基于克隆多尺度协同开采的离散微粒群算法  

Discrete particle swarm optimization based on clone multi-scale cooperative exploitation

作　　者：陶新民[1] 徐晶[2] 王妍[1] 刘玉[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院,哈尔滨150001 [2]黑龙江省科技学院数力系,哈尔滨150027

出　　处：《控制与决策》2011年第5期700-706,共7页Control and Decision

基　　金：国家自然科学基金项目(61074076);中国博士后科学基金项目(20090450119);中国博士点新教师基金项目(20092304120017);黑龙江省博士后基金项目(LBH-Z08227)

摘　　要：提出一种克隆多尺度协同开采的离散微粒群算法.多尺度变异概率根据粒子适应值大小进行动态调节,在算法初期通过大尺度概率变异增加算法多样性,后期通过逐渐减小的小尺度变异提高算法在最优解附近的局部精确解搜索性能,对当前最优解进行克隆选择,可进一步增强算法逃出局部极小解的能力以及所求解的精度.将算法应用于5个benchmark函数优化问题并与其他算法比较,结果表明该算法不仅能增强全局解搜索性能,同时最优解的精度也有所提高.A discrete particle swarm optimization（DPSO） algorithm based on multi-scale cooperative clone mutation（MSCMDPSO） is proposed.The clone mutation operator with multi-scale possibilities is introduced on the current optimical solution,which can not only improve the ability of local search,but also keep the abilities of global space search and escaping from local optima.The mutation operator with large-scale possibilities can be utilized to quickly localize the global optimized space at the early evolution.The scale-changing strategy produces a smaller multi-scale mutation operators according to the variation of the fitness value and makes mutation operators with smaller-scale possibilities implement local accurate minima solution search at the late evolution.The experiment studies on 5 standard benchmark functions,and the experimental results show the proposed method can not only effectively solve problem of lack of local search ability,but also significantly speed up the convergence and improve the stability.

关 键 词：离散微粒群 克隆 多尺度 协同开采 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]