The non-clique particle swarm optimizer

  • Authors:
  • Ziyu Chen;Zhongshi He;Cheng Zhang

  • Affiliations:
  • Chongqing University, Chongqing, China;Chongqing University, Chongqing, China;Chongqing University, Chongqing, China

  • Venue:
  • Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Neighborhood topology of particle swarm affects the performance of PSO. Through analyzing the graph properties of typical neighborhood topologies, this paper presents a non-clique static neighborhood topology which has lower clustering coefficient and smaller average path length. Compared to other topologies with the same neighborhood size and population size, the proposed topology has more uniform neighbor distribution. The experiment results demonstrate that the PSO based on the non-clique topology has great superiority both in robustness and efficiency.