广义NK模型下遗传算法和自适应遗传算法性能比较  

Performance Comparison Between Genetic Algorithm and Adaptive Genetic Algorithm in Generalized NK Model

作　　者：谢超凡[1] 徐鲁雄[1] 徐琳[1] 

机构地区：[1]福建师范大学福清分校,福建福清350300

出　　处：《太原师范学院学报（自然科学版）》2017年第2期47-51,共5页Journal of Taiyuan Normal University:Natural Science Edition

摘　　要：传统的优化算法,往往收敛于一个局部最优解,并且只提供解的单一性,而智能算法利用仿真原理进行设计,对于解决不规则、非结构化的问题具有巨大的优势,并且易于计算机实现、操作简单.在智能算法中,最具代表性的是遗传算法系列,为此在研究中使用广义NK模型来生成不同程度的复杂度问题空间,来比较分析对遗传算法和自适应遗传算法的性能影响,从而为实际问题对这两种算法的选择提供理论依据.The traditional optimization algorithms,tend to converge to a local optimal solution,and only provide a single solution, and the use of intelligent algorithm simulation principle designed for solving irregular and unstructured problems has great advantages, simple operation, and easy to realize by computer. In the algorithm,the most representative is the genetic algorithm for this series, using the generalized NK model to generate the space complexity problem in different degree in the study, to compare and analyze the impact on the performance of genetic algorithm and adaptive genetic algorithm,which provides a theoretical basis for the practical problems of the two kinds of algorithm selection.

关 键 词：智能算法 遗传算法 广义NK模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]