End-to-End Reinforcement Learning of Curative Curtailment with Partial Measurement Availability

TL;DR

This paper introduces a deep reinforcement learning method for managing distribution grid congestion that requires only partial measurements, achieving high accuracy in real-world low-voltage grids without extensive data.

Contribution

The novel end-to-end reinforcement learning approach enables congestion management with sparse measurements, reducing reliance on full grid observability and computationally intensive methods.

Findings

Resolves 100% of voltage violations in real grid tests

Achieves 98.8% asset overload resolution

Operates effectively with limited measurement data

Abstract

In the course of the energy transition, the expansion of generation and consumption will change, and many of these technologies, such as PV systems, electric cars and heat pumps, will influence the power flow, especially in the distribution grids. Scalable methods that can make decisions for each grid connection are needed to enable congestion-free grid operation in the distribution grids. This paper presents a novel end-to-end approach to resolving congestion in distribution grids with deep reinforcement learning. Our architecture learns to curtail power and set appropriate reactive power to determine a non-congested and, thus, feasible grid state. State-of-the-art methods such as the optimal power flow (OPF) demand high computational costs and detailed measurements of every bus in a grid. In contrast, the presented method enables decisions under sparse information with just some buses observable in the grid. Distribution grids are generally not yet fully digitized and observable, so this method can be used for decision-making on the majority of low-voltage grids. On a real low-voltage grid the approach resolves 100\% of violations in the voltage band and 98.8\% of asset overloads. The results show that decisions can also be made on real grids that guarantee sufficient quality for congestion-free grid operation.