A differential evolution based on individual-sorting and individual-sampling strategies

Yang Lou*, Junli Li, Yuhui Shi

*Corresponding author for this work

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

7 Citations (Scopus)

Abstract

Differential Evolution has been a simple and efficient heuristic for global optimization over continuous spaces due to its remarkable performance. In this paper, we firstly modified the traditional structure of population in Differential Evolution and proposed a new strategy for population setting, in which a population was sorted based on the fitness values of individuals. Another new method was saltatory sampling with a nonrandom order, which was utilized to select candidates for the mutation operation. Furthermore, the strategy of survival of the fittest was used for individual selection operation. Then we propose the Differential Evolution based on Individual-Sorting and Individual-Sampling (ISSDE), of which control parameters was experimentally set. The proposed algorithm is tested on benchmark functions and is compared with traditional Differential Evolution. The simulation results show that the proposed ISSDE has a better performance both in convergence speed and robustness.

Original languageEnglish
Title of host publicationIEEE SSCI 2011 - Symposium Series on Computational Intelligence - SDE 2011
Subtitle of host publication2011 IEEE Symposium on Differential Evolution
PublisherIEEE Computer Society
Pages33-40
Number of pages8
ISBN (Print)9781612840727
DOIs
Publication statusPublished - 2011

Publication series

NameIEEE SSCI 2011 - Symposium Series on Computational Intelligence - SDE 2011: 2011 IEEE Symposium on Differential Evolution

Keywords

  • Differential Evolution
  • Individual-Sampling
  • Individual-Sorting
  • Sampling
  • Sorting

Fingerprint

Dive into the research topics of 'A differential evolution based on individual-sorting and individual-sampling strategies'. Together they form a unique fingerprint.

Cite this