首页 | 本学科首页   官方微博 | 高级检索  
     

基于拥挤度和分散度的多样性处理方法
引用本文:张成,徐涛,郑连伟. 基于拥挤度和分散度的多样性处理方法[J]. 通化师范学院学报, 2008, 29(2): 7-9
作者姓名:张成  徐涛  郑连伟
作者单位:1. 沈阳化工学院,数理系,辽宁,沈阳,110142
2. 东北大学理学院,辽宁,沈阳,110004
摘    要:用进化策略求解多目标优岱问题时,为了保证Pareto前沿的多样性,该文提出了基于拥挤度和分散度的多样性处理方法,在分析基于拥挤距离处理多样性的基础上引入了拥挤度和分散度的概念,当两个个体具有相同的拥挤度时,通过其分散度来判断哪个个体更拥挤,这样能更好地保证解在Pareto前沿的多样性.仿真实验表明,该算法能更好地维持Pareto前沿的多样性。

关 键 词:进化策略  拥挤度和分散度  多样性处理  多目标优化算法
文章编号:1008-7974(2008)02-0007-03
修稿时间:2007-09-08

Diverse Processing Method Based on Crowding Degree and Disperson
ZHANG Cheng. Diverse Processing Method Based on Crowding Degree and Disperson[J]. Journal of Tonghua Teachers College, 2008, 29(2): 7-9
Authors:ZHANG Cheng
Affiliation:ZHANG Cheng et al ( Shenyang Institute of Chemical Technology, Shenyang, Liaoning 110142, China)
Abstract:Using the evolutionary strategy to solve multi - objective optimization problems, in order to maintain the diversity of the pareto front, the paper proposes the diverse processing method based on crowding degree and disperson. The concepts of crowding degree and disperson are induced based on the analysis of the diversity of crowding distance. We can judge which individual is more erowdly through its disperson when two individuals have the same crowding degree, then make sure the diversity of the pareto front. The simulation experiment's results show that this algorithm has' good performance to maintain the diversity of the pareto front.
Keywords:evolutionary strategy'  crowding degree and disperson  diverse processing  multi - objective optimization algorithm
本文献已被 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号