Which Neural Network to Choose for Post-Fault Localization, Dynamic State Estimation and Optimal Measurement Placement in Power Systems?

TL;DR

This paper compares various neural network architectures for fault localization, state estimation, and optimal sensor placement in power systems, leveraging physics-informed models and neural ODEs for improved accuracy and efficiency.

Contribution

It introduces a comprehensive comparison of neural network types for fault detection and state estimation, and proposes a neural network-based algorithm for optimal PMU placement in power systems.

Findings

Graphical Convolutional NN outperforms linear models in fault localization.

Neural-ODE models accurately predict post-fault states and system parameters.

The proposed methods improve observability and fault detection in power systems.

Abstract

We consider a power transmission system monitored with Phasor Measurement Units (PMUs) placed at significant, but not all, nodes of the system. Assuming that a sufficient number of distinct single-line faults, specifically pre-fault state and (not cleared) post-fault state, are recorded by the PMUs and are available for training, we, first, design a comprehensive sequence of Neural Networks (NNs) locating the faulty line. Performance of different NNs in the sequence, including Linear Regression, Feed-Forward NN, AlexNet, Graphical Convolutional NN, Neural Linear ODE and Neural Graph-based ODE, ordered according to the type and amount of the power flow physics involved, are compared for different levels of observability. Second, we build a sequence of advanced Power-System-Dynamics-Informed and Neural-ODE based Machine Learning schemes trained, given pre-fault state, to predict the post-fault state and also, in parallel, to estimate system parameters. Finally, third, and continuing to work with the first (fault localization) setting we design a (NN-based) algorithm which discovers optimal PMU placement.