Integrating autoencoders to improve fault classification with PV system insertion

The extensive integration of distributed generation (DG) units leads to significant changes in the operation of power distribution systems (PDS). Integrating DG units contributes to meeting the growing energy demand, diversifying the energy matrix, and reducing power grid losses. In contrast, they c...

Descripción completa

Detalles Bibliográficos
Autores: Silva Santos, Andréia [UNESP], da Silva, Reginaldo José [UNESP], Montenegro, Paula Andrea, Faria, Lucas Teles [UNESP], Lopes, Mara Lúcia Martins [UNESP], Minussi, Carlos Roberto [UNESP]
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:Brasil
Institución:Universidade Estadual Paulista (UNESP)
Repositorio:Repositório Institucional da UNESP
Idioma:inglés
OAI Identifier:oai:repositorio.unesp.br:11449/307384
Acceso en línea:http://dx.doi.org/10.1016/j.epsr.2025.111426
https://hdl.handle.net/11449/307384
Access Level:acceso abierto
Palabra clave:Artificial neural networks
Autoencoders
Fault classification
Photovoltaic systems
Power distribution systems
id BR_f0f25fc682e2aab360cef6ee58eec7df
oai_identifier_str oai:repositorio.unesp.br:11449/307384
network_acronym_str BR
network_name_str Brasil
repository_id_str
spelling Integrating autoencoders to improve fault classification with PV system insertionArtificial neural networksAutoencodersFault classificationPhotovoltaic systemsPower distribution systemsThe extensive integration of distributed generation (DG) units leads to significant changes in the operation of power distribution systems (PDS). Integrating DG units contributes to meeting the growing energy demand, diversifying the energy matrix, and reducing power grid losses. In contrast, they can affect conventional protection systems in power grids by altering current flow, which affects the characteristics, direction, and amplitude of short-circuit currents. Consequently, improper operation of protection equipment can cause false positives, negatively affecting the detection, classification, and reliability of the power grid. This study addresses fault classification in PDS, considering the extensive integration of DG units, specifically PV systems. PDS is evaluated at various levels of PV insertion using different fault scenarios modeled in the IEEE 34-bus test system. This includes five scenarios with variations in the PV system insertion. Autoencoders are applied during the pre-processing phase, while eleven different algorithms are used in the classification stage to identify fault types. They can improve the performance of the classification system by reducing the size of input signals and extracting the most relevant features. The results reveal that the K-nearest neighbor (KNN) and random forest (RF) algorithms demonstrate the best performance, maintaining a minimum accuracy of 95.42% in all scenarios.Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Laboratory of Intelligent Systems Department of Electrical Engineering School of Engineering São Paulo State University (UNESP), São PauloEnvironmental Engineering Program Universidad Mariana, NariñoDepartment of Engineering School of Engineering and Sciences São Paulo State University (UNESP), São PauloLaboratory of Intelligent Systems Department of Electrical Engineering School of Engineering São Paulo State University (UNESP), São PauloDepartment of Engineering School of Engineering and Sciences São Paulo State University (UNESP), São PauloCNPq: 302896/2022-8CAPES: UNESP/PROPG 37/2023Universidade Estadual Paulista (UNESP)Universidad Mariana2025-04-29T20:09:08Z2025-05-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1016/j.epsr.2025.111426Electric Power Systems Research, v. 242.0378-7796https://hdl.handle.net/11449/30738410.1016/j.epsr.2025.1114262-s2.0-85216846907Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengElectric Power Systems Researchinfo:eu-repo/semantics/openAccessSilva Santos, Andréia [UNESP]da Silva, Reginaldo José [UNESP]Montenegro, Paula AndreaFaria, Lucas Teles [UNESP]Lopes, Mara Lúcia Martins [UNESP]Minussi, Carlos Roberto [UNESP]2025-04-30T13:57:19Zoai:repositorio.unesp.br:11449/307384Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestrepositoriounesp@unesp.bropendoar:29462025-04-30T13:57:19Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Integrating autoencoders to improve fault classification with PV system insertion
title Integrating autoencoders to improve fault classification with PV system insertion
spellingShingle Integrating autoencoders to improve fault classification with PV system insertion
Silva Santos, Andréia [UNESP]
Artificial neural networks
Autoencoders
Fault classification
Photovoltaic systems
Power distribution systems
title_short Integrating autoencoders to improve fault classification with PV system insertion
title_full Integrating autoencoders to improve fault classification with PV system insertion
title_fullStr Integrating autoencoders to improve fault classification with PV system insertion
title_full_unstemmed Integrating autoencoders to improve fault classification with PV system insertion
title_sort Integrating autoencoders to improve fault classification with PV system insertion
dc.creator.none.fl_str_mv Silva Santos, Andréia [UNESP]
da Silva, Reginaldo José [UNESP]
Montenegro, Paula Andrea
Faria, Lucas Teles [UNESP]
Lopes, Mara Lúcia Martins [UNESP]
Minussi, Carlos Roberto [UNESP]
author Silva Santos, Andréia [UNESP]
author_facet Silva Santos, Andréia [UNESP]
da Silva, Reginaldo José [UNESP]
Montenegro, Paula Andrea
Faria, Lucas Teles [UNESP]
Lopes, Mara Lúcia Martins [UNESP]
Minussi, Carlos Roberto [UNESP]
author_role author
author2 da Silva, Reginaldo José [UNESP]
Montenegro, Paula Andrea
Faria, Lucas Teles [UNESP]
Lopes, Mara Lúcia Martins [UNESP]
Minussi, Carlos Roberto [UNESP]
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (UNESP)
Universidad Mariana
dc.subject.por.fl_str_mv Artificial neural networks
Autoencoders
Fault classification
Photovoltaic systems
Power distribution systems
topic Artificial neural networks
Autoencoders
Fault classification
Photovoltaic systems
Power distribution systems
description The extensive integration of distributed generation (DG) units leads to significant changes in the operation of power distribution systems (PDS). Integrating DG units contributes to meeting the growing energy demand, diversifying the energy matrix, and reducing power grid losses. In contrast, they can affect conventional protection systems in power grids by altering current flow, which affects the characteristics, direction, and amplitude of short-circuit currents. Consequently, improper operation of protection equipment can cause false positives, negatively affecting the detection, classification, and reliability of the power grid. This study addresses fault classification in PDS, considering the extensive integration of DG units, specifically PV systems. PDS is evaluated at various levels of PV insertion using different fault scenarios modeled in the IEEE 34-bus test system. This includes five scenarios with variations in the PV system insertion. Autoencoders are applied during the pre-processing phase, while eleven different algorithms are used in the classification stage to identify fault types. They can improve the performance of the classification system by reducing the size of input signals and extracting the most relevant features. The results reveal that the K-nearest neighbor (KNN) and random forest (RF) algorithms demonstrate the best performance, maintaining a minimum accuracy of 95.42% in all scenarios.
publishDate 2025
dc.date.none.fl_str_mv 2025-04-29T20:09:08Z
2025-05-01
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1016/j.epsr.2025.111426
Electric Power Systems Research, v. 242.
0378-7796
https://hdl.handle.net/11449/307384
10.1016/j.epsr.2025.111426
2-s2.0-85216846907
url http://dx.doi.org/10.1016/j.epsr.2025.111426
https://hdl.handle.net/11449/307384
identifier_str_mv Electric Power Systems Research, v. 242.
0378-7796
10.1016/j.epsr.2025.111426
2-s2.0-85216846907
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Electric Power Systems Research
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv repositoriounesp@unesp.br
_version_ 1853672144739762176
score 15,301629

Similares en LA Referencia