一种基于子域搜索的高效遗传算法

A Subdomains-based Genetic Algorithms of High Performance

论文根据机器学习的思想利用有限离散的方法设计了一种新的实数编码遗传算法——基于子域搜索的遗传算法(SBGA),该算法能够根据学习规则记忆前面搜索过的样本点信息,并利用这些信息指导后续的搜索。理论分析和数值仿真都表明了算法的稳健性,能够消除过早收敛现象,处理复杂约束,避免重复采样等。

A new method for real number encoding genetic algorithms is described in this paper.This machine-learning-based algorithm can utilize the sequence of points explored during a search to guide further search.The results from both theory analysis and numerical experiments show the proposed method can significantly improve the performance of genetic algorithms in many aspects,such as premature convergence,constraint handling and resampling.