基于异构多种群策略的动态概率粒子群优化算法  

Dynamic Probabilistic Particle Swarm Optimization Based on Heterogeneous Multiple Population Strategy

作　　者：倪庆剑[1,2] 邓建明[1] 邢汉承[1] 

机构地区：[1]东南大学计算机科学与工程学院,南京211189 [2]苏州大学江苏省计算机信息处理技术重点实验室,苏州215006

出　　处：《模式识别与人工智能》2014年第2期146-152,共7页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金资助项目(No.61170164)

摘　　要：结合动态概率粒子群优化算法(DPPSO)特点,针对传统的单种群粒子群优化算法易陷入局部最优、收敛速度较慢的缺点,文中提出一种基于异构多种群策略的DPPSO.该算法在进化过程中保持多个子种群,每个子种群以不同的DPPSO变体进行进化,子种群之间根据一定规律进行通信,从而保持整个种群内部的信息交流,进而协调DPPSO的勘探和开采能力.通过典型的Benchmark函数优化问题测试并分析基于异构多种群策略的DPPSO性能,结果显示,使用该策略的算法收敛速度较快,稳定性有较显著提高,具有较强的全局搜索能力.Aiming at premature convergence and the slow search speed of the traditional particle swarm optimization, a heterogeneous multiple population strategy is combined with the characteristics of dynamic probabilistic particle swarm optimization （ DPPSO ） . In the evolutionary process of DPPSO with the strategy, multiple sub-populations are maintained and each sub-population evolves with different DPPSO variants. According to certain rules, communication between the sub-populations are executed to maintain the information exchange inside the entire population and coordinate exploration and exploitation. DPPSO algorithms with the strategy are tested on four benchmark functions which are commonly used in the evolutionary computation. Experimental results demonstrate that the DPPSO with the strategy significantly improves the convergence speed and stability with strong global search ability.

关 键 词：粒子群优化算法( PSO) 动态概率粒子群优化算法( DPPSO) 多种群策略 PARTICLE SWARM OPTIMIZATION ( PSO ) Dynamic PROBABILISTIC PARTICLE SWARM OPTIMIZATION ( DPPSO) 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]