Topology-aware multi-cluster architecture based on efficient index techniques

Abstract

In this paper, we focus on how to construct an efficient unstructured P2P system. The main contributions of our proposal are two-fold. First, aiming at alleviating the topology mismatch problem between the P2P logical overlay network and the physical underlying network, we proposed a Topology-aware Multi-cluster Overlay (TMO) architecture where peers self-organize into clusters based on network locality. Second, in order to further improve the search efficiency of the TMO architecture, we present two novel index techniques, namely, cluster-index technique and topic-index technique. The two different techniques are highly effective in different application domains in which the TMO architecture is deployed. The simulation results indicate that our proposed schemes are efficient in both resource usage and data retrieval. © IFIP International Federation for Information Processing 2005.