QoE Evaluation for Adaptive Video Streaming: Enhanced MDT with Deep Learning

TL;DR

This paper introduces a deep learning-based architecture for virtual drive tests to evaluate and improve QoE in adaptive video streaming by detecting anomalies and predicting application performance using network and application KPIs.

Contribution

The work presents a novel architecture combining pattern recognition, KPI mapping, and anomaly detection for virtual drive tests, enhancing QoE evaluation without physical drive tests.

Findings

Mean maximum F1-score of 77% in anomaly detection.

Playback time is the most critical parameter for video quality.

RF indicators improve QoE estimation in specific cases.

Abstract

The network performance is usually assessed by drive tests, where teams of people with specially equipped vehicles physically drive out to test various locations throughout a radio network. However, intelligent and autonomous troubleshooting is considered a crucial enabler for 5G- and 6G-networks. In this paper, we propose an architecture for performing virtual drive tests by facilitating radio-quality data from the user equipment. Our architecture comprises three main components: i) a pattern recognizer that learns a typical pattern for the application from application Key Performance Indicators (KPI); ii) a predictor for mapping network KPI with the application KPI; iii) an anomaly detector that compares the predicted application performance with that of the typical application pattern. In this work, we use a commercial state-of-the-art network optimization tool to collect network and application KPI at different geographical locations and at various times of the day for training an initial learning model. We perform extensive numerical analysis to demonstrate key parameters impacting correct video quality prediction and anomaly detection. We show that the playback time is the single most important parameter affecting the video quality, since video packets are usually buffered ahead of time during the playback. However, radio frequency (RF) performance indicators characterizing the quality of the cellular connection improve the QoE estimation in exceptional cases. We demonstrate the efficacy of our approach by showing that the mean maximum F1-score of our method is 77%. Finally, the proposed architecture is flexible and autonomous, and it can operate with different user applications as long as the relevant user-based traces are available.