Optimizing push scheduling algorithm based on network coding for mesh Peer-to-Peer live streaming

Abstract

In most large-scale Peer-to-Peer (P2P) live streaming systems, mesh structures are constructed to provide robustness in dynamic P2P environment. The pull scheduling algorithm is widely used in this mesh structure, but it restricts the performance of entire system. Recently, network coding is introduced in mesh P2P streaming system to improve the performance, which makes the push scheduling strategy feasible. Although some push scheduling algorithms based on network coding have achieved some success, there is still a lack of the theoretical model and optimal solution. In this paper, we propose a novel optimal push scheduling algorithm based on network coding. The main contributions of this paper are: i) We put forward a new theoretical model, with a new evaluation function, which simultaneously considers the scarcity and timeliness of the segment; ii) We formulate the push scheduling strategy as an optimization problem and propose a greedy algorithm to solve it; iii) We systematically realize our proposed optimal push scheduling algorithm. Compared with the most famous push scheduling algorithm based on network coding R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> , the simulation results demonstrate that decode delay, decode ratio and redundant fraction of the P2P streaming system with our algorithm can be significantly improved, without losing throughput and increasing overhead.