Convolutional Neural Network for the Classification of the Control Mode of Grid-Connected Power Converters

With the integration of power converters into the power grid, it becomes crucial for the Transmission System Operator (TSO) to ascertain whether they are operating in Grid Forming or Grid Following modes. Due to intellectual properties, classification can only be performed based on non-intrusive mea...

Full description

Saved in:
Bibliographic Details
Main Authors: Rabah Ouali, Martin Legry, Jean-Yves Dieulot, Pascal Yim, Xavier Guillaud, Frédéric Colas
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/17/24/6458
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850049523762593792
author Rabah Ouali
Martin Legry
Jean-Yves Dieulot
Pascal Yim
Xavier Guillaud
Frédéric Colas
author_facet Rabah Ouali
Martin Legry
Jean-Yves Dieulot
Pascal Yim
Xavier Guillaud
Frédéric Colas
author_sort Rabah Ouali
collection DOAJ
description With the integration of power converters into the power grid, it becomes crucial for the Transmission System Operator (TSO) to ascertain whether they are operating in Grid Forming or Grid Following modes. Due to intellectual properties, classification can only be performed based on non-intrusive measurements and models, such as admittance at the PCC. This classification poses a challenge as the TSO lacks precise knowledge of the actual control structures and algorithms. This paper introduces a novel classification algorithm based on Convolutional Neural Networks (CNN), capable of detecting patterns in sequential data. The proposed CNN utilizes a new architecture to separate admittances along the d and q axes, and a decision layer allows to determine the correct converter mode. The performance of the proposed CNN model was assessed through two tests and compared to the traditional feedforward model. The proposed CNN architecture demonstrates significant classification capabilities, as it is able to identify the control mode of the converter even when its control structure is not part of the training dataset.
format Article
id doaj-art-9f9fbef92c4749e6a41106c97ad8d295
institution DOAJ
issn 1996-1073
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-9f9fbef92c4749e6a41106c97ad8d2952025-08-20T02:53:41ZengMDPI AGEnergies1996-10732024-12-011724645810.3390/en17246458Convolutional Neural Network for the Classification of the Control Mode of Grid-Connected Power ConvertersRabah Ouali0Martin Legry1Jean-Yves Dieulot2Pascal Yim3Xavier Guillaud4Frédéric Colas5Centre de Recherche en Informatique Signal et Automatique de Lille, University Lille, CNRS, Centrale Lille, UMR 9189, 59655 Lille, FranceL2EP—Laboratoire d’Electrotechnique et d’Electronique de Puissance, University Lille, Centrale Lille, Arts et Métiers Paris Tech, HEI, EA 2697, 59655 Lille, FranceCentre de Recherche en Informatique Signal et Automatique de Lille, University Lille, CNRS, Centrale Lille, UMR 9189, 59655 Lille, FranceCentre de Recherche en Informatique Signal et Automatique de Lille, University Lille, CNRS, Centrale Lille, UMR 9189, 59655 Lille, FranceL2EP—Laboratoire d’Electrotechnique et d’Electronique de Puissance, University Lille, Centrale Lille, Arts et Métiers Paris Tech, HEI, EA 2697, 59655 Lille, FranceL2EP—Laboratoire d’Electrotechnique et d’Electronique de Puissance, University Lille, Centrale Lille, Arts et Métiers Paris Tech, HEI, EA 2697, 59655 Lille, FranceWith the integration of power converters into the power grid, it becomes crucial for the Transmission System Operator (TSO) to ascertain whether they are operating in Grid Forming or Grid Following modes. Due to intellectual properties, classification can only be performed based on non-intrusive measurements and models, such as admittance at the PCC. This classification poses a challenge as the TSO lacks precise knowledge of the actual control structures and algorithms. This paper introduces a novel classification algorithm based on Convolutional Neural Networks (CNN), capable of detecting patterns in sequential data. The proposed CNN utilizes a new architecture to separate admittances along the d and q axes, and a decision layer allows to determine the correct converter mode. The performance of the proposed CNN model was assessed through two tests and compared to the traditional feedforward model. The proposed CNN architecture demonstrates significant classification capabilities, as it is able to identify the control mode of the converter even when its control structure is not part of the training dataset.https://www.mdpi.com/1996-1073/17/24/6458grid forminggrid followingdeep learningconvolutional neural networkfrequency admittance
spellingShingle Rabah Ouali
Martin Legry
Jean-Yves Dieulot
Pascal Yim
Xavier Guillaud
Frédéric Colas
Convolutional Neural Network for the Classification of the Control Mode of Grid-Connected Power Converters
Energies
grid forming
grid following
deep learning
convolutional neural network
frequency admittance
title Convolutional Neural Network for the Classification of the Control Mode of Grid-Connected Power Converters
title_full Convolutional Neural Network for the Classification of the Control Mode of Grid-Connected Power Converters
title_fullStr Convolutional Neural Network for the Classification of the Control Mode of Grid-Connected Power Converters
title_full_unstemmed Convolutional Neural Network for the Classification of the Control Mode of Grid-Connected Power Converters
title_short Convolutional Neural Network for the Classification of the Control Mode of Grid-Connected Power Converters
title_sort convolutional neural network for the classification of the control mode of grid connected power converters
topic grid forming
grid following
deep learning
convolutional neural network
frequency admittance
url https://www.mdpi.com/1996-1073/17/24/6458
work_keys_str_mv AT rabahouali convolutionalneuralnetworkfortheclassificationofthecontrolmodeofgridconnectedpowerconverters
AT martinlegry convolutionalneuralnetworkfortheclassificationofthecontrolmodeofgridconnectedpowerconverters
AT jeanyvesdieulot convolutionalneuralnetworkfortheclassificationofthecontrolmodeofgridconnectedpowerconverters
AT pascalyim convolutionalneuralnetworkfortheclassificationofthecontrolmodeofgridconnectedpowerconverters
AT xavierguillaud convolutionalneuralnetworkfortheclassificationofthecontrolmodeofgridconnectedpowerconverters
AT fredericcolas convolutionalneuralnetworkfortheclassificationofthecontrolmodeofgridconnectedpowerconverters