一种克服局部最优的收缩因子PSO算法.PDF

37 20 2011 10 Vol.37 No.20 Computer Engineering October 20 11 ·· 2011 A TP301.6 PSO ( 650224) Constriction Factor Particle Swarm Optimization Algorithm with Overcoming Local Optimum JI Xue-ling, LI Ming, LI Wei (College of Machinery and Transportation, Southwest Forestry University, Kunming 650224, China) Abstract The constriction factor Particle Swarm Optimization(PSO) algorithm is easily trapped in the local optimum and appeared premature convergence. An improved constriction factor PSO algorithm is proposed to overcome the local optimum. The improved algorithm introduces a position factor and speed factor parameter, if all particles are close to the global optimum and its velocity is less than the speed factor that it is set in advance, these particles are likely to be stagnant, a re-initialization is done to enhance these particles energy. When the algorithm is in local optimum, this method can disperse the particles and improve the diversity of the population and avoid premature convergence. Comparing the three multimodal functions simulation, the data can verify the performance of the improved algorithm, simulation result shows that the improved algorithm improves its convergence accuracy, and effectively avoids falling into local optimum. Key words Particle Swarm Optimization(PSO) algorithm; constriction factor; speed factor; position factor; premature convergence DOI: 10.3969/j.issn.1000-3428.2011.20.074 1 (Particle Swarm Optimization, PSO) 1999 M.Clerc [1] PSO