计算机科学 ›› 2017, Vol. 44 ›› Issue (6): 222-225.doi: 10.11896/j.issn.1002-137X.2017.06.037

• 人工智能 • 上一篇    下一篇

基于均匀设计的差分进化算法的参数设定

白芸,张天军,赵高长,刘杰   

  1. 西安科技大学理学院 西安710054,西安科技大学理学院 西安710054,西安科技大学理学院 西安710054,西安科技大学理学院 西安710054
  • 出版日期:2018-11-13 发布日期:2018-11-13
  • 基金资助:
    本文受国家自然科学基金项目(51374168,51174158),陕西省自然科学基础研究计划项目(2014JQ1034),陕西省教育厅科研计划项目(2013JK0583)资助

Parameter Establishment of Differential Evolution Algorithm Based on Uniform Design

BAI Yun, ZHANG Tian-jun, ZHAO Gao-chang and LIU Jie   

  • Online:2018-11-13 Published:2018-11-13

摘要: 差分进化算法参数的设定多采用经验选取方式,其缺点是试验运行量大以及难以得到最优参数组合,从而在很大程度上影响了算法的寻优能力。将均匀设计的试验方法引入差分进化算法的参数设定中,通过对单峰函数、多峰函数和病态函数等3种不同类型的标准测试函数进行均匀设计试验,找出适合不同类型标准测试函数的最优参数组合,从而达到对差分进化算法的参数进行设定的目的。结果显示,将经过均匀设计试验得到的两组最优的参数组合用于差分进化算法时,所获得的平均全局最优解为4.3215,平均标准差为3.650。可见,利用均匀试验设计方法对基本差分进化算法的参数进行设定是可行且有效的,同时具有较好的稳定性。

关键词: 差分进化算法,均匀设计,参数设定,测试函数

Abstract: The parameter establishment of differential evolution algorithm is generally determined by the experience selection method,whose shortcomings include the massive operational parameters,the difficulty in obtaining the best parameter combination,and obstacle in improving the optimization ability of the algorithm to a great extent.The article introduced the uniform design method to differential evolution algorithm in parameter establishment.The optimal parameters combination which can be applied to different types of standard test functions is discovered by means of the uniform design test for three different types of standard test function:the unimodal function,multi-peak function,and morbid function.Finally the differential evolutionary algorithm for parameter establishment can be specified.The result is as follows.When the two groups of optimal parameter combination obtained by the uniform design experiment are applied to the differential evolution,the average global optimal solution is 4.3215 and the average standard deviation is 3.650.It follows that the method of uniform experimental design is feasible and effective to set the parameters of the differen-tial evolution algorithm and the method offers good stability.

Key words: Differential evolution algorithm,Uniform design,Parameter establishment,Test function

[1] BIN G,ZHU J H,LANG W C.Research on Improved Differential Evolution Algorithm based on Hybrid Multi-strategy and its application[J].International Journal of Hybrid Information Technology,2015,8(4):147-156.
[2] FENG Q X,LIU S Y,TANG G Q,et al.Orthogonal Differential Evolution Algorithm for Solving System of Equations[J].Computer Science,2012,9(5):187-190.(in Chinese) 封全喜,刘三阳,唐国强,等.求解方程组的正交差分进化算法[J].计算机科学,2012,9(5):187-190.
[3] LI R P,FENG D,OUYANG H B,et al.An Improved Differen-tial Evolution Algorithm Reliability Problems[J].Journal of Northeastern University (Natural Science),2012,3(2):182-186.(in Chinese) 李若平,冯达,欧阳海滨,等.改进差分进化算法在系统可靠性问题中的应用[J].东北大学学报(自然科学版),2012,3(2):182-186.
[4] LI Z W,ZHOU X G,ZHANG G J.Dynamic Adaptive DifferentialEvolution Algorithm [J].Computer Science,2015,2(6A):52-57.(in Chinese) 李章维,周晓根,张贵军.一种动态自适应差分进化算法[J].计算机科学,2015,2(6A):52-57.
[5] LEE C H,KUO C T,CHANG H H.Performance enhancement of the differential evolution algorithm using local search and a self-adaptive scaling factor[J].International Journal of Innovative Computing,Information and Control,2012,8(4):2665-2679.
[6] ZHONG J H,ZHANG J.Adaptive Multi-objective Differential Evolution with Stochastic Coding Strategy [C]∥GECCO.2011:665-672.
[7] 方开泰,马长兴.正交与均匀试验设计[M].北京:科学出版社,2001.
[8] FANG K T.Uniform Design [J].Tactical Missile Technology,1994,3(2):56-69.(in Chinese) 方开泰.均匀设计[J].战术导弹技术,1994,3(2):56-69.
[9] HUANG Y Q,LIANG C Y,ZHANG X D.Parameter Establishment of an Ant System Based on Uniform Design [J].Control and Decision,2006,1(1):93-96.(in Chinese) 黄永青,梁昌勇,张祥德.基于均匀设计的蚁群算法参数设定[J].控制与决策,2006,1(1):93-96.
[10] HE T K,WANG F L,ZHANG C M.Parameter Establishment of Genetic Algorithm Based on Uniform Design[J].Journal of Northeastern University (Natural Science),2003,4(5):419-411.(in Chinese) 何太阔,王福利,张春梅.基于均匀设计的遗传算法参数设定[J].东北大学报(自然科学版),2003,4(5):419-411.
[11] LOCATELLI M,MAISCHBERGER M,SCHOEN F.DifferentialEvolution Algorithm Based on Local Search [J].Computers & Operations Search,2014,3:169-180.
[12] STORN R,PRICE K.Differential Evolution.A simple and Efficient Heuristic for Global Optimization over Continuous Spaces[J].Journal of Global Optimization,1997,1(4):341-359.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!