Comparative analysis of residential load forecasting with different levels of aggregation
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/242135 |
Resumo: | Microgrids need a robust residential load forecasting. As a consequence, this highlights the problem of predicting electricity consumption in small amounts of households. The individual demand curve is volatile, and more difficult to forecast than the aggregated demand curve. For this reason, Mean Absolute Percentage Error (MAPE) varies in a large range (of 1% to 45%), depending on the number of consumers analyzed. Different levels of aggregation of household consumers that can be used in microgrids are analyzed; the load forecasting of the single consumer and aggregated consumers are compared. The forecasting methodology used is the most consolidated of Recurrent Neural Networks, i.e., LSTM. The dataset used contains 920 residential consumers belonging to the Commission for Energy Regulation (CER), a control group that is in the Irish Social Science Data Archive (ISSDA) repository. The result shows that the forecasting of groups of more than 20 aggregated consumers has a lower MAPE that individual forecasting. On the other hand, individual forecasting is better for groups with fewer than 10 consumers. |
id |
UFRGS-2_e368400ae177726718fb34e97ced8784 |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/242135 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Peñaloza, Ana Karen ApoloLeborgne, Roberto ChouhyBalbinot, Alexandre2022-07-08T04:51:21Z20222673-4591http://hdl.handle.net/10183/242135001144081Microgrids need a robust residential load forecasting. As a consequence, this highlights the problem of predicting electricity consumption in small amounts of households. The individual demand curve is volatile, and more difficult to forecast than the aggregated demand curve. For this reason, Mean Absolute Percentage Error (MAPE) varies in a large range (of 1% to 45%), depending on the number of consumers analyzed. Different levels of aggregation of household consumers that can be used in microgrids are analyzed; the load forecasting of the single consumer and aggregated consumers are compared. The forecasting methodology used is the most consolidated of Recurrent Neural Networks, i.e., LSTM. The dataset used contains 920 residential consumers belonging to the Commission for Energy Regulation (CER), a control group that is in the Irish Social Science Data Archive (ISSDA) repository. The result shows that the forecasting of groups of more than 20 aggregated consumers has a lower MAPE that individual forecasting. On the other hand, individual forecasting is better for groups with fewer than 10 consumers.application/pdfengEngineering proceedings [recurso eletrônico]. Basel. Vol. 18, no. 1 (June 2022), art. 29, 9 p.Consumo de energiaPrevisão de demandaRedes neuraisLoad forecastingLSTMResidential load forecastingAggregationComparative analysis of residential load forecasting with different levels of aggregationEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT001144081.pdf.txt001144081.pdf.txtExtracted Texttext/plain38198http://www.lume.ufrgs.br/bitstream/10183/242135/2/001144081.pdf.txt56fe6885f314f1e59ae49d91569f40ceMD52ORIGINAL001144081.pdfTexto completo (inglês)application/pdf2877749http://www.lume.ufrgs.br/bitstream/10183/242135/1/001144081.pdfa810cbbd56add56367f919312f31bbe5MD5110183/2421352022-07-09 05:06:59.490028oai:www.lume.ufrgs.br:10183/242135Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2022-07-09T08:06:59Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Comparative analysis of residential load forecasting with different levels of aggregation |
title |
Comparative analysis of residential load forecasting with different levels of aggregation |
spellingShingle |
Comparative analysis of residential load forecasting with different levels of aggregation Peñaloza, Ana Karen Apolo Consumo de energia Previsão de demanda Redes neurais Load forecasting LSTM Residential load forecasting Aggregation |
title_short |
Comparative analysis of residential load forecasting with different levels of aggregation |
title_full |
Comparative analysis of residential load forecasting with different levels of aggregation |
title_fullStr |
Comparative analysis of residential load forecasting with different levels of aggregation |
title_full_unstemmed |
Comparative analysis of residential load forecasting with different levels of aggregation |
title_sort |
Comparative analysis of residential load forecasting with different levels of aggregation |
author |
Peñaloza, Ana Karen Apolo |
author_facet |
Peñaloza, Ana Karen Apolo Leborgne, Roberto Chouhy Balbinot, Alexandre |
author_role |
author |
author2 |
Leborgne, Roberto Chouhy Balbinot, Alexandre |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Peñaloza, Ana Karen Apolo Leborgne, Roberto Chouhy Balbinot, Alexandre |
dc.subject.por.fl_str_mv |
Consumo de energia Previsão de demanda Redes neurais |
topic |
Consumo de energia Previsão de demanda Redes neurais Load forecasting LSTM Residential load forecasting Aggregation |
dc.subject.eng.fl_str_mv |
Load forecasting LSTM Residential load forecasting Aggregation |
description |
Microgrids need a robust residential load forecasting. As a consequence, this highlights the problem of predicting electricity consumption in small amounts of households. The individual demand curve is volatile, and more difficult to forecast than the aggregated demand curve. For this reason, Mean Absolute Percentage Error (MAPE) varies in a large range (of 1% to 45%), depending on the number of consumers analyzed. Different levels of aggregation of household consumers that can be used in microgrids are analyzed; the load forecasting of the single consumer and aggregated consumers are compared. The forecasting methodology used is the most consolidated of Recurrent Neural Networks, i.e., LSTM. The dataset used contains 920 residential consumers belonging to the Commission for Energy Regulation (CER), a control group that is in the Irish Social Science Data Archive (ISSDA) repository. The result shows that the forecasting of groups of more than 20 aggregated consumers has a lower MAPE that individual forecasting. On the other hand, individual forecasting is better for groups with fewer than 10 consumers. |
publishDate |
2022 |
dc.date.accessioned.fl_str_mv |
2022-07-08T04:51:21Z |
dc.date.issued.fl_str_mv |
2022 |
dc.type.driver.fl_str_mv |
Estrangeiro info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/242135 |
dc.identifier.issn.pt_BR.fl_str_mv |
2673-4591 |
dc.identifier.nrb.pt_BR.fl_str_mv |
001144081 |
identifier_str_mv |
2673-4591 001144081 |
url |
http://hdl.handle.net/10183/242135 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Engineering proceedings [recurso eletrônico]. Basel. Vol. 18, no. 1 (June 2022), art. 29, 9 p. |
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.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/242135/2/001144081.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/242135/1/001144081.pdf |
bitstream.checksum.fl_str_mv |
56fe6885f314f1e59ae49d91569f40ce a810cbbd56add56367f919312f31bbe5 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801225060583735296 |