Pareto最优概念的多目标进化算法综述  

Overview on the Pareto Optimal-based Multiobjective Evolutionary Algorithms

作　　者：唐云岚[1,2] 赵青松[1] 高妍方[1] 陈英武[1] 

机构地区：[1]国防科学技术大学信息系统与管理学院,长沙410073 [2]武警工程学院通信工程系,西安710086

出　　处：《计算机科学》2008年第10期25-27,57,共4页Computer Science

基　　金：国家自然科学基金资助项目(70272002);高等学校博士学科点专项科研基金(20059998019)

摘　　要：群体搜索策略和群体间个体之间的信息交换是进化算法在解决多目标优化问题上的两大优势。目前,基于Pareto最优概念的多目标进化算法已成为多目标优化问题研究的主流方向。详细介绍了该领域的经典算法,特别对各种算法在种群快速收敛并均匀分布于问题的非劣最优域上所采取的策略进行了阐述,并归纳了算法性能评估中需要深入研究的问题。The strategy of community searches and the exchange of information between the individual are the superiority of evolution algorithm in solving the multi-objective optimization question. The pareto optimal-based multi-objective evolutionary algorithm which was used to deal with multi-objective optimization problems has become a hot research topic. In this paper, some state-of-the-art algorithms in this research field were described firstly. Then, strategies adopted by various kinds of algorithms about finding the non-dominated set of solutions and distribute them uniformly in the Pareto front were elaborated. Lastly, we summarized several research points of performance evaluation which need to be further studied.

关 键 词：进化算法 多目标优化 经典算法 综述 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] O224[自动化与计算机技术—控制科学与工程]