Triangular Gaussian mutation to differential evolution

Jinglei Guo, Yong Wu*, Wei Xie, Shouyong Jiang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

Differential evolution (DE) has been a popular algorithm for its simple structure and few control parameters. However, there are some open issues in DE regrading its mutation strategies. An interesting one is how to balance the exploration and exploitation behaviour when performing mutation, and this has attracted a growing number of research interests over a decade. To address this issue, this paper presents a triangular Gaussian mutation strategy. This strategy utilizes the physical positions and the fitness differences of the vertices in the triangular structure. Based on this strategy, a triangular Gaussian mutation to DE and its improved version (ITGDE) are suggested. Empirical studies are carried out on the 20 benchmark functions and show that, in comparison with several state-of-the-art DE variants, ITGDE obtains significantly better or at least comparable results, suggesting the proposed mutation strategy is promising for DE.

Original languageEnglish
Pages (from-to)9307-9320
Number of pages14
JournalSoft Computing
Volume24
Issue number12
Early online date31 Oct 2019
DOIs
Publication statusPublished - 1 Jun 2020

Keywords

  • Differential evolution
  • Gaussian distribution
  • Global optimum
  • Triangular structure

Fingerprint

Dive into the research topics of 'Triangular Gaussian mutation to differential evolution'. Together they form a unique fingerprint.

Cite this