基于随机算子的快速多目标遗传算法  

Fast genetic multi-objective genetic algorithm based on random operator

作　　者：彭琰[1] 郑金华[1] 

机构地区：[1]湘潭大学信息工程学院,湖南湘潭411105

出　　处：《计算机工程与应用》2007年第33期54-57,共4页Computer Engineering and Applications

基　　金：教育部留学回国人员科研启动基金(the Project-sponsored by SRF for ROCS;SEM; No.教外司留[2005]546 号);湖南省自然科学基金(the Natural Science Foundation of Hunan Province of China under Grant No.05JJ30125);湖南省教育厅资助科研课题(the Research Project of Department of Education of Hunan Province; China under Grant No.06A074)

摘　　要：在NSGA-Ⅱ算法的基础上,对NSGA-Ⅱ构造非支配集的方法进行了改进,用擂台赛法则构造非支配集,当非支配集小于种群大小时,采用随机算子在可行域内随机产生新的解个体填充到下一代父种群中,形成了一种新的多目标遗传算法。在实验部分将改进后的算法和NSGA-II进行了性能比较,实验结果表明改进后的算法具有良好的分布性,算法运行效率也较高。This paper improves the approach of constructing non-dominated set in NSGA-Ⅱ .We use AP （Arena＇s Principle） to construct non-dominated set.When non-dominated set is smaller than the size of the population,a random operator is used to generate new solutions in feasible area to fill with the next population.In the experiments,the improved algorithm is compared with NSGA-Ⅱ .Finally the experimental results demonstrate that the improved algorithm has a good diversity and is more efficient than NSGA- Ⅱ.

关 键 词：多目标遗传算法 非支配集 擂台赛法则 随机算子 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]