一种基于多种群协作进化的自适应差分进化算法研究

详细信息    查看全文 | 推荐本文 |

英文篇名：An Improved Multi-population Cooperative Adaptive Differential Evolution Algorithm and its Application 作者：周頔 英文作者：ZHOU Di;Industrial Technological Institute of Intelligent Manufacturing,Sichuan University of Arts and Science; 关键词：差分进化 ; 多种群协作 ; 局部搜索策略 ; 自适应 ; 高维函数优化 英文关键词：differential evolution;;multiple populations cooperation;;local-search strategy;;self-adaptive;;High-dimensional function optimization 中文刊名：JSSG 英文刊名：Computer & Digital Engineering 机构：四川文理学院智能制造产业技术研究院; 出版日期：2019-07-20 出版单位：计算机与数字工程 年：2019 期：v.47;No.357 基金：自然科学基金项目(编号:61304187,61771080);; 四川省教育厅科技计划项目(编号:18ZA0415)资助 语种：中文; 页：JSSG201907019 页数：5 CN：07 ISSN：42-1372/TP 分类号：89-92+159

摘要

针对差分进化算法求解高维复杂优化问题存在的全局搜索能力和收敛速度不足,论文充分利用局部搜索策略、协同进化机制以及多种群进化模式,提出一种改进的多种群协作自适应差分进化(MSDPIDE)算法。MSDPIDE算法按照个体适应度的差异将个体分成不同的子种群,在多种群协同进化过程中采用局部搜索策略和协同进化机制来提高个体多样性来避免早熟收敛,保证个体之间能够进行充分高效的信息交换,以平衡局部搜索能力与全局搜索能力。通过对9个典型的Benchmarks复杂函数进行了测试,并和DE、和CADE算法进行比较,实验结果表明MSDPIDE算法能有效地避免早熟收敛,具有较高的收敛速率、较高的计算精度、较好的稳定性和较强的全局搜索能力。
        For the low global searching ability and convergence speed of differential evolution algorithm(DE)in high-dimension complex function optimization,the different searching strategy and parallel evolution mechanism are used,a dynamic multiple populations parallel self-adaptive differential evolution algorithm with multiple strategies(MSDPIDE)is proposed to optimize functions in this paper. In MSDPIDE algorithm,the population is dynamically divided into multi-populations individuals according to the difference of individuals' fitness. Multiple strategies in multiple populations' parallel evolution are used to improve the individuals' diversity for avoiding premature convergence and ensure the efficiency and sufficiency information exchanging among sub-populations. In addition to,self-adaptive adjustment is introduced to automatically adjust the scaling factor and crossover factor during the running time. The MSDPIDE algorithm is tested on ten complex benchmark functions. The experiment results are compared with DE and CADE algorithms. The compared results show that the MSDPIDE algorithm takes on better searching accuracy,convergence speed,stability,remarkable global convergence ability,it is better in the searching precision,convergence speed,stability,remarkable global convergence ability,and it can avoid premature convergence effectively.

引文

[1]STORN R,PRICE K. Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization,1997,11(4):341-359.
    [2]LEE,Moo Ho;HAN,Chonghun;CHANG,Kun Soo. Dynamic optimization of a continuous polymer reactor using a modified differential evolution algorithm[J]. Industrial&Engineering Chemistry Research, 1999, 38(12):4825-4831.
    [3]方强,陈德钊,俞欢军,等.基于优进策略的差分进化算法及其化工应用[J].化工学报,2004,55(4):598-602.FANG Qiang,CHEN Dezhao,YU Huanjun,et al. Differential evolution algorithm based on eugenic strategy and its application to chemical engineering[J]. Journal of Chemical Industry and Engineering(China),2004,55(4):598-602.
    [4]张雪霞,陈维荣,戴朝华.带局部搜索的动态多群体自适应差分进化算法及函数优化[J].电子学报,2010,38(8):1825-1830.ZHANG Xuexia,CHEN Weirong,DAI Chaohua. Dynamic Multi-group self-adaptive differential evolution algorithm with local search for function optimization[J]. Acta Electronica Sinica,2010,38(8):1825-1830.
    [5] BREST Janez,GREINER Sa?o,BO?KOVIC'Borko,MERNIK Marjan,ZUMER Viljem. Self adapting control parameters in differential evolution:a comparative study on numerical benchmark problems[J]. IEEE Trans Evolutionary Computation,2006,10(6):646-657.
    [6]吴亮红,王耀南,袁小芳,等.双群体伪并行差分进化算法研究及应用[J].控制理论与应用,2007,24(3):453-458.WU Lianghong,WANG Yaonan,YUAN Xiaofang,et al.Research and application of pseudo parallel differential evolution algorithm with dual subpopulations[J]. Control Theory&Applications,2007,24(3):453-458.
    [7]GONG Wenyin,CAI Zhihua,JIANG Liangxiao. Enhancing the performance of differential evolution using orthogonal design method[J]. Applied Mathematics and Computation,2008:56-69.
    [8]ALI M M,Kajee-Bagdadi Z. A local exploration-based differential evolution algorithm for constrained global optimization[J]. Applied Mathematics and Computation,2009,208(1):31-48.
    [9]贾东立,郑国莘.基于混沌和高斯局部优化的混合差分进化算法[J].控制与决策,2010,25(6):899-902.JIA Dongli,ZHENG Guoxin. Hybrid differential evolution combined with chaos and Gaussian local optimization[J].Control and Decision,2010,25(6):899-902.
    [10]葛延峰,金文静,高立群,等.多种群并行的自适应差分进化算法[J].东北大学学报(自然科学版),2011,32(4):481-484.GE Yanfeng,JIN Wenjing,GAO Liqun,et al. An adaptive differential evolution algorithm based on a multi-population parallel[J]. Journal of Northeastern University(Natural Science),2011,32(4):481-484.
    [11]曲福恒,胡雅婷,杨勇,等.多策略多参数并行差分进化算法[J].计算机应用,2011,31(11):3097-3100.QU Fuheng,HU Yating,YANG Yong,et al. Differential evolution algorithm with different strategies and control parameters[J]. Journal of Computer Applications,2011,31(11):3097-3100.
    [12]陈华,范宜仁,邓少贵.基于logistic模型的自适应差分进化算法[J].控制与决策,2011,26(7):1105-1108.CHEN Hua,FAN Yiren,DENG Shaogui. Adaptive differential evolution algorithm based on logistic model[J].Control and Decision,2011,26(67):1105-1108.
    [13]WU Lianghong,WANG Yaonan. Self-adapting control parameters modified differential evolution for trajectory planning manipulator[J]. Control Theory Application,2007,5(4):365-373
    [14]CU Laizhong,LI Genghui,ZHU Zexuan,LIN Qiuzhen,WONG Kachun,CHEN Jianyong,LU Nan,LU Jian.Adaptive multiple-elites-guided composite differential evolution algorithm with a shift mechanism[J]. Information Sciences,2018,422:122-143
    [15]LUO Xuqiong,LIU Libin,OUYANG Aijia,LONG Guangqing. B-spline collocation and self-adapting differential evolution(jDE)algorithm for a singularly perturbed convection-diffusion problem[J]. Soft Computing,2018,22(8):2683-2693.
    [16]卢有麟,周建中,李英海,等.基于混沌搜索的自适应差分进化算法[J].计算机工程与应用,2008,44(10):31-33.LU Youlin,ZHOU Jianzhong,LI Yinghai,et al. Adaptive differential evolution algorithm combined with chaotic search[J]. Computer Engineering and Applications,2008,44(10):31-33.