Query-trail-mediated topology reconstruction for exploring performance trade-off in unstructured P2P networks

Authors:
Kei Ohnishi;Satoshi Nagamatsu;Yuji Oie
Affiliations:
(Correspd. E-mail: ohnishi@cse.kyutech.ac.jp) Department of Computer Science and Electronics, Faculty of Computer Science and Systems Engineering, Kyushu Institute of Technology, 680-4 Kawazu, Iiz ...;Department of Computer Science and Electronics, Faculty of Computer Science and Systems Engineering, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan;Department of Computer Science and Electronics, Faculty of Computer Science and Systems Engineering, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan
Venue:
International Journal of Hybrid Intelligent Systems - HIS 2007
Year:
2008

Citing 6
Cited 0

Search and replication in unstructured peer-to-peer networks

ICS '02 Proceedings of the 16th international conference on Supercomputing
Mapping the Gnutella Network

IEEE Internet Computing
Replication Methods for Load Balancing on Distributed Storagesin P2P Networks*The earlier version of this paper was presented at the 2005 International Symposium on Applications and the Internet (SAINT2005).

IEICE - Transactions on Information and Systems
Quickly routing searches without having to move content

IPTPS'05 Proceedings of the 4th international conference on Peer-to-Peer Systems
The case for a hybrid p2p search infrastructure

IPTPS'04 Proceedings of the Third international conference on Peer-to-Peer Systems
A survey and comparison of peer-to-peer overlay network schemes

IEEE Communications Surveys & Tutorials

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a topology reconstruction method to explore better trade-off points between search and access load balancing performance in unstructured Peer-to-Peer (P2P) file sharing networks. The proposed topology reconstruction method changes a network topology in a dynamic, autonomous, and decentralized manner. The topology reconstruction is based on local threshold-based rules that use query trails, which stand for information on previous successful search paths. The scenario for the evaluation of the proposed method is that the topology reconstruction method consisting of the local threshold-based rules operates to explore the performance trade-off in the situation that new kinds of files are about to spread over a power-law network. The simulation results show that, depending on the setting of the threshold values, compared to the case without topology reconstruction, the proposed method can explore better trade-off points between search and storage access load balancing performance in the assumed scenario.