A new mutation operator for real coded genetic algorithms
A new mutation operator for real coded genetic algorithms
复制标题
DOI：
10.1016/j.amc.2007.03.046
复制
发表时间：
2007-10-01
影响因子：
4
通讯作者：
Thakur, Manoj
中科院分区：
文献类型：
--
作者：
Deep, Kusum;Thakur, Manoj
在本文中，为实编码遗传算法（RCGA）引入了一种称为幂突变（PM）的新变异算子。 PM 的性能与其他两个现有的实际编码变异算子（取自文献）进行了比较：非均匀变异（NUM）和 Makinen、Periaux 和 Toivanen 变异（MPTM）。使用两种交叉的各种组合（拉普拉斯交叉 [Kusum Deep，Manoj Thakur，真实编码遗传算法的新交叉算子，应用数学和计算，已接受出版，doi:10.1016/j.amc.2006.10.047] 和启发式交叉 [Z. Michalewicz，遗传算法 + 数据结构 = 进化程序， Springer-Verlag，纽约，1992；A. H. Wright，实数参数优化的遗传算法，见：G. J. E. Rawlins (Ed.)，遗传算法基础 I，Morgan Kaufmann，San Mateo，1991，第 205-218 页]) 和三个变异算子（本文中新定义的变异，PM、NUM 和 MPTM）在一组 20 个基准全局优化测试问题。各种性能标准用于判断所有 RCGA 的效率、准确性和可靠性。结果表明，当与早期定义的拉普拉斯交叉结合使用时，使用所提出的幂突变的 RCGA 优于本研究中考虑的所有其他 GA。 (C) 2007 Elsevier Inc. 保留所有权利。
In this paper, a new mutation operator called power mutation (PM) is introduced for real coded genetic algorithms (RCGA). The performance of PM is compared with two other existing real coded mutation operators taken from literature namely: non-uniform mutation (NUM) and Makinen, Periaux and Toivanen mutation (MPTM). Using the various combinations of two crossovers (Laplace crossover [Kusum Deep, Manoj Thakur, A new crossover operator for real coded genetic algorithms, Applied Mathematics and Computations, accepted for publication, doi:10.1016/j.amc.2006.10.047] and Heuristic crossover [Z. Michalewicz, Genetic Algorithms + Data Structures = Evolution Programs, Springer-Verlag, New York, 1992; A. H. Wright, Genetic algorithms for real parameter optimization, in: G. J. E. Rawlins (Ed.), Foundations of Genetic Algorithms I, Morgan Kaufmann, San Mateo, 1991, pp. 205-218]) and three mutation operators (the newly defined mutation in this paper, PM, NUM and MPTM) six generational real coded GAs are compared on a set of 20 benchmark global optimization test problems. Various performance criterion are used to judge the efficiency, accuracy and reliability of all the RCGAs. The results show that the RCGA using the proposed power mutation, when used in conjunction with the earlier defined Laplace crossover, outperforms all other GAs considered in this study. (C) 2007 Elsevier Inc. All rights reserved.