Non-intrusive load monitoring applied to a home energy management system
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10773/39399 |
Resumo: | In recent years, there’s been a huge advancement in the field of the Internet of Things (IoT), this is due to the information that these systems are able to report and the automation that they can provide, but this comes with a problem. The abundance of these equipment’s has risen energy consumption by manyfold since there are now appliances in every corner of a household. One way to reduce this high consumption is by increasing the energetic literacy of homeowners. This need for teaching energetic demands allied with the need to reduce global energy consumption leads way for solutions such as Nonintrusive Load Monitoring (NILM) to appear. This solution collects the data of a given household in a nonintrusive fashion and then performs what is called energy disaggregation, which is the individualization of an appliance’s electrical readings from an aggregate reading. Inserted in a project, the proposition of this dissertation is to develop models that provide a good NILM solution and convert this solution to a functioning Home Energy Management System (HEMS). The hypothesis we wanted to test with this work was to verify that the average results for an ensemble would yield better results than the individual models contained in the ensemble. After validating this argument, we proposed two ensemble models, which we named Appliance Specific Ensembles (ASE) and then evaluate them with the other top-performing NILM models. Here we discover that our models outperform the best individual model of the state-of-the-art in two out of five appliances. We also proved that our ensembles are more resilient and fault-tolerant than the individual models contained in them, as some models would fail to correctly predict the usage and only predict a constant value. Using these models for predictions on different homes also yielded good and consistent results for our proposed ASE models, which is possible to visualize on our developed HEMS platform. |
id |
RCAP_e7a7179c04a94cf04c82e95c8819cd3d |
---|---|
oai_identifier_str |
oai:ria.ua.pt:10773/39399 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Non-intrusive load monitoring applied to a home energy management systemNon-Intrusive Load MonitoringEnergy disaggregationHome energy management systemsMachine learningRecurrent neural networksConvolutional neural networksEnsemble learningIn recent years, there’s been a huge advancement in the field of the Internet of Things (IoT), this is due to the information that these systems are able to report and the automation that they can provide, but this comes with a problem. The abundance of these equipment’s has risen energy consumption by manyfold since there are now appliances in every corner of a household. One way to reduce this high consumption is by increasing the energetic literacy of homeowners. This need for teaching energetic demands allied with the need to reduce global energy consumption leads way for solutions such as Nonintrusive Load Monitoring (NILM) to appear. This solution collects the data of a given household in a nonintrusive fashion and then performs what is called energy disaggregation, which is the individualization of an appliance’s electrical readings from an aggregate reading. Inserted in a project, the proposition of this dissertation is to develop models that provide a good NILM solution and convert this solution to a functioning Home Energy Management System (HEMS). The hypothesis we wanted to test with this work was to verify that the average results for an ensemble would yield better results than the individual models contained in the ensemble. After validating this argument, we proposed two ensemble models, which we named Appliance Specific Ensembles (ASE) and then evaluate them with the other top-performing NILM models. Here we discover that our models outperform the best individual model of the state-of-the-art in two out of five appliances. We also proved that our ensembles are more resilient and fault-tolerant than the individual models contained in them, as some models would fail to correctly predict the usage and only predict a constant value. Using these models for predictions on different homes also yielded good and consistent results for our proposed ASE models, which is possible to visualize on our developed HEMS platform.Nos últimos anos houve um grande avanço no campo da Internet of Things (IoT), isto devido às informações que estes sistemas são capazes de relatar e a automação que eles fornecem. No entanto, isto vem com um problema. A abundância destes equipamentos aumentou substancialmente o consumo de energia, uma vez que agora existem aparelhos em todos os cantos de uma casa. Uma forma de reduzir esse alto consumo é aumentando a literacia energética dos proprietários das casas. Essa necessidade de ensinar literacia energética juntamente com a necessidade de reduzir o consumo global de energia abre caminho para soluções como Non Intrusive Load Monitoring (NILM). Esta solução recolhe os dados de um determinado agregado familiar de forma não intrusiva e, em seguida, realiza o que se chama desagregação de energia, que é a individualização das leituras energéticas de um aparelho a partir de uma leitura agregada de todos os equipamentos. Inserido num projeto, a proposta desta dissertação é desenvolver modelos que providenciem uma boa solução NILM e por fim traduzam esta solução num Home Energy Management System (HEMS). A hipótese que queríamos testar com este trabalho era verificar se os resultados médios de um ensemble produziam melhores resultados do que os modelos individuais contidos nele. Depois de validar este argumento, propusemos dois modelos de ensemble, que nomeamos Appliance Specific Ensembles (ASE) e depois avaliamos estes modelos com os outros modelos state-of-the-art de NILM. Aqui descobrimos que os nossos modelos superam o melhor modelo individual state-of-the-art em dois de cinco aparelhos. Provamos também que os nossos ensembles são mais resistentes e tolerantes a falhas do que os modelos individuais neles contidos. Isto foi comprovado dado que alguns dos modelos falharam em prever corretamente o uso e apenas previam um valor constante. Os nossos modelos propostos (ASE) tiveram resultados bons e consistentes para previsões em diferentes casas, algo que foi possível visualizar na plataforma HEMS desenvolvida.2024-12-12T00:00:00Z2022-12-07T00:00:00Z2022-12-07info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/39399engCosta, Tomás Oliveira dainfo:eu-repo/semantics/embargoedAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-22T12:16:56Zoai:ria.ua.pt:10773/39399Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:09:35.112513Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Non-intrusive load monitoring applied to a home energy management system |
title |
Non-intrusive load monitoring applied to a home energy management system |
spellingShingle |
Non-intrusive load monitoring applied to a home energy management system Costa, Tomás Oliveira da Non-Intrusive Load Monitoring Energy disaggregation Home energy management systems Machine learning Recurrent neural networks Convolutional neural networks Ensemble learning |
title_short |
Non-intrusive load monitoring applied to a home energy management system |
title_full |
Non-intrusive load monitoring applied to a home energy management system |
title_fullStr |
Non-intrusive load monitoring applied to a home energy management system |
title_full_unstemmed |
Non-intrusive load monitoring applied to a home energy management system |
title_sort |
Non-intrusive load monitoring applied to a home energy management system |
author |
Costa, Tomás Oliveira da |
author_facet |
Costa, Tomás Oliveira da |
author_role |
author |
dc.contributor.author.fl_str_mv |
Costa, Tomás Oliveira da |
dc.subject.por.fl_str_mv |
Non-Intrusive Load Monitoring Energy disaggregation Home energy management systems Machine learning Recurrent neural networks Convolutional neural networks Ensemble learning |
topic |
Non-Intrusive Load Monitoring Energy disaggregation Home energy management systems Machine learning Recurrent neural networks Convolutional neural networks Ensemble learning |
description |
In recent years, there’s been a huge advancement in the field of the Internet of Things (IoT), this is due to the information that these systems are able to report and the automation that they can provide, but this comes with a problem. The abundance of these equipment’s has risen energy consumption by manyfold since there are now appliances in every corner of a household. One way to reduce this high consumption is by increasing the energetic literacy of homeowners. This need for teaching energetic demands allied with the need to reduce global energy consumption leads way for solutions such as Nonintrusive Load Monitoring (NILM) to appear. This solution collects the data of a given household in a nonintrusive fashion and then performs what is called energy disaggregation, which is the individualization of an appliance’s electrical readings from an aggregate reading. Inserted in a project, the proposition of this dissertation is to develop models that provide a good NILM solution and convert this solution to a functioning Home Energy Management System (HEMS). The hypothesis we wanted to test with this work was to verify that the average results for an ensemble would yield better results than the individual models contained in the ensemble. After validating this argument, we proposed two ensemble models, which we named Appliance Specific Ensembles (ASE) and then evaluate them with the other top-performing NILM models. Here we discover that our models outperform the best individual model of the state-of-the-art in two out of five appliances. We also proved that our ensembles are more resilient and fault-tolerant than the individual models contained in them, as some models would fail to correctly predict the usage and only predict a constant value. Using these models for predictions on different homes also yielded good and consistent results for our proposed ASE models, which is possible to visualize on our developed HEMS platform. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-12-07T00:00:00Z 2022-12-07 2024-12-12T00:00:00Z |
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.uri.fl_str_mv |
http://hdl.handle.net/10773/39399 |
url |
http://hdl.handle.net/10773/39399 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/embargoedAccess |
eu_rights_str_mv |
embargoedAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799137746388779008 |