Login | Register

Efficiency and stability of peer-to-peer file sharing systems

Title:

Efficiency and stability of peer-to-peer file sharing systems

Sang, Wei Qian (2007) Efficiency and stability of peer-to-peer file sharing systems. Masters thesis, Concordia University.

[img]
Preview
Text (application/pdf)
MR34721.pdf - Accepted Version
2MB

Abstract

In recent years, Peer-to-Peer (P2P) applications, from traditional file sharing to P2P live audio/video streaming, have become very popular. Among the P2P applications, P2P file sharing remains one of the most popular applications and its traffic has been dominating the Internet bandwidth for the past years. In this paper, I will mainly study the efficiency and stability of the P2P file sharing systems. In the P2P file sharing networks, the upload bandwidth of each peer is a very important resource of the network. The efficient use of it will affect the system performance significantly. Motivated by this fact, a stochastic model for P2P file sharing networks is proposed and numerically solved to analyze how the performance of a P2P file sharing network is affected by different parameters such as the piece numbers of the file, the number of neighbours of a peer, and the seed departure rate etc. Based on this result, some useful guidelines are also provided on how to design an efficient P2P system. Stability is another important issue in P2P file sharing systems. In this thesis, a simple fluid model is used to analyze the stability of BitTorrent-like P2P file sharing networks. The resulting fluid model is a switched linear system and it is proved that such a system is always globally stable. Numerical results based on extensive simulations are also provided to support the theoretical proof

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Electrical and Computer Engineering
Item Type:Thesis (Masters)
Authors:Sang, Wei Qian
Pagination:viii, 69 leaves : ill. ; 29 cm.
Institution:Concordia University
Degree Name:M.A. Sc.
Program:Electrical and Computer Engineering
Date:2007
Thesis Supervisor(s):Dongyu, Qiu
ID Code:975467
Deposited By: Concordia University Library
Deposited On:22 Jan 2013 16:08
Last Modified:18 Jan 2018 17:40
Related URLs:
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Back to top Back to top