关键词:粒子群优化算法; 早熟; 函数优化; 分合策略
Particle swarm optimization based on division and union strategy
CHEN Jian-chao1, HU Gui-wu1,2,3
(1. School of Mathematics & Computational Science, Guangdong University of Business Studies, Guangzhou 510320, China; 2. Key Laboratory of Data Engineer & Knowledge Engineer for Ministry ofEducation, Beijing 100872, China; 3. School of Information, Renmin University of China, Beijing 100872, China)
Abstract:Basing on a ubiquitous scheme:the world, long divided, must reunite; long united, must divide, which was reported to well represent the nature of social evolution process, this paper proposed divided and united particle swarm optimization. In the new algorithm, division strategy was able to improve the diversity of population, which overcame the local convergence of PSO.Union strategy was able to combine the merit of different population and improved its global research ability. Finally, used the novel algorithm to solve function optimization problem. The result shows that the algorithm is effective.......