Neutrino-like particle for particle swarm optimization

Hao Chun Lu, Hsuan Yu Tseng, Liming Yao*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

The real-world optimal problems frequently encountered by various industries are the nonlinear constrained optimization problems (NCOPs), where the constraints represent the limitations of practical resources. Many researchers have attempted to improve particle swarm optimization (PSO) in the past decades; however, in solving the NCOPs, the PSO-based approaches often cause premature convergences. The problem-specific constraints frequently generate many infeasible regions that block the movements of particles. The particles' behavior causes the exploration abilities of particles that tend to weaken along with time. The decreasing of exploration ability often comes from the particle becoming stagnant or moving unusefully. This study proposes a neutrino-like particle (NLP) with adaptive NLP hyperparameters that simulate the natural neutrino behavior. The proposed NLPs can be embedded in the PSO-based approaches for overcoming premature convergence. The experiment results demonstrate that all referenced PSO-based methods with the NLPs improved significantly compared with those without the NLPs to solve the NCOPs. All referenced PSO-based methods that embedded the NLPs also significantly outperform four recent strong algorithms in most IEEE CEC 2020 benchmark problems. Therefore, the proposed NLPs with adaptive NLP hyperparameters can effectively solve the premature convergences, reinforce the exploration ability, and maintain the exploitation capability for solving the NCOPs over the whole evolution process.

Original languageEnglish
Pages (from-to)859-913
Number of pages55
JournalInternational Journal of Intelligent Systems
Volume37
Issue number1
DOIs
StatePublished - Jan 2022

Keywords

  • exploration
  • neutrino-like particle
  • nonlinear constrained optimization problems
  • particle swarm optimization
  • premature convergances

Fingerprint

Dive into the research topics of 'Neutrino-like particle for particle swarm optimization'. Together they form a unique fingerprint.

Cite this