001021646 001__ 1021646
001021646 005__ 20240712112902.0
001021646 0247_ $$2doi$$a10.48550/ARXIV.2311.14033
001021646 0247_ $$2datacite_doi$$a10.34734/FZJ-2024-00902
001021646 037__ $$aFZJ-2024-00902
001021646 1001_ $$0P:(DE-Juel1)195931$$aHilger, Hannes$$b0
001021646 245__ $$aMultivariate Scenario Generation of Day-Ahead Electricity Prices using Normalizing Flows
001021646 260__ $$barXiv$$c2023
001021646 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1706103102_6905
001021646 3367_ $$2ORCID$$aWORKING_PAPER
001021646 3367_ $$028$$2EndNote$$aElectronic Article
001021646 3367_ $$2DRIVER$$apreprint
001021646 3367_ $$2BibTeX$$aARTICLE
001021646 3367_ $$2DataCite$$aOutput Types/Working Paper
001021646 520__ $$aTrading on electricity markets requires accurate information about the realization of electricity prices and the uncertainty attached to the predictions. We present a probabilistic forecasting approach for day-ahead electricity prices using the fully data-driven deep generative model called normalizing flows. Our modeling approach generates full-day scenarios of day-ahead electricity prices based on conditional features such as residual load forecasts. Furthermore, we propose extended feature sets of prior realizations and a periodic retraining scheme that allows the normalizing flow to adapt to the changing conditions of modern electricity markets. In particular, we investigate the impact of the energy crisis ensuing from the Russian invasion of Ukraine. Our results highlight that the normalizing flow generates high-quality scenarios that reproduce the true price distribution and yield highly accurate forecasts. Additionally, our analysis highlights how our improvements towards adaptations in changing regimes allow the normalizing flow to adapt to changing market conditions and enables continued sampling of high-quality day-ahead price scenarios.
001021646 536__ $$0G:(DE-HGF)POF4-1121$$a1121 - Digitalization and Systems Technology for Flexibility Solutions (POF4-112)$$cPOF4-112$$fPOF IV$$x0
001021646 588__ $$aDataset connected to DataCite
001021646 650_7 $$2Other$$aMachine Learning (cs.LG)
001021646 650_7 $$2Other$$aFOS: Computer and information sciences
001021646 7001_ $$0P:(DE-Juel1)162277$$aWitthaut, Dirk$$b1$$ufzj
001021646 7001_ $$0P:(DE-Juel1)172097$$aDahmen, Manuel$$b2$$ufzj
001021646 7001_ $$0P:(DE-HGF)0$$aGorjao, Leonardo Rydin$$b3
001021646 7001_ $$0P:(DE-Juel1)192442$$aTrebbien, Julius$$b4
001021646 7001_ $$0P:(DE-Juel1)179591$$aCramer, Eike$$b5$$eCorresponding author
001021646 773__ $$a10.48550/ARXIV.2311.14033
001021646 8564_ $$uhttps://juser.fz-juelich.de/record/1021646/files/2311.14033.pdf$$yOpenAccess
001021646 8564_ $$uhttps://juser.fz-juelich.de/record/1021646/files/2311.14033.gif?subformat=icon$$xicon$$yOpenAccess
001021646 8564_ $$uhttps://juser.fz-juelich.de/record/1021646/files/2311.14033.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001021646 8564_ $$uhttps://juser.fz-juelich.de/record/1021646/files/2311.14033.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001021646 8564_ $$uhttps://juser.fz-juelich.de/record/1021646/files/2311.14033.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001021646 909CO $$ooai:juser.fz-juelich.de:1021646$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001021646 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)195931$$aForschungszentrum Jülich$$b0$$kFZJ
001021646 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)195931$$a Uni Köln$$b0
001021646 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)162277$$aForschungszentrum Jülich$$b1$$kFZJ
001021646 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)162277$$a Uni Köln$$b1
001021646 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172097$$aForschungszentrum Jülich$$b2$$kFZJ
001021646 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a Norwegian University of Life Sciences$$b3
001021646 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)192442$$aForschungszentrum Jülich$$b4$$kFZJ
001021646 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)192442$$a Uni Köln$$b4
001021646 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-Juel1)179591$$aRWTH Aachen$$b5$$kRWTH
001021646 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)179591$$aForschungszentrum Jülich$$b5$$kFZJ
001021646 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)POF4-1121$$aDE-HGF$$bForschungsbereich Energie$$lEnergiesystemdesign (ESD)$$vDigitalisierung und Systemtechnik$$x0
001021646 9141_ $$y2023
001021646 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001021646 920__ $$lyes
001021646 9201_ $$0I:(DE-Juel1)IEK-10-20170217$$kIEK-10$$lModellierung von Energiesystemen$$x0
001021646 9801_ $$aFullTexts
001021646 980__ $$apreprint
001021646 980__ $$aVDB
001021646 980__ $$aUNRESTRICTED
001021646 980__ $$aI:(DE-Juel1)IEK-10-20170217
001021646 981__ $$aI:(DE-Juel1)ICE-1-20170217