Potential and challenges of AI-powered decision support for short-term system operations

Conference paper (2022)

Authors

Jan Viebahn TenneT TSO B.V.
Matija Naglic TenneT TSO B.V.
Antoine Marot Reseau de Transport d'Electricite
Benjamin Donnot Reseau de Transport d'Electricite
Simon H. Tindemans Intelligent Electrical Power Grids - EEMCS
Research Group
Intelligent Electrical Power Grids (EEMCS) (TU Delft)
Copyright: © 2022 Jan Viebahn, Matija Naglic, Antoine Marot, Benjamin Donnot, Simon H. Tindemans
Artificial Intelligence Decision-Making Congestion Management Control Centre Decision-Support R&D Ecosystem From Research to Deployment L2RPN Competitions
More Info
expand_more

Published Date

2022

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Electrical Sustainable Energy

Research Group

Intelligent Electrical Power Grids

Abstract

Given the increasing need to meet the new operational requirements of power systems and prepare for the future, adaptation of cutting-edge Artificial Intelligence (AI) technologies in the operational processes is paramount to timely meet the challenges. The focus of this paper is on applying AI in power system operations, in particular for the development of decision support tools. First, the paper elaborates on the decision-making process of the power system operators and presents a mirroring digital framework consisting of AI and control theory to mimic sequential decision making of the operators. Next, a demonstrating example in the field of congestion management is presented by a real-world AI use-case at TenneT TSO. The paper continues with state-of-the-art on sequential decision making applied to congestion management and elaborates on research challenges when applying AI to the power systems problems. Finally, the paper elaborates on the enabling capabilities with focus on people, data, and platform pillars an organisation needs for mastering the development as well as maintenance of AI solutions, and proposes a cyclic (agile) process approach to decrease time from development to actual deployment and cooperation between research and industry organisations.