On the efficiency and fairness of multiplayer HTTP-based adaptive video streaming

Abstract

User-perceived quality-of-experience (QoE) is critical in Internet video delivery systems. Many previous efforts have studied the design of client-side bitrate adaptation algorithms to maximize single-player QoE. However, multiplayer QoE fairness becomes critical as the growth of video traffic makes it more likely that multiple players share a bottleneck in the network. Despite several recent proposals, there are still a series of open questions. In this paper, we shed light to the problem space from a control theory perspective by formalizing the multiplayer QoE fairness problem and address two key questions. First, we derive the sufficient conditions of convergence to steady state QoE fairness under a TCP-based bandwidth sharing scheme. Based on the insight from this analysis that in-network active bandwidth allocation is needed, we propose a non-linear MPC-based, router-assisted bandwidth allocation algorithm that regards each player as a closed-loop system. We use trace-driven simulations to show the improvement over existing approaches. We identify several research directions enabled by the control theoretic modeling and envision that control theory can play an important role on guiding real system design in adaptive video streaming.