Universität zu Köln

Cramer, Eike ORCID: 0000-0002-6882-5469, Gorjao, Leonardo Rydin, Mitsos, Alexander ORCID: 0000-0003-0335-6566, Schafer, Benjamin ORCID: 0000-0003-1607-9748, Witthaut, Dirk ORCID: 0000-0002-3623-5341 and Dahmen, Manuel ORCID: 0000-0003-2757-5253 (2022). Validation Methods for Energy Time Series Scenarios From Deep Generative Models. IEEE Access, 10. S. 8194 - 8208. PISCATAWAY: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. ISSN 2169-3536

Full text not available from this repository.

Abstract

The 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.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Cramer, Eike UNSPECIFIED orcid.org/0000-0002-6882-5469 UNSPECIFIED Gorjao, Leonardo Rydin UNSPECIFIED UNSPECIFIED UNSPECIFIED Mitsos, Alexander UNSPECIFIED orcid.org/0000-0003-0335-6566 UNSPECIFIED Schafer, Benjamin UNSPECIFIED orcid.org/0000-0003-1607-9748 UNSPECIFIED Witthaut, Dirk UNSPECIFIED orcid.org/0000-0002-3623-5341 UNSPECIFIED Dahmen, Manuel UNSPECIFIED orcid.org/0000-0003-2757-5253 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-689943
DOI:	10.1109/ACCESS.2022.3141875
Journal or Publication Title:	IEEE Access
Volume:	10
Page Range:	S. 8194 - 8208
Date:	2022
Publisher:	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Place of Publication:	PISCATAWAY
ISSN:	2169-3536
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language MULTIFRACTAL FORMALISM; ELECTRICITY; SIGNALS; MARKET Multiple languages Computer Science, Information Systems; Engineering, Electrical & Electronic; Telecommunications Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/68994