Power Load Classification Based on Feature Weighted Fuzzy Clustering

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. B...

Full description

Saved in:
Bibliographic Details
Main Authors: Zongbiao MA, Su'an XU, Shaobin ZHU, Jing WANG
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2022-06-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202006320
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1004-9649