基于特征加权模糊聚类的电力负荷分类  

Power Load Classification Based on Feature Weighted Fuzzy Clustering

作　　者：马宗彪 许素安 朱少斌 王晶 MA Zongbiao;XU Su'an;ZHU Shaobin;WANG Jing(College of Mechanical and Electrical Engineering,China Jiliang University,Hangzhou 310018,China)

机构地区：[1]中国计量大学机电工程学院,浙江杭州310018

出　　处：《中国电力》2022年第6期25-32,共8页Electric Power

基　　金：国家自然科学基金资助项目(一种基于锁相外差干涉技术的大行程纳米定位控制方法,51105348)。

摘　　要：电力用户的负荷分类为电力系统和电力部门的系统规划、负荷预测、分时电价等研究提供了基本的指导工作。利用基于变分模态分解(variational mode decomposition,VMD)和模糊C均值聚类算法(fuzzy C-means,FCM)实现电力负荷的分类研究,针对FCM中欧氏距离的特征权重唯一的问题,利用基于特征加权的模糊聚类方法,提出基于特征加权的VMD-FCM聚类算法。根据电网实测负荷数据,VMD算法可对数据的固有模态有效分解,结合FCM算法引入的权重系数,显著提高了算法收敛速度和聚类准确度。对聚类结果分析表明:所提VMD-FCM聚类方法能够有效区分不同负荷类型,具有实际应用价值,从而为电力系统的设计规划提供指导作用。The load classification of power users provides basic guidance for the research of power system planning,load forecasting,and time-of-use electricity price.In this paper,the variational modal decomposition(VMD)and fuzzy C-means clustering algorithm(FCM)are used for power load classification.Based on the unique feature weight of Euclidean distance in FCM,a feature weighting based VMD-FCM clustering algorithm is proposed using the feature weighting based fuzzy clustering method.According to the measured load data of the power grid,the VMD method can effectively decompose the inherent modality of the data,and the introduced FCM-based weight coefficient significantly improves the algorithm’s convergence speed and clustering accuracy.The clustering results show that the proposed VMD-FCM clustering method can effectively distinguish different load types and has practical application values,thereby providing guidance for the design and planning of the power system.

关 键 词：负荷分类 模糊聚类 变分模态分解 特征加权 负荷特性曲线 

分 类 号：TM714[电气工程—电力系统及自动化]