Due to the mass-market of file sharing, majority of existing P2P systems are based on unstructured overlay networks, where P2P search still remains challenging issues. In this paper, we propose a small-world based semantic search architecture in P2P Networks, called CommuSearch, which has three distinguished features: 1) grouping peers into hierarchical class by exploiting heterogeneity; 2) constructing overlapped semantic communities according to small-world characteristics; and 3) parallel and hierarchical routing based on results caching. We conduct extensive simulation experiments and the numerical results show that the performance of CommuSearch substantially outperforms existing architectures in terms of average search latency, search success ratio and recall ratio, while the overhead incurred for maintaining the community is reasonably low.
展开▼