混杂免疫多目标优化算法及对动态经济环境调度问题优化  

Hybrid immune multi-objective optimization algorithm for dynamic emission economic dispatch

作　　者：唐湘黔 钱淑渠[2] 武慧虹[2] Tang Xiangqian;Qian Shuqu;Wu Huihong(College of Mathematics&Statistics,Guizhou University,Guiyang 550025,China;School of Mathematics&Computer Sciences,Anshun University,Anshun Guizhou 561000,China)

机构地区：[1]贵州大学数学与统计学院,贵阳550025 [2]安顺学院数学与计机科学学院,贵州安顺561000

出　　处：《计算机应用研究》2023年第9期2720-2728,共9页Application Research of Computers

基　　金：国家自然科学基金资助项目(62241301,61762001);贵州省教育厅创新群体重大研究资助项目(黔教合KY字[2019]069);贵州省教育厅青年科技人才成长资助项目(黔教合KY字[2020]131号);安顺学院研究生创新专项资助项目(asxysrt(202223)号)。

摘　　要：动态经济环境调度(DEED)问题是电力系统调度中一类含大规模约束的高维多目标优化问题,传统的进化算法易于陷入局部最优,使得所获的Pareto前沿分布性和收敛性差。为了充分挖掘免疫系统的克隆选择原理,提出一种混杂免疫多目标优化算法(HIMOA)。该算法以传统进化算法为基本框架,面对高维决策变量优化易于陷入局部最优的缺陷,改进外部存档更新机制以保存历代优秀的多样性个体,采用克隆、高斯突变策略强化局部开采能力,有效地迫使算法跳出停滞搜索状态。为应对大规模约束,提出逐步微调机组出力策略,提高进化群体的可行性。数值仿真实验以10机系统为测试算例,将HIMOA与著名的六种算法MODE、NSGA-Ⅱ、IMOEA/D-CH、ADEA、MOHDE_SAT、MONNDE进行比较分析,结果表明,HIMOA能为DEED问题的10机系统提供较好的Pareto解,所获的Pareto前沿收敛性和分布性优越于其他算法,各评价指标的箱型图表明HIMOA具有优越于其他算法的统计特征。Dynamic economic emission dispatch(DEED)problem in power system is a kind of high-dimensional multi-objective optimization problem with large-scale constraints.The traditional evolutionary algorithm is easy to fall into local optimization,and the distribution and convergence of the obtained Pareto frontier are poor.This paper fully explored the clonal selection principle of immune system,and proposed a hybrid immune multi-objective optimization algorithm(HIMOA).The proposed algorithm took the traditional evolutionary algorithm as the basic framework.Since the deficiency of falling local optimization for the high-dimensional decision variables optimization,it improved the external archive update mechanism to preserve the excellent individuals from previous generations,and adopted the cloning and Gaussian mutation strategy to strengthen the local exploitation ability,forcing effectively the HIMOA to jump out of the stagnant search state.In order to cope with the large-scale constraints,it designed the fine-turning output power step by step to improve the feasibility of the evolutionary population.In the numerical simulation experiment,taking a 10-unit system as a test example,and compared HIMOA with the famous algorithms MODE,NSGA-Ⅱ,IMOEA/D-CH,ADEA,MOHDE_SAT,MONNDE.The results show that HIMOA can provide a better Pareto solution to the 10-unit system of the DEED problem,and the convergence and distribution of the Pareto frontier obtained are better than other algorithms.The box diagram of each evaluation metric shows that HIMOA has better statistical characteristics than other algorithms.

关 键 词：动态经济环境调度 免疫系统 克隆选择原理 大规模约束 多目标优化 

分 类 号：TP304.7[自动化与计算机技术—计算机系统结构]