全局粒子群优化算法  

A Global Particle Swarm Optimization Algorithm

作　　者：高立群[1] 李若平[1] 邹德旋[1] 

机构地区：[1]东北大学信息科学与工程学院,辽宁沈阳110819

出　　处：《东北大学学报（自然科学版）》2011年第11期1538-1541,共4页Journal of Northeastern University(Natural Science)

基　　金：国家自然科学基金资助项目(60674021)

摘　　要：针对粒子群优化算法在解决大维数的无约束优化问题时具有较差的收敛性和稳定性,提出了一种全局粒子群优化(GPSO)算法.GPSO算法引入了一种新的惯性权重,它被定义为一个指数型函数与一个随机数的乘积,这有利于维持算法的全局搜索和局部搜索.同时,GPSO算法对全局最优解进行了小的扰动,这可以有效地避免算法早熟.使用三种粒子群优化算法来解决6个无约束优化问题.仿真结果说明,与其他两种粒子群优化算法相比,GPSO算法具有更快的收敛速度和更强的逃离局部最优的能力.Particle swarm optimization（PSO） algorithm shows good performance on solving small-scale unconstrained optimization problem,however,it has poor convergence and stability on solving large-scale ones.In order to improve the performance of the PSO algorithms,a global particle swarm optimization（GPSO） algorithm was proposed.The GPSO introduces a new inertia weight,and it is defined as the product of an exponential type function and a random number,which is beneficial to keeping the global and local searching capabilities of the proposed algorithm.On the other hand,the GPSO adds small disturbance to the global optimal solution,which can effectively avoiding the premature problems in the convergence of the GPSO algorithm.Three particle swarm optimization algorithms were used to solve six unconstrained optimization problems.Simulation results demonstrated that the GPSO has faster convergence rate and stronger capability of escaping from the local optimum when compared with the other two existing particle swarm optimization algorithms.

关 键 词：收敛性 稳定性 全局粒子群优化算法 惯性权重 扰动 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]