Naslov (eng)

Scalability and sample efficiency analysis of graph neural networks for power system state estimation

Autor

Kundačina, Ognjen
Gojić, Gorana
Ćosović, Mirsad
Mišković, Dragiša
Vukobratović, Dejan

Publisher

Opis (eng)

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.

Jezik

engleski

Datum

2023

Licenca

© All rights reserved

Deo kolekcije (1)

o:1610

Radovi saradnika Instituta za veštačku inteligenciju