一种改进的多目标演化算法  

Improved multi-objective evolutionary algorithm

作　　者：龚正[1] 王毅[1] 周佳[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》2010年第26期43-45,57,共4页Computer Engineering and Applications

摘　　要：保持解集的多样性和分布性是多目标进化算法的关键之一。在NSGA-Ⅱ的基础上,提出了一种用混合距离来估计个体的拥挤度,并使用优先队列根据个体的混合距离来逐个删除种群中超出的非劣解以保持解的多样性,实验结果表明,HD-NS-GA-Ⅱ比NSGA-Ⅱ的解分布的更加合理且分布度有很大的提高。Preserving the diversity of solution is a key for multi-objective evolution algorithm.This paper improves of NS- GA-Ⅱ, it suggests a new approach to measure individual crowding distance by hybrid distance and uses priority queue to prune the over-plus of non-dominated solution one by one according hybrid distance for preserving the diversity of solution. Experimental results show that the HD-NSGA-Ⅱ can obtain reasonable distributing solution and diversity of this algorithm are more efficient than NSGA-Ⅱ.

关 键 词：多目标进化算法 混合距离 优先队列 多样性 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]