Multinodal load forecasting for distribution systems using a fuzzy-artmap neural network
Main Author: | |
---|---|
Publication Date: | 2018 |
Other Authors: | , , , |
Format: | Article |
Language: | eng |
Source: | Repositório Institucional da UNESP |
Download full: | http://dx.doi.org/10.1016/j.asoc.2018.06.039 http://hdl.handle.net/11449/171211 |
Summary: | This work proposes a predictor system (multinodal forecasting) considering several points of an electrical network, such as substations, transformers, and feeders, based on an adaptive resonance theory (ART) neural network family. It is a problem similar to global forecasting, with the main difference being the strategy to align the input and output of the data with several parallel neural modules. Considering that multinodal prediction is more complex compared to global prediction, the multinodal prediction will use a fuzzy-ARTMAP neural network and a global load participation factor. The advantages of this approach are as follows: (1) the processing time is equivalent to the processing required for global forecasting (i.e., the additional time processing is quite low); and (2) Fuzzy-ARTMAP neural networks converge significantly faster than backpropagation neural networks (improved benchmark in precision). The preference for neural networks of the ART family is due to the characteristic stability and plasticity that these architectures have to provide results in a fast and precise way. To test the proposed forecast system, the results are presented for nine substations from the database of an electrical company. |
id |
UNSP_42d8c654907aaaf26980819841518d62 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/171211 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Multinodal load forecasting for distribution systems using a fuzzy-artmap neural networkAdaptive resonance theoryArtificial neural networksElectrical system distributionLoad forecastingThis work proposes a predictor system (multinodal forecasting) considering several points of an electrical network, such as substations, transformers, and feeders, based on an adaptive resonance theory (ART) neural network family. It is a problem similar to global forecasting, with the main difference being the strategy to align the input and output of the data with several parallel neural modules. Considering that multinodal prediction is more complex compared to global prediction, the multinodal prediction will use a fuzzy-ARTMAP neural network and a global load participation factor. The advantages of this approach are as follows: (1) the processing time is equivalent to the processing required for global forecasting (i.e., the additional time processing is quite low); and (2) Fuzzy-ARTMAP neural networks converge significantly faster than backpropagation neural networks (improved benchmark in precision). The preference for neural networks of the ART family is due to the characteristic stability and plasticity that these architectures have to provide results in a fast and precise way. To test the proposed forecast system, the results are presented for nine substations from the database of an electrical company.Electrical Engineering Department UNESP – São Paulo State University, Av. Brasil 56–P.O. Box 31IFSP - Federal Institute of Education Science and Technology of São Paulo Campus HortolândiaElectrical Engineering Department UNESP – São Paulo State University, Av. Brasil 56–P.O. Box 31Universidade Estadual Paulista (Unesp)Science and Technology of São PauloAbreu, Thays [UNESP]Amorim, Aline J. [UNESP]Santos-Junior, Carlos R.Lotufo, Anna D.P. [UNESP]Minussi, Carlos R. [UNESP]2018-12-11T16:54:25Z2018-12-11T16:54:25Z2018-10-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article307-316application/pdfhttp://dx.doi.org/10.1016/j.asoc.2018.06.039Applied Soft Computing Journal, v. 71, p. 307-316.1568-4946http://hdl.handle.net/11449/17121110.1016/j.asoc.2018.06.0392-s2.0-850498314672-s2.0-85049831467.pdfScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengApplied Soft Computing Journal1,199info:eu-repo/semantics/openAccess2023-11-05T06:10:49Zoai:repositorio.unesp.br:11449/171211Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-11-05T06:10:49Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Multinodal load forecasting for distribution systems using a fuzzy-artmap neural network |
title |
Multinodal load forecasting for distribution systems using a fuzzy-artmap neural network |
spellingShingle |
Multinodal load forecasting for distribution systems using a fuzzy-artmap neural network Abreu, Thays [UNESP] Adaptive resonance theory Artificial neural networks Electrical system distribution Load forecasting |
title_short |
Multinodal load forecasting for distribution systems using a fuzzy-artmap neural network |
title_full |
Multinodal load forecasting for distribution systems using a fuzzy-artmap neural network |
title_fullStr |
Multinodal load forecasting for distribution systems using a fuzzy-artmap neural network |
title_full_unstemmed |
Multinodal load forecasting for distribution systems using a fuzzy-artmap neural network |
title_sort |
Multinodal load forecasting for distribution systems using a fuzzy-artmap neural network |
author |
Abreu, Thays [UNESP] |
author_facet |
Abreu, Thays [UNESP] Amorim, Aline J. [UNESP] Santos-Junior, Carlos R. Lotufo, Anna D.P. [UNESP] Minussi, Carlos R. [UNESP] |
author_role |
author |
author2 |
Amorim, Aline J. [UNESP] Santos-Junior, Carlos R. Lotufo, Anna D.P. [UNESP] Minussi, Carlos R. [UNESP] |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Science and Technology of São Paulo |
dc.contributor.author.fl_str_mv |
Abreu, Thays [UNESP] Amorim, Aline J. [UNESP] Santos-Junior, Carlos R. Lotufo, Anna D.P. [UNESP] Minussi, Carlos R. [UNESP] |
dc.subject.por.fl_str_mv |
Adaptive resonance theory Artificial neural networks Electrical system distribution Load forecasting |
topic |
Adaptive resonance theory Artificial neural networks Electrical system distribution Load forecasting |
description |
This work proposes a predictor system (multinodal forecasting) considering several points of an electrical network, such as substations, transformers, and feeders, based on an adaptive resonance theory (ART) neural network family. It is a problem similar to global forecasting, with the main difference being the strategy to align the input and output of the data with several parallel neural modules. Considering that multinodal prediction is more complex compared to global prediction, the multinodal prediction will use a fuzzy-ARTMAP neural network and a global load participation factor. The advantages of this approach are as follows: (1) the processing time is equivalent to the processing required for global forecasting (i.e., the additional time processing is quite low); and (2) Fuzzy-ARTMAP neural networks converge significantly faster than backpropagation neural networks (improved benchmark in precision). The preference for neural networks of the ART family is due to the characteristic stability and plasticity that these architectures have to provide results in a fast and precise way. To test the proposed forecast system, the results are presented for nine substations from the database of an electrical company. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-12-11T16:54:25Z 2018-12-11T16:54:25Z 2018-10-01 |
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://dx.doi.org/10.1016/j.asoc.2018.06.039 Applied Soft Computing Journal, v. 71, p. 307-316. 1568-4946 http://hdl.handle.net/11449/171211 10.1016/j.asoc.2018.06.039 2-s2.0-85049831467 2-s2.0-85049831467.pdf |
url |
http://dx.doi.org/10.1016/j.asoc.2018.06.039 http://hdl.handle.net/11449/171211 |
identifier_str_mv |
Applied Soft Computing Journal, v. 71, p. 307-316. 1568-4946 10.1016/j.asoc.2018.06.039 2-s2.0-85049831467 2-s2.0-85049831467.pdf |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Applied Soft Computing Journal 1,199 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
307-316 application/pdf |
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_ |
1799964828906815488 |