Thomas Wolgast
Contact
Secretary:
Head
Thomas Wolgast
- Real-time capable optimal power flow
- Machine Learning / Reinforcement Learning
- Environment design for RL
- Attacks on energy systems
- System service markets
- Multi-agent systems
Department of Computing Science (» Postal address)
Curriculum vitae
Thomas Wolgast is doctoral student in the field of energy informatics at the University of Oldenburg.
He received his Master of Science in Power Engineering from the Leibniz University Hannover. His master thesis was the implementation and evaluation of multi-agent based voltage control concepts in the distribution grid.
Thomas uses reinforcement learning to approximate the optimal power flow, one of the most important optimisation problems in energy system research. One focus of the work is the environment design, as the optimal representation of the optimal power flow problem as a reinforcement learning environment.
Lectures
Winter term 2024 / 2025
Publications
- Wolgast, T., Nieße, A. Towards modular composition of agent-based voltage control concepts. Energy Inform 2, 26 (2019). https://doi.org/10.1186/s42162-019-0079-x
- Neugebauer, T.; Wolgast, T.; Nieße, A. Dynamic Inspection Interval Determination for Efficient Distribution Grid Asset-Management. Energies 2020, 13, 3875. https://doi.org/10.3390/en13153875
- Veith, Eric; Balduin, Stephan; Wenninghoff, Nils; Tröschel, Martin; Fischer, Lars; Nieße, Astrid et al. (2020): Analyzing Power Grid, ICT, and Market Without Domain Knowledge Using Distributed Artificial Intelligence. In:. CYBER 2020, The Fifth International Conference on Cyber-Technologies and Cyber-Systems, S. 86–93.
- Wolgast, Thomas (2020): Real-Time Capable Optimal Power Flow With Artificial Neural Networks. Abstracts from the 9th DACH+ Conference on Energy Informatics, Volume 3 Supplement 2, Sierre, Switzerland. 29-30 October 2020. https://doi.org/10.1186/s42162-020-00113-9
- Buchholz S, Tiemann PH, Wolgast T, Scheunert A, Gerlach J, Majumdar N, Breitner M, Hofmann L, Nieße A, Weyer H (2021) A sketch of unwanted gaming strategies in flexibility provision for the energy system. In: 16th International Conference on Wirtschaftsinformatik, Pre-Conference Community Workshop Energy Informatics and Electro Mobility ICT
- Wolgast, Thomas; Veith, Eric MSP; Nieße, Astrid (2021): Towards Reinforcement Learning for Vulnerability Detection in Power Systems and Markets. In: Proceedings of the Twelfth ACM International Conference on Future Energy Systems. e-Energy '21: The Twelfth ACM International Conference on Future Energy Systems. Virtual Event Italy, 28 06 2021 02 07 2021. New York,NY,United States: Association for Computing Machinery (ACM Digital Library), S. 292–293.
- Wolgast, Thomas; Veith, Eric MSP; Nieße, Astrid (2021): Towards reinforcement learning for vulnerability analysis in power-economic systems. In: Energy Informatics 4 (S3). DOI: 10.1186/s42162-021-00181-5.
- Thomas Wolgast, Nils Wenninghoff, Stephan Balduin, Eric Veith, Bastian Fraune, Torben Woltjen, Astrid Nieße, “Analyse–learning to attack cyber-physical energy systems with intelligent agents,” SoftwareX, Apr. 2023. DOI: 10.1016/j.softx.2023.101484
- Thomas Wolgast and Astrid Nieße. Learning the optimal power flow: Environment design matters. Energy and AI, page 100410, August 2024. ISSN 2666-5468. doi: 10.1016/j.egyai.2024.100410