A mixed strategy multi-objective coevolutionary algorithm based on single-point mutation and particle swarm optimization

  • Authors:

  • Xin Zhang;Hongbin Dong;Xue Yang;Jun He

  • Affiliations:

  • Department of Computer Science and Technology, Harbin Engineering University, Harbin, China,The 54th Research Institute of CETC, Shijiazhuang, China;Department of Computer Science and Technology, Harbin Engineering University, Harbin, China;Department of Computer Science and Technology, Harbin Engineering University, Harbin, China;Department of Computer Science, Aberystwyth University, Aberystwyth, UK

  • Venue:
  • RSKT'12 Proceedings of the 7th international conference on Rough Sets and Knowledge Technology
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The particle swarm optimization algorithm has been used for solving multi-objective optimization problems in last decade. This algorithm has a capacity of fast convergence; however its exploratory capability needs to be enriched. An alternative method of overcoming this disadvantage is to add mutation operator(s) into particle swarm optimization algorithms. Since the single-point mutation is good at global exploration, in this paper a new coevolutionary algorithm is proposed, which combines single-point mutation and particle swarm optimization together. The two operators are cooperated under the framework of mixed strategy evolutionary algorithms. The proposed algorithm is validated on a benchmark test set, and is compared with classical multi-objective optimization evolutionary algorithms such as NSGA2, SPEA2 and CMOPSO. Simulation results show that the new algorithm does not only guarantee its performance in terms of fast convergence and uniform distribution, but also have the advantages of stability and robustness.