The value of day-ahead forecasting for photovoltaics in the Spanish electricity market

Traditionally, the accuracy of solar power forecasts has been measured in terms of classic metrics, such as root mean square error (RMSE) or mean absolute error (MAE), and it is widely accepted that the smaller the error, the greater the economic benefits. Nevertheless, this is not as straightforwar...

ver descrição completa

Detalhes bibliográficos
Autores: Antonanzas, J. [0000-0002-8042-9207], Pozo-Vázquez, D. [0000-0002-1135-4926], Fernandez-Jimenez, L.A. [0000-0002-5633-4849], Martinez-de-Pison, F.J. [0000-0002-3063-7374]
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2017
País:España
Recursos:Universidad de La Rioja (UR)
Repositorio:RIUR. Repositorio Institucional de la Universidad de La Rioja
OAI Identifier:oai:portal.dialnet.es:doc/5bbc6947b750603269e81855
Acesso em linha:https://investigacion.unirioja.es/documentos/5bbc6947b750603269e81855
Access Level:acceso abierto
Palavra-chave:Day ahead market
Grid integration
PV power forecasting
Solar energy
id ES_8a1eb56d1baeab9a3df4a9c6db9af964
oai_identifier_str oai:portal.dialnet.es:doc/5bbc6947b750603269e81855
network_acronym_str ES
network_name_str España
repository_id_str
spelling The value of day-ahead forecasting for photovoltaics in the Spanish electricity marketAntonanzas, J. [0000-0002-8042-9207]Pozo-Vázquez, D. [0000-0002-1135-4926]Fernandez-Jimenez, L.A. [0000-0002-5633-4849]Martinez-de-Pison, F.J. [0000-0002-3063-7374]Day ahead marketGrid integrationPV power forecastingSolar energyTraditionally, the accuracy of solar power forecasts has been measured in terms of classic metrics, such as root mean square error (RMSE) or mean absolute error (MAE), and it is widely accepted that the smaller the error, the greater the economic benefits. Nevertheless, this is not as straightforward as it may seem, because market conditions must be studied first. Relationships between magnitudes of deviations between forecast and actual production and market penalties that apply at each moment are crucial. In this study, we analyze various day-ahead production forecasts for a 1.86 MW photovoltaic plant considering different techniques and sets of inputs. A nRMSE of 22.54% was obtained for a Support Vector Regression model trained by numerical weather predictions (NWP). This model produced the most benefits. An annual forecasting value of 4788€ with respect to a persistence model was obtained for trading in the Iberian (Spain and Portugal) day-ahead electricity market. Annual value added by the NWP service totaled 2801€ and room for improvement regarding NWP variables rose to 3877€. As a general trend, it was found that smaller errors (RMSE) generated higher incomes. For each 1 kW h improvement in RMSE, the annual value of forecasting increased 22.32€. Nevertheless, some models that gave larger errors than others also brought greater benefits. Thus, market conditions must be considered to accurately evaluate model economic performance. © 2017 Elsevier Ltd2017info:eu-repo/semantics/articleSubtype: Articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://investigacion.unirioja.es/documentos/5bbc6947b750603269e81855reponame:RIUR. Repositorio Institucional de la Universidad de La Riojainstname:Universidad de La Rioja (UR)Inglésinfo:eu-repo/semantics/altIdentifier/doi/10.1016/J.SOLENER.2017.09.043info:eu-repo/semantics/altIdentifier/wos/WOS:000418974500015info:eu-repo/semantics/altIdentifier/pissn/0038-092XThe value of day-ahead forecasting for photovoltaics in the Spanish electricity market, 2017, vol. 158, pág. 140-146info:eu-repo/semantics/openAccessoai:portal.dialnet.es:doc/5bbc6947b750603269e818552026-06-14T12:47:17Z
dc.title.none.fl_str_mv The value of day-ahead forecasting for photovoltaics in the Spanish electricity market
title The value of day-ahead forecasting for photovoltaics in the Spanish electricity market
spellingShingle The value of day-ahead forecasting for photovoltaics in the Spanish electricity market
Antonanzas, J. [0000-0002-8042-9207]
Day ahead market
Grid integration
PV power forecasting
Solar energy
title_short The value of day-ahead forecasting for photovoltaics in the Spanish electricity market
title_full The value of day-ahead forecasting for photovoltaics in the Spanish electricity market
title_fullStr The value of day-ahead forecasting for photovoltaics in the Spanish electricity market
title_full_unstemmed The value of day-ahead forecasting for photovoltaics in the Spanish electricity market
title_sort The value of day-ahead forecasting for photovoltaics in the Spanish electricity market
dc.creator.none.fl_str_mv Antonanzas, J. [0000-0002-8042-9207]
Pozo-Vázquez, D. [0000-0002-1135-4926]
Fernandez-Jimenez, L.A. [0000-0002-5633-4849]
Martinez-de-Pison, F.J. [0000-0002-3063-7374]
author Antonanzas, J. [0000-0002-8042-9207]
author_facet Antonanzas, J. [0000-0002-8042-9207]
Pozo-Vázquez, D. [0000-0002-1135-4926]
Fernandez-Jimenez, L.A. [0000-0002-5633-4849]
Martinez-de-Pison, F.J. [0000-0002-3063-7374]
author_role author
author2 Pozo-Vázquez, D. [0000-0002-1135-4926]
Fernandez-Jimenez, L.A. [0000-0002-5633-4849]
Martinez-de-Pison, F.J. [0000-0002-3063-7374]
author2_role author
author
author
dc.subject.none.fl_str_mv Day ahead market
Grid integration
PV power forecasting
Solar energy
topic Day ahead market
Grid integration
PV power forecasting
Solar energy
description Traditionally, the accuracy of solar power forecasts has been measured in terms of classic metrics, such as root mean square error (RMSE) or mean absolute error (MAE), and it is widely accepted that the smaller the error, the greater the economic benefits. Nevertheless, this is not as straightforward as it may seem, because market conditions must be studied first. Relationships between magnitudes of deviations between forecast and actual production and market penalties that apply at each moment are crucial. In this study, we analyze various day-ahead production forecasts for a 1.86 MW photovoltaic plant considering different techniques and sets of inputs. A nRMSE of 22.54% was obtained for a Support Vector Regression model trained by numerical weather predictions (NWP). This model produced the most benefits. An annual forecasting value of 4788€ with respect to a persistence model was obtained for trading in the Iberian (Spain and Portugal) day-ahead electricity market. Annual value added by the NWP service totaled 2801€ and room for improvement regarding NWP variables rose to 3877€. As a general trend, it was found that smaller errors (RMSE) generated higher incomes. For each 1 kW h improvement in RMSE, the annual value of forecasting increased 22.32€. Nevertheless, some models that gave larger errors than others also brought greater benefits. Thus, market conditions must be considered to accurately evaluate model economic performance. © 2017 Elsevier Ltd
publishDate 2017
dc.date.none.fl_str_mv 2017
dc.type.none.fl_str_mv info:eu-repo/semantics/article
Subtype: Article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://investigacion.unirioja.es/documentos/5bbc6947b750603269e81855
url https://investigacion.unirioja.es/documentos/5bbc6947b750603269e81855
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1016/J.SOLENER.2017.09.043
info:eu-repo/semantics/altIdentifier/wos/WOS:000418974500015
info:eu-repo/semantics/altIdentifier/pissn/0038-092X
The value of day-ahead forecasting for photovoltaics in the Spanish electricity market, 2017, vol. 158, pág. 140-146
dc.rights.none.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:RIUR. Repositorio Institucional de la Universidad de La Rioja
instname:Universidad de La Rioja (UR)
instname_str Universidad de La Rioja (UR)
reponame_str RIUR. Repositorio Institucional de la Universidad de La Rioja
collection RIUR. Repositorio Institucional de la Universidad de La Rioja
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869412677390958592
score 15,301629

Registos relacionados