Adaptive Differential Evolution Algorithm Based on Elite Differential Feedback Strategy

Yi WANG; Yu-bo PENG; Xin HUANG; Hong-zhi ZHENG; Peng-hui ZHANG

doi:10.12263/DZXB.20210513

您当前的位置：

首页 >

文章列表页 >

Adaptive Differential Evolution Algorithm Based on Elite Differential Feedback Strategy

更新时间：2022-07-25

- Adaptive Differential Evolution Algorithm Based on Elite Differential Feedback Strategy
- ACTA ELECTRONICA SINICA Pages: 1-11(2022)
- 作者机构：
  
  1.西北大学信息科学与技术学院，陕西西安 710127
  2.西安交通大学第一附属医院，陕西西安 710049
- 作者简介：
- 基金信息：
- DOI：10.12263/DZXB.20210513
  CLC： TP182;TP391
- Received：21 April 2021，
  
  Revised：2021-08-05，
  
  Published Online：25 July 2022，
- 稿件说明：
移动端阅览
Yi WANG, Yu-bo PENG, Xin HUANG, et al. Adaptive Differential Evolution Algorithm Based on Elite Differential Feedback Strategy[J/OL]. ACTA ELECTRONICA SINICA, 2022, 1-11.
DOI：

Yi WANG, Yu-bo PENG, Xin HUANG, et al. Adaptive Differential Evolution Algorithm Based on Elite Differential Feedback Strategy[J/OL]. ACTA ELECTRONICA SINICA, 2022, 1-11. DOI： 10.12263/DZXB.20210513.

摘要

为提升差分进化的收敛性与多样性能力，分析并归纳了影响差分进化算法性能的参数自适应调节机制与改进策略，提出一种基于精英差异反馈策略的自适应差分进化算法.首先，通过种群个体适应度评估，找出当前种群全局最优个体，并与待进化个体判定生成全局精英差异；其次，提出基于多样性扰动邻域生成策略，构建个体邻域，并基于邻域最优个体与待进化个体判定生成邻域精英差异；最后通过全局精英差异与邻域精英差异指导DE（Differential Evolution）算法交叉策略，平衡了DE算法的收敛性与多样性.同时，本算法步长因子

采用自适应调整策略，进而降低算法陷入搜索停滞的可能.通过本文在CEC2017测试集上与其他主流改进算法相比，实验结果表明该算法在寻优效率与收敛精度上显著优于对比方法.

Abstract

In order to improve the algorithm convergence and diversity capabilities in differential evolution

the parameter adaptive adjustment mechanism and improvement strategy that affect the performance of differential evolution algorithm are analyzed and summarized

and an adaptive differential evolution algorithm based on elite differential feedback strategy is proposed. First

through population individual fitness assessment

find the global optimal individual of the current population

and determine the global elite difference with the individual to be evolved; second

propose a strategy based on the diversity perturbation neighborhood generation strategy to construct individual neighborhoods based on neighborhoods The optimal individual and the individual to be evolved are determined to generate neighborhood elite differences; finally

the crossover strategy of DE algorithm is guided by global elite differences and neighborhood elite differences

which balances the convergence and diversity of DE algorithm. At the same time

the step factor F of this algorithm adopts an adaptive adjustment strategy

thereby reducing the possibility of the algorithm getting stuck in search. By comparing this article with other mainstream improved algorithms on the CEC2017 test set

the experimental results show that the algorithm is significantly better than the comparison method in terms of optimization efficiency and convergence accuracy.

关键词

Keywords

references

STORN R , PRICE K . Differential evolution-A simple and efficient adaptive scheme for global optimization over continuous spaces [J]. Journal of Global Optimization , 1997 , 11 ( 4 ) : 341 - 359 .

MENG Z Y , PAN J S , KONG L P . Parameters with adaptive learning mechanism (PALM) for the enhancement of differential evolution [J]. Knowledge-Based Systems , 2018 , 141 : 92 - 112 .

LIU X F , ZHAN Z H , LIN Y , et al . Historical and heuristic-based adaptive differential evolution [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems , 2019 , 49 ( 12 ): 2623 - 2635 .

CHANG Y C . Parameter selection of differential evolution by another differential evolution algorithm [C]. 2019 IEEE International Conference on Systems, Man and Cybernetics . Piscataway : IEEE , 2019 : 2506 - 2511 .

HIBA H , MAHDAVI S , RAHNAMAYAN S . Differential evolution with self-adaptive mutation scaling factor [C]. 2017 IEEE Symposium Series on Computational Intelligence . Piscataway : IEEE , 2017 : 1 - 8 .

閤大海 , 李元香 , 龚文引 , 等 . 一种求解约束优化问题的自适应差分进化算法 [J]. 电子学报 , 2016 , 44 ( 10 ): 2535 - 2542 .

XIA Dahai , LI Yuanxiang , GONG Wenyin , et al . An adaptive differential evolution algorithm for constrained optimization problems [J]. Acta Electronica Sinica , 2016 , 44 ( 10 ): 2535 - 2542 . (in Chinese)

刘昊 , 丁进良 , 杨翠娥 , 等 . 基于择优学习策略的差分进化算法 [J]. 上海交通大学学报 , 2017 , 51 ( 6 ): 704 - 708 .

LIU H , DING J L , YANG C E , et al . Perferred-learning-based differential evolution algorithm [J]. Journal of Shanghai Jiao Tong University , 2017 , 51 ( 6 ): 704 - 708 . (in Chinese)

刘会宇 , 韩继红 , 袁霖 , 等 . 基于双变异策略的自适应骨架差分进化算法 [J]. 通信学报 , 2017 , 38 ( 8 ): 201 - 212 .

LIU H Y , HAN J H , YUAN L , et al . Self-adaptive bare-bones differential evolution based on bi-mutation strategy [J]. Journal on Communications , 2017 , 38 ( 8 ): 201 - 212 . (in Chinese)

CAI Y Q , WU D W , ZHOU Y , et al . Self-organizing neighborhood-based differential evolution for global optimization [J]. Swarm and Evolutionary Computation , 2020 , 56 : 100699 .

王亚辉 , 吴金妹 , 贾晨辉 . 基于动态种群多策略差分进化模型的多目标进化算法 [J]. 电子学报 , 2016 , 44 ( 6 ): 1472 - 1480 .

WANG Y H , WU J M , JIA C H . Multi-objective evolutionary algorithm based on dynamic population multi-strategy differential models [J]. Acta Electronica Sinica , 2016 , 44 ( 6 ): 1472 - 1480 . (in Chinese)

ZHAN Z H , WANG Z J , JIN H , et al . Adaptive distributed differential evolution [J]. IEEE Transactions on Cybernetics , 2020 , 50 ( 11 ): 4633 - 4647 .

GE Y F , YU W J , ZHAN Z H , et al . Competition-based distributed differential evolution [C]. 2018 IEEE Congress on Evolutionary Computation (CEC) . Piscataway : IEEE , 2018 : 1 - 8 .

ZHANG J Q , SANDERSON A C . JADE: adaptive differential evolution with optional external archive [J]. IEEE Transactions on Evolutionary Computation , 2009 , 13 ( 5 ): 945 - 958 .

王柳静 , 张贵军 , 周晓根 . 基于状态估计反馈的策略自适应差分进化算法 [J]. 自动化学报 , 2020 , 46 ( 4 ): 752 - 766 .

WANG L J , ZHANG G J , ZHOU X G . Strategy self-adaptive differential evolution algorithm based on state estimation feedback [J]. Acta Automatica Sinica , 2020 , 46 ( 4 ): 752 - 766 . (in Chinese)

WANG Y , CAI Z X , ZHANG Q F . Differential evolution with composite trial vector generation strategies and control parameters [J]. IEEE Transactions on Evolutionary Computation , 2011 , 15 ( 1 ): 55 - 66 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Constrained Differential Evolution Using Opposition-Based Learning

Hierarchical Feature Selection from Coarse to Fine

An Estimation of Distribution Algorithm with Diversity Preservation

The Cellular Genetic Algorithm with Evolutionary Rule

Related Author

WEI Wen-hong

ZHOU Jian-long

TAO Ming

YUAN Hua-qiang

ZENG Hao

CAI Wan-han

REN Zhi-gang

CHEN Yi-qiao

Related Institution

School of Computer, Dongguan University of Technology

Department of Computer, Xi'an Jiaotong University City College

School of Computer Dongguan University of Technology Dongguan Guangdong China

Department of Computer Xi'an Jiaotong University City College Xi'an Shaanxi

School of Microelectronics and Communication Engineering, Chongqing University

⁰