A Trace-Driven Approach to Evaluate the Scalability of P2P-Based Video-on-Demand Service

Peer-to-peer (P2P) networks have been emerging as one of the most promising approaches to improve the scalability of video-on-demand (VoD) service over Internet. Although a number of architectures and streaming protocols have been proposed in past years, there is few work to study the practical performance of P2P-based VoD service especially considering the real user behavior which actually has significant impact on the system scalability. Therefore, in this paper, we first characterize the user behavior by analyzing a large amount of real traces from a popular VoD system supported by the biggest television station in China, cctv.com. Then, we examine the practical scalability of P2P-based VoD service through extensive trace-driven simulation under a general system framework. The results show that P2P networks scale well in providing VoD service under real user behavior by saving a considerable percentage of server bandwidth. Moreover, it is observed that adopting hard cache at client side achieves much better system scalability than that with soft cache. We also identify the impact of various aspects of user behavior upon system scalability through detailed simulation. We believe that our study will shine insightful light on the understanding of practical scalability of P2P-based VoD service and be helpful to future system design and optimization