🤖 AI Summary
Under energy transition, high renewable penetration and cross-border interconnections intensify grid uncertainty, rendering conventional power flow solvers inadequate for real-time operation, while purely data-driven models lack physical consistency. This paper proposes a physics-informed neural network (PINN) framework for power flow simulation, integrating Kirchhoff’s laws and other physical priors via hybrid modeling—combining MLP/GNN architectures with physics-constrained regularization and unsupervised loss. We introduce a novel four-dimensional evaluation framework (accuracy, physical consistency, industrial deployability, out-of-distribution generalization) and the LIPS benchmark platform. Systematic ablation studies demonstrate that explicit graph-structured modeling and direct optimization of physical equations are critical to reliability. The resulting model achieves high accuracy, strong physical consistency, robust out-of-distribution generalization, and practical industrial deployment potential. Code is fully open-sourced.
📝 Abstract
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.