Short-Term Electricity Demand Forecasting with Machine Learning

Detalhes bibliográficos
Autor(a) principal: Madrid, Ernesto Javier Aguilar
Data de Publicação: 2021
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/120626
Resumo: Project Work presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics
id RCAP_05841080a5c5aafa9018e8905757f35f
oai_identifier_str oai:run.unl.pt:10362/120626
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Short-Term Electricity Demand Forecasting with Machine LearningShort-Term Load Forecasting;Machine Learning;Weekly forecast;Electricity market;Extreme Gradient Boosting Regressor (XGBoost)Project Work presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business AnalyticsAn accurate short-term load forecasting (STLF) is one of the most critical inputs for power plant units’ planning commitment. STLF reduces the overall planning uncertainty added by the intermittent production of renewable sources; thus, it helps to minimize the hydro-thermal electricity production costs in a power grid. Although there is some research in the field and even several research applications, there is a continual need to improve forecasts. This project proposes a set of machine learning (ML) models to improve the accuracy of 168 hours forecasts. The developed models employ features from multiple sources, such as historical load, weather, and holidays. Of the five ML models developed and tested in various load profile contexts, the Extreme Gradient Boosting Regressor (XGBoost) algorithm showed the best results, surpassing previous historical weekly predictions based on neural networks. Additionally, because XGBoost models are based on an ensemble of decision trees, it facilitated the model’s interpretation, which provided a relevant additional result, the features’ importance in the forecasting.António, Nuno Miguel da ConceiçãoRUNMadrid, Ernesto Javier Aguilar2021-07-07T11:44:07Z2021-06-232021-06-23T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/120626TID:202743420enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:03:07Zoai:run.unl.pt:10362/120626Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:44:24.539905Repositório 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 Short-Term Electricity Demand Forecasting with Machine Learning
title Short-Term Electricity Demand Forecasting with Machine Learning
spellingShingle Short-Term Electricity Demand Forecasting with Machine Learning
Madrid, Ernesto Javier Aguilar
Short-Term Load Forecasting;
Machine Learning;
Weekly forecast;
Electricity market;
Extreme Gradient Boosting Regressor (XGBoost)
title_short Short-Term Electricity Demand Forecasting with Machine Learning
title_full Short-Term Electricity Demand Forecasting with Machine Learning
title_fullStr Short-Term Electricity Demand Forecasting with Machine Learning
title_full_unstemmed Short-Term Electricity Demand Forecasting with Machine Learning
title_sort Short-Term Electricity Demand Forecasting with Machine Learning
author Madrid, Ernesto Javier Aguilar
author_facet Madrid, Ernesto Javier Aguilar
author_role author
dc.contributor.none.fl_str_mv António, Nuno Miguel da Conceição
RUN
dc.contributor.author.fl_str_mv Madrid, Ernesto Javier Aguilar
dc.subject.por.fl_str_mv Short-Term Load Forecasting;
Machine Learning;
Weekly forecast;
Electricity market;
Extreme Gradient Boosting Regressor (XGBoost)
topic Short-Term Load Forecasting;
Machine Learning;
Weekly forecast;
Electricity market;
Extreme Gradient Boosting Regressor (XGBoost)
description Project Work presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics
publishDate 2021
dc.date.none.fl_str_mv 2021-07-07T11:44:07Z
2021-06-23
2021-06-23T00:00:00Z
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/10362/120626
TID:202743420
url http://hdl.handle.net/10362/120626
identifier_str_mv TID:202743420
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
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_ 1799138051610378240

Registros relacionados