Performance Evaluation of Edge Computing Assisted Adaptive Streaming Algorithms
Waqas ur Rahman, Choong Seon Hong, Eui‐Nam Huh · 2020
Multi-Access Edge Computing (MEC) adaptive streaming presents an opportunity to jointly optimize the quality of experience in cellular networks by moving the adaptation intelligence from the client to the edge cloud. In this paper, we investigate the performance of MEC-assisted algorithms and compare their performance with the client based adaptation logic. We conduct extensive experiments and quantify benefits and drawbacks of edge computing-assisted adaptation algorithms. The results from our experiments reveal that MEC-assisted algorithms outperforms the purely client-based heuristics in most of the video quality metrics. However, the results also show that the MEC-assisted algorithms are not able to protect the playback buffer from drying up under different network settings.