VAStream: Virtual adaptive substream partition and scheduling in data-driven P2P live streaming

Abstract

Substream-based P2P live streaming systems can achieve high performance according to multiple metrics, including distribution delay, system robustness and protocol overhead. However, the current division approach into substreams is not flexible and cannot be adaptive to dynamic network environments, which characterize the basic transport facilities for supporting P2P live streaming services. In this paper, we propose a virtual adaptive substream partition and scheduling protocol, namely VAStream, which can enforce substream partition or merge operation based on the current P2P network status. This protocol also presents properly crafted schemes to deal with the issues in complex network situation, and effectively makes use of peer resources. Comparing with other mechanisms, the simulation results show that VAStream can achieve low distribution delay, high chunk arrival ratio and good system robustness.