Unsupervised non-technical losses identification through optimum-path forest

Detalhes bibliográficos
Autor(a) principal: Passos Junior, Leandro Aparecido
Data de Publicação: 2016
Outros Autores: Oba Ramos, Caio Cesar [UNESP], Rodrigues, Douglas, Pereira, Danillo Roberto [UNESP], Souza, Andre Nunes de [UNESP], Pontara da Costa, Kelton Augusto [UNESP], Papa, Joao Paulo [UNESP]
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1016/j.epsr.2016.05.036
http://hdl.handle.net/11449/161932
Resumo: Non-technical losses (NTL) identification has been paramount in the last years. However, it is not straightforward to obtain labelled datasets to perform a supervised NTL recognition task. In this paper, the optimum-path forest (OPF) clustering algorithm has been employed to identify irregular and regular profiles of commercial and industrial consumers obtained from a Brazilian electrical power company. Additionally, a model for the problem of NTL recognition as an anomaly detection task has been proposed when there are little or no information about irregular consumers. For such purpose, two new approaches based on the OPF framework have been introduced and compared against the well-known k-means, Gaussian mixture model, Birch, affinity propagation and one-class support vector machines. The experimental results have shown the robustness of OPF for both unsupervised NTL recognition and anomaly detection problems. In short, the main contributions of this paper are fourfold: (i) to employ unsupervised OPF for non-technical losses detection, (ii) to model the problem of NTL as being an anomaly detection task, (iii) to employ unsupervised OPF to estimate the parameters of the Gaussian distributions, and (iv) to present an anomaly detection approach based on unsupervised optimum-path forest. (C) 2016 Elsevier B.V. All rights reserved.
id UNSP_0829e1150bff4edfa4634cda81adb688
oai_identifier_str oai:repositorio.unesp.br:11449/161932
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Unsupervised non-technical losses identification through optimum-path forestNon-technical lossesOptimum-path forestClusteringAnomaly detectionNon-technical losses (NTL) identification has been paramount in the last years. However, it is not straightforward to obtain labelled datasets to perform a supervised NTL recognition task. In this paper, the optimum-path forest (OPF) clustering algorithm has been employed to identify irregular and regular profiles of commercial and industrial consumers obtained from a Brazilian electrical power company. Additionally, a model for the problem of NTL recognition as an anomaly detection task has been proposed when there are little or no information about irregular consumers. For such purpose, two new approaches based on the OPF framework have been introduced and compared against the well-known k-means, Gaussian mixture model, Birch, affinity propagation and one-class support vector machines. The experimental results have shown the robustness of OPF for both unsupervised NTL recognition and anomaly detection problems. In short, the main contributions of this paper are fourfold: (i) to employ unsupervised OPF for non-technical losses detection, (ii) to model the problem of NTL as being an anomaly detection task, (iii) to employ unsupervised OPF to estimate the parameters of the Gaussian distributions, and (iv) to present an anomaly detection approach based on unsupervised optimum-path forest. (C) 2016 Elsevier B.V. All rights reserved.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Univ Fed Sao Carlos, Dept Comp, Sao Carlos, SP, BrazilSao Paulo State Univ, Dept Comp, Bauru, BrazilSao Paulo State Univ, Dept Elect Engn, Bauru, BrazilSao Paulo State Univ, Dept Comp, Bauru, BrazilSao Paulo State Univ, Dept Elect Engn, Bauru, BrazilFAPESP: 2009/16206-1FAPESP: 2012/14158-2FAPESP: 2013/20387-7FAPESP: 2014/16250-9FAPESP: 2015/00801-9CNPq: 303182/2011-3CNPq: 470571/2013-6CNPq: 306166/2014-3Elsevier B.V.Universidade Federal de São Carlos (UFSCar)Universidade Estadual Paulista (Unesp)Passos Junior, Leandro AparecidoOba Ramos, Caio Cesar [UNESP]Rodrigues, DouglasPereira, Danillo Roberto [UNESP]Souza, Andre Nunes de [UNESP]Pontara da Costa, Kelton Augusto [UNESP]Papa, Joao Paulo [UNESP]2018-11-26T17:06:13Z2018-11-26T17:06:13Z2016-11-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article413-423application/pdfhttp://dx.doi.org/10.1016/j.epsr.2016.05.036Electric Power Systems Research. Lausanne: Elsevier Science Sa, v. 140, p. 413-423, 2016.0378-7796http://hdl.handle.net/11449/16193210.1016/j.epsr.2016.05.036WOS:000383527300044WOS000383527300044.pdfWeb of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengElectric Power Systems Research1,048info:eu-repo/semantics/openAccess2024-06-28T13:34:25Zoai:repositorio.unesp.br:11449/161932Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-06T00:08:47.946414Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Unsupervised non-technical losses identification through optimum-path forest
title Unsupervised non-technical losses identification through optimum-path forest
spellingShingle Unsupervised non-technical losses identification through optimum-path forest
Passos Junior, Leandro Aparecido
Non-technical losses
Optimum-path forest
Clustering
Anomaly detection
title_short Unsupervised non-technical losses identification through optimum-path forest
title_full Unsupervised non-technical losses identification through optimum-path forest
title_fullStr Unsupervised non-technical losses identification through optimum-path forest
title_full_unstemmed Unsupervised non-technical losses identification through optimum-path forest
title_sort Unsupervised non-technical losses identification through optimum-path forest
author Passos Junior, Leandro Aparecido
author_facet Passos Junior, Leandro Aparecido
Oba Ramos, Caio Cesar [UNESP]
Rodrigues, Douglas
Pereira, Danillo Roberto [UNESP]
Souza, Andre Nunes de [UNESP]
Pontara da Costa, Kelton Augusto [UNESP]
Papa, Joao Paulo [UNESP]
author_role author
author2 Oba Ramos, Caio Cesar [UNESP]
Rodrigues, Douglas
Pereira, Danillo Roberto [UNESP]
Souza, Andre Nunes de [UNESP]
Pontara da Costa, Kelton Augusto [UNESP]
Papa, Joao Paulo [UNESP]
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade Federal de São Carlos (UFSCar)
Universidade Estadual Paulista (Unesp)
dc.contributor.author.fl_str_mv Passos Junior, Leandro Aparecido
Oba Ramos, Caio Cesar [UNESP]
Rodrigues, Douglas
Pereira, Danillo Roberto [UNESP]
Souza, Andre Nunes de [UNESP]
Pontara da Costa, Kelton Augusto [UNESP]
Papa, Joao Paulo [UNESP]
dc.subject.por.fl_str_mv Non-technical losses
Optimum-path forest
Clustering
Anomaly detection
topic Non-technical losses
Optimum-path forest
Clustering
Anomaly detection
description Non-technical losses (NTL) identification has been paramount in the last years. However, it is not straightforward to obtain labelled datasets to perform a supervised NTL recognition task. In this paper, the optimum-path forest (OPF) clustering algorithm has been employed to identify irregular and regular profiles of commercial and industrial consumers obtained from a Brazilian electrical power company. Additionally, a model for the problem of NTL recognition as an anomaly detection task has been proposed when there are little or no information about irregular consumers. For such purpose, two new approaches based on the OPF framework have been introduced and compared against the well-known k-means, Gaussian mixture model, Birch, affinity propagation and one-class support vector machines. The experimental results have shown the robustness of OPF for both unsupervised NTL recognition and anomaly detection problems. In short, the main contributions of this paper are fourfold: (i) to employ unsupervised OPF for non-technical losses detection, (ii) to model the problem of NTL as being an anomaly detection task, (iii) to employ unsupervised OPF to estimate the parameters of the Gaussian distributions, and (iv) to present an anomaly detection approach based on unsupervised optimum-path forest. (C) 2016 Elsevier B.V. All rights reserved.
publishDate 2016
dc.date.none.fl_str_mv 2016-11-01
2018-11-26T17:06:13Z
2018-11-26T17:06:13Z
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.2016.05.036
Electric Power Systems Research. Lausanne: Elsevier Science Sa, v. 140, p. 413-423, 2016.
0378-7796
http://hdl.handle.net/11449/161932
10.1016/j.epsr.2016.05.036
WOS:000383527300044
WOS000383527300044.pdf
url http://dx.doi.org/10.1016/j.epsr.2016.05.036
http://hdl.handle.net/11449/161932
identifier_str_mv Electric Power Systems Research. Lausanne: Elsevier Science Sa, v. 140, p. 413-423, 2016.
0378-7796
10.1016/j.epsr.2016.05.036
WOS:000383527300044
WOS000383527300044.pdf
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Electric Power Systems Research
1,048
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 413-423
application/pdf
dc.publisher.none.fl_str_mv Elsevier B.V.
publisher.none.fl_str_mv Elsevier B.V.
dc.source.none.fl_str_mv Web of Science
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
_version_ 1808129589331886080