目标空间映射策略的高维多目标粒子群优化算法  

Multi-objective particle swarm optimization algorithm based on an objective space papping strategy

作　　者：陈强[1] 王宇嘉[1] 梁海娜 孙欣 CHEN Qiang;WANG Yujia;LIANG Haina;SUN Xin(School of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China)

机构地区：[1]上海工程技术大学电子电气工程学院,上海201620

出　　处：《智能系统学报》2021年第2期362-370,共9页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金项目(61403249).

摘　　要：为了平衡优化算法在高维多目标优化问题中收敛性和多样性之间的关系,增加算法的选择压力,本文提出了一种基于目标空间映射策略的高维多目标粒子群优化算法(many-objective particle swarm optimization algorithm based on objective space mapping strategy,MOPSO-OSM)。在求解高维多目标优化问题时,Pareto准则难以从众多的非支配解中确定最优“折中”解,因此将高维多目标空间映射为以收敛性和多样性评价指标的2维空间,再将上述2维空间根据性能指标的优劣划分为4个不同区域。同时,使用反向学习策略提高算法跳出局部最优的能力。实验表明,MOPSO-OSM算法可以有效平衡收敛性和多样性之间的关系,达到求解复杂多目标优化问题的目的。To balance the relationship between the convergence and diversity of the optimization algorithm in the multi-objective problem,the selection pressure of the algorithm is increased.A high-dimensional MOPSO-OSM(multi-objective particle swarm optimization algorithm based on objective space mapping strategy)is proposed in this paper.When solving high-dimensional multi-objective optimization problems,the Pareto based criterion cannot identify the best compromise solutions from many nondominated solutions.Therefore,the high-dimensional multi-objective optimization space is mapped into two-dimensional space based on indexes of convergence and diversity.Then,the two-dimensional space is divided into four regions according to the performance index.Simultaneously,the ability of the jumping local optimal solution is improved using the opposition learning strategy.The experimental results show that MOPSO-OSM can balance the relationship between convergence and diversity and solve complex problems.

关 键 词：目标空间映射策略 性能指标 反向学习 粒子群 高维多目标优化 Pareto准则 收敛性 分布性 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]