Data-driven identification of household-transformer relationships in power distribution networks using Hausdorff similarity assessment

Precisely identifying the household-transformer relationship is of significant importance for both stability power system and quality customer electricity consumption. However, complex network structures frequent reconfigurations may lead to inaccurate records relationships. In this paper, a novel data-driven similarity assessment solution proposed enhance accuracy scalability Initially, data processing method based on dynamic temporal regularization with sliding windows employed optimize dataset as well efficiency processing. Then, two-stage relationship. The first stage involves initial normalized clustering basic information distribution substations, while second assesses between households transformer operational states Hausdorff distance. superior performance extensively assessed through real historical datasets, compared benchmarks.