Chaotic co-evolutionary algorithm based on differential evolution and particle swarm optimization

Meng Zhang, Weiguo Zhang, Yong Sun

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 Scopus citations

Abstract

A chaotic co-evolutionary algorithm based on differential evolution and particle swarm optimization (CCDEPSO) is proposed. CCDEPSO is a two-population co-evolutionary algorithm, in which the individuals of one population are evolved according to differential evolution algorithm (DE) and the other individuals are evolved according to particle swarm optimization algorithm (PSO). In order to realize co-evolving of the two sub-populations, an information sharing scheme by sharing the fitness value and the corresponding position value of the two sub-populations is introduced. Furthermore, in order to improve the searching speed and avoid the results trapping in local optima prematurely, chaotic initialization and chaotic perturbation based on Tent map are introduced in CCDEPSO. The comparative testing experiments are performed by means of CCDEPSO, DE, CPSO and PSO algorithms on six benchmark functions. Experimental results demonstrate that the global optimization ability of CCDEPSO is better than other algorithms above mentioned.

Original languageEnglish
Title of host publicationProceedings of the 2009 IEEE International Conference on Automation and Logistics, ICAL 2009
Pages885-889
Number of pages5
DOIs
StatePublished - 2009
Event2009 IEEE International Conference on Automation and Logistics, ICAL 2009 - Shenyang, China
Duration: 5 Aug 20097 Aug 2009

Publication series

NameProceedings of the 2009 IEEE International Conference on Automation and Logistics, ICAL 2009

Conference

Conference2009 IEEE International Conference on Automation and Logistics, ICAL 2009
Country/TerritoryChina
CityShenyang
Period5/08/097/08/09

Keywords

  • Co-evolutionary
  • Differential evolution
  • Information sharing
  • Particle swarm optimization
  • Tent map

Fingerprint

Dive into the research topics of 'Chaotic co-evolutionary algorithm based on differential evolution and particle swarm optimization'. Together they form a unique fingerprint.

Cite this