Graph Neural Networks for Grid Control: Prospects in AI-assisted Transmission Grid Operation

Abstract:
Transmission grid congestion management and outage planning are critical tasks in modern grid operation due to the non-linear nature of power flows and the large-scale optimization challenges faced by operators. Traditionally, overloads are addressed through generator redispatch, a costly and therefore suboptimal measure. In the project "Graph Neural Networks for Grid Control" (GNN4GC), we investigate alternative strategies, focusing on topological remedial actions that could minimize or even completely eliminate redispatch costs. Topology optimization, a core aspect of this project, presents significant challenges due to its combinatorial nature, requiring extensive computational resources for power flow calculations. To address this, GNN4GC is split into three stages. In the first stage, we explore the use of Graph Neural Networks (GNNs) to accelerate these calculations and benchmark their performance against established tools like pandapower and a DC power flow solver developed by 50Hertz Transmission GmbH and TenneT TSO GmbH. In the second stage, we use Reinforcement Learning and other heuristics to select suitable topologies and solve the topology optimization problem. As a third stage, we test the respective agent on real-life grids to benchmark the methodology. The aim of the final stage is to build a recommender system that can be used in a control room in the future.