Example-based learning particle swarm optimization for continuous optimization

  • Authors:

  • Han Huang;Hu Qin;Zhifeng Hao;Andrew Lim

  • Affiliations:

  • School of Software Engineering, South China University of Technology, Guangzhou 510006, PR China and State Key Lab. for Novel Software Technology, Nanjing University, Jiangsu 210093, PR China and ...;School of Management, Huazhong University of Science and Technology, Wuhan, PR China and Department of Management Sciences, College of Business, City University of Hong Kong, Hong Kong;Faculty of Computer Science, Guangdong University of Technology, Guangzhou 510006, PR China;Department of Management Sciences, College of Business, City University of Hong Kong, Hong Kong

  • Venue:
  • Information Sciences: an International Journal
  • Year:
  • 2012

Quantified Score

Hi-index 0.09

Visualization

Abstract

Particle swarm optimization (PSO) is a heuristic optimization technique based on swarm intelligence that is inspired by the behavior of bird flocking. The canonical PSO has the disadvantage of premature convergence. Several improved PSO versions do well in keeping the diversity of the particles during the searching process, but at the expense of rapid convergence. This paper proposes an example-based learning PSO (ELPSO) to overcome these shortcomings by keeping a balance between swarm diversity and convergence speed. Inspired by a social phenomenon that multiple good examples can guide a crowd towards making progress, ELPSO uses an example set of multiple global best particles to update the positions of the particles. In this study, the particles of the example set were selected from the best particles and updated by the better particles in the first-in-first-out order in each iteration. The particles in the example set are different, and are usually of high quality in terms of the target optimization function. ELPSO has better diversity and convergence speed than single-gbest and non-gbest PSO algorithms, which is proved by mathematical and numerical results. Finally, computational experiments on benchmark problems show that ELPSO outperforms all of the tested PSO algorithms in terms of both solution quality and convergence time.