Artificial neural network-based short-term demand forecaster.
Autor(a) principal: | |
---|---|
Data de Publicação: | 2003 |
Outros Autores: | , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFOP |
Texto Completo: | http://www.repositorio.ufop.br/handle/123456789/1196 |
Resumo: | The importance of Short-Term Load Forecasting (STLF) has been increasing lately. With deregulation and competition, energy price forecasting has become a big business. Bus load forecasting is essential to feed analytical methods utilized for determining energy prices. The variability and non-stationarity of loads are becoming worse due to the dynamics of energy tariffs. Besides, the number of nodal loads to be predicted does not allow frequent interventions from load forecasting experts. More autonomous load predictors are needed in the new competitive scenario. The application of neural network-based STLF has developed sophisticated practical systems over the years. However, the question of how to maximize the generalization ability of such machines, together with the choice of architecture, activation functions, training set data and size, etc. makes up a huge number of possible combinations for the final Neural Network (NN) design, whose optimal solution has not been figured yet. This paper describes a STLF system which uses a non-parametric model based on a linear model coupled with a polynomial network, identified by pruning/growing mechanisms. The load forecaster has special features of data preprocessing and confidence intervals calculations, which are also described. Results of load forecasts are presented for one year with forecasting horizons from 15 min. to 168 hours ahead |
id |
UFOP_249a9a431f5b26330ea3e5f468a2ec72 |
---|---|
oai_identifier_str |
oai:localhost:123456789/1196 |
network_acronym_str |
UFOP |
network_name_str |
Repositório Institucional da UFOP |
repository_id_str |
3233 |
spelling |
Silva, Alexandre Pinto Alves daRodrigues, Ubiratan de PaulaReis, Agnaldo José da RochaMoulin, Luciano SouzaNascimento, Paulo Cesar do2012-07-24T17:04:56Z2012-07-24T17:04:56Z2003SILVA, A. P. A. da et al. Artificial neural network-based short-term demand forecaster. In. 5th Latin-American Congress: Eletricity Generation and Transmission (CLGAGTEE), 5., 2003. São Pedro, SP. Anais... Guaratinguetá: Book of Abstracts and Proceedings of 5 Latin-American Congress: Electricity Generation and Transmission, 2003. Disponível em: <http://www.seeds.usp.br/pir/arquivos/congressos/CLAGTEE2003/Papers/ELF%20B-210.pdf>. Acesso em: 24 jul. 2012.8590347117http://www.repositorio.ufop.br/handle/123456789/1196The importance of Short-Term Load Forecasting (STLF) has been increasing lately. With deregulation and competition, energy price forecasting has become a big business. Bus load forecasting is essential to feed analytical methods utilized for determining energy prices. The variability and non-stationarity of loads are becoming worse due to the dynamics of energy tariffs. Besides, the number of nodal loads to be predicted does not allow frequent interventions from load forecasting experts. More autonomous load predictors are needed in the new competitive scenario. The application of neural network-based STLF has developed sophisticated practical systems over the years. However, the question of how to maximize the generalization ability of such machines, together with the choice of architecture, activation functions, training set data and size, etc. makes up a huge number of possible combinations for the final Neural Network (NN) design, whose optimal solution has not been figured yet. This paper describes a STLF system which uses a non-parametric model based on a linear model coupled with a polynomial network, identified by pruning/growing mechanisms. The load forecaster has special features of data preprocessing and confidence intervals calculations, which are also described. Results of load forecasts are presented for one year with forecasting horizons from 15 min. to 168 hours aheadArtificial neural network-based short-term demand forecaster.info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjectengreponame:Repositório Institucional da UFOPinstname:Universidade Federal de Ouro Preto (UFOP)instacron:UFOPinfo:eu-repo/semantics/openAccessLICENSElicense.txtlicense.txttext/plain; charset=utf-81748http://www.repositorio.ufop.br/bitstream/123456789/1196/5/license.txt8a4605be74aa9ea9d79846c1fba20a33MD55ORIGINALEVENTO_ArtificialNeuralNetwork.pdfEVENTO_ArtificialNeuralNetwork.pdfapplication/pdf493501http://www.repositorio.ufop.br/bitstream/123456789/1196/1/EVENTO_ArtificialNeuralNetwork.pdf8c0fc6d147185173ac3d90fb6f67c7fcMD51123456789/11962019-02-28 09:41:00.896oai:localhost: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Repositório InstitucionalPUBhttp://www.repositorio.ufop.br/oai/requestrepositorio@ufop.edu.bropendoar:32332019-02-28T14:41Repositório Institucional da UFOP - Universidade Federal de Ouro Preto (UFOP)false |
dc.title.pt_BR.fl_str_mv |
Artificial neural network-based short-term demand forecaster. |
title |
Artificial neural network-based short-term demand forecaster. |
spellingShingle |
Artificial neural network-based short-term demand forecaster. Silva, Alexandre Pinto Alves da |
title_short |
Artificial neural network-based short-term demand forecaster. |
title_full |
Artificial neural network-based short-term demand forecaster. |
title_fullStr |
Artificial neural network-based short-term demand forecaster. |
title_full_unstemmed |
Artificial neural network-based short-term demand forecaster. |
title_sort |
Artificial neural network-based short-term demand forecaster. |
author |
Silva, Alexandre Pinto Alves da |
author_facet |
Silva, Alexandre Pinto Alves da Rodrigues, Ubiratan de Paula Reis, Agnaldo José da Rocha Moulin, Luciano Souza Nascimento, Paulo Cesar do |
author_role |
author |
author2 |
Rodrigues, Ubiratan de Paula Reis, Agnaldo José da Rocha Moulin, Luciano Souza Nascimento, Paulo Cesar do |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Silva, Alexandre Pinto Alves da Rodrigues, Ubiratan de Paula Reis, Agnaldo José da Rocha Moulin, Luciano Souza Nascimento, Paulo Cesar do |
description |
The importance of Short-Term Load Forecasting (STLF) has been increasing lately. With deregulation and competition, energy price forecasting has become a big business. Bus load forecasting is essential to feed analytical methods utilized for determining energy prices. The variability and non-stationarity of loads are becoming worse due to the dynamics of energy tariffs. Besides, the number of nodal loads to be predicted does not allow frequent interventions from load forecasting experts. More autonomous load predictors are needed in the new competitive scenario. The application of neural network-based STLF has developed sophisticated practical systems over the years. However, the question of how to maximize the generalization ability of such machines, together with the choice of architecture, activation functions, training set data and size, etc. makes up a huge number of possible combinations for the final Neural Network (NN) design, whose optimal solution has not been figured yet. This paper describes a STLF system which uses a non-parametric model based on a linear model coupled with a polynomial network, identified by pruning/growing mechanisms. The load forecaster has special features of data preprocessing and confidence intervals calculations, which are also described. Results of load forecasts are presented for one year with forecasting horizons from 15 min. to 168 hours ahead |
publishDate |
2003 |
dc.date.issued.fl_str_mv |
2003 |
dc.date.accessioned.fl_str_mv |
2012-07-24T17:04:56Z |
dc.date.available.fl_str_mv |
2012-07-24T17:04:56Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
SILVA, A. P. A. da et al. Artificial neural network-based short-term demand forecaster. In. 5th Latin-American Congress: Eletricity Generation and Transmission (CLGAGTEE), 5., 2003. São Pedro, SP. Anais... Guaratinguetá: Book of Abstracts and Proceedings of 5 Latin-American Congress: Electricity Generation and Transmission, 2003. Disponível em: <http://www.seeds.usp.br/pir/arquivos/congressos/CLAGTEE2003/Papers/ELF%20B-210.pdf>. Acesso em: 24 jul. 2012. |
dc.identifier.uri.fl_str_mv |
http://www.repositorio.ufop.br/handle/123456789/1196 |
dc.identifier.isbn.none.fl_str_mv |
8590347117 |
identifier_str_mv |
SILVA, A. P. A. da et al. Artificial neural network-based short-term demand forecaster. In. 5th Latin-American Congress: Eletricity Generation and Transmission (CLGAGTEE), 5., 2003. São Pedro, SP. Anais... Guaratinguetá: Book of Abstracts and Proceedings of 5 Latin-American Congress: Electricity Generation and Transmission, 2003. Disponível em: <http://www.seeds.usp.br/pir/arquivos/congressos/CLAGTEE2003/Papers/ELF%20B-210.pdf>. Acesso em: 24 jul. 2012. 8590347117 |
url |
http://www.repositorio.ufop.br/handle/123456789/1196 |
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.source.none.fl_str_mv |
reponame:Repositório Institucional da UFOP instname:Universidade Federal de Ouro Preto (UFOP) instacron:UFOP |
instname_str |
Universidade Federal de Ouro Preto (UFOP) |
instacron_str |
UFOP |
institution |
UFOP |
reponame_str |
Repositório Institucional da UFOP |
collection |
Repositório Institucional da UFOP |
bitstream.url.fl_str_mv |
http://www.repositorio.ufop.br/bitstream/123456789/1196/5/license.txt http://www.repositorio.ufop.br/bitstream/123456789/1196/1/EVENTO_ArtificialNeuralNetwork.pdf |
bitstream.checksum.fl_str_mv |
8a4605be74aa9ea9d79846c1fba20a33 8c0fc6d147185173ac3d90fb6f67c7fc |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFOP - Universidade Federal de Ouro Preto (UFOP) |
repository.mail.fl_str_mv |
repositorio@ufop.edu.br |
_version_ |
1801685711826452480 |