Overview

This dissertation, Scheduling Algorithms for Data Distribution in Peer-to-peer Collaborative File Distribution Networks by Siu-kei, Jonathan, Chan, 陳兆基, was obtained from The University of Hong Kong (Pokfulam, Hong Kong) and is being sold pursuant to Creative Commons: Attribution 3.0 Hong Kong License. The content of this dissertation has not been altered in any way. We have altered the formatting in order to facilitate the ease of printing and reading of the dissertation. All rights not granted by the above license are retained by the author. Abstract: Abstract of thesis entitled Scheduling Algorithms for Data Distribution in Peer-to-Peer Collaborative File Distribution Networks submitted by CHAN Siu Kei, Jonathan for the degree of Master of Philosophy at The University of Hong Kong in October 2006 Peer-to-Peer (P2P) applications have become immensely popular among Internet users. One of the most popular applications of P2P networks is collaborative sharing of large video/audio files and software. Some examples of applications in widespread use are BitTorrent, Gnutella, Kazaa and Napster. Traditional methods for file sharing, such as the client/server approach (e.g. File Transfer Protocol, World Wide Web), are not scalable with increased network size. P2P file sharing solves this problem by allowing peers to act as servers. Interestingly, in a well-designed P2P file sharing network, performance generally improves as the number of peers participating in the file sharing session increases, as each peer can download simultaneously from multiple peers. P2P file sharing systems have attracted considerable attention in the past few years since their inception. However, the research to date has mainly focused on peer and content discovery, overlay topology formation, fairness and incentive issues. Little attention has been devoted to investigate the data distribution problem, which is also a core component of any file sharing application. In this study, we present an initial attempt at addressing this collaborative file distribution problem, and formally define the scheduling problem in simplified contexts. We develop several algorithms (Rarest Piece First, Most Demanding Node First, Bipartite Matching and Maximum Flow Algorithms) to solve the data distribution problem and study their performance. We deduce theoretical bounds on the minimum download time experienced by users and also perform simulations to evaluate our algorithms. Simulation results show that our novel graph-based Bipartite Matching or Maximum Flow Algorithms outperform other algorithms in terms of total download time required. Therefore, we believe our algorithms may be employed as the core scheduling modules in P2P file sharing applications. (Total number of words: 280) Signed ______________________ CHAN Siu Kei, Jonathan DOI: 10.5353/th_b3704588 Subjects: Peer-to-peer architecture (Computer networks)Computer schedulingAlgorithms

Full Product Details

9781361471036

Table of Contents

Reviews

Author Information

Tab Content 6

Countries Available