Publicação
Previsão da potência média produzida por turbinas eólicas utilizando redes neurais
| Resumo: | This thesis presents the development and evaluation of artificial neural network models applied to short-term wind power generation forecasting in a wind farm. The main objective of the study was to explore the performance of Multi-Layer Perceptron (MLP) and Long Short-Term Memory (LSTM) architectures, using real data from wind turbines collected by SCADA systems between 2016 and 2017 in Portugal. Data preprocessing included normalization techniques, seasonal decomposition, and the construction of sliding windows for temporal modeling. Several configurations of MLP and LSTM were implemented, varying in the number of neurons, hidden layers, and training strategies, including early stopping and different data partitioning approaches. The evaluation employed statistical metrics to assess forecasting accuracy, including RMSE, NRMSE, and R2. Early stopping and randomized data splits were analyzed to enhance model performance and robustness. The models achieved results above 83% for the coefficient of determination (R2). The main objective of this work was to develop MLP and LSTM models capable of accurately predicting the average power output of a wind turbine in a short-term horizon. To achieve this, different layer configurations, neuron counts, and validation techniques were tested for both approaches. Additionally, both single-variable and multivariable inputs were considered for the LSTM models. Finally, the three best-performing models were selected based on the evaluation metrics and compared with existing studies in the literature. |
|---|---|
| Autores principais: | Campos, Letícia Góes |
| Assunto: | Artificial neural networks Wind power Multi-layer perceptron Python Forecasting Time series prediction LSTM |
| Ano: | 2025 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Instituto Politécnico de Bragança |
| Idioma: | português |
| Origem: | Biblioteca Digital do IPB |
| _version_ | 1867173294966308864 |
|---|---|
| author | Campos, Letícia Góes |
| author_facet | Campos, Letícia Góes |
| author_role | author |
| contributor_name_str_mv | Teixeira, João Teixeira Poubel , Raphael Paulo Braga Biblioteca Digital do IPB |
| country_str | PT |
| creators_json_txt | [{\"Person.name\":\"Campos, Letícia Góes\"}] |
| datacite.contributors.contributor.contributorName.fl_str_mv | Teixeira, João Teixeira Poubel , Raphael Paulo Braga Biblioteca Digital do IPB |
| datacite.creators.creator.creatorName.fl_str_mv | Campos, Letícia Góes |
| datacite.date.Accepted.fl_str_mv | 2025-01-01T00:00:00Z |
| datacite.date.available.fl_str_mv | 2025-11-11T14:54:34Z |
| datacite.date.embargoed.fl_str_mv | 2025-11-11T14:54:34Z |
| datacite.rights.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| datacite.subjects.subject.fl_str_mv | Artificial neural networks Wind power Multi-layer perceptron Python Forecasting Time series prediction LSTM |
| datacite.titles.title.fl_str_mv | Previsão da potência média produzida por turbinas eólicas utilizando redes neurais |
| dc.contributor.none.fl_str_mv | Teixeira, João Teixeira Poubel , Raphael Paulo Braga Biblioteca Digital do IPB |
| dc.creator.none.fl_str_mv | Campos, Letícia Góes |
| dc.date.Accepted.fl_str_mv | 2025-01-01T00:00:00Z |
| dc.date.available.fl_str_mv | 2025-11-11T14:54:34Z |
| dc.date.embargoed.fl_str_mv | 2025-11-11T14:54:34Z |
| dc.format.none.fl_str_mv | application/pdf |
| dc.identifier.none.fl_str_mv | http://hdl.handle.net/10198/35036 |
| dc.language.none.fl_str_mv | por |
| dc.rights.cclincense.fl_str_mv | http://creativecommons.org/licenses/by/4.0/ |
| dc.rights.none.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| dc.subject.none.fl_str_mv | Artificial neural networks Wind power Multi-layer perceptron Python Forecasting Time series prediction LSTM |
| dc.title.fl_str_mv | Previsão da potência média produzida por turbinas eólicas utilizando redes neurais |
| dc.type.none.fl_str_mv | http://purl.org/coar/resource_type/c_bdcc |
| description | This thesis presents the development and evaluation of artificial neural network models applied to short-term wind power generation forecasting in a wind farm. The main objective of the study was to explore the performance of Multi-Layer Perceptron (MLP) and Long Short-Term Memory (LSTM) architectures, using real data from wind turbines collected by SCADA systems between 2016 and 2017 in Portugal. Data preprocessing included normalization techniques, seasonal decomposition, and the construction of sliding windows for temporal modeling. Several configurations of MLP and LSTM were implemented, varying in the number of neurons, hidden layers, and training strategies, including early stopping and different data partitioning approaches. The evaluation employed statistical metrics to assess forecasting accuracy, including RMSE, NRMSE, and R2. Early stopping and randomized data splits were analyzed to enhance model performance and robustness. The models achieved results above 83% for the coefficient of determination (R2). The main objective of this work was to develop MLP and LSTM models capable of accurately predicting the average power output of a wind turbine in a short-term horizon. To achieve this, different layer configurations, neuron counts, and validation techniques were tested for both approaches. Additionally, both single-variable and multivariable inputs were considered for the LSTM models. Finally, the three best-performing models were selected based on the evaluation metrics and compared with existing studies in the literature. |
| dirty | 0 |
| eu_rights_str_mv | openAccess |
| format | masterThesis |
| fulltext.url.fl_str_mv | https://bibliotecadigital.ipb.pt/bitstreams/7a99dca9-05a5-43c9-a303-eb710d14ede3/download |
| id | ipb_9d2b03d60cefac849a31abce80cd5ffe |
| identifier.url.fl_str_mv | http://hdl.handle.net/10198/35036 |
| instacron_str | ipb |
| institution | Instituto Politécnico de Bragança |
| instname_str | Instituto Politécnico de Bragança |
| language | por |
| network_acronym_str | ipb |
| network_name_str | Biblioteca Digital do IPB |
| oai_identifier_str | oai:bibliotecadigital.ipb.pt:10198/35036 |
| organization_str_mv | urn:organizationAcronym:ipb |
| person_str_mv | Campos, Letícia Góes |
| publishDate | 2025 |
| reponame_str | Biblioteca Digital do IPB |
| repository_id_str | urn:repositoryAcronym:ipb |
| service_str_mv | urn:repositoryAcronym:ipb |
| spelling | porporThis thesis presents the development and evaluation of artificial neural network models applied to short-term wind power generation forecasting in a wind farm. The main objective of the study was to explore the performance of Multi-Layer Perceptron (MLP) and Long Short-Term Memory (LSTM) architectures, using real data from wind turbines collected by SCADA systems between 2016 and 2017 in Portugal. Data preprocessing included normalization techniques, seasonal decomposition, and the construction of sliding windows for temporal modeling. Several configurations of MLP and LSTM were implemented, varying in the number of neurons, hidden layers, and training strategies, including early stopping and different data partitioning approaches. The evaluation employed statistical metrics to assess forecasting accuracy, including RMSE, NRMSE, and R2. Early stopping and randomized data splits were analyzed to enhance model performance and robustness. The models achieved results above 83% for the coefficient of determination (R2). The main objective of this work was to develop MLP and LSTM models capable of accurately predicting the average power output of a wind turbine in a short-term horizon. To achieve this, different layer configurations, neuron counts, and validation techniques were tested for both approaches. Additionally, both single-variable and multivariable inputs were considered for the LSTM models. Finally, the three best-performing models were selected based on the evaluation metrics and compared with existing studies in the literature.application/pdfPrevisão da potência média produzida por turbinas eólicas utilizando redes neuraisCampos, Letícia GóesTeixeira, João TeixeiraPoubel , Raphael Paulo BragaHostingInstitutionOrganizationalBiblioteca Digital do IPBe-mailmailto:dspace@ipb.ptdspace@ipb.ptURNurn:tid:2040452662025-11-11T14:54:34Z202520252025-01-01T00:00:00ZHandlehttp://hdl.handle.net/10198/35036http://purl.org/coar/access_right/c_abf2open accessArtificial neural networksWind powerMulti-layer perceptronPythonForecastingTime series predictionLSTM2252894 bytesliteraturehttp://purl.org/coar/resource_type/c_bdccmaster thesis2025http://creativecommons.org/licenses/by/4.0/http://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://bibliotecadigital.ipb.pt/bitstreams/7a99dca9-05a5-43c9-a303-eb710d14ede3/download |
| spellingShingle | Previsão da potência média produzida por turbinas eólicas utilizando redes neurais Campos, Letícia Góes Artificial neural networks Wind power Multi-layer perceptron Python Forecasting Time series prediction LSTM |
| status | SINGLETON |
| subject.fl_str_mv | Artificial neural networks Wind power Multi-layer perceptron Python Forecasting Time series prediction LSTM |
| title | Previsão da potência média produzida por turbinas eólicas utilizando redes neurais |
| title_full | Previsão da potência média produzida por turbinas eólicas utilizando redes neurais |
| title_fullStr | Previsão da potência média produzida por turbinas eólicas utilizando redes neurais |
| title_full_unstemmed | Previsão da potência média produzida por turbinas eólicas utilizando redes neurais |
| title_short | Previsão da potência média produzida por turbinas eólicas utilizando redes neurais |
| title_sort | Previsão da potência média produzida por turbinas eólicas utilizando redes neurais |
| topic | Artificial neural networks Wind power Multi-layer perceptron Python Forecasting Time series prediction LSTM |
| topic_facet | Artificial neural networks Wind power Multi-layer perceptron Python Forecasting Time series prediction LSTM |
| url | http://hdl.handle.net/10198/35036 |
| visible | 1 |