基于自适应策略的改进粒子群算法  

An Improved Particle Swarm Algorithm Based on Adaptive Strategy

作　　者：陈金辉[1] 陈辰[1] 董飚 

机构地区：[1]南京信息工程大学信息与控制学院,江苏南京210044 [2]江苏智能传感网络工程技术研究开发中心,江苏南京210023

出　　处：《计算机仿真》2015年第3期298-303,共6页Computer Simulation

基　　金：2012江苏省"青蓝工程"项目(ZK13-02-03)

摘　　要：粒子群算法的参数速度权重在寻优过程中具有重要的作用。如何寻找合适的速度权重是提高算法性能的关键,为解决上述问题,提出了一种基于自适应策略的改进粒子群算法。改进粒子群算法在每次种群进行迭代时,根据每个粒子的适应度值自适应地改变每个粒子的速度权重,动态调整每个种群粒子的活性,提高了算法的全局寻优能力和收敛能力。仿真结果表明,在单目标函数中,改进算法能够更快速地找到最优位置,提高了算法的寻优能力;在多目标函数中,改进算法能够更快速地收敛到问题的Pareto最优边界,提高了算法的收敛能力。The parameter of speed weight plays an important role in the optimization process of PSO. How to find the parameter is a key to improve the algorithm,so an improved PSO based on adaptive strategy is proposed. When the algorithm is iterating,according to the fitness value of each particle,the speed weight of each particle is adaptively changed,so that global optimization ability and the convergence ability can be improved. The simulation results show that the improved particle swarm can fast find the best position to improve global optimization ability in the single-objective function; the improved particle swarm algorithm can quickly converge to the Pareto optimal boundary of the issue to improve convergence ability in multi-objective function.

关 键 词：粒子群算法 搜索能力 局部最优 自适应策略 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]