Identification Method for Household-Transformer Relationship Based on UMAP and BIRCH Clustering

The relationship between households and transformers in the low-voltage station areas is frequently changed due to the routine maintenance, renovation and upgrading of distribution network. Since it is difficult to maintain the household-transformer relationship in low-voltage station areas manually, an identification method based on voltage measurement data of smart meters is proposed. Firstly, the spatial distribution features of the original voltage data are extracted by the uniform manifold approximation and projection (UMAP) technology while dimensionality reduction is performed. Then, the balanced iterative reducing and clustering using hierarchies (BIRCH) algorithm is used to cluster the feature data, chieving recognition between nodes and their respective station areas. Finally, the results of an example are analyzed to prove the feasibility of the algorithm.