Online forecasting using neighbor-based incremental learning for electricity markets

Electricity market forecasting is very useful for the different actors involved in the energy sector to plan both the supply chain and market operation. Nowadays, energy demand data are data coming from smart meters and have to be processed in real-time for more efficient demand management. In addit...

Descripción completa

Detalles Bibliográficos
Autores: Melgar-García, L., Gutiérrez Avilés, David, Rubio Escudero, Cristina, Troncoso, A.
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/174882
Acceso en línea:https://hdl.handle.net/11441/174882
https://doi.org/10.1007/s00521-024-10876-x
Access Level:acceso abierto
Palabra clave:Real-time forecasting
Incremental learning
Streaming time series
Electricity
id ES_a7fb4e04cd9214a0d7182bbf1efbf2e9
oai_identifier_str oai:idus.us.es:11441/174882
network_acronym_str ES
network_name_str España
repository_id_str
spelling Online forecasting using neighbor-based incremental learning for electricity marketsMelgar-García, L.Gutiérrez Avilés, DavidRubio Escudero, CristinaTroncoso, A.Real-time forecastingIncremental learningStreaming time seriesElectricityElectricity market forecasting is very useful for the different actors involved in the energy sector to plan both the supply chain and market operation. Nowadays, energy demand data are data coming from smart meters and have to be processed in real-time for more efficient demand management. In addition, electricity prices data can present changes over time such as new patterns and new trends. Therefore, real-time forecasting algorithms for both demand and prices have to adapt and adjust to online data in order to provide timely and accurate responses. This work presents a new algorithm for electricity demand and prices forecasting in real-time. The proposed algorithm generates a prediction model based on the k-nearest neighbors algorithm, which is incrementally updated in an online scenario considering both changes to existing patterns and adding new detected patterns to the model. Both time-frequency and error threshold based model updates have been evaluated. Results using energy demand from 2007 to 2016 and prices data for different time periods from the Spanish electricity market are reported and compared with other benchmark algorithms.SpringerLenguajes y Sistemas InformáticosMinisterio de Ciencia, Innovación y Educación. España2025info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/174882https://doi.org/10.1007/s00521-024-10876-xreponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésNeural Computing & Applications.PID2020-117954RB-C2TED2021-131311B-C22PID2023-146037OB-C22https://link.springer.com/article/10.1007/s00521-024-10876-xinfo:eu-repo/semantics/openAccessoai:idus.us.es:11441/1748822026-06-17T12:51:07Z
dc.title.none.fl_str_mv Online forecasting using neighbor-based incremental learning for electricity markets
title Online forecasting using neighbor-based incremental learning for electricity markets
spellingShingle Online forecasting using neighbor-based incremental learning for electricity markets
Melgar-García, L.
Real-time forecasting
Incremental learning
Streaming time series
Electricity
title_short Online forecasting using neighbor-based incremental learning for electricity markets
title_full Online forecasting using neighbor-based incremental learning for electricity markets
title_fullStr Online forecasting using neighbor-based incremental learning for electricity markets
title_full_unstemmed Online forecasting using neighbor-based incremental learning for electricity markets
title_sort Online forecasting using neighbor-based incremental learning for electricity markets
dc.creator.none.fl_str_mv Melgar-García, L.
Gutiérrez Avilés, David
Rubio Escudero, Cristina
Troncoso, A.
author Melgar-García, L.
author_facet Melgar-García, L.
Gutiérrez Avilés, David
Rubio Escudero, Cristina
Troncoso, A.
author_role author
author2 Gutiérrez Avilés, David
Rubio Escudero, Cristina
Troncoso, A.
author2_role author
author
author
dc.contributor.none.fl_str_mv Lenguajes y Sistemas Informáticos
Ministerio de Ciencia, Innovación y Educación. España
dc.subject.none.fl_str_mv Real-time forecasting
Incremental learning
Streaming time series
Electricity
topic Real-time forecasting
Incremental learning
Streaming time series
Electricity
description Electricity market forecasting is very useful for the different actors involved in the energy sector to plan both the supply chain and market operation. Nowadays, energy demand data are data coming from smart meters and have to be processed in real-time for more efficient demand management. In addition, electricity prices data can present changes over time such as new patterns and new trends. Therefore, real-time forecasting algorithms for both demand and prices have to adapt and adjust to online data in order to provide timely and accurate responses. This work presents a new algorithm for electricity demand and prices forecasting in real-time. The proposed algorithm generates a prediction model based on the k-nearest neighbors algorithm, which is incrementally updated in an online scenario considering both changes to existing patterns and adding new detected patterns to the model. Both time-frequency and error threshold based model updates have been evaluated. Results using energy demand from 2007 to 2016 and prices data for different time periods from the Spanish electricity market are reported and compared with other benchmark algorithms.
publishDate 2025
dc.date.none.fl_str_mv 2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/174882
https://doi.org/10.1007/s00521-024-10876-x
url https://hdl.handle.net/11441/174882
https://doi.org/10.1007/s00521-024-10876-x
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Neural Computing & Applications.
PID2020-117954RB-C2
TED2021-131311B-C22
PID2023-146037OB-C22
https://link.springer.com/article/10.1007/s00521-024-10876-x
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869415840736083969
score 15,812455

Similares en LA Referencia