Cargando…

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

We consider a power transmission system monitored using 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 the pre-fault state and the (not cleared) post-fault state, are recorded by...

Descripción completa

Detalles Bibliográficos
Autores principales: Afonin, Andrei, Chertkov, Michael
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8438307/
https://www.ncbi.nlm.nih.gov/pubmed/34532706
http://dx.doi.org/10.3389/fdata.2021.692493
_version_ 1783752343321313280
author Afonin, Andrei
Chertkov, Michael
author_facet Afonin, Andrei
Chertkov, Michael
author_sort Afonin, Andrei
collection PubMed
description We consider a power transmission system monitored using 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 the pre-fault state and the (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 NNs, AlexNet, graph convolutional NNs, neural linear ordinary differential equations (ODEs) and neural graph-based ODEs, 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 that are trained, given the 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 an (NN-based) algorithm which discovers optimal PMU placement.
format Online
Article
Text
id pubmed-8438307
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-84383072021-09-15 Which Neural Network to Choose for Post-Fault Localization, Dynamic State Estimation, and Optimal Measurement Placement in Power Systems? Afonin, Andrei Chertkov, Michael Front Big Data Big Data We consider a power transmission system monitored using 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 the pre-fault state and the (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 NNs, AlexNet, graph convolutional NNs, neural linear ordinary differential equations (ODEs) and neural graph-based ODEs, 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 that are trained, given the 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 an (NN-based) algorithm which discovers optimal PMU placement. Frontiers Media S.A. 2021-08-31 /pmc/articles/PMC8438307/ /pubmed/34532706 http://dx.doi.org/10.3389/fdata.2021.692493 Text en Copyright © 2021 Afonin and Chertkov. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Big Data
Afonin, Andrei
Chertkov, Michael
Which Neural Network to Choose for Post-Fault Localization, Dynamic State Estimation, and Optimal Measurement Placement in Power Systems?
title Which Neural Network to Choose for Post-Fault Localization, Dynamic State Estimation, and Optimal Measurement Placement in Power Systems?
title_full Which Neural Network to Choose for Post-Fault Localization, Dynamic State Estimation, and Optimal Measurement Placement in Power Systems?
title_fullStr Which Neural Network to Choose for Post-Fault Localization, Dynamic State Estimation, and Optimal Measurement Placement in Power Systems?
title_full_unstemmed Which Neural Network to Choose for Post-Fault Localization, Dynamic State Estimation, and Optimal Measurement Placement in Power Systems?
title_short Which Neural Network to Choose for Post-Fault Localization, Dynamic State Estimation, and Optimal Measurement Placement in Power Systems?
title_sort which neural network to choose for post-fault localization, dynamic state estimation, and optimal measurement placement in power systems?
topic Big Data
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8438307/
https://www.ncbi.nlm.nih.gov/pubmed/34532706
http://dx.doi.org/10.3389/fdata.2021.692493
work_keys_str_mv AT afoninandrei whichneuralnetworktochooseforpostfaultlocalizationdynamicstateestimationandoptimalmeasurementplacementinpowersystems
AT chertkovmichael whichneuralnetworktochooseforpostfaultlocalizationdynamicstateestimationandoptimalmeasurementplacementinpowersystems