Use of virtual load curves for the training of neural networks for residential electricity consumption forecasting applications
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/INDUSCON.2018.8627295 http://hdl.handle.net/11449/190173 |
Resumo: | Smart grids are becoming increasingly closer to consumers, especially residential consumers, bringing with them a wide range of possibilities. The level of information obtained on a smart grid will be much higher when compared to a traditional network and at this point, more informed consumers tend to consume more efficiently, bringing benefits to themselves and to the system. An interesting fact for control within a residence is forecasting consumption, allowing the consumer to know in advance how much to consume up to a certain period. Artificial neural networks are one of several methods used to forecast time series, however, require a high volume of historical data for the training of the network, given that these may not be accessible or even exist. At this point, the objective of this work is to evaluate the use of load curves obtained through computational tools for the pre-training of artificial neural networks used in the consumption forecast. A tool is used to create random load curves according to the region and socioeconomic characteristics. The load curves are transformed into cumulative consumption curves and used as training vectors of the artificial neural network. The results of the tests were very promising, they showed that the pretraining with the virtual data makes possible the forecast of the time series even in the absence of real data for the training, showing that the methodology developed has great potential of application in works related to the forecast consumption. |
id |
UNSP_78604851f991c2f36c6db97af1174c72 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/190173 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Use of virtual load curves for the training of neural networks for residential electricity consumption forecasting applicationsArtificial neural networksLoad curvesLoad forecastingSmart gridsSmart grids are becoming increasingly closer to consumers, especially residential consumers, bringing with them a wide range of possibilities. The level of information obtained on a smart grid will be much higher when compared to a traditional network and at this point, more informed consumers tend to consume more efficiently, bringing benefits to themselves and to the system. An interesting fact for control within a residence is forecasting consumption, allowing the consumer to know in advance how much to consume up to a certain period. Artificial neural networks are one of several methods used to forecast time series, however, require a high volume of historical data for the training of the network, given that these may not be accessible or even exist. At this point, the objective of this work is to evaluate the use of load curves obtained through computational tools for the pre-training of artificial neural networks used in the consumption forecast. A tool is used to create random load curves according to the region and socioeconomic characteristics. The load curves are transformed into cumulative consumption curves and used as training vectors of the artificial neural network. The results of the tests were very promising, they showed that the pretraining with the virtual data makes possible the forecast of the time series even in the absence of real data for the training, showing that the methodology developed has great potential of application in works related to the forecast consumption.Laboratory of Power Systems and Intelligent Techniques - LSISPOTI University of São Paulo - USPLaboratory of Power Systems and Intelligent Techniques - LSISPOTI São Paulo State University - UNESPLaboratory of Power Systems and Intelligent Techniques - LSISPOTI Sacred Heart University - USCLaboratory of Power Systems and Intelligent Techniques - LSISPOTI São Paulo State University - UNESPUniversidade de São Paulo (USP)Universidade Estadual Paulista (Unesp)Sacred Heart University - USCHaroldo, L. M. Do AmaralSouza, Andre N. De [UNESP]Gastaldello, Danilo S.Palma, Thiago X. Da S. [UNESP]Maranho, Alexander Da S. [UNESP]Papa, Joao P. [UNESP]2019-10-06T17:04:39Z2019-10-06T17:04:39Z2019-01-25info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject85-90http://dx.doi.org/10.1109/INDUSCON.2018.86272952018 13th IEEE International Conference on Industry Applications, INDUSCON 2018 - Proceedings, p. 85-90.http://hdl.handle.net/11449/19017310.1109/INDUSCON.2018.86272952-s2.0-85062540331Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPeng2018 13th IEEE International Conference on Industry Applications, INDUSCON 2018 - Proceedingsinfo:eu-repo/semantics/openAccess2024-04-23T16:11:26Zoai:repositorio.unesp.br:11449/190173Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-04-23T16:11:26Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Use of virtual load curves for the training of neural networks for residential electricity consumption forecasting applications |
title |
Use of virtual load curves for the training of neural networks for residential electricity consumption forecasting applications |
spellingShingle |
Use of virtual load curves for the training of neural networks for residential electricity consumption forecasting applications Haroldo, L. M. Do Amaral Artificial neural networks Load curves Load forecasting Smart grids |
title_short |
Use of virtual load curves for the training of neural networks for residential electricity consumption forecasting applications |
title_full |
Use of virtual load curves for the training of neural networks for residential electricity consumption forecasting applications |
title_fullStr |
Use of virtual load curves for the training of neural networks for residential electricity consumption forecasting applications |
title_full_unstemmed |
Use of virtual load curves for the training of neural networks for residential electricity consumption forecasting applications |
title_sort |
Use of virtual load curves for the training of neural networks for residential electricity consumption forecasting applications |
author |
Haroldo, L. M. Do Amaral |
author_facet |
Haroldo, L. M. Do Amaral Souza, Andre N. De [UNESP] Gastaldello, Danilo S. Palma, Thiago X. Da S. [UNESP] Maranho, Alexander Da S. [UNESP] Papa, Joao P. [UNESP] |
author_role |
author |
author2 |
Souza, Andre N. De [UNESP] Gastaldello, Danilo S. Palma, Thiago X. Da S. [UNESP] Maranho, Alexander Da S. [UNESP] Papa, Joao P. [UNESP] |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade de São Paulo (USP) Universidade Estadual Paulista (Unesp) Sacred Heart University - USC |
dc.contributor.author.fl_str_mv |
Haroldo, L. M. Do Amaral Souza, Andre N. De [UNESP] Gastaldello, Danilo S. Palma, Thiago X. Da S. [UNESP] Maranho, Alexander Da S. [UNESP] Papa, Joao P. [UNESP] |
dc.subject.por.fl_str_mv |
Artificial neural networks Load curves Load forecasting Smart grids |
topic |
Artificial neural networks Load curves Load forecasting Smart grids |
description |
Smart grids are becoming increasingly closer to consumers, especially residential consumers, bringing with them a wide range of possibilities. The level of information obtained on a smart grid will be much higher when compared to a traditional network and at this point, more informed consumers tend to consume more efficiently, bringing benefits to themselves and to the system. An interesting fact for control within a residence is forecasting consumption, allowing the consumer to know in advance how much to consume up to a certain period. Artificial neural networks are one of several methods used to forecast time series, however, require a high volume of historical data for the training of the network, given that these may not be accessible or even exist. At this point, the objective of this work is to evaluate the use of load curves obtained through computational tools for the pre-training of artificial neural networks used in the consumption forecast. A tool is used to create random load curves according to the region and socioeconomic characteristics. The load curves are transformed into cumulative consumption curves and used as training vectors of the artificial neural network. The results of the tests were very promising, they showed that the pretraining with the virtual data makes possible the forecast of the time series even in the absence of real data for the training, showing that the methodology developed has great potential of application in works related to the forecast consumption. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-10-06T17:04:39Z 2019-10-06T17:04:39Z 2019-01-25 |
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.uri.fl_str_mv |
http://dx.doi.org/10.1109/INDUSCON.2018.8627295 2018 13th IEEE International Conference on Industry Applications, INDUSCON 2018 - Proceedings, p. 85-90. http://hdl.handle.net/11449/190173 10.1109/INDUSCON.2018.8627295 2-s2.0-85062540331 |
url |
http://dx.doi.org/10.1109/INDUSCON.2018.8627295 http://hdl.handle.net/11449/190173 |
identifier_str_mv |
2018 13th IEEE International Conference on Industry Applications, INDUSCON 2018 - Proceedings, p. 85-90. 10.1109/INDUSCON.2018.8627295 2-s2.0-85062540331 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2018 13th IEEE International Conference on Industry Applications, INDUSCON 2018 - Proceedings |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
85-90 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1799965226071752704 |