Detection of users-transformer relationship in the secondary power distribution system with smart meter data

Due to frequent changes in settings at the secondary power distribution system, the records of the relationship between users and transformers do not update simultaneously. Relying on manual detections not only takes too much time but also requires special equipment. The paper proposes a method to detect the relationship between users and the transformer based on the distribution network operational data collected from smart meter. The method uses Principal Component Analysis (PCA) and Independent Component Analysis (ICA) to extract features from voltage time series data. The data in the paper is collected from local electricity utilities and the case study shows that using the proposed method can successfully identify the relationship between users and transformers with the voltage and current low-frequency time series data.