Accelerating Quasi-Static Time Series Simulations with Foundation Models

TL;DR

This paper explores how grid foundation models can enhance neural power flow solvers, making quasi-static time series simulations faster and more accessible for grid operation and planning.

Contribution

It proposes using grid foundation models to amortize training costs and improve neural power flow solvers for various grid tasks, promoting collaboration and open-source development.

Findings

Neural power flow solvers can be accelerated by foundation models.

Foundation models reduce training costs for neural power flow solutions.

Open-source foundation models can democratize AI benefits in power grid management.

Abstract

Quasi-static time series (QSTS) simulations have great potential for evaluating the grid's ability to accommodate the large-scale integration of distributed energy resources. However, as grids expand and operate closer to their limits, iterative power flow solvers, central to QSTS simulations, become computationally prohibitive and face increasing convergence issues. Neural power flow solvers provide a promising alternative, speeding up power flow computations by 3 to 4 orders of magnitude, though they are costly to train. In this paper, we envision how recently introduced grid foundation models could improve the economic viability of neural power flow solvers. Conceptually, these models amortize training costs by serving as a foundation for a range of grid operation and planning tasks beyond power flow solving, with only minimal fine-tuning required. We call for collaboration between the AI and power grid communities to develop and open-source these models, enabling all operators, even those with limited resources, to benefit from AI without building solutions from scratch.