Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFS |
Texto Completo: | http://ri.ufs.br/jspui/handle/riufs/10783 |
Resumo: | In the last years, the electric power quality analysis came back to the fore with the advance in many computational areas and the serious issues related to the deterioration of it, that can cause damages to the life, lifetime reduction of the electrical devices, and, consequent environment and economic impacts. In this sense, it was verified that the interest in researches related to the classification of the disturbances that cause the deterioration of the energy quality returned to grow, mainly the creation of systems that can implement it in a real environment. Then, this work aims to verify, experimentally, many strands related to the process of electrical disturbance classification and implementation of embedded systems with the purpose of implement the classification process. Therefore, it was analyzed experimentally the accuracy of different machine learning algorithms (obtaining as a better result the accuracy of the Random forest, both in noisy and not noisy signals), efficiency of the algorithms in embedded environments (in which the Decision Tree was the best), and the analysis of the classification of multiple disturbances (in which 22 disturbances were analyzed and the Random Forest get an accuracy above 90% in not noisy environment). Besides that, it was implemented a benchmark2 of simulated disturbances and make it available for the community (as well as the source code in Python), aiming to stay easier make comparisons among different proposes of different authors. |
id |
UFS-2_d115c99f13021fab4470f5cc4a03a6f0 |
---|---|
oai_identifier_str |
oai:ufs.br:riufs/10783 |
network_acronym_str |
UFS-2 |
network_name_str |
Repositório Institucional da UFS |
repository_id_str |
|
spelling |
Santos, Reneilson Yves CarvalhoMoreno Ordonez, Edward DavidEstombelo-Montesco, Carlos Alberto2019-03-28T23:40:33Z2019-03-28T23:40:33Z2019-02-21SANTOS, Reneilson Yves Carvalho. Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos. 2019. 205 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Sergipe, São Cristóvão, SE, 2019.http://ri.ufs.br/jspui/handle/riufs/10783In the last years, the electric power quality analysis came back to the fore with the advance in many computational areas and the serious issues related to the deterioration of it, that can cause damages to the life, lifetime reduction of the electrical devices, and, consequent environment and economic impacts. In this sense, it was verified that the interest in researches related to the classification of the disturbances that cause the deterioration of the energy quality returned to grow, mainly the creation of systems that can implement it in a real environment. Then, this work aims to verify, experimentally, many strands related to the process of electrical disturbance classification and implementation of embedded systems with the purpose of implement the classification process. Therefore, it was analyzed experimentally the accuracy of different machine learning algorithms (obtaining as a better result the accuracy of the Random forest, both in noisy and not noisy signals), efficiency of the algorithms in embedded environments (in which the Decision Tree was the best), and the analysis of the classification of multiple disturbances (in which 22 disturbances were analyzed and the Random Forest get an accuracy above 90% in not noisy environment). Besides that, it was implemented a benchmark2 of simulated disturbances and make it available for the community (as well as the source code in Python), aiming to stay easier make comparisons among different proposes of different authors.Nos últimos anos, a análise da qualidade da energia elétrica voltou à tona com o avanço em diversas áreas computacionais e os graves problemas relacionados à deterioração desta, podendo causar riscos à vida, redução de vida útil de equipamentos e consequentes impactos ambientais e econômicos. Neste sentido, verificou-se ainda que o interesse em pesquisas relacionadas à classificação dos distúrbios que causam a deterioração da rede elétrica voltou a crescer, principalmente a criação de sistemas passíveis de implementação em ambientes reais. Desta forma, este trabalho buscou verificar, experimentalmente, as mais diversas vertentes relacionadas ao processo de classificação de distúrbios elétricos e criação de sistemas embarcados com este fim. Foi, portanto, analisado experimentalmente a acurácia de algoritmos de classificação (obtendo como melhor resultado a acurácia do Random Forest, tanto para sinais sem ruído quanto para sinais ruidosos), eficiência em ambientes embarcados (obtendo a Árvore de Decisão como melhor eficiência nestes ambientes), e análise de classificação de distúrbios múltiplos (no qual analisou-se 22 distúrbios distintos, com e sem ruído e atingiu-se uma acurácia acima de 90% para ambientes não ruidosos com o Random Forest). Além disso, construiu-se um benchmark1 de distúrbios simulados e disponibilizou-o para a comunidade (assim como seu código fonte em Python), de forma a facilitar a comparação entre diferentes propostas nesta área.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPESSão Cristóvão, SEporComputaçãoAlgoritmosAlgoritmos de classificaçãoDistúrbios elétricosCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOAnálises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricosinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisPós-Graduação em Ciência da ComputaçãoUFSreponame:Repositório Institucional da UFSinstname:Universidade Federal de Sergipe (UFS)instacron:UFSinfo:eu-repo/semantics/openAccessTEXTRENEILSON_YVES_CARVALHO_SANTOS.pdf.txtRENEILSON_YVES_CARVALHO_SANTOS.pdf.txtExtracted texttext/plain328320https://ri.ufs.br/jspui/bitstream/riufs/10783/3/RENEILSON_YVES_CARVALHO_SANTOS.pdf.txt2c42c435b9ab9d50b64f5cf87412f249MD53THUMBNAILRENEILSON_YVES_CARVALHO_SANTOS.pdf.jpgRENEILSON_YVES_CARVALHO_SANTOS.pdf.jpgGenerated Thumbnailimage/jpeg1284https://ri.ufs.br/jspui/bitstream/riufs/10783/4/RENEILSON_YVES_CARVALHO_SANTOS.pdf.jpgb34144372a32ad9857105b93739a5cb7MD54LICENSElicense.txtlicense.txttext/plain; charset=utf-81475https://ri.ufs.br/jspui/bitstream/riufs/10783/1/license.txt098cbbf65c2c15e1fb2e49c5d306a44cMD51ORIGINALRENEILSON_YVES_CARVALHO_SANTOS.pdfRENEILSON_YVES_CARVALHO_SANTOS.pdfapplication/pdf3285952https://ri.ufs.br/jspui/bitstream/riufs/10783/2/RENEILSON_YVES_CARVALHO_SANTOS.pdf8091a7dd9384ad706b1b447d47fe4fddMD52riufs/107832019-03-28 20:40:33.795oai:ufs.br:riufs/10783TElDRU7Dh0EgREUgRElTVFJJQlVJw4fDg08gTsODTy1FWENMVVNJVkEKCkNvbSBhIGFwcmVzZW50YcOnw6NvIGRlc3RhIGxpY2Vuw6dhLCB2b2PDqiAobyBhdXRvcihlcykgb3UgbyB0aXR1bGFyIGRvcyBkaXJlaXRvcyBkZSBhdXRvcikgY29uY2VkZSDDoCBVbml2ZXJzaWRhZGUgRmVkZXJhbCBkZSBTZXJnaXBlIG8gZGlyZWl0byBuw6NvLWV4Y2x1c2l2byBkZSByZXByb2R1emlyIHNldSB0cmFiYWxobyBubyBmb3JtYXRvIGVsZXRyw7RuaWNvLCBpbmNsdWluZG8gb3MgZm9ybWF0b3Mgw6F1ZGlvIG91IHbDrWRlby4KClZvY8OqIGNvbmNvcmRhIHF1ZSBhIFVuaXZlcnNpZGFkZSBGZWRlcmFsIGRlIFNlcmdpcGUgcG9kZSwgc2VtIGFsdGVyYXIgbyBjb250ZcO6ZG8sIHRyYW5zcG9yIHNldSB0cmFiYWxobyBwYXJhIHF1YWxxdWVyIG1laW8gb3UgZm9ybWF0byBwYXJhIGZpbnMgZGUgcHJlc2VydmHDp8Ojby4KClZvY8OqIHRhbWLDqW0gY29uY29yZGEgcXVlIGEgVW5pdmVyc2lkYWRlIEZlZGVyYWwgZGUgU2VyZ2lwZSBwb2RlIG1hbnRlciBtYWlzIGRlIHVtYSBjw7NwaWEgZGUgc2V1IHRyYWJhbGhvIHBhcmEgZmlucyBkZSBzZWd1cmFuw6dhLCBiYWNrLXVwIGUgcHJlc2VydmHDp8Ojby4KClZvY8OqIGRlY2xhcmEgcXVlIHNldSB0cmFiYWxobyDDqSBvcmlnaW5hbCBlIHF1ZSB2b2PDqiB0ZW0gbyBwb2RlciBkZSBjb25jZWRlciBvcyBkaXJlaXRvcyBjb250aWRvcyBuZXN0YSBsaWNlbsOnYS4gVm9jw6ogdGFtYsOpbSBkZWNsYXJhIHF1ZSBvIGRlcMOzc2l0bywgcXVlIHNlamEgZGUgc2V1IGNvbmhlY2ltZW50bywgbsOjbyBpbmZyaW5nZSBkaXJlaXRvcyBhdXRvcmFpcyBkZSBuaW5ndcOpbS4KCkNhc28gbyB0cmFiYWxobyBjb250ZW5oYSBtYXRlcmlhbCBxdWUgdm9jw6ogbsOjbyBwb3NzdWkgYSB0aXR1bGFyaWRhZGUgZG9zIGRpcmVpdG9zIGF1dG9yYWlzLCB2b2PDqiBkZWNsYXJhIHF1ZSBvYnRldmUgYSBwZXJtaXNzw6NvIGlycmVzdHJpdGEgZG8gZGV0ZW50b3IgZG9zIGRpcmVpdG9zIGF1dG9yYWlzIHBhcmEgY29uY2VkZXIgw6AgVW5pdmVyc2lkYWRlIEZlZGVyYWwgZGUgU2VyZ2lwZSBvcyBkaXJlaXRvcyBhcHJlc2VudGFkb3MgbmVzdGEgbGljZW7Dp2EsIGUgcXVlIGVzc2UgbWF0ZXJpYWwgZGUgcHJvcHJpZWRhZGUgZGUgdGVyY2Vpcm9zIGVzdMOhIGNsYXJhbWVudGUgaWRlbnRpZmljYWRvIGUgcmVjb25oZWNpZG8gbm8gdGV4dG8gb3Ugbm8gY29udGXDumRvLgoKQSBVbml2ZXJzaWRhZGUgRmVkZXJhbCBkZSBTZXJnaXBlIHNlIGNvbXByb21ldGUgYSBpZGVudGlmaWNhciBjbGFyYW1lbnRlIG8gc2V1IG5vbWUocykgb3UgbyhzKSBub21lKHMpIGRvKHMpIApkZXRlbnRvcihlcykgZG9zIGRpcmVpdG9zIGF1dG9yYWlzIGRvIHRyYWJhbGhvLCBlIG7Do28gZmFyw6EgcXVhbHF1ZXIgYWx0ZXJhw6fDo28sIGFsw6ltIGRhcXVlbGFzIGNvbmNlZGlkYXMgcG9yIGVzdGEgbGljZW7Dp2EuIAo=Repositório InstitucionalPUBhttps://ri.ufs.br/oai/requestrepositorio@academico.ufs.bropendoar:2019-03-28T23:40:33Repositório Institucional da UFS - Universidade Federal de Sergipe (UFS)false |
dc.title.pt_BR.fl_str_mv |
Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos |
title |
Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos |
spellingShingle |
Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos Santos, Reneilson Yves Carvalho Computação Algoritmos Algoritmos de classificação Distúrbios elétricos CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
title_short |
Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos |
title_full |
Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos |
title_fullStr |
Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos |
title_full_unstemmed |
Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos |
title_sort |
Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos |
author |
Santos, Reneilson Yves Carvalho |
author_facet |
Santos, Reneilson Yves Carvalho |
author_role |
author |
dc.contributor.author.fl_str_mv |
Santos, Reneilson Yves Carvalho |
dc.contributor.advisor1.fl_str_mv |
Moreno Ordonez, Edward David |
dc.contributor.advisor-co1.fl_str_mv |
Estombelo-Montesco, Carlos Alberto |
contributor_str_mv |
Moreno Ordonez, Edward David Estombelo-Montesco, Carlos Alberto |
dc.subject.por.fl_str_mv |
Computação Algoritmos Algoritmos de classificação Distúrbios elétricos |
topic |
Computação Algoritmos Algoritmos de classificação Distúrbios elétricos CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
dc.subject.cnpq.fl_str_mv |
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
description |
In the last years, the electric power quality analysis came back to the fore with the advance in many computational areas and the serious issues related to the deterioration of it, that can cause damages to the life, lifetime reduction of the electrical devices, and, consequent environment and economic impacts. In this sense, it was verified that the interest in researches related to the classification of the disturbances that cause the deterioration of the energy quality returned to grow, mainly the creation of systems that can implement it in a real environment. Then, this work aims to verify, experimentally, many strands related to the process of electrical disturbance classification and implementation of embedded systems with the purpose of implement the classification process. Therefore, it was analyzed experimentally the accuracy of different machine learning algorithms (obtaining as a better result the accuracy of the Random forest, both in noisy and not noisy signals), efficiency of the algorithms in embedded environments (in which the Decision Tree was the best), and the analysis of the classification of multiple disturbances (in which 22 disturbances were analyzed and the Random Forest get an accuracy above 90% in not noisy environment). Besides that, it was implemented a benchmark2 of simulated disturbances and make it available for the community (as well as the source code in Python), aiming to stay easier make comparisons among different proposes of different authors. |
publishDate |
2019 |
dc.date.accessioned.fl_str_mv |
2019-03-28T23:40:33Z |
dc.date.available.fl_str_mv |
2019-03-28T23:40:33Z |
dc.date.issued.fl_str_mv |
2019-02-21 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
SANTOS, Reneilson Yves Carvalho. Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos. 2019. 205 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Sergipe, São Cristóvão, SE, 2019. |
dc.identifier.uri.fl_str_mv |
http://ri.ufs.br/jspui/handle/riufs/10783 |
identifier_str_mv |
SANTOS, Reneilson Yves Carvalho. Análises experimentais de algoritmos de aprendizagem de máquina na classificação de distúrbios elétricos. 2019. 205 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Sergipe, São Cristóvão, SE, 2019. |
url |
http://ri.ufs.br/jspui/handle/riufs/10783 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.program.fl_str_mv |
Pós-Graduação em Ciência da Computação |
dc.publisher.initials.fl_str_mv |
UFS |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFS instname:Universidade Federal de Sergipe (UFS) instacron:UFS |
instname_str |
Universidade Federal de Sergipe (UFS) |
instacron_str |
UFS |
institution |
UFS |
reponame_str |
Repositório Institucional da UFS |
collection |
Repositório Institucional da UFS |
bitstream.url.fl_str_mv |
https://ri.ufs.br/jspui/bitstream/riufs/10783/3/RENEILSON_YVES_CARVALHO_SANTOS.pdf.txt https://ri.ufs.br/jspui/bitstream/riufs/10783/4/RENEILSON_YVES_CARVALHO_SANTOS.pdf.jpg https://ri.ufs.br/jspui/bitstream/riufs/10783/1/license.txt https://ri.ufs.br/jspui/bitstream/riufs/10783/2/RENEILSON_YVES_CARVALHO_SANTOS.pdf |
bitstream.checksum.fl_str_mv |
2c42c435b9ab9d50b64f5cf87412f249 b34144372a32ad9857105b93739a5cb7 098cbbf65c2c15e1fb2e49c5d306a44c 8091a7dd9384ad706b1b447d47fe4fdd |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFS - Universidade Federal de Sergipe (UFS) |
repository.mail.fl_str_mv |
repositorio@academico.ufs.br |
_version_ |
1802110699794595840 |