Advanced state estimation in distribution networks using graph and physics-informed neural networks

Abstract

This document presents a study on state estimation in electrical distribution networks using Graph Neural Networks and graph-based Physics-Informed Neural Networks. Accurate state estimation is crucial for reliable operation, monitoring, and control of modern distribution systems, especially with high penetration of Distributed Energy Resources. Graph-based PhysicsInformed Neural Networks leverage the network’s topology and physical laws to provide scalable and physically consistent estimation. A central focus of this work is the integration of Graph Neural Networks with power flow physics. The proposed approach embeds Kirchhoff’s laws and nodal voltage-current relationships into the neural network’s loss function, ensuring that predictions respect the underlying physics. The network architecture considers node and edge features, such as bus voltages, branchcurrents, loads, and line parameters, enabling themodeltocapturebothtopologicaland electrical dependencies. The study includes detailed modeling of the distribution network and the formulation of the state estimation problem as a physics-informed learning task. Simulations are carried out in Python using PyTorch Geometric to validate the proposed framework.