Title: An analytical evaluation method based on generalised random graphs for unstructured peer-to-peer content-sharing systems

Authors: Keiichi Endo

Addresses: Graduate School of Science and Engineering, Ehime University, Matsuyama 790-8577, Japan

Abstract: This paper presents a method that can be used to analyse the performance of peer-to-peer content-sharing systems. By using this method, we can analytically calculate the number of newly visited nodes at each step of a query spreading process, which is closely related to various types of performances such as search success rate and search time. Our method is based on the analytical framework proposed by Gaeta et al. Since the existing framework is based on the assumption that the probability of encountering the same node in the query spreading process after multiple hops is negligible, it is not suitable for relatively small networks or highly clustered networks. In this paper, we propose a method to make the analytical framework applicable to those networks by considering the possibility that a node receives the same query from different nodes.

Keywords: analytical evaluation; unstructured peer-to-peer networks; content sharing systems; highly clustered P2P networks; generalised random graphs.

DOI: 10.1504/IJCNDS.2011.040560

International Journal of Communication Networks and Distributed Systems, 2011 Vol.6 No.4, pp.392 - 403

Published online: 05 Jun 2011 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article