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

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.

[1]  A. Yadav,et al.  Long term estimation of global horizontal irradiance using machine learning algorithms , 2023, Optik.

[2]  D. Mansour,et al.  A New Method for Estimating Transformer Health Index Based on Ultraviolet-Visible Spectroscopy , 2022, 2022 23rd International Middle East Power Systems Conference (MEPCON).

[3]  D. Mansour,et al.  Application of Infrared Spectroscopy for Discrimination Between Electrical and Thermal Faults in Transformer Oil , 2022, 2022 9th International Conference on Condition Monitoring and Diagnosis (CMD).

[4]  Guangye Li,et al.  Low-voltage distribution network topology identification based on constrained least square and graph theory , 2022, Soft Computing - A Fusion of Foundations, Methodologies and Applications.

[5]  A. Yadav,et al.  Time Series Forecasting of Solar Power Generation Using Facebook Prophet and XG Boost , 2022, 2022 IEEE Delhi Section Conference (DELCON).

[6]  Gadelha T. Filho Vinicius,et al.  Rural electrification planning based on graph theory and geospatial data: A realistic topology oriented approach , 2021 .

[7]  Yingqi Yi,et al.  Consumer phase identification under incomplete data condition with dimensional calibration , 2021, International Journal of Electrical Power & Energy Systems.

[8]  M. Lehtonen,et al.  Accurate Insulating Oil Breakdown Voltage Model Associated with Different Barrier Effects , 2021, Processes.

[9]  Liang Zhao,et al.  Robust PCA-deep belief network surrogate model for distribution system topology identification with DERs , 2021 .

[10]  Canbing Li,et al.  Consumer phase identification in low-voltage distribution network considering vacant users , 2020 .

[11]  Yun Tang,et al.  The role of nitric oxide (NO) levels in patients with obstructive sleep apnea-hypopnea syndrome: a meta-analysis , 2020, Sleep and Breathing.

[12]  Nan Zhou,et al.  Power Distribution Network Dynamic Topology Awareness and Localization Based on Subspace Perturbation Model , 2020, IEEE Transactions on Power Systems.

[13]  Erik Poll,et al.  Smart metering in the Netherlands: What, how, and why , 2019, International Journal of Electrical Power & Energy Systems.

[14]  Di Wu,et al.  A Graph-theoretic Method for Identification of Electric Power Distribution System Topology , 2019, 2019 1st Global Power, Energy and Communication Conference (GPECOM).

[15]  S. Naik,et al.  Programmable protective device for LV distribution system protection , 2018, Protection and Control of Modern Power Systems.

[16]  Ramkrishna Pasumarthy,et al.  Identifying Topology of Low Voltage Distribution Networks Based on Smart Meter Data , 2018, IEEE Transactions on Smart Grid.

[17]  Michael Chertkov,et al.  Topology Estimation Using Graphical Models in Multi-Phase Power Distribution Grids , 2018, IEEE Transactions on Power Systems.

[18]  Alessandro Luiz Batschauer,et al.  A Voltage Regulator for Power Quality Improvement in Low-Voltage Distribution Grids , 2018, IEEE Transactions on Power Electronics.

[19]  Vassilis Kekatos,et al.  Inverter Probing for Power Distribution Network Topology Processing , 2018, IEEE Transactions on Control of Network Systems.

[20]  Su Goog Shon,et al.  New Identification Method for Power Transformer and Phase in Distribution Systems , 2018 .

[21]  Vassilis Kekatos,et al.  Voltage Analytics for Power Distribution Network Topology Verification , 2017, IEEE Transactions on Smart Grid.

[22]  Yang Weng,et al.  Distributed Energy Resources Topology Identification via Graphical Modeling , 2017, IEEE Transactions on Power Systems.

[23]  Andrija T. Sarić,et al.  Verification and estimation of phase connectivity and power injections in distribution network , 2017 .

[24]  Yang Weng,et al.  Urban MV and LV Distribution Grid Topology Estimation via Group Lasso , 2016, IEEE Transactions on Power Systems.

[25]  Antonio Simoes Costa,et al.  Integrated State & topology estimation based on a priori topology information , 2015, 2015 IEEE Eindhoven PowerTech.

[26]  Wenpeng Luan,et al.  Smart Meter Data Analytics for Distribution Network Connectivity Verification , 2015, IEEE Transactions on Smart Grid.

[27]  Michael Chertkov,et al.  Structure Learning in Power Distribution Networks , 2015, IEEE Transactions on Control of Network Systems.

[28]  Georgios B. Giannakis,et al.  Online Energy Price Matrix Factorization for Power Grid Topology Tracking , 2014, IEEE Transactions on Smart Grid.

[29]  Balasubramaniam Natarajan,et al.  Distribution Grid State Estimation from Compressed Measurements , 2014, IEEE Transactions on Smart Grid.

[30]  Wenpeng Luan,et al.  Distribution network topology error correction using smart meter data analytics , 2013, 2013 IEEE Power & Energy Society General Meeting.

[31]  Jia Liu,et al.  A topology identification method based on one-dimensional convolutional neural network for distribution network , 2023, Energy Reports.

[32]  Jianzhong Wu,et al.  Topology and Parameter Identification of Distribution Network Using Smart Meter and µPMU Measurements , 2022, IEEE Transactions on Instrumentation and Measurement.

[33]  M. Lehtonen,et al.  Reliable Estimation for Health Index of Transformer Oil Based on Novel Combined Predictive Maintenance Techniques , 2022, IEEE Access.

[34]  Hsiao-Dong Chiang,et al.  Power flow matching-based topology identification of medium-voltage distribution networks via AMI measurements , 2021 .

[35]  Boming Zhang,et al.  A Mixed Integer Quadratic Programming Model for Topology Identification in Distribution Network , 2016, IEEE Transactions on Power Systems.

[36]  J. M. Mora-Merchan,et al.  Phase topology identification in low-voltage distribution networks: A Bayesian approach , 2022, International Journal of Electrical Power & Energy Systems.