Computing QoE-Relevant Adaptive Video Streaming Metrics Using Discrete-Time Analysis

Abstract

HTTP Adaptive Streaming (HAS) is the de-facto standard for video delivery over the Internet. Splitting the video clip into small segments and providing multiple quality levels per segment allows the client to dynamically adapt the quality to current network conditions. The performance of HAS, and as a consequence the user Quality of Experience (QoE), is influenced by a multitude of parameters. This includes adjustable settings like quality switching thresholds, the initial buffer level, or the maximum buffer, as well as video characteristics like segment duration or the variation of segment sizes along the video. Finding an appropriate tuning of those parameters still remains a challenge, which is mainly tackled by performing testbed measurements or simulative analysis. Due to the large problem space and the complex interactions of the involved influence factors, a holistic comparison of a multitude of parameter settings is extremely time intensive. To tackle this problem, we propose to enhance a GI/GI/1 system with pq-policy, which models video buffer behavior, with the capability to switch between different quality levels. This allows to investigate all relevant QoE influence factors for HAS-based video delivery. In a first evaluation, we illustrate the impact of different quality switching thresholds on the QoE influence factors for varying network conditions.

Efficient Video QoE Prediction in Intelligent O-RAN

“…However, this research does not use AI/ML techniques and instead uses an adaptive genetic algorithm for resource provi-sioning. Schwarzmann et al estimate video streaming QoE in 5G architecture using regression techniques on a mobile-streaming use case [13]. They proved that the subjective QoE score can accurately be predicted using linear regression techniques.…”