Improved Schemes for Node Clustering in Decentralized Peer-to-Peer Networks

Abstract

Node Clustering has wide ranging applications in decentralized Peer-to-Peer (P2P) networks such as P2P file sharing systems, mobile ad-hoc networks, P2P sensor networks and so forth. In this work, We propose two distributed approaches for node clustering that based on the scaled coverage measure (SCM), a measure of the accuracy of the partition of the network into clusters. The novelty of our approaches is to process nodes in local vicinity in special orders. Simulation study shows that our approach derives a more accurate partition with less orphan nodes, and converges faster than previously proposed methods, for both random topologies and power law topologies.