Universität zu Köln

Kruse, Johannes ORCID: 0000-0002-3478-3379, Schafer, Benjamin ORCID: 0000-0003-1607-9748 and Witthaut, Dirk (2022). Secondary control activation analysed and predicted with explainable AI. Electr. Power Syst. Res., 212. LAUSANNE: ELSEVIER SCIENCE SA. ISSN 1873-2046

Full text not available from this repository.

Abstract

The transition to a renewable energy system challenges power grid operation and stability. Secondary control is key in restoring the power system to its reference following a disturbance. Underestimating the necessary control capacity may require emergency measures, such that a solid understanding of its predictability and driving factors is needed. Here, we establish an explainable machine learning model for the analysis of secondary control power in Germany. Training gradient boosted trees, we obtain an accurate ex-post description of control activation. Our explainable model demonstrates the strong impact of external drivers such as forecasting errors and the generation mix, while daily patterns in the reserve activation play a minor role. Training a prototypical forecasting model, we identify forecast error estimates as crucial to improve predictability. Generally, input data and model training have to be carefully adapted to serve the different purposes of either ex-post analysis or forecasting and reserve sizing.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Kruse, Johannes UNSPECIFIED orcid.org/0000-0002-3478-3379 UNSPECIFIED Schafer, Benjamin UNSPECIFIED orcid.org/0000-0003-1607-9748 UNSPECIFIED Witthaut, Dirk UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-685898
DOI:	10.1016/j.epsr.2022.108489
Journal or Publication Title:	Electr. Power Syst. Res.
Volume:	212
Date:	2022
Publisher:	ELSEVIER SCIENCE SA
Place of Publication:	LAUSANNE
ISSN:	1873-2046
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language ARTIFICIAL-INTELLIGENCE; TRANSPARENCY Multiple languages Engineering, Electrical & Electronic Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/68589