Journal of South China University of Technology (Natural Science Edition) ›› 2013, Vol. 41 ›› Issue (5): 73-79.doi: 10.3969/j.issn.1000-565X.2013.05.012

• Computer Science & Technology • Previous Articles     Next Articles

Improved Evolutionary Programming Algorithm Based on Heuristic Mutation

Hu Lian-min1 Huang Han2 Cai Zhao-quan3   

  1. 1.School of Computer Science and Engineering,South China University of Technology,Guangzhou 510006,Guangdong,China;2.School of Software Engineering,South China University of Technology,Guangzhou 510006,Guangdong,China;3.Science and Technology Department,Huizhou University,Huizhou 516007,Guangdong,China
  • Received:2012-10-23 Revised:2013-02-25 Online:2013-05-25 Published:2013-04-01
  • Contact: 胡廉民(1969-)，男，硕士，华南理工大学访问学者，乐山师范学院副教授，主要从事信息安全、智能计算研究． E-mail:123890547@qq.com
  • About author:胡廉民(1969-)，男，硕士，华南理工大学访问学者，乐山师范学院副教授，主要从事信息安全、智能计算研究．
  • Supported by:

    国家自然科学基金资助项目( 61003066， 61170193) ; 广东省自然科学基金资助项目( S2012010010613) ; 教育部博士点基金资助项目( 20090172120035) ; 华南理工大学中央高校基本科研业务费重点项目( 2012ZZ0087) ; 珠江科技新星项目( 2012J2200007)

PDF

788

Abstract:

The common evolutionary programming ( EP) algorithms are of poor robustness because they perform themutation based on a fixed probability distribution.In this paper,first,the influence of mutation operators on thecomputational efficiency of evolutionary programming algorithms is analyzed,and the essential drawback of Gauss,Cauchy and Lévy mutation operators,namely the lack of heuristic information,is pointed out.Then,a heuristicmutation operator based on the differential information among individuals is designed,which uses the difference betweentwo individuals to update the mutated variables and to provide chances for an individual to maintain its statusquo in some dimensions.With the help of the proposed heuristic mutation operator,evolutionary programming algorithmscan adapt to different continuous optimization problems and the algorithm robustness improves.Numericalexperiments of several Benchmark problems demonstrate that the improved evolutionary programming algorithmbased on heuristic mutation is of higher convergence speed and better average performance than six other evolutionaryalgorithms based on probability distribution.

Key words: evolutionary programming algorithm, heuristic mutation, continuous optimization, convergence speed

CLC Number: