动态小生境半径两阶段多模态差分进化算法-控制与决策.PDF

第31 卷 第7 期 控 制 与 决 策 2016 年 7 月 Vol. 31 No. 7 Control and Decision Jul. 2016 文章编号: 1001-0920 (2016) 07-1185-07 DOI: 10.13195/j.kzyjc.2015.0752 动态小生境半径两阶段多模态差分进化算法 张贵军, 陈 铭, 周晓根 (浙江工业大学信息工程学院，杭州310023) 摘 要: 针对多模态优化问题, 提出一种动态小生境半径两阶段多模态差分进化算法. 基于构象空间退火思想, 设计 一种两阶段退火策略来动态调整小生境半径, 并根据退火过程将整个优化过程分为两个阶段. 在第1 阶段, 通过差分 限制变异策略生成高质量的新个体来维持种群的多样性, 促进多模收敛; 在第2 阶段, 利用种子邻近变异策略对已探 测到的生境高度搜索, 加快算法的收敛速度. 实验结果表明, 所提出算法能够有效实现从全局探测到局部增强的自适 应平滑过渡, 是一种有效的多模态优化算法. 关键词: 差分进化；多模态优化；小生境；两阶段优化；构象空间退火 中图分类号: TP301 文献标志码: A Two-stage differential evolution algorithm using dynamic niche radius for multimodal optimization ZHANG Gui-jun, CHEN Ming, ZHOU Xiao-gen (College of Information Engineering，Zhejiang University of Technology ，Hangzhou 310023 ，China ．Correspondent: ZHANG Gui-jun ，E-mail ：zgj@zjut.edu.cn) Abstract: A two-stage differential evolution algorithm using dynamic niche radius is proposed for multimodal optimization, in which a two-stage annealing schedule based on the idea of conformational space annealing is designed to adjust the niche radius dynamically. Meanwhile, the optimization process is divided into two stages according to the annealing process. Thus, at the first stage, a differential vector limited mutation is used to generate the high-quality individuals to keep the population diversity, thereby facilitating multiple convergence. At the second stage, to enhance the convergence speed, a seed neighborhood mutation strategy is used to exploit the niche highly. Experiment results show that, the proposed algorithm can navigate from global exploration to local exploitation adaptive