Power to the Relational Inductive Bias
Martin Ringsquandl, Houssem Sellami, Marcel E. Hildebrandt, Dagmar Beyer, Sylwia Henselmeyer, Sebastian Weber, Mitchell Joblin · 2021
The application of graph neural networks (GNNs) to the domain of electrical power grids has high potential impact on smart grid monitoring. Even though there is a natural correspondence of power flow to message-passing in GNNs, their performance on power grids is not well-understood. We argue that there is a gap between GNN research driven by benchmarks which contain graphs that differ from power grids in several important aspects. Additionally, inductive learning of GNNs across multiple power grid topologies has not been explored with real-world data.