eess.SYNov 6, 2026

Extending Grid Foundation Models for Phasor-Domain Dynamic Simulation

Authors: Boyang Zhao, Yifan Zhou, Alban Puech, Tilman Bockhacker, Hendrik Hamann

Organizations: Department of Electrical and Computer Engineering, Stony Brook University, Stony Brook, NY, USA · IBM Research, ETH Zürich, Zurich, Switzerland · School of Marine and Atmospheric Sciences, Stony Brook University, Stony Brook, NY, USA · Brookhaven National Laboratory, Upton, NY, USA

Abstract

Grid Foundation Models (GridFMs) are emerging as a powerful framework for learning and transferring knowledge across power grids and grid analysis tasks. This work extends GridFMs from steady-state analysis to dynamic simulation. We present DynGridFM, which uses component-wise tokenization and a structured latent operator to learn shared dynamic representations across heterogeneous grids and enable transfer to unseen systems. Pretrained on nine grids, DynGridFM is adapted to a held-out 48-machine grid, where fine-tuning on 64 trajectories achieves accuracy comparable to training from scratch on 128. On a single GPU, it achieves 924x to 1232x speedup over numerical simulators on one CPU core.

Figures & tables

Explore similar work

CardsList
  1. Generalization Testing of Grid Foundation Models for Power Flow and Optimal Power Flow

    Nov 14, 2026Ayushi Jolotia, Parikshit PareekPower SystemsOptimal Power Flow

  2. GridSFM: A Foundation Model for Solving AC Optimal Power Flow

    Sep 24, 2026Luke Bhan, Weiwei Yang, Margaret Capetz +1Neural Surrogate ModelingOptimal Power Flow