Masters thesis

Author: Bc. Patrik Filipiak
Name: Reinforcement learning for power grid optimization.
Supervisor: doc. Ing. Peter Lacko, PhD.
Goal:

1. Study the literature related reinforcement learning optimalization.
2. In an appropriate simulation environment, propose and implement a method for optimizing the distribution grid based on selected factors (e.g., electricity costs, charging demands of electric vehicles)
3. Compare the results with existing solutions.

• 3.10. - Simulation environment setup
• 17.10. - Running tests to learn how the environment works
• 24.10. - New literature review
• 7.11. - Design of prototype: benchmark problem tests
• 14.11. - Running benchmark tests
• 28.11. - Analysis of results from benchmark tests
• 5.12. - Preparing presentation

1. Reinforcement learning for electric vehicle applications in power systems:A critical review
   Authors: Dawei Qiu, Yi Wang, Weiqi Hua and Goran Strbac
   Date of access: 11.12.2025
2. FleetRL: Realistic reinforcement learning environments for commercial vehicle fleets
   Authors:Enzo Cording and Jagruti Thakur
   Date of access: 2.6.2025
3. EV2Gym: A Flexible V2G Simulator for EV Smart Charging Research and Benchmarking
   Authors:Orfanoudakis, Stavros and Diaz-Londono, Cesar and Emre Yılmaz, Yunus and Palensky, Peter and Vergara, Pedro P.
   Date of access: 11.12.2025
4. Physics-Informed Reinforcement Learning for Large-Scale EV Smart Charging Considering Distribution Network Voltage Constraints
   Authors:Stavros Orfanoudakis, Frans A. Oliehoek, Peter Palensky, Pedro P. Vergara
   Date of access: 11.12.2025