Reinforcement Learning for Coordinated Protection in Power Grids

Type: MA thesis

Status: open

Supervisors: Julian Oelhaf

Tasks:

  • Develop and evaluate reinforcement learning (RL) strategies to coordinate protection elements (e.g., circuit breakers, relays) in high-voltage transmission grids.

  • Design grid scenarios (e.g., multi-faults, communication delays, islanding) and simulate them using synthetic fault data.

  • Train RL agents to minimize fault impact and improve restoration behavior.

  • Analyze robustness under different operating conditions and topologies.

  • (Optional) Investigate hybrid RL + rule-based schemes or curriculum learning.

  • (Optional) Contribute to a research publication based on your results.

Requirements:

  • Solid experience with PyTorch

  • Experience training deep learning models

  • Ability to attend in-person meetings

  • Bonus: Background in electrical engineering, power systems, or control theory

Application:

Send your application with the subject
“Application RL Protection Thesis + your full name” to julian.oelhaf@fau.de and include:

  • Curriculum Vitae (CV)

  • Short motivation letter (max. one page)

  • Transcript of records

 

This topic can also be conducted as a smaller project (e.g., research or programming project) instead of a full thesis.