A Server-assisted Adaptive Content Replacement Algorithm for Peer-to-Peer Video-on-Demand System
In recent years, Peero-to-Peer assisted Video-on-Demand (P2P VoD) has become an effective and efficient approach to distribute high-quality videos to large number of peers. In a P2P VoD system, each peer contributes storage to store several videos (the terms video and movie are used interchangeably) or video segments to help offload the server. The replication strategy, which determines the videos stored at each peer’s storage, plays an important role. There are two approaches. The first approach formulates the problem as a combinatorial optimization problem to minimize the server load. The drawbacks with this approach are (a) the need to collect a large amount of detailed parameters that may be highly dynamic; and (b) the optimization problem is combinatorial in nature, hence computationally expensive. The second approach relies on simple adaptive algorithms such as Least-Frequently-Requested (LFR) and First-In-First-Out (FIFO). This approach does not work well enough to offload the server for some peer access patterns. In this paper, we propose a hybrid replication strategy that requires server’s assistance in collecting and maintain some state information. Our hybrid solution is light-weight in terms of information collection as well as computational complexity in comparison to the optimization approach. On the other hand, our replication strategy achieves much better performance compared with those simple adaptive replication strategies (LFR and FIFO). Moreover, it is adaptive and can respond to peer churn and popularity churn quickly.
信息和通信技术/电信
多媒体
11/ENG/408
Inventor(s): Professor Dah Ming CHIU, Department of Information Engineering
香港
