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

被引:4
作者
Gao, Yongmin [1 ]
Kang, Bing [1 ]
Xiao, Hui [1 ]
Wang, Zongyao [1 ]
Ding, Guili [1 ]
Xu, Zhihao [1 ]
Liu, Chuan [1 ]
Wang, Daxing [1 ]
Li, Yutong [1 ]
机构
[1] Nanchang Inst Technol, Coll Elect Engn, Nanchang, Jiangxi, Peoples R China
关键词
distribution network; feeder-transformer relationship; topology identification; data-driven; machine-learning; TOPOLOGY IDENTIFICATION; CONNECTIVITY;
D O I
10.3389/fenrg.2023.1225407
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
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.
引用
收藏
页数:18
相关论文
共 38 条
[1]   Distribution Grid State Estimation from Compressed Measurements [J].
Alam, S. M. Shafiul ;
Natarajan, Balasubramaniam ;
Pahwa, Anil .
IEEE TRANSACTIONS ON SMART GRID, 2014, 5 (04) :1631-1642
[2]   Reliable Estimation for Health Index of Transformer Oil Based on Novel Combined Predictive Maintenance Techniques [J].
Badawi, Mohamed ;
Ibrahim, Shimaa A. ;
Mansour, Diaa-Eldin A. ;
El-Faraskoury, Adel A. ;
Ward, Sayed A. ;
Mahmoud, Karar ;
Lehtonen, Matti ;
Darwish, Mohamed M. F. .
IEEE ACCESS, 2022, 10 :25954-25972
[3]   Inverter Probing for Power Distribution Network Topology Processing [J].
Cavraro, Guido ;
Kekatos, Vassilis .
IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2019, 6 (03) :980-992
[4]   Voltage Analytics for Power Distribution Network Topology Verification [J].
Cavraro, Guido ;
Kekatos, Vassilis ;
Veeramachaneni, Sriharsha .
IEEE TRANSACTIONS ON SMART GRID, 2019, 10 (01) :1058-1067
[5]  
Darwish M., 2022, 2022 23 INT MIDDL E
[6]  
Darwish MMF, 2022, INT CONF CONDIT MON, P255, DOI 10.23919/CMD54214.2022.9991616
[7]   Topology Estimation Using Graphical Models in Multi-Phase Power Distribution Grids [J].
Deka, Deepjyoti ;
Chertkov, Michael ;
Backhaus, Scott .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2020, 35 (03) :1663-1673
[8]   Structure Learning in Power Distribution Networks [J].
Deka, Deepjyoti ;
Backhaus, Scott ;
Chertkov, Michael .
IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2018, 5 (03) :1061-1074
[9]  
Freitas V, 2015, 2015 IEEE EINDHOVEN POWERTECH
[10]  
[高泽璞 Gao Zepu], 2020, [电力系统保护与控制, Power System Protection and Control], V48, P34