o:2500 Scalability and sample efficiency analysis of graph neural networks for power system state estimation en Data-driven state estimation (SE) is becoming increasingly important in modern power systems, as it allows for more efficient analysis of system behaviour using real-time measurement data. This paper thoroughly evaluates a phasor measurement unit-only state estimator based on graph neural networks (GNNs) applied over factor graphs. To assess the sample efficiency of the GNN model, we perform multiple training experiments on various training set sizes. Additionally, to evaluate the scalability of the GNN model, we conduct experiments on power systems of various sizes. Our results show that the GNN-based state estimator exhibits high accuracy and efficient use of data. Additionally, it demonstrated scalability in terms of both memory usage and inference time, making it a promising solution for data-driven SE in modern power systems. 1552099 10.1109/BalkanCom58402.2023.10167975 2023-07-04T14:12:41.951Z 44 yes 46 Ognjen Kundačina The Institute for Artificial Intelligence Research and Development of Serbia 0000-0003-0198-3363 Gorana Gojić The Institute for Artificial Intelligence Research and Development of Serbia person 0000-0002-6100-5871 Mirsad Ćosović The Institute for Artificial Intelligence Research and Development of Serbia person 0000-0003-2474-8446 Dragiša Mišković The Institute for Artificial Intelligence Research and Development of Serbia person 0000-0002-0455-9552 Dejan Vukobratović Faculty of Technical Sciences, Novi Sad, Serbia person 0000-0002-5305-8420 application/pdf 17380 https://unilib.phaidrabg.rs/o:2500 no yes 1 70 92000004 71A08 2023 International Balkan Conference on Communications and Networking (BalkanCom) IEEE 2023