Machine Learning Approach to Estimate Video QoE of Encrypted DASH Traffic in 5G Networks

Abstract

5G communication technologies promise reduced latency and increased throughput, among other features. The so-called enhanced Mobile Broadband (eMBB) type of services will contribute to further adoption of video streaming services. In this work, we use a realistic emulation environment based on 5G traces to investigate how Dynamic Adaptive Streaming over HTTP (DASH) video content using three state-of-art Adaptive Bitrate Streaming (ABS) algorithms is impacted in static and mobility scenarios. Given the wide adoption of end-to-end encryption, we use machine learning (ML) models to estimate multiple key video Quality of Experience (QoE) indicators (KQIs) taking network-level Quality of Service (QoS) metrics as input features. The proposed feature extraction method does not require chunk-detection, significantly reducing the complexity of the monitoring approach and providing new means for QoE evaluation of HAS protocols. We show that our ML classifiers achieve a QoE prediction accuracy above 91%.