Balancing Performance and Fairness in P2P Live Video Systems

Measurement studies of popular peer-to-peer (P2P) live video systems reveal that there exists extreme unfairness among peers in the swarm. Such kind of unfairness will provide disincentives to altruistic super peers and encourage free riding behavior in the system. It is essential for video service providers to take fairness into consideration when designing their systems. In this paper, we develop a simple model of P2P live video systems to understand the fairness problem from a theoretic perspective. We identify the fundamental tradeoff between fairness and performance, and propose a semidistributed algorithm based on the subgradient method to tune the P2P live video system toward optimal fairness while still maintaining the targeted universal streaming rate. We also conduct extensive trace-driven simulations to validate the effectiveness of our proposed algorithm. The simulation results show that our algorithm can guide the system toward optimal fairness quickly without degrading streaming performance at the same time.