A Dynamic SGP Selection Algorithm based on Evolutionary Game for Hybrid P2P Streaming System

Abstract

Due to high efficiency and good scalability, hierarchical hybrid P2P architecture has drawn more and more attentions in P2P video streaming applications recently. The problem about Super Group Peers (SGPs) selection, which is the key problem in hierarchical hybrid P2P architecture, is becoming highly challenging because super peers must be selected from a huge and dynamically changing network. In this paper, we propose a SGP selection game model based on evolutionary game framework and analyze its evolutionarily stable strategies in theory. Moreover, we propose a distributed Q-Learning algorithm, which has the ability to make the peers converge to the ESSs based on its own payoff history. Compared to the randomly super peer selection scheme in traditional P2P streaming systems, experiment results show that the proposed algorithm achieves better performance in terms of social welfare, average upload rates of SGPs, and keeps the upload capacity of the P2P streaming system increasing steadily with the number of peers increasing.