Publicação

Wavelet LSTM for Fault Forecasting in Electrical Power Grids

Ver documento

Detalhes bibliográficos
Resumo:An electric power distribution utility is responsible for providing energy to consumers in a continuous and stable way. Failures in the electrical power system reduce the reliability indexes of the grid, directly harming its performance. For this reason, there is a need for failure prediction to reestablish power in the shortest possible time. Considering an evaluation of the number of failures over time, this paper proposes performing failure prediction during the first year of the pandemic in Brazil (2020) to verify the feasibility of using time series forecasting models for fault prediction. The long short-term memory (LSTM) model will be evaluated to obtain a forecast result that an electric power utility can use to organize maintenance teams. The wavelet transform has shown itself to be promising in improving the predictive ability of LSTM, making the wavelet LSTM model suitable for the study at hand. The assessments show that the proposed approach has better results regarding the error in prediction and has robustness when statistical analysis is performed.
Autores principais:Branco, Nathielle
Outros Autores:Santos Matos Cavalca, Mariana; Stefenon, Stéfano Frizzo; LEITHARDT, VALDERI
Assunto:electrical power grids; fault forecasting; long short-term memory; time series forecasting; wavelet transform
Ano:2022
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso aberto
Instituição associada:Instituto Politécnico de Portalegre
Idioma:inglês
Origem:Instituto Politécnico de Portalegre
_version_ 1865248821656682496
author Branco, Nathielle
author2 Santos Matos Cavalca, Mariana
Stefenon, Stéfano Frizzo
LEITHARDT, VALDERI
author2_role author
author
author
author_facet Branco, Nathielle
Santos Matos Cavalca, Mariana
Stefenon, Stéfano Frizzo
LEITHARDT, VALDERI
author_role author
contributor_name_str_mv Repositório Comum
country_str PT
creators_json_str [{\"Person.name\":\"Branco, Nathielle\",\"Person.identifier.orcid\":\"0000-0001-7565-3274\"},{\"Person.name\":\"Santos Matos Cavalca, Mariana\",\"Person.identifier.orcid\":\"0000-0001-5728-2158\"},{\"Person.name\":\"Stefenon, Stéfano Frizzo\",\"Person.identifier.orcid\":\"0000-0002-3723-616X\"},{\"Person.name\":\"LEITHARDT, VALDERI\",\"Person.identifier.orcid\":\"0000-0003-0446-9271\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Repositório Comum
datacite.creators.creator.creatorName.fl_str_mv Branco, Nathielle
Santos Matos Cavalca, Mariana
Stefenon, Stéfano Frizzo
LEITHARDT, VALDERI
datacite.date.Accepted.fl_str_mv 2022-10-30T00:00:00Z
datacite.date.available.fl_str_mv 2023-02-01T18:09:26Z
datacite.date.embargoed.fl_str_mv 2023-02-01T18:09:26Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv electrical power grids;
fault forecasting;
long short-term memory;
time series forecasting;
wavelet transform
datacite.titles.title.fl_str_mv Wavelet LSTM for Fault Forecasting in Electrical Power Grids
dc.contributor.none.fl_str_mv Repositório Comum
dc.creator.none.fl_str_mv Branco, Nathielle
Santos Matos Cavalca, Mariana
Stefenon, Stéfano Frizzo
LEITHARDT, VALDERI
dc.date.Accepted.fl_str_mv 2022-10-30T00:00:00Z
dc.date.available.fl_str_mv 2023-02-01T18:09:26Z
dc.date.embargoed.fl_str_mv 2023-02-01T18:09:26Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10400.26/43551
dc.language.none.fl_str_mv eng
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv electrical power grids;
fault forecasting;
long short-term memory;
time series forecasting;
wavelet transform
dc.title.fl_str_mv Wavelet LSTM for Fault Forecasting in Electrical Power Grids
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description An electric power distribution utility is responsible for providing energy to consumers in a continuous and stable way. Failures in the electrical power system reduce the reliability indexes of the grid, directly harming its performance. For this reason, there is a need for failure prediction to reestablish power in the shortest possible time. Considering an evaluation of the number of failures over time, this paper proposes performing failure prediction during the first year of the pandemic in Brazil (2020) to verify the feasibility of using time series forecasting models for fault prediction. The long short-term memory (LSTM) model will be evaluated to obtain a forecast result that an electric power utility can use to organize maintenance teams. The wavelet transform has shown itself to be promising in improving the predictive ability of LSTM, making the wavelet LSTM model suitable for the study at hand. The assessments show that the proposed approach has better results regarding the error in prediction and has robustness when statistical analysis is performed.
dirty 0
eu_rights_str_mv openAccess
format article
fulltext.url.fl_str_mv https://comum.rcaap.pt/bitstreams/88ccd7f7-50a2-421b-abc7-442fa6ab89d5/download
id ipp_ddca4e30e1eec1cff41b21685e82aec4
identifier.url.fl_str_mv http://hdl.handle.net/10400.26/43551
instacron_str ipp
institution Instituto Politécnico de Portalegre
instname_str Instituto Politécnico de Portalegre
language eng
network_acronym_str ipp
network_name_str Instituto Politécnico de Portalegre
oai_identifier_str oai:comum.rcaap.pt:10400.26/43551
organization_str_mv urn:organizationAcronym:ipp
person_str_mv Branco, Nathielle
Branco, Nathielle
http://orcid.org/0000-0001-7565-3274
0000-0001-7565-3274
Santos Matos Cavalca, Mariana
Santos Matos Cavalca, Mariana
http://orcid.org/0000-0001-5728-2158
0000-0001-5728-2158
Stefenon, Stéfano Frizzo
Stefenon, Stéfano Frizzo
https://www.ciencia-id.pt/4019-BB36-7F74
4019-BB36-7F74
http://orcid.org/0000-0002-3723-616X
0000-0002-3723-616X
LEITHARDT, VALDERI
LEITHARDT, VALDERI
https://www.ciencia-id.pt/0614-5834-E7F3
0614-5834-E7F3
http://orcid.org/0000-0003-0446-9271
0000-0003-0446-9271
publishDate 2022
reponame_str Instituto Politécnico de Portalegre
repository_id_str urn:repositoryAcronym:ipp
service_str_mv urn:repositoryAcronym:ipp
spelling engpt_PTAn electric power distribution utility is responsible for providing energy to consumers in a continuous and stable way. Failures in the electrical power system reduce the reliability indexes of the grid, directly harming its performance. For this reason, there is a need for failure prediction to reestablish power in the shortest possible time. Considering an evaluation of the number of failures over time, this paper proposes performing failure prediction during the first year of the pandemic in Brazil (2020) to verify the feasibility of using time series forecasting models for fault prediction. The long short-term memory (LSTM) model will be evaluated to obtain a forecast result that an electric power utility can use to organize maintenance teams. The wavelet transform has shown itself to be promising in improving the predictive ability of LSTM, making the wavelet LSTM model suitable for the study at hand. The assessments show that the proposed approach has better results regarding the error in prediction and has robustness when statistical analysis is performed.application/pdfpt_PTWavelet LSTM for Fault Forecasting in Electrical Power GridsPersonalBranco, NathielleDSpacehttp://dspace.org/items/4d5ebdfb-3a32-4508-8692-156f7fa846aaDSpacehttp://dspace.org/items/4d5ebdfb-3a32-4508-8692-156f7fa846aaBrancoNathielleORCIDhttp://orcid.org0000-0001-7565-3274PersonalSantos Matos Cavalca, MarianaDSpacehttp://dspace.org/items/e88ef994-d875-4f7d-8f5d-bfcd4fab6bb1DSpacehttp://dspace.org/items/e88ef994-d875-4f7d-8f5d-bfcd4fab6bb1Santos Matos CavalcaMarianaORCIDhttp://orcid.org0000-0001-5728-2158Scopus Author IDhttps://www.scopus.com36545649600Scopus Author IDhttps://www.scopus.com57188836598PersonalStefenon, Stéfano FrizzoDSpacehttp://dspace.org/items/ae8b0861-1e25-47fb-bcdb-a44c98768634DSpacehttp://dspace.org/items/ae8b0861-1e25-47fb-bcdb-a44c98768634StefenonStefano FrizzoCiência IDhttps://www.ciencia-id.pt4019-BB36-7F74ORCIDhttp://orcid.org0000-0002-3723-616XResearcher IDhttps://www.researcherid.comAAD-7639-2019Scopus Author IDhttps://www.scopus.com57194147390PersonalLEITHARDT, VALDERIDSpacehttp://dspace.org/items/ab15f7c6-e882-406e-813d-2629e9cec5c8DSpacehttp://dspace.org/items/ab15f7c6-e882-406e-813d-2629e9cec5c8REIS QUIETINHO LEITHARDTVALDERICiência IDhttps://www.ciencia-id.pt0614-5834-E7F3ORCIDhttp://orcid.org0000-0003-0446-9271Scopus Author IDhttps://www.scopus.com35303109600HostingInstitutionOrganizationalRepositório Comume-mailmailto:comum@rcaap.ptcomum@rcaap.ptDOIIsPartOf10.3390/s222183232023-02-01T18:09:26Z2022-10-302022-11-03T15:10:51Z2022-10-30T00:00:00ZHandlehttp://hdl.handle.net/10400.26/43551http://purl.org/coar/access_right/c_abf2open accesselectrical power grids;fault forecasting;long short-term memory;time series forecasting;wavelet transform1403744 bytesliteraturehttp://purl.org/coar/resource_type/c_6501journal articlehttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://comum.rcaap.pt/bitstreams/88ccd7f7-50a2-421b-abc7-442fa6ab89d5/downloadSensors
spellingShingle Wavelet LSTM for Fault Forecasting in Electrical Power Grids
Branco, Nathielle
electrical power grids;
fault forecasting;
long short-term memory;
time series forecasting;
wavelet transform
status NEW
subject.fl_str_mv electrical power grids;
fault forecasting;
long short-term memory;
time series forecasting;
wavelet transform
title Wavelet LSTM for Fault Forecasting in Electrical Power Grids
title_full Wavelet LSTM for Fault Forecasting in Electrical Power Grids
title_fullStr Wavelet LSTM for Fault Forecasting in Electrical Power Grids
title_full_unstemmed Wavelet LSTM for Fault Forecasting in Electrical Power Grids
title_short Wavelet LSTM for Fault Forecasting in Electrical Power Grids
title_sort Wavelet LSTM for Fault Forecasting in Electrical Power Grids
topic electrical power grids;
fault forecasting;
long short-term memory;
time series forecasting;
wavelet transform
topic_facet electrical power grids;
fault forecasting;
long short-term memory;
time series forecasting;
wavelet transform
url http://hdl.handle.net/10400.26/43551
visible 1