改进的多种群协同进化微粒群优化算法

Multi-species cooperative particle swarm optimization algorithm

提出一种改进的基于多种群协同进化的微粒群优化算法(PSO).该算法首先利用免疫算法实现解空间的均匀划分,增加了算法稳定性和全局搜索能力.在运行过程中,通过种群进化信息生成解优胜区域,指导变异生成的微粒群向最优解子空间逼近,提高算法逃出局部最优的能力.将此算法与PSO算法和多种群协同进化微粒群算法进行比较,数据实验证明,该算法不仅能有效地克服其他算法易陷入局部极小值的缺点,而且全局收敛能力和稳定性均有显著提高.

A particle swarm optimization algorithm based on multi-species cooperative evolution is presented. In this approach, the result space separation based on immune system is introduced into the particle swarm optimization （PSO） initial step, which reinforces the stability and global exploration ability of the PSO algorithm. In the evolution process, the best result value space is generated by using the multi-species evolution information, which is explored to induce the new particle swarm generated by stochastic mutation operation to fly into the better result space, which can avoid the premature convergence and speed up the convergence. The comparison of the performance of the proposed approach with that of traditional PSO algorithm and other multi-species cooperative particle swarm optimization algorithms is experimented. The experimental results show that the proposed method can not only effectively solve the premature convergence problem, but also significantly speed up the convergence and improve the stability.