Study Design and Demystification of Physics Informed Neural Networks for Power Flow Simulation
This work addresses the need for fast, physically-constrained power flow simulators for grid operators dealing with renewable energy integration, though it appears incremental in systematically comparing existing PINN approaches.
The paper conducted an ablation study to analyze how different physics-informed neural network (PINN) hybridization strategies affect performance in power flow simulation, evaluating models across accuracy, physical compliance, industrial readiness, and out-of-distribution generalization using their custom LIPS benchmarking pipeline.
In the context of the energy transition, with increasing integration of renewable sources and cross-border electricity exchanges, power grids are encountering greater uncertainty and operational risk. Maintaining grid stability under varying conditions is a complex task, and power flow simulators are commonly used to support operators by evaluating potential actions before implementation. However, traditional physical solvers, while accurate, are often too slow for near real-time use. Machine learning models have emerged as fast surrogates, and to improve their adherence to physical laws (e.g., Kirchhoff's laws), they are often trained with embedded constraints which are also known as physics-informed or hybrid models. This paper presents an ablation study to demystify hybridization strategies, ranging from incorporating physical constraints as regularization terms or unsupervised losses, and exploring model architectures from simple multilayer perceptrons to advanced graph-based networks enabling the direct optimization of physics equations. Using our custom benchmarking pipeline for hybrid models called LIPS, we evaluate these models across four dimensions: accuracy, physical compliance, industrial readiness, and out-of-distribution generalization. The results highlight how integrating physical knowledge impacts performance across these criteria. All the implementations are reproducible and provided in the corresponding Github page.