基于临近结点聚类构建层次化BitTorrent文件共享系统

为了提高BitTorrent对等网络系统的文件共享性能,本文提出基于临近结点聚类方法,将临近的结点聚合成结点簇,同一结点簇中结点优先建立共享连接,构建了层次化BitTorrent文件共享机制.通过基于马尔可夫链的流体数学模型分析该系统性能,证明了层次化结构的BitTorrent系统比原BitTorrent系统具有更好的文件共享性能.模拟实验证实了理论分析结果,并显示该系统有效地降低了中央服务器Tracker的负载,提高了系统可扩展性和稳定性.

Building Hierarchical BitTorrent-like Peer-to-Peer File Sharing Systems Based on Proximity-Aware Peer Clustering

In this paper, a hierarchical BitTorrent-like file sharing system is proposed to improve the performance of file sharing. Peers in such system are grouped into clusters according to their proximity in the underlying overlay network. A fluid model is developed to compare the proposed hierarchical BitTorrent-like system with the original BitTorrent system. With this model, we find that the hierarchical BitTorrent-like system improves the performance of file sharing quite effeclively.Finally,the simulation results prove that the hierarchical BitTorrent-like system achieves better scalability and efficiency while retaining the robustness and incentives of the original BitTorrent paradigm.