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

Jan Viebahn, Matija Naglic, Antoine Marot, Benjamin Donnot, Simon H. Tindemans

Research output: Contribution to conferencePaperpeer-review

662 Downloads (Pure)

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.
Original languageEnglish
Number of pages16
Publication statusPublished - 2022
EventCIGRE paris Session 2022 - Palais des Congrès, Paris, France
Duration: 28 Aug 20222 Sept 2022

Conference

ConferenceCIGRE paris Session 2022
Country/TerritoryFrance
CityParis
Period28/08/222/09/22

Keywords

  • Artificial Intelligence
  • Control Centre
  • Decision-Making
  • Decision-Support
  • R&D Ecosystem
  • From Research to Deployment
  • Congestion Management
  • L2RPN Competitions

Fingerprint

Dive into the research topics of 'Potential and challenges of AI-powered decision support for short-term system operations'. Together they form a unique fingerprint.

Cite this