Physics-Informed Neural Network for Modeling the Dynamic Behavior of Grid-Forming Converters

Hussein Jaffal; Arianna Fois; Sarra Bouchkati; Amirali Mahjoob; Andreas Ulbig

Physics-Informed Neural Network for Modeling the Dynamic Behavior of Grid-Forming Converters

Systems and Control 2026-07-24 v1

Authors: Hussein Jaffal , Arianna Fois , Sarra Bouchkati , Amirali Mahjoob , Andreas Ulbig

Abstract

This paper investigates physics-informed neural networks for modeling the full dynamic behavior of droop-controlled grid-forming converters. The approach is trained on synthetic data generated via numerical solvers and benchmarked against both traditional integration methods and a vanilla neural network. Results show higher predictive accuracy than the vanilla network using the same training data and substantially reduced runtime compared with numerical solvers.

Keywords

physics-informed neural network grid-forming converter droop control dynamic modeling synthetic data numerical solver

Cite

@article{arxiv.2607.22327,
  title  = {Physics-Informed Neural Network for Modeling the Dynamic Behavior of Grid-Forming Converters},
  author = {Hussein Jaffal and Arianna Fois and Sarra Bouchkati and Amirali Mahjoob and Andreas Ulbig},
  journal= {arXiv preprint arXiv:2607.22327},
  year   = {2026}
}

Comments

This work has been accepted by IFAC for publication under a Creative Commons license CC-BY-NC-ND