Particle swarm optimisation: time for uniformisation
by Juan Luis Fernández-Martínez; Esperanza García-Gonzalo
International Journal of Computing Science and Mathematics (IJCSM), Vol. 4, No. 1, 2013

Abstract: Particle swarm optimisation (PSO) is an evolutionary algorithm that has been successfully applied to many optimisation problems in different fields. PSO has been heuristically proposed based in a social analogy for large groups in nature. Since its publication, research has been carried to understand the PSO convergence and improving its numerical performance. Accordingly several modifications of the basic PSO have been proposed, mostly in a heuristic way. Nevertheless, many of these modifications were not really needed, since they were proposed based on a deficient mathematical analysis of the PSO stability conditions. PSO trajectories are stochastic processes and PSO can be considered as a discrete stochastic gradient algorithm. Nevertheless, PSO is not heuristic, since its convergence and the stability of particle trajectories are related. In conclusion, it is time for uniformisation, because paradoxically this wide range of PSO versions have generated mistrust, providing the impression that PSO success depends more on the version that has been adopted and on the skills of the PSO designer.

Online publication date: Sat, 10-May-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computing Science and Mathematics (IJCSM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com