A CoEvolutionary algorithm based on Elitism and Gravitational Evolution strategies

Yang LOU, Junli LI*, Linpeng JIN, Gang LI

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

6 Citations (Scopus)

Abstract

A global optimization algorithm based on elitism and gravitational evolution strategies is proposed, namely Elitism and Gravitational Evolution based CoEvolutionary Algorithm (EGCoEA). The search agents are divided into two subpopulations with the subpopulation of elites and the common subpopulation, and they updated via three methods. The values of Gravitational Measurement (GM) are used to define the relationships of the elites and the common individuals. The experimental study is carried out to test EGCoEA, compared with Maximal Gravitation Optimization Algorithm (MGOA) and M-Elite Coevolutionary Algorithm (MECA) by a series of typical benchmark functions, including both low-dimensional and high-dimensional problems. The results show EGCoEA performs better than the other two algorithms in solving these problems.

Original languageEnglish
Pages (from-to)2741-2750
Number of pages10
JournalJournal of Computational Information Systems
Volume8
Issue number7
Publication statusPublished - Apr 2012
Externally publishedYes

Bibliographical note

This research was supported by the Natural Science Foundation of China under Grant No. 60832003, the Natural Science Foundation of Zhejiang Province under Grant No.Y1100076, K.C. Wong Magna Fund in Ningbo University, and the Scientific Research Foundation of Graduate School of Ningbo University.

Keywords

  • Coevolutionary algorithm
  • Elitist strategy
  • Gravitational measurement
  • Gravitational optimization

Fingerprint

Dive into the research topics of 'A CoEvolutionary algorithm based on Elitism and Gravitational Evolution strategies'. Together they form a unique fingerprint.

Cite this