全局最优值引导的混沌蜂群算法  

Artificial bee colony algorithm with global best-guided and chaotic-local-search strategy

作　　者：李荣[1] 杨勇[1] 施建中[1] 

机构地区：[1]南京工程学院能源与动力工程学院,江苏南京211167

出　　处：《计算机工程与设计》2016年第6期1649-1653,共5页Computer Engineering and Design

基　　金：南京工程学院校级青年基金项目(QKJB201301;QKJA201303)

摘　　要：针对蜂群算法局部搜索能力差及容易陷入局部最优值的缺点,提出具有全局最优值引导的混沌蜂群算法。使用混沌序列初始化食源,增加初始解的随机性和多样性;观察蜂采用具有全局最优值引导的搜索策略,提高算法的收敛速度和全局搜索能力;在观察蜂搜索结束后,选取最优食源,对其进行混沌局部搜索,防止算法早熟,提高算法的局部搜索能力。经典函数的测试结果表明,相比其它算法,该算法能有效避免陷入局部极值,提高了算法的优化精度和收敛速度。Taking the prematurity and low searching speed of artificial bee colony（ABC）into account,an improved ABC algorithm with global best-guided and chaotic-local-search strategy was proposed.The chaotic series were applied to generate candidate solutions to increase the randomness of the population.The global best-guided search method was adopted to onlooker bees to improve the convergence speed and global search ability of the algorithm.A chaotic-local-search（CLS）method was used to help the algorithm overcome the drawback of prematurity and improve the local search ability of the algorithm.Experimental results of classic functions show that the proposed algorithm can effectively avoid falling into the local extremum,improve the precision of the optimal solution and convergence rate.

关 键 词：混沌序列 最优值引导 混沌局部搜索 蜂群算法 局部极值 

分 类 号：TP271[自动化与计算机技术—检测技术与自动化装置]