摘要
由于高维多目标优化问题包含的目标很多,已有的方法往往难以解决该问题.本文提出一种有效解决该问题的基于集合的进化算法,该方法以超体积、分布度,以及延展度为新的目标,将原优化问题转化为3目标优化问题;定义基于集合的Pareto占优关系,设计体现用户偏好的适应度函数;此外,还提出集合进化策略.将所提方法应用于4个基准高维多目标优化问题,并与其他2种方法比较,实验结果表明了所提方法的优越性.
Previous methods are difficult to tackle a many-objective optimization problem since it contains many objectives. A set-based evolutionary algorithm was proposed to effectively solve the above problem in this study. In the proposed method, the o- riginal optimization problem was first transformed into a tri-objective one by taking such indicators as hyper-volume, distribution and spread as three new objectives; thereafter, a set-based Pareto dominance relation was defined, and a fitness function reflecting a user's preference was designed; additionally, set-based evolutionary strategies were suggested. The proposed method was applied to four benchmark many-objective optimization problems and compared with the other two methods. The experimental results show its advantages.
出处
《电子学报》
EI
CAS
CSCD
北大核心
2014年第1期77-83,共7页
Acta Electronica Sinica
基金
中央高校基本科研业务费专项资金资助(No.2013XK09)
国家自然科学基金(No.61105063)
关键词
进化算法
高维多目标优化
集合进化
用户偏好
evolutionary algorithm
many-objective optimization
set-based evolution
user preference