000909688 001__ 909688
000909688 005__ 20240712112909.0
000909688 0247_ $$2doi$$a10.1109/ACCESS.2022.3141875
000909688 0247_ $$2Handle$$a2128/31846
000909688 0247_ $$2WOS$$aWOS:000747195700001
000909688 037__ $$aFZJ-2022-03341
000909688 082__ $$a621.3
000909688 1001_ $$0P:(DE-Juel1)179591$$aCramer, Eike$$b0
000909688 245__ $$aValidation methods for energy time series scenarios from deep generative models
000909688 260__ $$aNew York, NY$$bIEEE$$c2022
000909688 3367_ $$2DRIVER$$aarticle
000909688 3367_ $$2DataCite$$aOutput Types/Journal article
000909688 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1663228249_31072
000909688 3367_ $$2BibTeX$$aARTICLE
000909688 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000909688 3367_ $$00$$2EndNote$$aJournal Article
000909688 520__ $$aThe design and operation of modern energy systems are heavily influenced by time-dependent and uncertain parameters, e.g., renewable electricity generation, load-demand, and electricity prices. These are typically represented by a set of discrete realizations known as scenarios. A popular scenario generation approach uses deep generative models (DGM) that allow scenario generation without prior assumptions about the data distribution. However, the validation of generated scenarios is difficult, and a comprehensive discussion about appropriate validation methods is currently lacking. To start this discussion, we provide a critical assessment of the currently used validation methods in the energy scenario generation literature. In particular, we assess validation methods based on probability density, auto-correlation, and power spectral density. Furthermore, we propose using the multifractal detrended fluctuation analysis (MFDFA) as an additional validation method for non-trivial features like peaks, bursts, and plateaus. As representative examples, we train generative adversarial networks (GANs), Wasserstein GANs (WGANs), and variational autoencoders (VAEs) on two renewable power generation time series (photovoltaic and wind from Germany in 2013 to 2015) and an intra-day electricity price time series form the European Energy Exchange in 2017 to 2019. We apply the four validation methods to both the historical and the generated data and discuss the interpretation of validation results as well as common mistakes, pitfalls, and limitations of the validation methods. Our assessment shows that no single method sufficiently characterizes a scenario but ideally validation should include multiple methods and be interpreted carefully in the context of scenarios over short time periods.
000909688 536__ $$0G:(DE-HGF)POF4-1112$$a1112 - Societally Feasible Transformation Pathways (POF4-111)$$cPOF4-111$$fPOF IV$$x0
000909688 536__ $$0G:(DE-HGF)POF4-1122$$a1122 - Design, Operation and Digitalization of the Future Energy Grids (POF4-112)$$cPOF4-112$$fPOF IV$$x1
000909688 536__ $$0G:(DE-Juel1)HDS-LEE-20190612$$aHDS LEE - Helmholtz School for Data Science in Life, Earth and Energy (HDS LEE) (HDS-LEE-20190612)$$cHDS-LEE-20190612$$x2
000909688 536__ $$0G:(DE-Ds200)HGF-ZT-I-0029$$aHGF-ZT-I-0029 - Helmholtz UQ: Uncertainty Quantification - from data to reliable knowledge (HGF-ZT-I-0029)$$cHGF-ZT-I-0029$$x3
000909688 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000909688 7001_ $$0P:(DE-Juel1)173608$$aGorjao, Leonardo Rydin$$b1
000909688 7001_ $$0P:(DE-Juel1)172025$$aMitsos, Alexander$$b2
000909688 7001_ $$00000-0003-1607-9748$$aSchafer, Benjamin$$b3
000909688 7001_ $$0P:(DE-Juel1)162277$$aWitthaut, Dirk$$b4
000909688 7001_ $$0P:(DE-Juel1)172097$$aDahmen, Manuel$$b5$$eCorresponding author
000909688 773__ $$0PERI:(DE-600)2687964-5$$a10.1109/ACCESS.2022.3141875$$gVol. 10, p. 8194 - 8207$$p8194 - 8207$$tIEEE access$$v10$$x2169-3536$$y2022
000909688 8564_ $$uhttps://juser.fz-juelich.de/record/909688/files/Validation_Methods_for_Energy_Time_Series_Scenarios_From_Deep_Generative_Models.pdf$$yOpenAccess
000909688 8767_ $$d2023-05-31$$eAPC$$jPublish and Read$$zToken
000909688 909CO $$ooai:juser.fz-juelich.de:909688$$pdnbdelivery$$popenCost$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
000909688 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)179591$$aForschungszentrum Jülich$$b0$$kFZJ
000909688 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172025$$aForschungszentrum Jülich$$b2$$kFZJ
000909688 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)162277$$aForschungszentrum Jülich$$b4$$kFZJ
000909688 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172097$$aForschungszentrum Jülich$$b5$$kFZJ
000909688 9131_ $$0G:(DE-HGF)POF4-111$$1G:(DE-HGF)POF4-110$$2G:(DE-HGF)POF4-100$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-1112$$aDE-HGF$$bForschungsbereich Energie$$lEnergiesystemdesign (ESD)$$vEnergiesystemtransformation$$x0
000909688 9131_ $$0G:(DE-HGF)POF4-112$$1G:(DE-HGF)POF4-110$$2G:(DE-HGF)POF4-100$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-1122$$aDE-HGF$$bForschungsbereich Energie$$lEnergiesystemdesign (ESD)$$vDigitalisierung und Systemtechnik$$x1
000909688 9141_ $$y2022
000909688 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-01-28
000909688 915__ $$0StatID:(DE-HGF)1230$$2StatID$$aDBCoverage$$bCurrent Contents - Electronics and Telecommunications Collection$$d2021-01-28
000909688 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000909688 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-01-28
000909688 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2021-01-28
000909688 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000909688 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2021-01-28
000909688 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bIEEE ACCESS : 2021$$d2022-11-11
000909688 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2022-11-11
000909688 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2022-11-11
000909688 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2022-06-13T11:44:26Z
000909688 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2022-06-13T11:44:26Z
000909688 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Blind peer review$$d2022-06-13T11:44:26Z
000909688 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2022-11-11
000909688 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2022-11-11
000909688 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2022-11-11
000909688 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2022-11-11
000909688 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
000909688 915pc $$0PC:(DE-HGF)0001$$2APC$$aLocal Funding
000909688 915pc $$0PC:(DE-HGF)0002$$2APC$$aDFG OA Publikationskosten
000909688 915pc $$0PC:(DE-HGF)0003$$2APC$$aDOAJ Journal
000909688 920__ $$lyes
000909688 9201_ $$0I:(DE-Juel1)IEK-STE-20101013$$kIEK-STE$$lSystemforschung und Technologische Entwicklung$$x0
000909688 9201_ $$0I:(DE-Juel1)IEK-10-20170217$$kIEK-10$$lModellierung von Energiesystemen$$x1
000909688 9801_ $$aFullTexts
000909688 980__ $$ajournal
000909688 980__ $$aVDB
000909688 980__ $$aUNRESTRICTED
000909688 980__ $$aI:(DE-Juel1)IEK-STE-20101013
000909688 980__ $$aI:(DE-Juel1)IEK-10-20170217
000909688 980__ $$aAPC
000909688 981__ $$aI:(DE-Juel1)ICE-1-20170217