Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.8/7759 |
Resumo: | Solar panels can generate energy to meet almost all of the energy needs of a house. Batteries store energy generated during daylight hours for future use. Also, it may be possible to sell extra electricity back to distribution companies. However, the efficiency of photovoltaic systems varies according to several factors, such as the solar exposition at ground levels, atmospheric temperature, and relative humidity, and predicting the energy generated by such a system is not easy. This work is on the use of deep learning to predict the generation of photovoltaic energy by residential systems. We use real-world data to evaluate the performance of LSTM, Convolutional, and hybrid Convolutional-LSTM networks in predicting photovoltaic power generation at different forecasting horizons. We also assess the generalizability of the solutions, evaluating the use of models trained with data aggregated by geographic areas to predict the energy generation by individual systems. We compare the performance of deep networks with Prophet in terms of MAE, RMSE, and NRMSE, and in most cases, Convolutional and Convolutional-LSTM networks achieve the best results. Using models trained with region-based data to predict the power generation of individual systems is confirmed to be a promising approach. |
id |
RCAP_70dceceafa766cb403011886d2d403e2 |
---|---|
oai_identifier_str |
oai:iconline.ipleiria.pt:10400.8/7759 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generationTime series forecastingPhotovoltaic power generationDeep learningLSTMConvolutional neural networksSolar panels can generate energy to meet almost all of the energy needs of a house. Batteries store energy generated during daylight hours for future use. Also, it may be possible to sell extra electricity back to distribution companies. However, the efficiency of photovoltaic systems varies according to several factors, such as the solar exposition at ground levels, atmospheric temperature, and relative humidity, and predicting the energy generated by such a system is not easy. This work is on the use of deep learning to predict the generation of photovoltaic energy by residential systems. We use real-world data to evaluate the performance of LSTM, Convolutional, and hybrid Convolutional-LSTM networks in predicting photovoltaic power generation at different forecasting horizons. We also assess the generalizability of the solutions, evaluating the use of models trained with data aggregated by geographic areas to predict the energy generation by individual systems. We compare the performance of deep networks with Prophet in terms of MAE, RMSE, and NRMSE, and in most cases, Convolutional and Convolutional-LSTM networks achieve the best results. Using models trained with region-based data to predict the power generation of individual systems is confirmed to be a promising approach.ElsevierIC-OnlineCosta, Rogério Luís de C.2022-10-11T13:16:30Z2022-112022-10-10T09:39:06Z2022-11-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.8/7759engCosta, Rogério Luís de C. (2022). Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation. Engineering Applications of Artificial Intelligence, 116. https://doi.org/10.1016/j.engappai.2022.1054580952-1976cv-prod-3056327https://doi.org/10.1016/j.engappai.2022.105458info: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:RCAAP2024-01-17T15:55:53Zoai:iconline.ipleiria.pt:10400.8/7759Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T01:50:38.012131Repositório 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 |
Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation |
title |
Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation |
spellingShingle |
Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation Costa, Rogério Luís de C. Time series forecasting Photovoltaic power generation Deep learning LSTM Convolutional neural networks |
title_short |
Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation |
title_full |
Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation |
title_fullStr |
Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation |
title_full_unstemmed |
Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation |
title_sort |
Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation |
author |
Costa, Rogério Luís de C. |
author_facet |
Costa, Rogério Luís de C. |
author_role |
author |
dc.contributor.none.fl_str_mv |
IC-Online |
dc.contributor.author.fl_str_mv |
Costa, Rogério Luís de C. |
dc.subject.por.fl_str_mv |
Time series forecasting Photovoltaic power generation Deep learning LSTM Convolutional neural networks |
topic |
Time series forecasting Photovoltaic power generation Deep learning LSTM Convolutional neural networks |
description |
Solar panels can generate energy to meet almost all of the energy needs of a house. Batteries store energy generated during daylight hours for future use. Also, it may be possible to sell extra electricity back to distribution companies. However, the efficiency of photovoltaic systems varies according to several factors, such as the solar exposition at ground levels, atmospheric temperature, and relative humidity, and predicting the energy generated by such a system is not easy. This work is on the use of deep learning to predict the generation of photovoltaic energy by residential systems. We use real-world data to evaluate the performance of LSTM, Convolutional, and hybrid Convolutional-LSTM networks in predicting photovoltaic power generation at different forecasting horizons. We also assess the generalizability of the solutions, evaluating the use of models trained with data aggregated by geographic areas to predict the energy generation by individual systems. We compare the performance of deep networks with Prophet in terms of MAE, RMSE, and NRMSE, and in most cases, Convolutional and Convolutional-LSTM networks achieve the best results. Using models trained with region-based data to predict the power generation of individual systems is confirmed to be a promising approach. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-10-11T13:16:30Z 2022-11 2022-10-10T09:39:06Z 2022-11-01T00:00:00Z |
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://hdl.handle.net/10400.8/7759 |
url |
http://hdl.handle.net/10400.8/7759 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Costa, Rogério Luís de C. (2022). Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation. Engineering Applications of Artificial Intelligence, 116. https://doi.org/10.1016/j.engappai.2022.105458 0952-1976 cv-prod-3056327 https://doi.org/10.1016/j.engappai.2022.105458 |
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.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
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_ |
1799136998836928512 |