Open AccessConsumer-Transformer Relationship Identification Based on Two-scale similarity and SC Algorithm
Author(s) -
Xuanping Lai,
Siyangjie Liu,
Min Cao,
Yongjie Nie,
Tengfei Zhao
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 - 10.1088/1742-6596/2005/1/012073
Subject(s) - cluster analysis , euclidean distance , similarity (geometry) , spectral clustering , algorithm , chaotic , transformer , voltage , computer science , scale (ratio) , matrix (chemical analysis) , identification (biology) , data mining , pattern recognition (psychology) , mathematics , artificial intelligence , engineering , geography , electrical engineering , materials science , cartography , composite material , image (mathematics) , botany , biology
In view of the chaotic relationship between user-transformer in the current low-voltage stations, manual identification consumes a long time period, low identification accuracy, and high input system costs. This paper proposes a method for identifying household change relations in low-voltage stations based on dual-scale similarity and spectral clustering algorithm. First, according to the different similarities of user voltage curves in different stations, consider Euclidean distance and cosine distance to establish a two-scale spectral clustering similarity matrix from the distance and shape of the voltage curve. Then based on the two-scale similarity matrix, perform spectral clustering on the voltage curves of the same station area to complete the clustering of users in the same station area. Examples show that the method proposed in the article has high recognition accuracy, low input cost, and has good application effects.