使用角度选择策略的第二代Pareto强度进化算法  

STRENGTH PARETO EVOLUTIONARY ALGORITHM II USING ANGLE SELECTION STRATEGY

作　　者：罗校清[1] Luo Xiaoqing(Hunan Software Vocational Institute, Xiangtan 411100, Hunan, China)

机构地区：[1]湖南软件职业学院

出　　处：《计算机应用与软件》2018年第7期290-298,共9页Computer Applications and Software

基　　金：2017年度湖南省教育科学"十三五"规划课题(XJK17CZY058)

摘　　要：现实世界中的许多优化问题都是多目标优化问题,其中有许多多目标优化问题无法用传统的数学方法解决。进化优化的方法能在一次运行后获得一组逼近真实Pareto前沿的折衷解。针对第二代Pareto强度进化算法收敛性不足的问题,提出使用角度选择策略的第二代Pareto强度进化算法。采用个体之间的角度信息来表示个体的收敛性及分布性,使用该方法改进第二代Pareto强度进化算法的种群修剪方法,进一步增加收敛压力,同时保持好的分布性。实验结果表明,SPEA2+算法能有效地解决具有2个和3个目标的优化问题。In the real world,there are a large number of multi-objective optimization problems which cannot be solved by traditional mathematical methods. The evolutionary optimization method can obtain a set of trade-off solutions after a single run. According to the strength Pareto evolutionary algorithm II,this paper proposed applying the angle selection strategy to the strength Pareto evolutionary algorithm II. It applied the angle information among individuals to represent the convergence and diversity of individuals,and employed this strategy to modify the population truncation method in the strength Pareto evolutionary algorithm II. It improved convergence pressure and maintained good diversity. The experimental results show that the proposed algorithm can effectively solve the problems with two and three objectives and is superior to the other four tested algorithms.

关 键 词：进化多目标优化 多目标进化算法 多目标优化问题 性能指标 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]