筛选和记忆相结合的粒子群算法  

Swarm optimization algorithm with particle selection and memory

作　　者：杨华芬[1] 杨有[2] 杨丽华[3] 董德春[1] 

机构地区：[1]曲靖师范学院计算机科学与工程学院,云南曲靖655011 [2]重庆师范大学计算机与信息科学学院,重庆401331 [3]曲靖师范学院数学与信息科学学院,云南曲靖655011

出　　处：《计算机应用研究》2016年第4期1039-1043,共5页Application Research of Computers

基　　金：云南省自然科学基金资助项目(2013FZ098;2013FZ114);曲靖师范学院科研基金资助项目(2009MS006)

摘　　要：针对粒子群算法优化高维复杂问题出现局部最优的缺陷,提出初始粒子筛选和最差粒子记忆相结合的粒子群算法。利用熵度量粒子分量分布的均匀性,只有各分量满足均匀性要求时,该粒子才被筛选为初始粒子,以控制粒子在解空间的分布。在速度更新过程中引入最差粒子,避免粒子重复搜索曾经找到的最差位置,以提高算法的搜索效率。根据粒子寻优的成功率动态调整权重,以有效平衡深度和广度搜索能力。用该算法优化六个经典测试函数,与三种改进的PSO算法相比,该算法不仅可以平衡局部和全局的搜索能力,还可以提高算法的搜索效率和精度。PSO is prone to premature convergence and is difficult to balance capability of searching globally and locally when it is used in high dimension complex question. Entropy is used to measure the diversity of particles in order to control the distribution. The particles which meet the need of the diversity are received as initial particles. To avoid searching these poor location repeatedly and increase the search efficiency of algorithm,it introduced the worst particle during velocity updating. In order to balance the global and local search ability,it dynamicall adjusted inertia weight according to success of particles evolution. The lower the success radio is,the lower the inertia weight is. To verify the validity of this algorithm,six classical test functions were optimized by the proposed algorithm and three improved PSO. The result shows that the proposed algorithm can not only balance the global and local search ability,but also improve the search efficiency and accuracy of the algorithm.

关 键 词：粒子群 熵 优化 多样性 最差粒子 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]