基于改进角度惩罚距离和自适应参考向量的高维多目标进化算法  

Improved angle penalized distance and adaptive reference vector based many-objective evolutionary algorithm

作　　者：曾亮 向思颖 曾维钧 王嘉诚 王珊珊 李维刚[3] ZENG Liang;XIANG Si-ying;ZENG Wei-jun;WANG Jia-cheng;WANG Shan-shan;LI Wei-gang(School of Electrical and Electronic Engineering,Hubei University of Technology,Wuhan 430068,China;Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System,Hubei University of Technology,Wuhan 430068,China;School of Information Science and Engineering,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]湖北工业大学电气与电子工程学院,武汉430068 [2]湖北工业大学太阳能高效利用及储能运行控制湖北省重点实验室,武汉430068 [3]武汉科技大学信息科学与工程学院,武汉430081

出　　处：《控制与决策》2024年第10期3199-3206,共8页Control and Decision

基　　金：国家重点研发计划项目(2018YFC0116100);湖北省重点研发计划项目(2020BAB114,2023BAB094);湖北省教育厅科学研究计划重点项目(D20211402);太阳能高效利用及储能运行控制湖北省重点实验室2023年度开放研究基金项目(HBSEES202309)。

摘　　要：为了解决现有多目标进化算法难以处理复杂帕累托前沿的问题,提出一种基于改进角度惩罚距离和自适应参考向量的高维多目标进化算法(improved angle penalized distance and adaptive reference vector based manyobjective evolutionary algorithm,PDAREA).算法中采用改进的角度惩罚距离策略进行个体选择,有效减少种群中个体收敛性与分布性的冲突.自适应参考向量策略能够根据目标函数的变化动态调整参考向量的分布,可有效改善个体在帕累托前沿上分布不均的问题.通过参考向量再生策略,提高算法处理带有不规则帕累托前沿问题的能力和效率.最后,将所提出算法与7个主流算法进行仿真实验对比,并应用于两个实际问题中.结果表明,所提出算法在求解带有复杂帕累托前沿的高维多目标优化问题上具有较强的竞争力,能有效平衡种群收敛性与分布性.In order to solve the problem that the existing multi-objective evolutionary algorithm is difficult to deal with the complex Pareto front(PF),an improved angle penalized distance and adaptive reference vector based multi-objective evolutionary algorithm(PDAREA)is proposed.An improved angle penalty distance strategy is used for individual selection to efficiently reduce the conflict between individual convergence and distribution in the population.The adaptive reference vector strategy can dynamically adjust the distribution of reference vectors according to the change of the objective function,which effectively improves the problem of uneven distribution of individuals on PF.Through the reference vector regeneration strategy,the ability and efficiency of the algorithm to deal with problems with irregular Pareto fronts is promoted.Finally,the proposed algorithm is compared with seven mainstream algorithms in simulation experiments,and applied to two practical applications.The results show that the proposed algorithm is highly competitive in solving many-objective optimization problems with complex Pareto fronts,which can effectively balance the convergence and distribution of the population.

关 键 词：高维多目标优化 进化算法 角度惩罚距离 自适应参考向量 帕累托前沿 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]