Physics-Informed Inductive Biases for Voltage Prediction in Distribution Grids
This work addresses voltage prediction for distribution grid operators, but it is incremental as it evaluates existing strategies rather than introducing a new method.
The paper tackled the problem of voltage prediction in distribution grids, which is critical for power system stability, by systematically evaluating three physics-informed inductive biases to improve generalization with limited data, using the ENGAGE dataset to assess performance and out-of-distribution generalization.
Voltage prediction in distribution grids is a critical yet difficult task for maintaining power system stability. Machine learning approaches, particularly Graph Neural Networks (GNNs), offer significant speedups but suffer from poor generalization when trained on limited or incomplete data. In this work, we systematically investigate the role of inductive biases in improving a model's ability to reliably learn power flow. Specifically, we evaluate three physics-informed strategies: (i) power-flow-constrained loss functions, (ii) complex-valued neural networks, and (iii) residual-based task reformulation. Using the ENGAGE dataset, which spans multiple low- and medium-voltage grid configurations, we conduct controlled experiments to isolate the effect of each inductive bias and assess both standard predictive performance and out-of-distribution generalization. Our study provides practical insights into which model assumptions most effectively guide learning for reliable and efficient voltage prediction in modern distribution networks.