Optimal super-peer selection for large-scale P2P system

Abstract

The peer-to-peer (P2P) systems have grown significantly over the last few years due to their potential for sharing various resources. Unstructured hybrid P2P system can improve the performance of the entire network and system using SP (Super-peer), which has the responsibility for query processing instead of OPs (Ordinary-Peer). In these systems, selecting the best SP to join is an important problem, but it is difficult to choose the optimal SP by the various reasons such as heterogeneous capacity, content similarity and dynamic capacity change. In this paper, we present the SP selection's problem and SP selection strategy based on dynamic capacity of the SP and content similarity. Also we measure the SP's score with weight to the factors distance cost, processing power and content similarity. Through the simulation, we show query processing performance is improved when OPs use our strategy to choose the best SP. © 2006 IEEE.