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

Nov 14, 2026

Generalization Testing of Grid Foundation Models for Power Flow and Optimal Power Flow

There is growing interest in foundation models (FMs) for power grids, particularly for power flow and optimal power flow. Their usefulness depends on generalization accuracy, which existing works test on their own benchmarks. We propose a three-axis framework to test their generalization limits: changed admittance matrices of training grids, load levels, and unseen grids. We test GENCO, LUMINA and GridSFM against the DC baseline, alongside their reported limitations, and discuss theoretical reasons for their failures. Experiments reveal that adding a line degrades all FMs more than removing one, and longer lines eventually make LUMINA and fine-tuned GENCO worse than DC. All three degrade beyond their training load range, where the loading-voltage curve steepens. On unseen grids, LUMINA degrades sharply even inside its training range, and GridSFM fails on the grid farthest from it. Thus, beyond training conditions, FMs behave more like meta-models requiring test-time fine-tuning data and compute.
Sep 24, 2026

GridSFM: A Foundation Model for Solving AC Optimal Power Flow

We introduce GridSFM, a framework that combines a pretrained foundation model across grid topologies with physics-informed fine-tuning for solving AC Optimal Power Flow (AC-OPF) at scale. It is a 1515 million parameter physics-inspired graph neural network pretrained across 5454 topologies of 500500 to 4,0004{,}000 buses. Our model attains a 2.45%2.45\% zero-shot generation-cost error on a 10,00010{,}000 bus case held-out operating conditions with no degradation as system size grows. Building on this, we pair the pretrained backbone with a physics-informed fine-tuning design based on Newton's method for power flow. With only 100100 solved instances, GridSFM adapts to unseen grids up to 10,00010{,}000 buses. We show it out performs single topology, dedicated neural network models that are trained more data, both in terms of cost and solver iterations when deployed as warm starting points. In designing this foundation model, we overcome the fact that the feasible set for AC-OPF can be disconnected. This is an obstruction that prevents any continuous neural network from approximating the solution map. To do so, we lift the problem and relax its constraints with logarithmically penalized slacks. We prove that the resulting elastic feasible set is contractible, that the AC-OPF minimizers remain minimizers of the elastic problem above an explicit penalty threshold, and that projecting an approximate solution back onto the AC-OPF feasible set is well posed. We release all models, data, and code so that the community can build on a shared starting point for AC-OPF.
Nov 6, 2026

Can Time Series Foundation Models Serve as Surrogates for Power Systems Dynamic Simulation?

High-fidelity dynamic simulation is essential for scientific and engineering applications, but its computational cost limits large-scale scenario screening. We investigate the use of pretrained time-series foundation models (TSFMs) as computationally efficient surrogates to address this limitation. In-context learning and post-training strategies, including retrieval-augmented reference sample selection and physics-informed regularization, are considered in the investigation. Results are benchmarked against a traditional AI model representative of the state-of-the-art in the domain. Experiments using an open-source TSFM and data from a simulated 9-bus power system indicate promising results. Retrieval augmentation improves in-context learning performance, and fine-tuning leads to superior results compared to the traditional AI model, especially when including physics-informed regularization. The fine-tuned TSFMs achieve lower errors and improved computational costs compared to the traditional AI model, and a 563×\times speedup compared to the original physics-based simulation.