About

Hannah Markgraf joined the Cyber-Physical Systems Group as PhD candidate under the supervision of Prof. Dr.-Ing. Matthias Althoff in February 2022. She received her M.Sc. in Automation & Control and her B.Sc. in Mechanical Engineering from RWTH Aachen University. Her current research focuses on safe multi-agent reinforcement learning and its applications to power systems.

Offered Thesis Topics

I am always looking for motivated students who are interested in writing a thesis related to my area of research. If you are considering one of the currently offered topics or want to discuss your own research idea, please get in touch via email including your CV, transcript of records, and a brief statement of your motivation.

Currently available:

Ongoing:

• [BA] Continuous Improvement of Energy Management Systems Using Offline Reinforcement Learning
• [MA] Control Strategy for Energy Management Systems for Commercial Electrical Energy Systems

Finished:

• [BA] Provably Safe Reinforcement Learning Control of a Quadrotor
• [MA] How to Achieve Optimality in Safe Reinforcement Learning? (co-advised with Hanna Krasowski and Lukas Schäfer)
• [IDP] Economic dispatch with power flow constraints using safe reinforcement learning (co-supervised with Michael Eichelbeck)
• [IDP] Probabilistic occupancy prediction of EV charging stations: A data-driven approach

Teaching

Lectures

• SoSe 23 - Cyber-Physical Systems
• WiSe 22/23 - Formal Methods for Cyber-Physical Systems

Practical Course - Machine Learning for Power Systems (co-organized with Michael Eichelbeck)

• WiSe 23/24 - Benchmarking reinforcement learning for energy system control
• SoSe 23 - Safe multi-agent reinforcement learning
• SoSe 23 - Safe reinforcement learning for households with heat pumps

Seminar - Cyber-Physical Systems

• WiSe 22/23 - Forecasting of renewable energy generation and power demand (co-advised with Michael Eichelbeck)
• WiSe 22/23 - Solving optimal power flow with machine learning (co-advised with Michael Eichelbeck)
• SoSe 22 - Constraint set certification for reinforcement learning (co-advised with Lukas Schäfer)
• SoSe 22 - Safe reinforcement learning with logical specifications (co-advised with Hanna Krasowski)