Physics-Informed Graph Learning for Robust Fault Location in Distribution Systems

The rapid growth of distributed energy resources potentially increases power grid instability. One promising strategy is to employ data in power grids to efficiently respond to abnormal events (e.g., faults) by detection and location. Unfortunately, most existing works lack physical interpretation and are vulnerable to the practical challenges: sparse observation, insufficient labeled datasets, and stochastic environment. We propose a physics-informed graph learning framework of two stages to handle these challenges when locating faults. StageI focuses on informing a graph neural network (GNN) with the geometrical structure of power grids; stage-II employs the physical similarity of labeled and unlabeled data samples to improve the location accuracy. We provide a random walk-based underpinning of designing our GNNs to address the challenge of sparse observation and augment the correct prediction probability. We compare our approach with three baselines in the IEEE 123-node benchmark system, showing that the proposed method outperforms the others by significant margins, especially when label rates are low. Also, we validate the robustness of our algorithms to out-of-distribution-data (ODD) due to topology changes and load variations. Additionally, we adapt our graph learning framework to the IEEE 37-node test feeder and show high location performance with the proposed training strategy.

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  Ruslan Salakhutdinov,et al.  Revisiting Semi-Supervised Learning with Graph Embeddings , 2016, ICML.

[3]  Jun Hu,et al.  Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks , 2020, IEEE Journal on Selected Areas in Communications.

[4]  Ken-ichi Kawarabayashi,et al.  Representation Learning on Graphs with Jumping Knowledge Networks , 2018, ICML.

[5]  Shenxing Shi,et al.  Fault Location for Radial Distribution Network via Topology and Reclosure-Generating Traveling Waves , 2019, IEEE Transactions on Smart Grid.

[6]  A.G. Phadke,et al.  Synchronized phasor measurements in power systems , 1993, IEEE Computer Applications in Power.

[7]  Xiang Cheng,et al.  Data-Driven Fault Localization in Distribution Systems with Distributed Energy Resources , 2019, 2019 IEEE Sustainable Power and Energy Conference (iSPEC).

[8]  M. Majidi,et al.  A Novel Method for Single and Simultaneous Fault Location in Distribution Networks , 2015, IEEE Transactions on Power Systems.

[9]  Murti V. Salapaka,et al.  Graphical Models in Meshed Distribution Grids: Topology Estimation, Change Detection & Limitations , 2020, IEEE Transactions on Smart Grid.

[10]  W. H. Kersting,et al.  Radial distribution test feeders , 1991, 2001 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.01CH37194).

[11]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[12]  H.H. Zurn,et al.  Application of neural-network modules to electric power system fault section estimation , 2004, IEEE Transactions on Power Delivery.

[13]  Michael Chertkov,et al.  Real-Time Faulted Line Localization and PMU Placement in Power Systems Through Convolutional Neural Networks , 2018, IEEE Transactions on Power Systems.

[14]  D. Slepčev,et al.  Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates , 2020, ICML.

[15]  Roger C. Dugan,et al.  An open source platform for collaborating on smart grid research , 2011, 2011 IEEE Power and Energy Society General Meeting.

[16]  Wenting Li,et al.  Real-Time Event Identification Through Low-Dimensional Subspace Characterization of High-Dimensional Synchrophasor Data , 2018, IEEE Transactions on Power Systems.

[17]  Jure Leskovec,et al.  Representation Learning on Graphs: Methods and Applications , 2017, IEEE Data Eng. Bull..

[18]  Fault location in distribution system using convolutional neural network based on domain transformation , 2021, CSEE Journal of Power and Energy Systems.

[19]  Daniel Arnold,et al.  Linear Single- and Three-Phase Voltage Forecasting and Bayesian State Estimation With Limited Sensing , 2020, IEEE Transactions on Power Systems.

[20]  S. M. Brahma,et al.  Fault Location in Power Distribution System With Penetration of Distributed Generation , 2011, IEEE Transactions on Power Delivery.

[21]  Vigna K. Ramachandaramurthy,et al.  Fault-Location Scheme for Power Distribution System with Distributed Generation , 2015, IEEE Transactions on Power Delivery.

[22]  David E. Culler,et al.  Micro-synchrophasors for distribution systems , 2014, ISGT 2014.

[23]  Hamid Reza Shaker,et al.  A Novel Fault Location Methodology for Smart Distribution Networks , 2021, IEEE Transactions on Smart Grid.

[24]  Yixin Yu,et al.  A Comprehensive Resilience-Oriented FLISR Method for Distribution Systems , 2021, IEEE Transactions on Smart Grid.

[25]  Percy Liang,et al.  Understanding Black-box Predictions via Influence Functions , 2017, ICML.

[26]  Emmanuel J. Candès,et al.  Robust Subspace Clustering , 2013, ArXiv.

[27]  D. Novosel,et al.  IEEE PSRC Report on Performance of Relaying During Wide-Area Stressed Conditions , 2010, IEEE Transactions on Power Delivery.

[28]  Rabih A. Jabr,et al.  Fault Location in Distribution Networks Through Graph Marking , 2018, IEEE Transactions on Smart Grid.

[29]  Bo Wang,et al.  An Efficient PMU-Based Fault-Location Technique for Multiterminal Transmission Lines , 2014, IEEE Transactions on Power Delivery.

[30]  Mohsen Ghasemi,et al.  Fault location in power distribution network with presence of distributed generation resources using impedance based method and applying π line model , 2017, Energy.

[31]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[32]  M. Sami Fadali,et al.  A Sparse-Data-Driven Approach for Fault Location in Transmission Networks , 2017, IEEE Transactions on Smart Grid.

[33]  Jure Leskovec,et al.  Unifying Graph Convolutional Neural Networks and Label Propagation , 2020, ArXiv.

[34]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[35]  Gerard-Andre Capolino,et al.  Regression Models With Graph-Regularization Learning Algorithms for Accurate Fault Location in Smart Grids , 2021, IEEE Systems Journal.

[36]  Wenting Li,et al.  Identifying Overlapping Successive Events Using a Shallow Convolutional Neural Network , 2019, IEEE Transactions on Power Systems.

[37]  Tianshu Bi,et al.  Sparse Voltage Measurement-Based Fault Location Using Intelligent Electronic Devices , 2020, IEEE Transactions on Smart Grid.

[38]  A. Arabali,et al.  Fault Location in Distribution Networks by Compressive Sensing , 2015, IEEE Transactions on Power Delivery.

[39]  Fadi Thabtah,et al.  Data imbalance in classification: Experimental evaluation , 2020, Inf. Sci..

[40]  Rex E. Gantenbein,et al.  United States Department of Energy , 2004 .

[41]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..