A model for identifying the feeder-transformer relationship in distribution grids using a data-driven machine-learning algorithm

Frontiers in Energy Research

Energy Research

Daxing Wang¹  Yongmin Gao¹  Hui Xiao¹  Guili Ding¹  Chuan Liu¹  Zongyao Wang¹  Yutong Li¹  Zhihao Xu¹  Bing Kang² 

[1] College of Electrical Engineering, Nanchang Institute of Technology, Nanchang, Jiangxi, China;null;

关键词: distribution network;    feeder-transformer relationship;    topology identification;    data-driven;    machine-learning;   

DOI  :  10.3389/fenrg.2023.1225407

 received in 2023-05-19, accepted in 2023-07-17,  发布年份 2023

来源: Frontiers

【 摘 要 】

With the increasing demand for reliable power supply and the widespread integration of distributed energy sources, the topology of distribution networks is subject to frequent changes. Consequently, the dynamic alterations in the connection relationships between distribution transformers and feeders occur frequently, and these changes are not accurately monitored by grid companies in real-time. In this paper, we present a data-driven machine learning approach for identifying the feeder-transformer relationship in distribution networks. Initially, we preprocess the collected three-phase voltage magnitude data of distribution transformers, addressing data quality and enhancing usability through three-phase voltage normalization. Subsequently, we derive the correlation coefficient calculations between distribution transformers, as well as between distribution transformers and feeders. To tackle the challenging task of determining the correlation coefficient threshold, we propose a multi-feature fusion approach. We extracted additional features from the feeders and combined them with the correlation coefficients to create a feature matrix. Machine learning algorithms were then applied to calculate the results. Through experimentation on a real distribution network in Jiangxi province, we demonstrated the effectiveness of the proposed method. When compared to other approaches, our method achieved outstanding results with an F1 score of 0.977, indicating high precision and recall. The precision value was 0.973 and the recall value was 0.981. Importantly, our method eliminates the need for additional measurement installations, as the required data can be obtained using existing collection devices. This significantly reduces the application cost associated with implementing our approach.

【 授权许可】

Unknown   
Copyright © 2023 Gao, Kang, Xiao, Wang, Ding, Xu, Liu, Wang and Li.