Publikationen

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.

Measuring and monitoring YouTube Quality of Experience is a challenging task, especially when dealing with cellular networks and smartphone users. Using a large-scale database of crowdsourced YouTube-QoE measurements in smartphones, we conceive multiple machine-learning models to infer different YouTube-QoE-relevant metrics and userbehavior- related metrics from network-level measurements, without requiring root access to the smartphone, video-player embedding, or any other reverse-engineering-like approaches. The dataset includes measurements from more than 360 users worldwide, spanning over the last five years. Our preliminary results suggest that QoE-based monitoring of YouTube mobile can be realized through machine learning models with high accuracy, relying only on network-related features and without accessing any higher-layer metric to perform the estimations.

We address the problem of real-time QoE monitoring of HAS, from the ISP perspective, focusing in particular on videoresolution analysis. Given the wide adoption of end-to-end encryption, we resort to machine-learning models to predict different video resolution levels in a fine-grained scale, ranging from 144p to 1080p resolution, using as input only packet-level data. The proposed measurement system performs predictions in real time, during the course of an ongoing video-streaming session, with a time granularity as small as one second. We consider the particular case of YouTube video streaming. Empirical evaluations on a large and heterogeneous corpus of YouTube measurements demonstrate that the proposed system can predict video resolution with very high accuracy, and in real time. Different from state of the art, the prediction task is not bound to coarse-grained video quality classes and does not require chunk-detection approaches for feature extraction.

Spotify is the most-listened audio streaming provider in 2019 with 217 million active users per month. Providers are therefore interested in the quality and functionality of Spotify in order to provide their users with the best possible streaming quality. While video streaming services such as Netflix and their streaming approach have been extensively explored in previous research, audio streaming services like Spotify and their corresponding behavior at certain network conditions have not been considered in detail yet. In this paper, we perform a QoE analysis under various network conditions and examine the app browsing performance of the audio streaming platform Spotify using its native Android mobile application. We have developed a measurement tool that emulates a user listening to audio through Spotify. While streaming, application and network layer parameters are captured that have a high correlation to the user’s QoE. The paper shows a baseline scenario including the streaming of a single song as well as playlist streaming behavior. Next, the effect of interruptions on the streaming behavior is evaluated and finally, the influence of network impairments on QoE key performance indicators such as initial delay is shown.

Measuring and monitoring YouTube Quality of Experience is a challenging task, especially when dealing with cellular networks and smartphone users. Using a large-scale database of crowdsourced YouTube-QoE measurements in smartphones, we conceive multiple machine-learning models to infer different YouTube-QoE-relevant metrics and user-behavior-related metrics from network-level measurements, without requiring root access to the smartphone, video-player embedding, or any other reverse-engineering-like approaches. The dataset includes measurements from more than 360 users worldwide, spanning over the last five years. Our preliminary results suggest that QoE-based monitoring of YouTube mobile can be realized through machine learning models with high accuracy, relying only on network-related features and without accessing any higher-layer metric to perform the estimations.