Open AccessResearch on Classification of Daily Load Curve of Distribution Network Based on Improved SSA-FCM
Author(s) -
Hongyin Shi,
Cao Rong,
Wenbo Hao,
Mingyu Xu,
Heng Hu,
Peng Jiang,
Feng Zhou
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2121/1/012011
Subject(s) - cluster analysis , fuzzy logic , cluster (spacecraft) , mathematics , data mining , algorithm , computer science , mathematical optimization , pattern recognition (psychology) , artificial intelligence , programming language
In the analysis of three-phase unbalance in distribution network, the accuracy of daily load curve classification results determines the size of three-phase unbalance. Aiming at the shortcomings of Fuzzy C-Means (FCM), a fuzzy C-Means clustering algorithm (SSA-FCM) optimized based on Sparrow Search Algorithm (SSA) is proposed. The cluster validity evaluation index is introduced to get the optimal quantity of clusters, and the SSA is used to search for the initial cluster center, which solves the problem that the FCM algorithm relies on the initial value and is easy to converge to local optimal solution. The simulation results show that, compared with the FCM algorithm, the load curves classified into the same category by SSA-FCM are closer together.