Abstract:Aiming at the problem that Particle Swarm Optimization(PSO)is easy to fall into local optimum,slow convergence speed and low preacision,a new mutation strategy is proposed to perform global best particle based on Dimension-by-dimension Centroid Opposition-Based Learning.The dimension-by-dimension mutation reduces inter-dimensional interference,and leads the particles to a better position by updating the global optimal position,while enhancing the diversity of the population.The simulation experiment was compared with the Hybrid Particle Swarm Optimization based on Cauchy mutation(HPSO)and Particle Swarm Optimization besed Centroid Opposition-Based Learning(COPSO)on eight standard test functions.Experiments show that the Particle Swarm Optimization based on Dimension-by-dimension Centroid Opposition-Based Learning(DCOPSO)has higher convergence speed and accuracy.
罗强,季伟东,徐浩天,孙小晴. 一种最优粒子逐维变异的粒子群优化算法[J]. 小型微型计算机系统, 2020, 41(2): 259-263.
LUO Qiang,JI Wei-dong,XU Hao-tian,SUN Xiao-qing. Particle Swarm Optimization with Global Best Particle Dimension-by-dimension Mutation. Journal of Chinese Computer Systems, 2020, 41(2): 259-263.