Optimization of P2P-based Distributed Systems

Document Type

Article

Publication Date

2011

Publication Title

Journal of Applied Computer Science

Volume

19

Issue

1

First page number:

117

Last page number:

138

Abstract

Various kinds of distributed systems gain much attention in recent years. One of the most significant example is the Peer-to-Peer (P2P) paradigm widely used in many applications including: file-sharing systems (e.g. BitTorrent), computing systems (e.g. SETI@home), communication systems (e.g. Skype) and many others. In this work we present our latest research related to the problem of P2P-based distributed systems optimization. We consider two following problems: optimization of data distribution P2P systems and optimization of P2P computing systems. For both problems we formulate Integer Programming models. Due to the complexity of these problems, exact methods can be applied only for relatively small instances. Therefore, we propose several heuristic algorithms including tabu search, evolutionary algorithm, constructive heuristic and random approach. Results of extensive numerical experiments show the effectiveness of proposed algorithms in comparison to optimal results yielded by CPLEX solver. The optimization methods presented in this paper can be used for optimization of various P2P systems.

Keywords

Computer networks; Distributed systems; Electronic data processing--Distributed processing; Heuristic; Heuristic algorithms; Heuristic programming; Optimization; P2P; Peer-to-peer architecture (Computer networks)

Disciplines

Computer and Systems Architecture | Computer Engineering | Electrical and Computer Engineering | Engineering

Language

English

Permissions

Use Find in Your Library, contact the author, or interlibrary loan to garner a copy of the item. Publisher policy does not allow archiving the final published version. If a post-print (author's peer-reviewed manuscript) is allowed and available, or publisher policy changes, the item will be deposited.


Search your library

Share

COinS