Compound particle swarm optimization in dynamic environments.

Date

2008

Advisors

Journal Title

Journal ISSN

ISSN

Volume Title

Publisher

Springer-Verlag.

Type

Article

Peer reviewed

Yes

Abstract

Adaptation to dynamic optimization problems is currently receiving a growing interest as one of the most important applications of evolutionary algorithms. In this paper, a compound particle swarm optimization (CPSO) is proposed as a new variant of particle swarm optimization to enhance its performance in dynamic environments. Within CPSO, compound particles are constructed as a novel type of particles in the search space and their motions are integrated into the swarm. A special reflection scheme is introduced in order to explore the search space more comprehensively. Furthermore, some information preserving and anti-convergence strategies are also developed to improve the performance of CPSO in a new environment. An experimental study shows the efficiency of CPSO in dynamic environments.

Description

Keywords

Citation

Liu, L., Wang, D. and Yang, S. (2008) Compound particle swarm optimization in dynamic environments. In: » Applications of Evolutionary Computing: Proceedings of EvoWorkshops 2008: EvoCOMNET, EvoFIN, EvoHOT, EvoIASP, EvoMUSART, EvoNUM, EvoSTOC, and EvoTransLog, Naples, Italy, March 26-28, 2008. Berlin: Springer-Verlag, pp. 616-625.

Rights

Research Institute

Institute of Artificial Intelligence (IAI)