基于改进粒子群算法的电力工程数据多目标优化方法  

Multi⁃objective optimization method of power engineering data based on improved particle swarm optimization algorithm

作　　者：杨宝杰 石凯元 陈佳凯 梁富军 梁悦 YANG Baojie;SHI Kaiyuan;CHEN Jiakai;LIANG Fujun;LIANG Yue(Electric Power Construction Engineering Consulting Branch,State Grid Beijing Electric Power Company,Beijing 100021,China)

机构地区：[1]国网北京市电力公司电力建设工程咨询分公司,北京100021

出　　处：《电子设计工程》2024年第5期95-99,共5页Electronic Design Engineering

基　　金：国网北京市电力公司科技项目(52022319004L)。

摘　　要：针对电力工程项目信息处理过程中存在的计算精度低、处理速度慢等问题,文中提出了基于改进粒子群算法的电力工程数据多目标优化方法。在综合考虑多方面影响因素的基础上构建了电力工程数据多目标优化模型,提出了非支配排序改进粒子群(NSIPSO)算法。其针对传统粒子群算法初期搜索能力弱、后期收敛速度较慢的不足之处,将惯性权重、飞行时间与学习参数加以改进,同时还结合非支配排序算法和精英保留策略,实现了多目标模型的快速、精准求解。仿真算例结果表明,与NSPSO算法相比,所提NSIPSO算法仅迭代27次即可达到计算精度为0.01%的收敛指标,且多目标优化模型得到决策结果的综合模糊隶属度达3.2,能够为电力工程项目提供更合理、均衡的策略。Aiming at the problems of low calculation accuracy and slow processing speed in the information processing of power engineering projects,a multi-objective optimization method of power engineering data based on improved particle swarm optimization algorithm is proposed in this paper.Based on the comprehensive consideration of various influencing factors,a multi-objective optimization model of power engineering data is constructed,and a Non-dominated Sorting Improved Particle Swarm Optimization(NSIPSO)algorithm is proposed.Aiming at the shortcomings of the traditional particle swarm optimization algorithm,such as weak search ability in the initial stage and slow convergence speed in the later stage,the algorithm realizes the rapid and accurate solution of the multi-objective model through the improvement strategy of inertia weight,flight time and learning parameters,combined with the non dominated sorting algorithm and elite retention strategy.The simulation results show that,compared with NSPSO algorithm,the proposed NSIPSO algorithm can achieve the convergence index of 0.01%in calculation accuracy with only 27 iterations,and the comprehensive fuzzy membership degree of the decision-making results obtained by the multi-objective optimization model is 3.2,which can provide a more reasonable and balanced strategy for the power engineering project.

关 键 词：粒子群 多目标 非支配排序 NSIPSO 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置] TN99[自动化与计算机技术—控制科学与工程]