NSGA-II中一种改进的分布性保持策略  

Improved diversity maintenance strategy in NSGA-II

作　　者：文诗华[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》2010年第33期49-53,共5页Computer Engineering and Applications

基　　金：国家自然科学基金No.60773047;湖南省自然科学基金No.05JJ30125;湖南省教育厅重点科研项目No.06A074~~

摘　　要：NSGA-II以其良好的收敛性和时间效率广泛应用于多目标优化中,然而其基于聚集距离的种群维护策略并不能很好地保持解集的分布性。提出一种改进的分布性保持策略,设置随种群密集程度自适应变化的阈值,动态地维护种群,使得分布性优秀的个体有更大的生存机会。与NSGA-II和ε-MOEA在5个测试函数上进行比较实验,结果表明改进算法在有效提高分布性的同时,拥有良好的收敛性。NSGA-Ⅱ is widely used in multi-objective evolutionary optimization for its high convergence and time efficiency. However,the population maintenance based on crowding distance in NSGA-Ⅱ has not worked well in maintaining the diversity of solution sets.This paper proposes an improved strategy to dynamically maintain diversity by setting a self-adaptive threshold value, and the better diversity individuals have more chances to survive.Comparing new algorithm to NSGA-Ⅱ and -MOEA in five test problems, the results show that improved algorithm efficiently promotes the diversity and achieves efficient convergence at the same time.

关 键 词：多目标进化算法 种群维护 分布性 聚集距离 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]