Solving AC Power Flow with Graph Neural Networks under Realistic Constraints

Abstract

In this paper we propose a graph neural network architecture solving the AC power flow problem under realistic constraints. While the energy transition is changing the energy industry to a digitalized and decentralized energy system, the challenges are increasingly shifting to the distribution grid level to integrate new loads and generation technologies. To ensure a save and resilient operation of distribution grids, AC power flow calculations are the means of choice to determine grid operating limits or analyze grid asset utilization in planning procedures. In our approach we demonstrate the development of a framework which makes use of graph neural networks to learn the physical constraints of the power flow. We present our model architecture on which we perform unsupervised training to learn a general solution of the AC power flow formulation that is independent of the specific topologies and supply tasks used for training. Finally, we demonstrate, validate and discuss our results on medium voltage benchmark grids.

Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids

“…The proposed data-driven method showed better performance in mesh and radial networks. In [35], an unsupervised graph neural network is presented to capture the topology configuration and physical properties of distribution grids for PF calculations. Authors in [36] propose a support matrix regression to construct the PF mapping by learning the physical embedding in the observable area and general approximation for unobservable regions.…”