School of Computing

An estimation of distribution particle swarm optimization algorithm

Mudassar Iqbal and Marco A. Montes de Oca

In Dorigo M. and et al, editors, Ant Colony Optimization and Swarm Intelligence. 5th International Workshop, ANTS 2006, Brussels, volume 4150/2006 of LNCS, pages 182-196, Berlin, Germany, August 2006. Springer Verlag.

Abstract

In this paper we present an estimation of distribution par-ticle swarm optimization algorithm that borrows ideas from recent de-velopments in ant colony optimization. In the classical particle swarm optimization algorithm, particles exploit their individual memory to ex-plore the search space. However, the swarm as a whole has no means to exploit its collective memory (represented by the array of pbests) to guide its search. This causes a re-exploration of already known bad regions of the search space, wasting costly function evaluations. In our approach, we use the swarm�s collective memory to estimate the distribu-tion of promising regions in the search space and probabilistically guide the particles� movement towards them. Our experiments show that this approach is able to find similar or better solutions than the standard particle swarm optimizer with fewer function evaluations.

Download publication 194 kbytes (PDF)

Bibtex Record

@conference{2601,
author = {Mudassar Iqbal and Marco A. Montes de Oca},
title = {An Estimation of Distribution Particle Swarm Optimization Algorithm},
month = {August},
year = {2006},
pages = {182-196},
keywords = {determinacy analysis, Craig interpolants},
note = {},
doi = {},
url = {http://www.cs.kent.ac.uk/pubs/2006/2601},
    editor = {Dorigo M. and et al},
    publication_type = {conference},
    submission_id = {27116_1187714292},
    ISBN = {978-3-540-38482-3},
    booktitle = {Ant Colony Optimization and Swarm Intelligence. 5th International Workshop, ANTS 2006, Brussels},
    volume = {4150/2006},
    series = {LNCS},
    address = {Berlin, Germany},
    publisher = {Springer Verlag},
    ISSN = {0302-9743},
    refereed = {Yes},
}

School of Computing, University of Kent, Canterbury, Kent, CT2 7NF

Enquiries: +44 (0)1227 824180 or contact us.

Last Updated: 21/03/2014