictability of network conditions pose one of the biggest challenges to video streaming. In this chapter, we analyze HTTP Adaptive Streaming, a technology that relieves these issues by adapting the video reproduction to the current network conditions. Particularly, we study how context awareness can be combined with the adaptive streaming logic to design a proactive client-based video streaming strategy. Our results show that such a context-aware strategy manages to successfully mitigate stallings in light of network connectivity problems, such as an outage. Moreover, we analyze the performance of this strategy by comparing it to the optimal case, as well as by considering situations where the awareness of the context lacks reliability.

Due to biased assumptions on the underlying ordinal rating scale in subjective Quality of Experience (QoE) studies, Mean Opinion Score (MOS)-based evaluations provide results, which are hard to interpret and can be misleading. This paper proposes to consider the full QoE distribution for evaluating, reporting, and modeling QoE results instead of relying on MOS-based metrics derived from results based on ordinal rating scales. The QoE distribution can be represented in a concise way by using the parameters of a multinomial distribution without losing any information about the underlying QoE ratings, and even keeps backward compatibility with previous, biased MOS-based results. Considering QoE results as a realization of a multinomial distribution allows to rely on a well-established theoretical background, which enables meaningful evaluations also for ordinal rating scales. Moreover, QoE models based on QoE distributions keep detailed information from the results of a QoE study of a technical system, and thus, give an unprecedented richness of insights into the end users’ experience with the technical system. In this work, existing and novel statistical methods for QoE distributions are summarized and exemplary evaluations are outlined. Furthermore, using the novel concept of quality steps, simulative and analytical QoE models based on QoE distributions are presented and showcased. The goal is to demonstrate the fundamental advantages of considering QoE distributions over MOS-based evaluations if the underlying rating data is ordinal in nature.

Evaluating the Quality of Experience (QoE) of video streaming and its influence factors has become paramount for streaming providers, as they want to maintain high satisfaction for their customers. In this context, crowdsourced user studies became a valuable tool to evaluate different factors which can affect the perceived user experience on a large scale. In general, most of these crowdsourcing studies either use, what we refer to, as an in vivo or an in vitro interface design. In vivo design means that the study participant has to rate the QoE of a video that is embedded in an application similar to a real streaming service, e.g., YouTube or Netflix. In vitro design refers to a setting, in which the video stream is separated from a specific service and thus, the video plays on a plain background. Although these interface designs vary widely, the results are often compared and generalized. In this work, we use a crowdsourcing study to investigate the influence of three interface design alternatives, an in vitro and two in vivo designs with different levels of interactiveness, on the perceived video QoE. Contrary to our expectations, the results indicate that there is no significant influence of the study’s interface design in general on the video experience. Furthermore, we found that the in vivo design does not reduce the test takers’ attentiveness. However, we observed that participants who interacted with the test interface reported a higher video QoE than other groups.

Video streaming is the killer application of the Internet today. In this paper, we address the problem of real-time, passive Quality-of-Experience (QoE) monitoring of HTTP Adaptive Video Streaming (HAS), from the Internet-Service-Provider (ISP) perspective - i.e., relying exclusively on in-network traffic measurements. Given the wide adoption of end-to-end encryption, we resort to machine-learning (ML) models to estimate multiple key video-QoE indicators (KQIs) from the analysis of the encrypted traffic. We present ViCrypt, an ML-driven monitoring solution able to infer the most important KQIs for HTTP Adaptive Streaming (HAS), namely stalling, initial delay, video resolution, and average video bitrate. ViCrypt performs estimations in real-time, during the playback of an ongoing video-streaming session, with a fine-grained temporal resolution of just one second. For this, it relies on lightweight, stream-like features continuously extracted from the encrypted stream of packets. Empirical evaluations on a large and heterogeneous corpus of YouTube measurements show that ViCrypt can infer the targeted KQIs with high accuracy, enabling large-scale passive video-QoE monitoring and proactive QoE-aware traffic management. Different from the state of the art, and besides real-time operation, ViCrypt is not bound to coarse-grained KQI-classes, providing better and sharper insights than other solutions. Finally, ViCrypt does not require chunk-detection approaches for feature extraction, significantly reducing the complexity of the monitoring approach, and potentially improving on generalization to different HAS protocols used by other video-streaming services such as Netflix and Amazon.

The application area of smart speakers is steadily increasing with the Amazon Echo family and Google Home being brand leaders. Use cases include, among others, updating the calendar, home automation, or simply assisting users in their every day life. With the increasing amount of devices, the traffic generation and requesting process becomes a relevant subject to be studied in order to create traffic models and predict the impact on networks by these types of devices. Furthermore, with a detailed understanding of the devices, service quality can be monitored and improved for the end user. For that reason, in this work the requesting and traffic generation process of the Amazon Echo Dot and Google Home are studied and the generated network load of both devices is compared. With the insights of this study and additional device usage statistics, detailed traffic and usage models can be created.

Bridge-local latency computation is often regarded with caution, while new shaping mechanisms and timed gates are developed to achieve deterministic guarantees. However, these new concepts require additional hardware support in the forwarding devices, and many of them are based on assumptions of central control and network-wide information being available. This document presents a per-hop latency bound for individual streams in a class-based network that applies the IEEE 802.1Q strict priority transmission selection algorithm. It does not rely on shaping or timed gates and uses the accumulated latency fields during the reservation process to provide upper bounds with bridge-local information. The presented delay bound is proven formally and then evaluated with respect to its accuracy. It shows that deterministic latency with priority queuing is indeed feasible, and it indicates the required information that must be provided during resource reservation, e.g., to protocols developed in IEEE 802.1Qdd.

This work presents a proven per-hop latency bound for real-time networks with admission control that does not rely on shaping or timed gates. It can be applied in a distributed control plane using only bridge-local information, making it an ideal candidate for brownfield real-time network installations. A brief comparison with Asynchronous Traffic Shaping (ATS) shows that the achieved network utilization is comparable to that of ATS in some scenarios, while it only lags behind in scenarios with accumulating bursts where re-shaping could actually reduce the interference of the observed streams.

The goal of the white paper at hand is as follows. The definitions of the terms build a framework for discussions around the hype topic ‘crowdsourcing’. This serves as a basis for differentiation and a consistent view from different perspectives on crowdsourced network measurements, with the goal to provide a commonly accepted definition in the community. The focus is on the context of mobile and fixed network operators, but also on measurements of different layers (network, application, user layer). In addition, the white paper shows the value of crowdsourcing for selected use cases, e.g., to improve QoE or regulatory issues. Finally, the major challenges and issues for researchers and practitioners are highlighted. This white paper is the outcome of the Würzburg seminar on “Crowdsourced Network and QoE Measurements” which took place from 25-26 September 2019 in Würzburg, Germany. International experts were invited from industry and academia. They are well known in their communities, having different backgrounds in crowdsourcing, mobile networks, network measurements, network performance, Quality of Service (QoS), and Quality of Experience (QoE). The discussions in the seminar focused on how crowdsourcing will support vendors, operators, and regulators to determine the Quality of Experience in new 5G networks that enable various new applications and network architectures. As a result of the discussions, the need for a white paper manifested, with the goal of providing a scientific discussion of the terms “crowdsourced network measurements” and “crowdsourced QoE measurements”, describing relevant use cases for such crowdsourced data, and its underlying challenges. During the seminar, those main topics were identified, intensively discussed in break-out groups, and brought back into the plenum several times. The outcome of the seminar is this white paper at hand which is – to our knowledge – the first one covering the topic of crowdsourced network and QoE measurements.