Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninja
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.9/3278 |
Resumo: | ABSTRACT: Driven by climatic processes, wind power generation is inherently variable. Long-term simulated wind power time series are therefore an essential component for understanding the temporal availability of wind power and its integration into future renewable energy systems. In the recent past, mainly power curve-based models such as Renewables.ninja (RN) have been used for deriving synthetic time series for wind power generation, despite their need for accurate location information and bias correction, as well as their insufficient replication of extreme events and short-term power ramps. In this paper, we assessed how time series generated by machine learning models (MLMs) compare to RN in terms of their ability to replicate the characteristics of observed nationally aggregated wind power generation for Germany. Hence, we applied neural networks to one wind speed input dataset derived from MERRA2 reanalysis with no location information and two with additional location information. The resulting time series and RN time series were compared with actual generation. All MLM time series feature an equal or even better time series quality than RN, depending on the characteristics considered. We conclude that MLM models show a similar performance to RN, even when information on turbine locations and turbine types is unavailable. |
id |
RCAP_e14403c5181706e1dac463515465617b |
---|---|
oai_identifier_str |
oai:repositorio.lneg.pt:10400.9/3278 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninjaWind energyWind power generationSimulationMachine learningNetwork trainingABSTRACT: Driven by climatic processes, wind power generation is inherently variable. Long-term simulated wind power time series are therefore an essential component for understanding the temporal availability of wind power and its integration into future renewable energy systems. In the recent past, mainly power curve-based models such as Renewables.ninja (RN) have been used for deriving synthetic time series for wind power generation, despite their need for accurate location information and bias correction, as well as their insufficient replication of extreme events and short-term power ramps. In this paper, we assessed how time series generated by machine learning models (MLMs) compare to RN in terms of their ability to replicate the characteristics of observed nationally aggregated wind power generation for Germany. Hence, we applied neural networks to one wind speed input dataset derived from MERRA2 reanalysis with no location information and two with additional location information. The resulting time series and RN time series were compared with actual generation. All MLM time series feature an equal or even better time series quality than RN, depending on the characteristics considered. We conclude that MLM models show a similar performance to RN, even when information on turbine locations and turbine types is unavailable.MDPIRepositório do LNEGBaumgartner, JohannGruber, KatharinaSimoes, SofiaSaint-Drenan, Yves-MarieSchmidt, Johannes2020-06-01T10:20:37Z2020-01-01T00:00:00Z2020-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.9/3278engBaumgartner, Johann... [et.al.] - Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninja. In: Energies, 2020, Vol. 13(9), article 22771996-107310.3390/en13092277info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2022-09-06T12:28:45Zoai:repositorio.lneg.pt:10400.9/3278Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T15:36:30.503437Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninja |
title |
Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninja |
spellingShingle |
Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninja Baumgartner, Johann Wind energy Wind power generation Simulation Machine learning Network training |
title_short |
Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninja |
title_full |
Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninja |
title_fullStr |
Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninja |
title_full_unstemmed |
Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninja |
title_sort |
Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninja |
author |
Baumgartner, Johann |
author_facet |
Baumgartner, Johann Gruber, Katharina Simoes, Sofia Saint-Drenan, Yves-Marie Schmidt, Johannes |
author_role |
author |
author2 |
Gruber, Katharina Simoes, Sofia Saint-Drenan, Yves-Marie Schmidt, Johannes |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Repositório do LNEG |
dc.contributor.author.fl_str_mv |
Baumgartner, Johann Gruber, Katharina Simoes, Sofia Saint-Drenan, Yves-Marie Schmidt, Johannes |
dc.subject.por.fl_str_mv |
Wind energy Wind power generation Simulation Machine learning Network training |
topic |
Wind energy Wind power generation Simulation Machine learning Network training |
description |
ABSTRACT: Driven by climatic processes, wind power generation is inherently variable. Long-term simulated wind power time series are therefore an essential component for understanding the temporal availability of wind power and its integration into future renewable energy systems. In the recent past, mainly power curve-based models such as Renewables.ninja (RN) have been used for deriving synthetic time series for wind power generation, despite their need for accurate location information and bias correction, as well as their insufficient replication of extreme events and short-term power ramps. In this paper, we assessed how time series generated by machine learning models (MLMs) compare to RN in terms of their ability to replicate the characteristics of observed nationally aggregated wind power generation for Germany. Hence, we applied neural networks to one wind speed input dataset derived from MERRA2 reanalysis with no location information and two with additional location information. The resulting time series and RN time series were compared with actual generation. All MLM time series feature an equal or even better time series quality than RN, depending on the characteristics considered. We conclude that MLM models show a similar performance to RN, even when information on turbine locations and turbine types is unavailable. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-06-01T10:20:37Z 2020-01-01T00:00:00Z 2020-01-01T00:00:00Z |
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://hdl.handle.net/10400.9/3278 |
url |
http://hdl.handle.net/10400.9/3278 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Baumgartner, Johann... [et.al.] - Less information, similar performance : comparing machine learning-based time series of wind power generation to renewables.ninja. In: Energies, 2020, Vol. 13(9), article 2277 1996-1073 10.3390/en13092277 |
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.publisher.none.fl_str_mv |
MDPI |
publisher.none.fl_str_mv |
MDPI |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799130231377756160 |