Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection

Detalhes bibliográficos
Autor(a) principal: Pereira, Luis A. M. [UNESP]
Data de Publicação: 2013
Outros Autores: Afonso, Luis C. S. [UNESP], Papa, João Paulo [UNESP], Vale, Zita A., Ramos, Caio C. O., Gastaldello, Danillo S., Souza, André N.
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1109/ISGT-LA.2013.6554383
http://hdl.handle.net/11449/76325
Resumo: The non-technical loss is not a problem with trivial solution or regional character and its minimization represents the guarantee of investments in product quality and maintenance of power systems, introduced by a competitive environment after the period of privatization in the national scene. In this paper, we show how to improve the training phase of a neural network-based classifier using a recently proposed meta-heuristic technique called Charged System Search, which is based on the interactions between electrically charged particles. The experiments were carried out in the context of non-technical loss in power distribution systems in a dataset obtained from a Brazilian electrical power company, and have demonstrated the robustness of the proposed technique against with several others nature-inspired optimization techniques for training neural networks. Thus, it is possible to improve some applications on Smart Grids. © 2013 IEEE.
id UNSP_2cd0356aeb50f1751842d8a5c57ef697
oai_identifier_str oai:repositorio.unesp.br:11449/76325
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detectionCharged System SearchNeural NetworksNontechnical LossesCharged system searchesCompetitive environmentMeta-heuristic techniquesMulti-layer perceptron neural networksNon-technical lossOptimization techniquesPower distribution systemTrivial solutionsElectric load distributionElectric utilitiesPrivatizationSmart power gridsNeural networksThe non-technical loss is not a problem with trivial solution or regional character and its minimization represents the guarantee of investments in product quality and maintenance of power systems, introduced by a competitive environment after the period of privatization in the national scene. In this paper, we show how to improve the training phase of a neural network-based classifier using a recently proposed meta-heuristic technique called Charged System Search, which is based on the interactions between electrically charged particles. The experiments were carried out in the context of non-technical loss in power distribution systems in a dataset obtained from a Brazilian electrical power company, and have demonstrated the robustness of the proposed technique against with several others nature-inspired optimization techniques for training neural networks. Thus, it is possible to improve some applications on Smart Grids. © 2013 IEEE.Research Executive AgencyDepartment of Computing Faculty of Science São Paulo State University-UNESP, BauruKnowledge Engineering and Decision Support Research Center-GECAD Polytechnic Institute of Porto-IPP, PortoDepartment of Electrical Engineering Polytechnic School University of São Paulo-USP, São PauloDepartment of Computing Faculty of Science São Paulo State University-UNESP, BauruREA: 318912Universidade Estadual Paulista (Unesp)Polytechnic Institute of Porto-IPPUniversidade de São Paulo (USP)Pereira, Luis A. M. [UNESP]Afonso, Luis C. S. [UNESP]Papa, João Paulo [UNESP]Vale, Zita A.Ramos, Caio C. O.Gastaldello, Danillo S.Souza, André N.2014-05-27T11:30:15Z2014-05-27T11:30:15Z2013-08-26info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1109/ISGT-LA.2013.65543832013 IEEE PES Conference on Innovative Smart Grid Technologies, ISGT LA 2013.http://hdl.handle.net/11449/7632510.1109/ISGT-LA.2013.6554383WOS:0003265899000152-s2.0-848823083639039182932747194Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPeng2013 IEEE PES Conference on Innovative Smart Grid Technologies, ISGT LA 2013info:eu-repo/semantics/openAccess2024-04-23T16:11:19Zoai:repositorio.unesp.br:11449/76325Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:15:36.977857Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection
title Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection
spellingShingle Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection
Pereira, Luis A. M. [UNESP]
Charged System Search
Neural Networks
Nontechnical Losses
Charged system searches
Competitive environment
Meta-heuristic techniques
Multi-layer perceptron neural networks
Non-technical loss
Optimization techniques
Power distribution system
Trivial solutions
Electric load distribution
Electric utilities
Privatization
Smart power grids
Neural networks
title_short Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection
title_full Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection
title_fullStr Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection
title_full_unstemmed Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection
title_sort Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection
author Pereira, Luis A. M. [UNESP]
author_facet Pereira, Luis A. M. [UNESP]
Afonso, Luis C. S. [UNESP]
Papa, João Paulo [UNESP]
Vale, Zita A.
Ramos, Caio C. O.
Gastaldello, Danillo S.
Souza, André N.
author_role author
author2 Afonso, Luis C. S. [UNESP]
Papa, João Paulo [UNESP]
Vale, Zita A.
Ramos, Caio C. O.
Gastaldello, Danillo S.
Souza, André N.
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
Polytechnic Institute of Porto-IPP
Universidade de São Paulo (USP)
dc.contributor.author.fl_str_mv Pereira, Luis A. M. [UNESP]
Afonso, Luis C. S. [UNESP]
Papa, João Paulo [UNESP]
Vale, Zita A.
Ramos, Caio C. O.
Gastaldello, Danillo S.
Souza, André N.
dc.subject.por.fl_str_mv Charged System Search
Neural Networks
Nontechnical Losses
Charged system searches
Competitive environment
Meta-heuristic techniques
Multi-layer perceptron neural networks
Non-technical loss
Optimization techniques
Power distribution system
Trivial solutions
Electric load distribution
Electric utilities
Privatization
Smart power grids
Neural networks
topic Charged System Search
Neural Networks
Nontechnical Losses
Charged system searches
Competitive environment
Meta-heuristic techniques
Multi-layer perceptron neural networks
Non-technical loss
Optimization techniques
Power distribution system
Trivial solutions
Electric load distribution
Electric utilities
Privatization
Smart power grids
Neural networks
description The non-technical loss is not a problem with trivial solution or regional character and its minimization represents the guarantee of investments in product quality and maintenance of power systems, introduced by a competitive environment after the period of privatization in the national scene. In this paper, we show how to improve the training phase of a neural network-based classifier using a recently proposed meta-heuristic technique called Charged System Search, which is based on the interactions between electrically charged particles. The experiments were carried out in the context of non-technical loss in power distribution systems in a dataset obtained from a Brazilian electrical power company, and have demonstrated the robustness of the proposed technique against with several others nature-inspired optimization techniques for training neural networks. Thus, it is possible to improve some applications on Smart Grids. © 2013 IEEE.
publishDate 2013
dc.date.none.fl_str_mv 2013-08-26
2014-05-27T11:30:15Z
2014-05-27T11:30:15Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1109/ISGT-LA.2013.6554383
2013 IEEE PES Conference on Innovative Smart Grid Technologies, ISGT LA 2013.
http://hdl.handle.net/11449/76325
10.1109/ISGT-LA.2013.6554383
WOS:000326589900015
2-s2.0-84882308363
9039182932747194
url http://dx.doi.org/10.1109/ISGT-LA.2013.6554383
http://hdl.handle.net/11449/76325
identifier_str_mv 2013 IEEE PES Conference on Innovative Smart Grid Technologies, ISGT LA 2013.
10.1109/ISGT-LA.2013.6554383
WOS:000326589900015
2-s2.0-84882308363
9039182932747194
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2013 IEEE PES Conference on Innovative Smart Grid Technologies, ISGT LA 2013
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
_version_ 1808128780904955904