[1]杨振宇,唐珂.差分进化算法参数控制与适应策略综述[J].智能系统学报,2011,(05):415-423.
 YANG Zhenyu,TANG Ke.An overview of parameter control and adaptation strategiesin differential evolution algorithm[J].CAAI Transactions on Intelligent Systems,2011,(05):415-423.
点击复制

差分进化算法参数控制与适应策略综述(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
期数:
2011年05期
页码:
415-423
栏目:
出版日期:
2011-10-30

文章信息/Info

Title:
An overview of parameter control and adaptation strategiesin differential evolution algorithm
文章编号:
1673-4785(2011)05-0415-09
作者:
杨振宇1唐珂2
1.华东师范大学 计算机科学技术系,上海 200241;
2.中国科学技术大学 计算机科学与技术学院,安徽 合肥 230027
Author(s):
YANG Zhenyu1 TANG Ke2
1.Department of Computer Science and Technology, East China Normal University, Shanghai 200241, China;
2.School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China
关键词:
进化计算差分进化参数控制适应策略自适应
Keywords:
evolutionary computation differential evolution parameter control adaptation strategies selfadaptation
分类号:
TP18;O224
文献标志码:
A
摘要:
差分进化算法逐渐成为进化计算领域最流行的随机搜索算法之一,已被成功用于求解各类应用问题.差分进化算法参数设置与其性能密切相关,因此算法参数控制与适应策略设计是目前该领域的研究热点之一,目前已涌现出大量参数控制方案,但尚缺乏系统性的综述与分析.首先简要介绍差分进化算法的基本原理与操作,然后将目前参数控制与适应策略分成基于经验的参数控制、参数随机化适应策略、基于统计学习的参数随机化适应策略和参数自适应策略4类进行系统性综述,重点介绍其中的参数适应与自适应策略.此外,为分析各种参数控制与适应策略的功效,以实值函数优化为问题背景设计了相关实验,进一步分析各种策略的效率与实用性,实验结果表明,参数自适应控制策略是目前该领域最有效的方法之一.
Abstract:
Differential evolution algorithms have gradually become one of the most popular types of stochastic search algorithms in the area of evolutionary computation. They have been successfully applied to solve various problems in realworld applications. Since their performance often depends heavily on the parameter settings, the design of parameter control and adaptation strategies is one of the current hot topics of research in differential evolution. Although numerous parameter control schemes have been proposed, systematic overviews and analysis are still lacking. In this paper, first the basic principles and operations of the differential evolution algorithm were briefly introduced, and then a detailed overview was provided on different parameter control and adaptation strategies by dividing them into the following four classes: empirical parameter settings, randomized parameter adaptation strategies, randomized parameter adaptation strategies with statistical learning, and parameter selfadaptation strategies. The overview emphasized the latter two classes. To study the efficacy of these parameter control and adaptation strategies, experiments with the background of realvalued function optimization were conducted to compare their efficiency and practicability further. The results showed that the parameter selfadaptation is one of the most effective strategies so far.

参考文献/References:

[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]PRICE K, STORN R, LAMPINEN J. Differential evolution: a practical approach to global optimization[M]. Berlin, Germany: SpringerVerlag, 2005.
[3]CHAKRABORTY U K. Advances in differential evolution[M]. Berlin, Germany: SpringerVerlag, 2008.
[4]STORN R, PRICE K. Differential evolution: a simple and efficient adaptive scheme for global optimization over continuous spaces[EB/OL]. [20101025]. http://www.icsi.berkeley.edu/〖KG-*1/3〗~storn/TR95012.pdf.
[5]STORN R. System design by constraint adaptation and differential evolution[J]. IEEE Transactions on Evolutionary Computation, 1999, 3(1): 2234.
[6]THOMSEN R. Flexible ligand docking using differential evolution[C]//Proceedings of the 2003 IEEE Congress on Evolution Computation. Canberra, Australia, 2003: 23542361.
[7]BACK T, SCHWEFEL H P. An overview of evolutionary algorithms for parameter optimization[J]. Evolutionary Computation, 1993, 1(1): 123.
[8]DAS S, KONAR A, CHAKRABORTY U K. Two improved differential evolution schemes for faster global search[C]//Proceedings of the 2005 Genetic and Evolutionary Computation Conference. Washington, DC, USA, 2005: 991998.
[9]ZHANG J, SANDERSON A C. JADE: adaptive differential evolution with optimal external archive[J]. IEEE Transactions on Evolutionary Computation, 2009, 13(5): 945958.
[10]BREST J, GREINER S, BOSKOVC B, et al. Selfadapting control parameters in differential evolution: a comparative study on numerical benchmark problems[J]. IEEE Transactions on Evolutionary Computation, 2006, 10(6): 646657.
[11]GAMPERLE R, MULLER S, KOUMOUTSAKOS P. A parameter study for differential evolution[C]//WSEAS International Conference on Advances in Intelligent Systems, Fuzzy Systems, Evolutionary Computation. Interlaken, Switzerland, 2002: 293298.
[12]VESTERSTROM J, THOMSEN R. A comparative study of differential evolution, particle swarm optimization and evolutionary algorithms on numerical benchmark problems[C]//Proceedings of the 2004 IEEE Congress on Evolution Computation. Portland, USA, 2004: 19801987.
[13]KENNEDY J, EBERHART R C. Particle swarm optimization[C]//IEEE International Conference on Neural Networks. Perth, Australia, 1995: 19421948.
[14]RIGET J, VESTERSTROM J. A diversityguided particle swarm optimizer—the arPSO, Technical Report 200202[R]. Aarhus, Denmark: Department of Computer Science, University of Aarhus, 2002.
[15]THOMSEN R. Flexible ligand docking using evolutionary algorithms: investigating the effects of variation operators and local search hybrids[J]. BioSystems, 2003, 72(1/2): 5773.
[16]ROMKKONEN J, KUKKONEN S, PRICE K V. Realparameter optimization with differential evolution[C]//Proceedings of the 2005 IEEE Congress on Evolution Computation. Edinburgh, UK, 2005: 506513.
[17]RAHNAMAYAN S, TIZHOOSH H R, SALAMA M A. Oppositionbased differential evolution[J]. IEEE Transactions on Evolutionary Computation, 2008, 12(1): 6479.
[18]KAELO P, ALI M M. A numerical study of some modified differential evolution algorithms[J]. European Journal of Operational Research, 2006, 169(3): 11761184.
[19]YANG Zhenyu, YAO Xin, HE Jingsong. Making a difference to differential evolution[M]//MICHALEWICZ Z, SIARRY P. Advances in Metaheuristics for Hard Optimization. Berlin, Germany: Springer, 2008: 397414.
[20]ABBASS H A, SARKER R, NEWTON C. PDE: a Paretofrontier differential evolution approach for multiobjective optimization problems[C]//Proceedings of the 2003 IEEE Congress on Evolution Computation. Canberra, Australia, 2003: 971978.
[21]QIN A K, SUGANTHAN P N. Selfadaptive differential evolution algorithm for numerical optimization[C]//Proceedings of the 2005 IEEE Congress on Evolution Computation. Edinburgh, UK, 2005: 17851791.
[22]QIN A K, HUANG V L, SUGANTHAN P N. Differential evolution algorithm with strategy adaptation for global numerical optimization[J]. IEEE Transactions on Evolutionary Computation, 2009, 13(2): 398417.
[23]YAO Xin, LIU Yong, LIN Guangming. Evolutionary programming made faster[J]. IEEE Transactions on Evolutionary Computation, 1999, 3(2): 82102.
[24]YANG Zhenyu, TANG Ke, YAO Xin. Selfadaptive differential evolution with neighborhood search[C]//Proceedings of the 2008 IEEE Congress on Evolution Computation. Hong Kong, China, 2008: 11101116.
[25]YANG Zhenyu, TANG Ke, YAO Xin. Large scale evolutionary optimization using cooperative coevolution[J]. Information Sciences, 2008, 178(15): 29852999.
[26]YANG Zhenyu, TANG Ke, YAO Xin. Scalability of generalized adaptive differential evolution for largescale continuous optimization[J]. Soft Computing, 2011(in press).
[27]HINTERDING R, MICHALEWICZ Z, EIBEN A E. Adaptation in evolutionary computation: a survey[C]//Proceedings of the 1997 IEEE International Conference on Evolutionary Computation. Indianapolis, USA, 1997: 6569.
[28]ABBASS H A. The selfadaptive Pareto differential evolution algorithm[C]//Proceedings of the 2002 IEEE Congress on Evolution Computation. Honolulu, USA, 2002: 831836.
[29]OMRAN M, SALMAN A, ENGELBRECHT A. Selfadaptive differential evolution[C]//Proceedings of the International Conference on Computational Intelligence and Security. Xi’an, China, 2005: 192199.
[30]SALMAN A, ENGELBRECHT A, OMRAN M. Empirical analysis of selfadaptive differential evolution[J]. European Journal of Operational Research, 2007, 183(2): 785804.

相似文献/References:

[1]刘三阳,张晓伟.混合差分变异策略[J].智能系统学报,2008,(06):487.
 LIU San-yang,ZHANG Xiao-wei.A hybrid strategy for differential variation[J].CAAI Transactions on Intelligent Systems,2008,(05):487.
[2]毕晓君,刘国安,肖婧.基于自适应差分进化的干线交通信号协调控制[J].智能系统学报,2012,(05):437.
 BI Xiaojun,LIU Guoan,XIAO Jing.Coordination and control of arterial traffic signalsbased on adaptive differential evolution[J].CAAI Transactions on Intelligent Systems,2012,(05):437.
[3]刘恋,常冬霞,邓勇.动态小生境人工鱼群算法的图像分割[J].智能系统学报,2015,(5):669.[doi:10.11992/tis.201501001]
 LIU lian,CHANG Dongxia,DENG Yong.An image segmentation method based on dynamic niche artificial fish-swarm algorithm[J].CAAI Transactions on Intelligent Systems,2015,(05):669.[doi:10.11992/tis.201501001]
[4]杨艳霞.一种基于模拟退火操作的混合差分进化算法[J].智能系统学报,2014,(01):109.[doi:10.3969/j.issn.1673-4785.201305027]
 YANG Yanxia.A hybrid differential evolutionary algorithm based on the simulated annealing operation[J].CAAI Transactions on Intelligent Systems,2014,(05):109.[doi:10.3969/j.issn.1673-4785.201305027]
[5]丁青锋,尹晓宇.差分进化算法综述[J].智能系统学报,2017,(04):431.[doi:10.11992/tis.201605015]
 DING Qingfeng,YIN Xiaoyu.Research survey of differential evolution algorithms[J].CAAI Transactions on Intelligent Systems,2017,(05):431.[doi:10.11992/tis.201605015]
[6]钱伟懿,李明.依概率收敛的改进粒子群优化算法[J].智能系统学报,2017,(04):511.[doi:10.11992/tis.201610004]
 QIAN Weiyi,LI Ming.Improved particle swarm optimization algorithmwith probability convergence[J].CAAI Transactions on Intelligent Systems,2017,(05):511.[doi:10.11992/tis.201610004]

备注/Memo

备注/Memo:
收稿日期: 2010-11-02.
基金项目:海外及港澳学者合作研究基金资助项目(61028009).
 通信作者:唐珂.E-mail:ketang@ustc.edu.cn.
作者简介:
杨振宇,男,1982年生,讲师,博士,主要研究方向为进化计算与应用,发表学术论文多篇,其中被SCI、EI检索10余篇.
唐珂,男,1981年生,教授,博士,IEEE Computational Intelligence Magazine副编辑,IEEE 计算智能协会Emergent Technologies Technical Committee委员.主要研究方向为计算智能、机器学习、模式识别等,发表学术论文50余篇.
更新日期/Last Update: 2011-11-16