基于精英区域学习的多种群自适应的差分进化算法  

Based On Populations of Elite Regional Learning Adaptive Differential Evolution Algorithm

作　　者：蔡万刚[1] 蔡志伟[1] 郑建国[1] 

机构地区：[1]东华大学管理学院,上海200051

出　　处：《运筹与管理》2017年第8期27-33,共7页Operations Research and Management Science

基　　金：国家自然科学基金资助项目(70971020);上海市自然科学基金资助项目(15ZR1401600)

摘　　要：为了进一步提高差分进化算法的收敛速度、算法精度和稳定性,采用多种群技术来增加算法收敛速度和降低复杂度;利用精英区域学习策略来对算法的全局搜索能力和算法精度进一步提升,引进自适应免疫搜索策略,以实现自适应修正差分算法的变异因子和交叉因子。通过五个测试函数,把本文算法与最新文献中的算法进行对比,表明算法在收敛速度、精度和高维问题寻优能力方面的优越性。In order to further improve the convergence speed differential evolution algorithm accuracy and stabili- ty, using a variety of techniques to increase the population convergence rate and reduce complexity; the use of elite regional learning strategy algorithm global search capability and algorithms further enhance the accuracy of the introduction of immune self-adaptive search strategy in order to achieve variation factor and crossover factor adaptive differential correction algorithm. Through five test functions, the proposed algorithm with the latest liter- ature comparison algorithm, show the superiority of the algorithm in convergence speed, high precision aspects optimization capability dimensional problem.

关 键 词：差分进化算法 多种群技术 免疫自适应搜索策略 精英区域学习策略 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]