Christian Rothenberg, SMARTNESS PI Director, Raza Mustafa and Chadi Barakat (Inria, Université Cote d’Azur) have a new publication in the IEEE Wireless Communications and Networking Conference (WCNC), 2024. The publication “YouTube goes 5G: QoE Benchmarking and ML-based Stall Prediction” is a result of a research collaboration between INTRIG / UNICAMP and INRIA on real 5G/4G performance and adaptive video streaming. Due to a VISA-related issue, the paper had to be presented by Rosario Patane from Université Paris-Saclay. Thanks!
Given the dominance of adaptive video streaming services on Internet traffic, understanding how YouTube Quality of Experience (QoE) relates to real 4G and 5G Channel Level Metrics (CLM) is of interest to not only the research community but also to Mobile Network Operators (MNOs) and content creators. In this context, we collect YouTube and CLM logs with a one-second granularity spanning six months.
Then, the authors group the traces by their context, i.e., Mobility, Pedestrian, Bus/Railway terminals, and Static Outdoor, and derive key performance footprints of real 4G and 5G video streaming in the wild. They also develop Machine Learning (ML) classifiers to predict objective QoE video stalls by using past patterns from CLM traces. All datasets and software artifacts are released for reproducibility purposes.
News
New publication presented at WCNC
