Efficient content distribution method based on location and similarity in unstructured P2P system

Abstract

The peer-to-peer (P2P) systems have grown significantly over the last few years due to their high potential of sharing various resources. However, identifying the location and content similarity between peers is very costly and time-consuming as it involves the cooperation of many peers. In this study, we propose an ISP2P (Intelligent Super-Peer based P2P) system, which classifies the peers into three types, ASP (Agent Super-Peer), SP (Super-Peer) and OP (Ordinary-Peer), and utilizes the location information and content types to provide efficient content distribution and retrieval service. The proposed system can improve the performance of average message response time and reduce the message traffic by using the similarity of the network distance and contents. © Springer-Verlag Berlin Heidelberg 2007.