AQCS: Adaptive Queue-Based Chunk Scheduling for P2P Live Streaming

Abstract

P2P streaming has been popular and is expected to attract even more users. One major challenge for P2P streaming is to offer users satisfactory Quality of Experience (QoE) in terms of video resolution, startup delay, and playback smoothness, all require efficient utilization of bandwidth resources in P2P networks. In this paper, we propose AQCS, adaptive queue-based chunk scheduling, that can support the maximum streaming rate allowed by a P2P streaming system with small signaling overhead and short startup delay. AQCS is a distributed algorithm with minimum requirement on peers. Queue-based design enables peers to be self-adaptive to the bandwidth variations and peer churn, and automatically converges to the optimal operating point. The prototype of AQCS is implemented and various implementation issues are examined. The experiments over the PlanetLab further demonstrate AQCS's optimality and its robustness against changing system/network environment.