A FCM-based peer grouping scheme for node failure recovery in wireless P2P file sharing

  • Authors:
  • Xi Li;Ji Hong;F. Richard Yu;Zheng Ruiming

  • Affiliations:
  • Key Lab of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, P. R. China;Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada;Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada;Key Lab of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, P. R. China

  • Venue:
  • ICC'09 Proceedings of the 2009 IEEE international conference on Communications
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

An effective node failure recovery scheme is very important in wireless peer-to-peer (P2P) file sharing networks. Most of the existing failure recovery protocols are based on backup path mechanism, in which a new path will be used if the original one breaks. However, due to the limited resources in wireless environments, the maintenance of backup paths is expensive. Moreover, the time spending on path switch may be unacceptable long. In this paper, we propose a novel peer grouping scheme to select a qualified peer from a group to replace the failed node. The main criteria in deciding the backup node is derived with the help of recent advances in fuzzy cognitive maps (FCM). Several influential factors are considered, including energy, movement, lingering time and security, with further investigation on their respective contributions to node failure risk. We compare the performance of the proposed scheme with that of traditional path redirection and multi-path backup algorithms. The FCM-based peer grouping scheme has significant improvement in failure recovery time and file transfer time.