Load disaggregation using microscopic power features and pattern recognition
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3390/en12142641 http://hdl.handle.net/11449/190485 |
Resumo: | A new generation of smart meters are called cognitive meters, which are essentially based on Artificial Intelligence (AI) and load disaggregation methods for Non-Intrusive Load Monitoring (NILM). Thus, modern NILM may recognize appliances connected to the grid during certain periods, while providing much more information than the traditional monthly consumption. Therefore, this article presents a new load disaggregation methodology with microscopic characteristics collected from current and voltage waveforms. Initially, the novel NILM algorithm—called the Power Signature Blob (PSB)—makes use of a state machine to detect when the appliance has been turned on or off. Then, machine learning is used to identify the appliance, for which attributes are extracted from the Conservative Power Theory (CPT), a contemporary power theory that enables comprehensive load modeling. Finally, considering simulation and experimental results, this paper shows that the new method is able to achieve 95% accuracy considering the applied data set. |
id |
UNSP_59098a2287cd183300dc96b1a3c41d34 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/190485 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Load disaggregation using microscopic power features and pattern recognitionArtificial intelligenceCognitive metersLoad disaggregationMachine learningNILMState machineA new generation of smart meters are called cognitive meters, which are essentially based on Artificial Intelligence (AI) and load disaggregation methods for Non-Intrusive Load Monitoring (NILM). Thus, modern NILM may recognize appliances connected to the grid during certain periods, while providing much more information than the traditional monthly consumption. Therefore, this article presents a new load disaggregation methodology with microscopic characteristics collected from current and voltage waveforms. Initially, the novel NILM algorithm—called the Power Signature Blob (PSB)—makes use of a state machine to detect when the appliance has been turned on or off. Then, machine learning is used to identify the appliance, for which attributes are extracted from the Conservative Power Theory (CPT), a contemporary power theory that enables comprehensive load modeling. Finally, considering simulation and experimental results, this paper shows that the new method is able to achieve 95% accuracy considering the applied data set.Department of Computer Science Federal University of São Carlos (UFSCar)Institute of Science and Technology of Sorocaba São Paulo State University (UNESP)School of Electrical and Computer Engineering (FEEC) University of Campinas (UNICAMP)Department of Electrical Engineering Colorado School of MinesInstitute of Science and Technology of Sorocaba São Paulo State University (UNESP)Universidade Federal de São Carlos (UFSCar)Universidade Estadual Paulista (Unesp)Universidade Estadual de Campinas (UNICAMP)Colorado School of Minesde Souza, Wesley AngelinoGarcia, Fernando Deluno [UNESP]Marafão, Fernando Pinhabel [UNESP]Da Silva, Luiz Carlos PereiraSimões, Marcelo Godoy2019-10-06T17:14:42Z2019-10-06T17:14:42Z2019-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/en12142641Energies, v. 12, n. 14, 2019.1996-1073http://hdl.handle.net/11449/19048510.3390/en121426412-s2.0-85068766271Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengEnergiesinfo:eu-repo/semantics/openAccess2021-10-22T23:59:52Zoai:repositorio.unesp.br:11449/190485Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-22T23:59:52Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Load disaggregation using microscopic power features and pattern recognition |
title |
Load disaggregation using microscopic power features and pattern recognition |
spellingShingle |
Load disaggregation using microscopic power features and pattern recognition de Souza, Wesley Angelino Artificial intelligence Cognitive meters Load disaggregation Machine learning NILM State machine |
title_short |
Load disaggregation using microscopic power features and pattern recognition |
title_full |
Load disaggregation using microscopic power features and pattern recognition |
title_fullStr |
Load disaggregation using microscopic power features and pattern recognition |
title_full_unstemmed |
Load disaggregation using microscopic power features and pattern recognition |
title_sort |
Load disaggregation using microscopic power features and pattern recognition |
author |
de Souza, Wesley Angelino |
author_facet |
de Souza, Wesley Angelino Garcia, Fernando Deluno [UNESP] Marafão, Fernando Pinhabel [UNESP] Da Silva, Luiz Carlos Pereira Simões, Marcelo Godoy |
author_role |
author |
author2 |
Garcia, Fernando Deluno [UNESP] Marafão, Fernando Pinhabel [UNESP] Da Silva, Luiz Carlos Pereira Simões, Marcelo Godoy |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de São Carlos (UFSCar) Universidade Estadual Paulista (Unesp) Universidade Estadual de Campinas (UNICAMP) Colorado School of Mines |
dc.contributor.author.fl_str_mv |
de Souza, Wesley Angelino Garcia, Fernando Deluno [UNESP] Marafão, Fernando Pinhabel [UNESP] Da Silva, Luiz Carlos Pereira Simões, Marcelo Godoy |
dc.subject.por.fl_str_mv |
Artificial intelligence Cognitive meters Load disaggregation Machine learning NILM State machine |
topic |
Artificial intelligence Cognitive meters Load disaggregation Machine learning NILM State machine |
description |
A new generation of smart meters are called cognitive meters, which are essentially based on Artificial Intelligence (AI) and load disaggregation methods for Non-Intrusive Load Monitoring (NILM). Thus, modern NILM may recognize appliances connected to the grid during certain periods, while providing much more information than the traditional monthly consumption. Therefore, this article presents a new load disaggregation methodology with microscopic characteristics collected from current and voltage waveforms. Initially, the novel NILM algorithm—called the Power Signature Blob (PSB)—makes use of a state machine to detect when the appliance has been turned on or off. Then, machine learning is used to identify the appliance, for which attributes are extracted from the Conservative Power Theory (CPT), a contemporary power theory that enables comprehensive load modeling. Finally, considering simulation and experimental results, this paper shows that the new method is able to achieve 95% accuracy considering the applied data set. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-10-06T17:14:42Z 2019-10-06T17:14:42Z 2019-01-01 |
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/10.3390/en12142641 Energies, v. 12, n. 14, 2019. 1996-1073 http://hdl.handle.net/11449/190485 10.3390/en12142641 2-s2.0-85068766271 |
url |
http://dx.doi.org/10.3390/en12142641 http://hdl.handle.net/11449/190485 |
identifier_str_mv |
Energies, v. 12, n. 14, 2019. 1996-1073 10.3390/en12142641 2-s2.0-85068766271 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Energies |
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_ |
1799964942356447232 |