协同进化多生境遗传算法  

Co-evolutionary Multi-niche Genetic Algorithm

作　　者：郭方炜 许峰[1] 

机构地区：[1]安徽理工大学数学与大数据学院,安徽淮南232001

出　　处：《软件导刊》2017年第4期51-54,共4页Software Guide

基　　金：安徽省教育厅自然科学基金项目(2014KB236)

摘　　要：为了提高多生境遗传算法的优化效率,提出了一种基于协同进化的多生境遗传算法,其基本思想是:将种群分割为若干子种群,每个子种群采用合作型协同进化方法独立进化;个体评价采用多生境方法,具体作法为:在对个体的适应值进行共享调整的同时,在选择中采用确定性排挤方法,在替换中采用最相似个体适应度最差个体被替换策略,以维持种群的多样性。数值实验表明,上述算法在维持多生境遗传算法较强全局搜索能力的同时,可适当提高算法运行效率。In order to improve the optimization efficiency of multi-niche genetic algorithm, a multi-niche genetic algorithm based on co-evolution is proposed. The basic idea is that the population is divided into several sub-populations, and each sub-population evolves independently using cooperative co-evolutionary method. Multi-niche method is used to individual evaluation, and the specific methods is that individual adaptive value is share adjustment at the same time, the determinis- tic crowding method is used to choice, and WAMS is used to replace, so that maintain the diversity of population. Numer- ical experiments show that the algorithm can improve the operation efficiency of the algorithm, while maintaining the strong global searching ability of the multi - niche genetic algorithm.

关 键 词：遗传算法 协同进化 多生境 多峰函数 算法效率 

分 类 号：TP312[自动化与计算机技术—计算机软件与理论]