纺织高校基础科学学报2017，Vol.30Issue(2)：272-278,7.DOI:10.13338/j.issn.1006-8341.2017.02.019
基于种群分类的差分进化算法
Differential evolution algorithm based on population classification
摘要
Abstract
To prevent differential evolution algorithm from falling into local optimum and reducing the convergence rate, a differential evolution algorithm based on population classification is proposed.The proposed algorithm firstly divides the whole population into three sub-populations (superior, general and inferior sub-populations) by means of chosing three individuals randomly from the population and comparing with target individuals according to their fitness values.Then, three mutation operators with different characteristics are assigned for each sub-population above according to their special individual information, and control parameters among each mutation operator are suitably adjusted.The proposed algorithm could not only enhance the robustness, but also balance effectively the exploration and exploitation abilities by making full use of the information of individuals.Lastly, the effectiveness of this algorithm is shown by numerical experiments.关键词
差分进化/随机方法/种群分类/变异策略Key words
differential evolution/stochastic method/population classification/mutation strategy分类
信息技术与安全科学引用本文复制引用
闫学青,高兴宝..基于种群分类的差分进化算法[J].纺织高校基础科学学报,2017,30(2):272-278,7.基金项目
国家自然科学基金资助项目(61273311) （61273311）
