Towards Better Quality of Experience in HTTP Adaptive Streaming

TL;DR

This paper challenges the common belief that stalling events have the worst impact on QoE in HTTP Adaptive Streaming, showing that quality switches can be equally or more detrimental based on subjective user studies.

Contribution

It provides empirical evidence that quality switches can impair QoE more than stalling events, prompting a reevaluation of QoE assessment and adaptation strategies in ABR algorithms.

Findings

Stalling events are not always the worst QoE impairments.

Quality switches can have a greater negative impact on user experience.

Reevaluation of QoE factors in adaptive streaming is necessary.

Abstract

HTTP Adaptive Streaming (HAS) is nowadays a popular solution for multimedia delivery. The novelty of HAS lies in the possibility of continuously adapting the streaming session to current network conditions, facilitated by Adaptive Bitrate (ABR) algorithms. Various popular streaming and Video on Demand services such as Netflix, Amazon Prime Video, and Twitch use this method. Given this broad consumer base, ABR algorithms continuously improve to increase user satisfaction. The insights for these improvements are, among others, gathered within the research area of Quality of Experience (QoE). Within this field, various researchers have dedicated their works to identifying potential impairments and testing their impact on viewers' QoE. Two frequently discussed visual impairments influencing QoE are stalling events and quality switches. So far, it is commonly assumed that those stalling events have the worst impact on QoE. This paper challenged this belief and reviewed this assumption by comparing stalling events with multiple quality and high amplitude quality switches. Two subjective studies were conducted. During the first subjective study, participants received a monetary incentive, while the second subjective study was carried out with volunteers. The statistical analysis demonstrated that stalling events do not result in the worst degradation of QoE. These findings suggest that a reevaluation of the effect of stalling events in QoE research is needed. Therefore, these findings may be used for further research and to improve current adaptation strategies in ABR algorithms.