Selection of features from power theories to compose NILM datasets
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.aei.2022.101556 http://hdl.handle.net/11449/234180 |
Resumo: | The load disaggregation concept is gaining attention due to the increasing need for optimized energy utilization and detailed characterization of electricity consumption profiles, especially through Nonintrusive Load Monitoring (NILM) approaches. This occurs since knowledge about individualized consumption per appliance allows to create strategies striving for energy savings, improvement of energy efficiency, and creating energy awareness to consumers. Moreover, by using feature extraction to devise energy disaggregation, one can achieve accurate identification of electric appliances. However, even though several literature works propose distinct features to be utilized, no consensus exists in the literature about the most appropriate set of features that ensure high accuracy on load disaggregation. Thus, beyond presenting a critical analysis of some significant features often selected in the literature, this paper proposes identifying the most relevant ones considering collinearity and machine learning algorithms. The results show that high-performance metrics can be achieved with fewer features than usually adopted in the literature. Moreover, it is demonstrated that the Conservative Power Theory can offer the most representative features for appliance identification, leading to efficient power consumption disaggregation. |
id |
UNSP_2ab3113743188a1db4972fd575851f9e |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/234180 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Selection of features from power theories to compose NILM datasetsElectric consumption managementFeatures qualityLoad disaggregationNonintrusive load monitoringSmart metersThe load disaggregation concept is gaining attention due to the increasing need for optimized energy utilization and detailed characterization of electricity consumption profiles, especially through Nonintrusive Load Monitoring (NILM) approaches. This occurs since knowledge about individualized consumption per appliance allows to create strategies striving for energy savings, improvement of energy efficiency, and creating energy awareness to consumers. Moreover, by using feature extraction to devise energy disaggregation, one can achieve accurate identification of electric appliances. However, even though several literature works propose distinct features to be utilized, no consensus exists in the literature about the most appropriate set of features that ensure high accuracy on load disaggregation. Thus, beyond presenting a critical analysis of some significant features often selected in the literature, this paper proposes identifying the most relevant ones considering collinearity and machine learning algorithms. The results show that high-performance metrics can be achieved with fewer features than usually adopted in the literature. Moreover, it is demonstrated that the Conservative Power Theory can offer the most representative features for appliance identification, leading to efficient power consumption disaggregation.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Department of Electrical Engineering Federal University of Technology - Parana (UTFPR) Cornélio Procópio PRSchool of Electrical and Computer Engineering University of Campinas (UNICAMP) Campinas SPInstitute of Science and Technology São Paulo State University (UNESP) Sorocaba SPInstitute of Science and Technology São Paulo State University (UNESP) Sorocaba SPFAPESP: 2016/08645-9PRUniversidade Estadual de Campinas (UNICAMP)Universidade Estadual Paulista (UNESP)Souza, Wesley A.Alonso, Augusto M.S.Bosco, Thais B. [UNESP]Garcia, Fernando D. [UNESP]Gonçalves, Flavio A.S. [UNESP]Marafão, Fernando P. [UNESP]2022-05-01T13:57:30Z2022-05-01T13:57:30Z2022-04-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1016/j.aei.2022.101556Advanced Engineering Informatics, v. 52.1474-0346http://hdl.handle.net/11449/23418010.1016/j.aei.2022.1015562-s2.0-85125149045Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengAdvanced Engineering Informaticsinfo:eu-repo/semantics/openAccess2022-05-01T13:57:30Zoai:repositorio.unesp.br:11449/234180Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T14:49:41.245828Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Selection of features from power theories to compose NILM datasets |
title |
Selection of features from power theories to compose NILM datasets |
spellingShingle |
Selection of features from power theories to compose NILM datasets Souza, Wesley A. Electric consumption management Features quality Load disaggregation Nonintrusive load monitoring Smart meters |
title_short |
Selection of features from power theories to compose NILM datasets |
title_full |
Selection of features from power theories to compose NILM datasets |
title_fullStr |
Selection of features from power theories to compose NILM datasets |
title_full_unstemmed |
Selection of features from power theories to compose NILM datasets |
title_sort |
Selection of features from power theories to compose NILM datasets |
author |
Souza, Wesley A. |
author_facet |
Souza, Wesley A. Alonso, Augusto M.S. Bosco, Thais B. [UNESP] Garcia, Fernando D. [UNESP] Gonçalves, Flavio A.S. [UNESP] Marafão, Fernando P. [UNESP] |
author_role |
author |
author2 |
Alonso, Augusto M.S. Bosco, Thais B. [UNESP] Garcia, Fernando D. [UNESP] Gonçalves, Flavio A.S. [UNESP] Marafão, Fernando P. [UNESP] |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
PR Universidade Estadual de Campinas (UNICAMP) Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Souza, Wesley A. Alonso, Augusto M.S. Bosco, Thais B. [UNESP] Garcia, Fernando D. [UNESP] Gonçalves, Flavio A.S. [UNESP] Marafão, Fernando P. [UNESP] |
dc.subject.por.fl_str_mv |
Electric consumption management Features quality Load disaggregation Nonintrusive load monitoring Smart meters |
topic |
Electric consumption management Features quality Load disaggregation Nonintrusive load monitoring Smart meters |
description |
The load disaggregation concept is gaining attention due to the increasing need for optimized energy utilization and detailed characterization of electricity consumption profiles, especially through Nonintrusive Load Monitoring (NILM) approaches. This occurs since knowledge about individualized consumption per appliance allows to create strategies striving for energy savings, improvement of energy efficiency, and creating energy awareness to consumers. Moreover, by using feature extraction to devise energy disaggregation, one can achieve accurate identification of electric appliances. However, even though several literature works propose distinct features to be utilized, no consensus exists in the literature about the most appropriate set of features that ensure high accuracy on load disaggregation. Thus, beyond presenting a critical analysis of some significant features often selected in the literature, this paper proposes identifying the most relevant ones considering collinearity and machine learning algorithms. The results show that high-performance metrics can be achieved with fewer features than usually adopted in the literature. Moreover, it is demonstrated that the Conservative Power Theory can offer the most representative features for appliance identification, leading to efficient power consumption disaggregation. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-05-01T13:57:30Z 2022-05-01T13:57:30Z 2022-04-01 |
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.aei.2022.101556 Advanced Engineering Informatics, v. 52. 1474-0346 http://hdl.handle.net/11449/234180 10.1016/j.aei.2022.101556 2-s2.0-85125149045 |
url |
http://dx.doi.org/10.1016/j.aei.2022.101556 http://hdl.handle.net/11449/234180 |
identifier_str_mv |
Advanced Engineering Informatics, v. 52. 1474-0346 10.1016/j.aei.2022.101556 2-s2.0-85125149045 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Advanced Engineering Informatics |
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_ |
1808128421618778112 |