SDN - based Dynamic Bandwidth Allocation for Multiple Video-on-Demand Players over HTTP

This nowadays, HTTP adaptive streaming (HAS) has been becoming the de-factor standard for video streaming over the multimedia network. However, HAS-alone cannot guarantee a seamless viewing experience, the adaptation of HAS in the management network faces a big challenge because of purely client-driven approaches which lead to unfair competition of available bandwidth resource when multiple bitrate-adaptive players share a same bottleneck network link. At that time, each HAS client tries independently to maximize its own bandwidth sharing, which leads to the competition of network resources among clients causing greatly reduced QoE (Quality of Experience) of end users. This competition will affect negatively several main metrics for each video player: fairness, efficiency, and stability. In this paper, we propose a scheme of bitrate adaptation for the HAS system combined with a Software Defined Networking (SDN)-based dynamic resource allocation, which aims to improve the quality of experience among competing clients. Our experiment results show that the proposed method significantly outperforms the conventional method on all the key QoE parameters under several scenarios.