• Corpus ID: 253511200

PPGN: Physics-Preserved Graph Networks for Real-Time Fault Location in Distribution Systems with Limited Observation and Labels

  title={PPGN: Physics-Preserved Graph Networks for Real-Time Fault Location in Distribution Systems with Limited Observation and Labels},
  author={Wenting Li and Deepjyoti Deka},
Electric faults may trigger blackouts or wildfires without timely monitoring and control strategy. Traditional solutions for locating faults in distribution systems are not real-time when network observability is low, while novel black-box machine learning methods are vulnerable to stochastic environments. We propose a novel Physics-Preserved Graph Network (PPGN) architecture to accurately locate faults at the node level with limited observability and labeled training data. PPGN has a unique two… 

Figures and Tables from this paper



Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks

Simulation results show that the GCN model significantly outperforms other widely-used machine learning schemes with very high fault location accuracy and is robust to measurement noise and data loss errors.

Real-Time Faulted Line Localization and PMU Placement in Power Systems Through Convolutional Neural Networks

This paper proposes a faulted line localization method based on a convolutional neural network (CNN) classifier using bus voltages, based on features with physical interpretations that improve the robustness of the location performance.

Physical Equation Discovery Using Physics-Consistent Neural Network (PCNN) Under Incomplete Observability

A Physics-Consistent Neural Network (PCNN) is proposed for physical systems with the following properties, and it is theoretically proved that the shallow NN in the PCNN is convex with respect to physical variables, leading to a set of convex optimizations to seek for the physics-consistent initial guess for thePCNN.

Physics-Informed Learning for High Impedance Faults Detection

High impedance faults (HIFs) in distribution grids may cause wildfires and threaten human lives. Conventional protection relays at substations fail to detect more than 10% HIFs since over-currents

Fault Location in Distribution Networks by Compressive Sensing

This paper proposes a novel method for fault location in distribution networks using compressive sensing. During fault and prefault voltages are measured by smart meters along the feeders. The

Model-Free Renewable Scenario Generation Using Generative Adversarial Networks

This work proposed a data-driven approach for scenario generation using generative adversarial networks, which is based on two interconnected deep neural networks that captures renewable energy production patterns in both temporal and spatial dimensions for a large number of correlated resources.

Identifying Overlapping Successive Events Using a Shallow Convolutional Neural Network

A data-driven event identification method that can accurately identify the types of overlapping events and is demonstrated to be more accurate and stable than a direct application of CNN on time series.

A New Fault Location Technique in Smart Distribution Networks Using Synchronized/Nonsynchronized Measurements

This paper proposes a new impedance-based technique to locate all fault types in distribution networks with/without distributed generators. A new procedure to form an impedance matrix using only

The Graph Neural Network Model

A new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains, and implements a function tau(G,n) isin IRm that maps a graph G and one of its nodes n into an m-dimensional Euclidean space.

Unifying Graph Convolutional Neural Networks and Label Propagation

This work proposes an end-to-end model that unifies GCN and LPA for node classification, and shows superiority over state-of-the-art GCN-based methods in terms of node classification accuracy.