Information Sharing Strategies for Particle Swarm Optimization Algorithm
-
摘要: 为寻求更有效的信息共享策略,分析了粒子群优化(PSO)算法的信息共享机制及由粒子个体最优位置构成的平衡点的作用.在此基础上,以标准PSO算法为原型,提出了4种使用不同信息共享策略的PSO算法,并用5个经典测试函数测试、比较了它们的性能.仿真结果表明,提出的前2种信息共享策略可以明显改善PSO算法的性能.基于PSO算法的理论分析和仿真结果,给出了一个好的信息共享策略应满足的条件:粒子应有选择地共享邻域个体的信息,以保证粒子群的平衡点具有良好的质量与多样性,同时又不过于随机地变化.Abstract: To find out a more efficient information sharing strategy,the information sharing mechanism and the role of the equilibrium point in particle swarm optimization (PSO) algorithms were analyzed. Based on the analysis,four kinds of PSO algorithms using different information sharing strategies were presented. Five classical benchmark functions were used to test and compare these PSO algorithms. The simulation results show that the first two PSO algorithms in the four algorithms evidently outperform the standard PSO algorithm. Based on the theoretical analysis of PSO algorithms and the simulation results,some conditions for a good information sharing strategy were summarized. That is,particles should selectively share the information of their neighbors in order to guarantee that their equilibrium points have both good quality and diversity but do not change too randomly.
-
Key words:
- particle swarm optimization /
- equilibrium point /
- information sharing /
- diversity
-
SHI Y,EBERHART R C.A modified particle swarm optimizer[C]//Pree.of the IEEE International Conference on Evolutionary Computation.Anchorage:IEEE Press,1998:69-73.[2] 谢晓锋,张文俊,杨之廉.微粒群算法综述[J].控制与决策,2003,18(2):129-134.XIE Xiaofeng,ZHANG Wenjun,YANG Zhilian.Overview of particle swarm optimization[J].Control and Decision,2003,18(2):129-134.[3] KENNEDY J,MENDES R.Population structure and particle swarm performance[C]∥Proc.of the IEEE International Conference on Evolutionary Computation.Honolulu:IEEE Press,2002:1671-1676.[4] JANSON S,MIDDENDORF M.A hierarchical particle swarm optimizer and its adaptive variant[J].IEEE Trans.on Systems.Man,and Cybernetics-Part B:Cybernectics,2005,35(6):1272-1282.[5] MENDES R,KENNEDY J.The fully informed particle swarm:simpler,maybe better[J].IEEE Trans.on Evolutionary Computation.2004,8(3):204-210.[6] KENNEDY J,MENDES R.Neighborhood topologies in fully informed and best-of-neighborhood particle swarm[J].IEEE Trans.on Systems,Man,and Cybernetics-Part C:Applications and Reviews,2006,36(4):5 15-5 19.[7] 林川,冯全源.一种新的自适应粒子群优化算法[J].计算机工程,2008,34(7):181-183.LIN Chuan.FENG Quanyuan.New adaptive particle swarm optimization algorithm[J].Computer Engineering,2008,34(7):181-183.[8] 林川,冯全源.基于微粒群本质特征的混沌微粒群优化算法[J].西南交通大学学报,2007,42(6):665-669.LIN Chuan,FENG Quanyuan.Chaotic particle swarm optimization algorithm based on the essence of particle swarm[J].Journal of Southwest Jiaotong University,2007,42(6):665-669.[9] PERAM T,VEERAMACHANENI K,MOHAN C K.Fitness-distance-ratio based particle swarm optimization[C]//Proc.of the IEEE Swarm Intelligence Symposium.Indianapolis:IEEE Press,2003:174-181.[10] LIN Chuan,FENG Quanyuan.The standard particle swarm optimization algorithm convergence analysis and parameter selection[C]//Proc.of Third Int.Conf.on Natural Computation.Haikou:IEEE Press,2007:823-826.
点击查看大图
计量
- 文章访问数: 1702
- HTML全文浏览量: 84
- PDF下载量: 296
- 被引次数: 0