Particle swarm optimization by using coefficient of variation for terminating scheme and it's application to electric power leveling systems

Research output: Contribution to journalArticle

1 Citation (Scopus)


Recently, metaheuristics becomes practical technique for various optimization problems. Metaheuristics is the technique of obtaining an approximate solution efficiently for optimization problems. Genetic Algorithm (GA), Simulated Annealing (SA), Particle Swarm Optimization (PSO), etc. are typical metaheuristics. PSO is an effective method among them in terms of the processing time and the accuracy in solution. The processing time of PSO depends on the number of the particle and the generation. The terminating condition in the conventional PSO is the preset maximum number of generations. Thus, even though the particles have already converged to the optimal solution, the search continues up to the preset one. This paper proposes a novel scheme of terminating in PSO by using the coefficient of variation (CV) which achieves the shortening of the processing time. The proposed method judges the convergence of the swarm by using CV, and terminates the search. In this paper, the validity is shown by the benchmark problems and the proposed method is applied to the optimization problem for the electric power leveling systems in the rolling mills.

Original languageEnglish
Pages (from-to)488-494+11
JournalIEEJ Transactions on Power and Energy
Issue number5
Publication statusPublished - May 8 2013



  • Coefficient of variation
  • Optimization
  • Particle swarm optimization
  • Terminating condition
  • Time shortening

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Cite this