Affiliation:
1. Chongqing University of Posts and Telecommunications
2. Nicholls State University Thibodaux
Abstract
Our understanding for the traffic behaviors on P2P networks is, unfortunately, still incomplete in the sense that the current studies on traffic measurement primarily focus on the traffic in large, and insufficient efforts have been devoted to the investigation of the inter-peer traffic. Toward resolving this issue, we in this paper propose and implement a method for measuring the traffic between any individual peers. Through deploying this measurement method on the PlanetLab platform, traffic data are collected and analyzed in the following aspects: data correctness, Poisson property, traffic self-similarity of individual peers, and traffic self-similarity of the BT system. Results of these analyses suggest that the proposed method is feasible, effective, and can be extended to larger networks.
Publisher
Trans Tech Publications, Ltd.
Reference16 articles.
1. Sandvine Intelligent Broadband Networks, Global internet phenomena report: 2012 2H, http: /www. sandvine. com.
2. Sandvine Intelligent Broadband Networks, Global internet phenomena report: 2012 1H, , http: /www. sandvine. com.
3. E.P. Markatos, Tracing a large-scale peer to peer system: an hour in the life of Gnutella, " Proc. the 2nd IEEE/ACM International Symposium on Cluster Computing and the Grid(CCGrid , 02), May 2002, pp.65-74, doi: 10. 1109/CCGRID. 2002. 1017113.
4. D. Tutsch, G. Babin and P. Kropf, Applicaion-layer traffic analysis of a peer-to-peer system, IEEE Internet Computing, vol. 12, Sept. -Oct. 2008, pp.70-77, doi: 10. 1109/MIC. 2008. 93.
5. Z.M. Jiang, X. Zhou, and R. s. Xu, Review of p2p network behavior securigy monitoring research, Computer Science, vol. 36, 2009, pp.1-4.