QoE evaluation in adaptive streaming: enhanced MDT with deep learning

We propose an architecture for performing virtual drive tests for mobile network performance evaluation by facilitating radio signal strength data from user equipment. Our architecture comprises three main components: (i) pattern recognizer that learns a typical (nominal) behavior for application KPIs (key performance indicators); (ii) predictor that maps from network KPIs to application KPIs; (iii) anomaly detector that compares predicted application performance with said typical pattern. To simulate user-traces, we utilize a commercial state-of-the-art network optimization tool, which collects application and network KPIs at different geographical locations at various times of the day, to train an initial learning model. Although the collected data is related to an adaptive video streaming application, the proposed architecture is flexible, autonomous and can be used for other applications. We perform extensive numerical analysis to demonstrate key parameters impacting video quality prediction and anomaly detection. Playback time is shown to be the most important parameter affecting video quality, most likely due to video packet buffering during playback. We additionally observe that network KPIs, which characterize the cellular connection strength, improve QoE (quality of experience) estimation in anomalous cases diverging from the nominal. The efficacy of our approach is demonstrated with a mean-maximum F1-score of 77%