Robustness of Reinforcement Learning-Based Congestion Management in Low-Voltage Grids

2026-07-17

AI Summary

This study addresses the risk of voltage violations in low-voltage distribution networks caused by the integration of photovoltaic systems, electric vehicles, and heat pumps. Under conditions of sparse observability, measurement noise, and model mismatch, the authors propose a decoupled congestion management approach that uniquely integrates a random forest pre-classifier with an Actor-Critic reinforcement learning controller. The pre-classifier efficiently identifies potential voltage violations, while the controller enacts corrective curtailment actions. Experimental results demonstrate that the proposed method reduces violation magnitudes by 98.9% when system parameters are accurate, exhibits negligible performance degradation under measurement noise, and remains effective in mitigating most violations despite model mismatch. This significantly enhances the robustness of congestion control in partially observable distribution grids.

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.

Problem

• congestion management
• low-voltage grids
• reinforcement learning
• measurement noise
• grid-model mismatch

Innovation

• reinforcement learning
• congestion management
• low-voltage grids
• robustness
• actor-critic