摘要
提出一种新的快速演化算法,并把它运用于函数优化问题的求解中。新算法的特征是引入一种基于高斯变异、Cau-chy变异以及Lévy变异的混合自适应变异算子,采用多父体搜索策略,提出随机排序选择策略。通过23个标准测试函数进行测试,结果表明,新算法在21个测试函数中的结果比FEP和EP好,具有稳定、高效和快速等特点。
A novel and fast evolutionary algorithm （NFEA） is proposed, and then it is used to solve the function optimization problems. It has some new features, such as introducing a hybrid adaptive mutation operator based on Gaussian mutation, Cauchy mutation and Lévy mutation, using multi-parent search strategy and stochastic ranking strategy. The new algorithm is tested on 23 benchmark functions, the results indicate that the new algorithm is stable, effective and fast, and its performance is better than or as well as the FEP and CEP.
出处
《计算机工程与设计》
CSCD
北大核心
2008年第17期4535-4537,4540,共4页
Computer Engineering and Design
基金
河南省教育厅项目支柱和许昌市科技计划基金项目(07020065、07020062)
关键词
演化算法
函数优化
混合自适应变异
随机排序
evolutionary algorithm
function optimization
hybrid adaptive mutation
stochastic rankinc,
