基于改进FCM聚类的分布式光伏三相不平衡度概率建模方法  

Probabilistic modeling method of distributed photovoltaic threephase unbalance degree based on improved FCM clustering

作　　者：张鹏 潘玲 陈冉 沈冰 喻梦洁 汪颖[2] ZHANG Peng;PAN Ling;CHEN Ran;SHEN Bing;YU Mengjie;WANG Ying(Electric Power Research Institute,State Grid Shanghai Electric Power Company,Shanghai 200437,China;College of Electrical Engineering,Sichuan University,Chengdu 610065,China)

机构地区：[1]国网上海市电力公司电力科学研究院,上海200437 [2]四川大学电气工程学院,四川成都610065

出　　处：《武汉大学学报（工学版）》2024年第10期1469-1478,共10页Engineering Journal of Wuhan University

基　　金：国家自然科学基金项目(编号:52077145);国家电网有限责任公司科技项目(编号:20222900610-WB01)。

摘　　要：低压配电网中光伏大规模接入加剧了电网三相不平衡问题,准确刻画分布式光伏三相不平衡度发射特性对于三相不平衡度的责任分摊、影响评估等研究具有重要意义,因此提出基于改进模糊C均值(fuzzy C-mean, FCM)聚类的分布式光伏三相不平衡度概率建模方法。首先,基于分布式光伏功率特征与三相不平衡度的相关性,实现聚类特征的筛选,并引入邓恩指数用于改进FCM算法,对三相不平衡度数据进行聚类划分。然后,采用核密度估计方法对划分的三相不平衡度数据进行非参数估计,得到三相不平衡度概率模型。最后,应用实测数据验证了所提方法的准确性和有效性。Large-scale access of photovoltaic in low-voltage distribution network aggravates the three-phase imbalance problem of power grid.Accurately characterizing the emission characteristics of distributed photovoltaic three-phase unbalance degree is of great significance for the researches of responsibility allocation and impact assessment of three-phase unbalance degree.Therefore,a distributed photovoltaic three-phase unbalance degree probability modeling method based on improved fuzzy C-means(FCM)clustering is proposed.Firstly,based on the correlation between distributed photovoltaic power characteristics and three-phase unbalance degree,the clustering features are screened,and Dunn index is introduced to improve the FCM algorithm to cluster the three-phase unbalance degree data.Then,the kernel density estimation method is used for non-parametric estimation of the clustered three-phase unbalance degree data,and the three-phase unbalance degree probability model is obtained.Finally,the accuracy and effectiveness of the proposed method are verified by the measured data.

关 键 词：FCM聚类 分布式光伏 三相不平衡度 概率建模 

分 类 号：TM712[电气工程—电力系统及自动化]