Self-adaptive differential evolution algorithm based on exponential smoothing

被引：0
|
作者：
Zhao Z.-W. [1 ,2 ,3 ]
Yang J.-M. [1 ,2 ]
Hu Z.-Y. [1 ,2 ]
Che H.-J. [1 ,2 ]
机构：
[1] School of Electrical Engineering, Yanshan University, Qinhuangdao
[2] National Engineering Research Center for Equipment and Technology of Cold Strip Rolling, Yanshan University, Qinhuangdao
[3] Department of Computer Science and Technology, Tangshan University, Tangshan
来源：
Zhao, Zhi-Wei (wzzwzz@sina.com) | 1600年 / Northeast University卷 / 31期
关键词：
Cauchy distribution; Differential evolution; Exponential smoothing; Normal distribution; Self-adaptation;
D O I：
10.13195/j.kzyjc.2015.0487
中图分类号：
学科分类号：
摘要：
This paper presents a differential evolution algorithm based on exponential smoothing (ESADE), with selfadaptive strategy and control parameters, which employs single exponential smoothing and roulette wheel selection, and adaptively selects mutation strategy for each individual from the strategy candidate pool to match different stages of the evolution according to their previous successful experience. Cauchy distribution and normal distribution are used to generate appropriate values for control parameters during the evolutionary process, and single exponential smoothing method is used to realize self-adaption. A large amount of simulation experiments are made, and experimental results show that the ESADE is better than other DE algorithms. © 2016, Editorial Office of Control and Decision. All right reserved.
引用
收藏
页码：790 / 796
页数：6
相关论文
共 16 条
  • [1] Storn R., Price K., Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces, J of Global Optimization, 11, 4, pp. 341-359, (1997)
  • [2] Rogalsky T., Kocabiyik S., Derksen R., Differential evolution in aerodynamic optimization, Canadian Aeronautics and Space J, 46, 4, pp. 183-190, (2000)
  • [3] Ilonen J., Kamarainen J.K., Lampinen J., Differential evolution training algorithm for feeFig1d-forward neural networks, Neural Process Letters, 17, 1, pp. 93-105, (2003)
  • [4] Storn R., Differential evolution design of an IIR-filter, Proc of IEEE Int Conf on Evolutionary Computation, pp. 268-273, (1996)
  • [5] Chen Y., Mahalec V., Chen Y., Et al., Reconfiguration of satellite orbit for cooperative observation using variablesize multi-objective differential evolution, European J of Operational Research, 242, 1, pp. 10-20, (2015)
  • [6] Brest J., Greiner S., Boskovic B., Et al., Self-adapting control parameters in differential evolution: A comparative study on numerical benchmark problems, IEEE Trans on Evolutionary Computation, 10, 6, pp. 646-657, (2006)
  • [7] Zou D., Wu J., Gao L., Et al., A modified differential evolution algorithm for unconstrained optimization problems, Neurocomputing, 120, 10, pp. 1608-1623, (2011)
  • [8] Pan Q.K., Suganthan P.N., Wang L., Et al., A differential evolution algorithm with self-adapting strategy and control parameters, Computers and Operations Research, 38, 1, pp. 394-408, (2011)
  • [9] Mallipeddi R., Lee M., An evolving surrogate modelbased differential evolution algorithm, Applied Soft Computing, 34, 1, pp. 770-787, (2015)
  • [10] Fan Q., Yan X., Self-adaptive differential evolution algorithm with discrete mutation control parameters, Expert Systems with Applications, 42, 3, pp. 1551-1572, (2015)
12