Robustness of Reinforcement Learning-Based Congestion Management in Low-Voltage Grids
Artificial Intelligence
Summary
The authors focus on managing power problems in small electric grids caused by solar panels, electric cars, and heat pumps. They build a system that first predicts if there will be a problem using a random forest, then uses a special controller to fix it. They test this on a real grid with limited data and find their method works very well, especially when grid information is accurate. Even when the grid data is off, their system still helps reduce most problems.
Authors
Josef Hoppe, Sarra Bouchkati, Farah Nasr, Jonathan Krapp, Alexander Och, Maximilian Wirth, Jan Schiefelbein-Lach, Oliver Pohl, Andreas Ulbig, Michael T. Schaub
Abstract
Increases in photovoltaic generation, charging of electric vehicles and heat-pump demand challenge operating limits in low-voltage distribution grids. This requires curative curtailment methods that can operate under sparse observability, noisy measurements, and imperfect grid models. Unlike prior end-to-end reinforcement-learning approaches for partially observable curtailment, this work decouples congestion detection and control by combining a random-forest violation pre-classifier with an actor-critic controller, and evaluates its robustness to measurement noise and grid-parameter mismatch. The framework is tested on a real low-voltage grid using synthetic future operating scenarios with low observability and controllability. With accurate grid parameters, the controller reduces total violation magnitude by 98.9%, and this performance remains nearly unchanged under the tested measurement-noise settings. Grid-model mismatch proves to be more challenging, but the controller still mitigates most violations under the tested mismatch assumptions.