Acceleration of Power System Dynamic Simulations using a Deep Equilibrium Layer and Neural ODE Surrogate

TL;DR

This paper introduces a data-driven surrogate model using deep equilibrium layers and neural ODEs to accelerate power system dynamic simulations, reducing computational time while maintaining accuracy without detailed physics models.

Contribution

It presents a novel implicit machine learning surrogate that efficiently models power system dynamics, integrating seamlessly with existing workflows and bypassing the need for detailed component models.

Findings

Achieves similar accuracy to physics-based models

Reduces simulation time significantly

Easily integrates into current simulation workflows

Abstract

The dominant paradigm for power system dynamic simulation is to build system-level simulations by combining physics-based models of individual components. The sheer size of the system along with the rapid integration of inverter-based resources exacerbates the computational burden of running time domain simulations. In this paper, we propose a data-driven surrogate model based on implicit machine learning -- specifically deep equilibrium layers and neural ordinary differential equations -- to learn a reduced order model of a portion of the full underlying system. The data-driven surrogate achieves similar accuracy and reduction in simulation time compared to a physics-based surrogate, without the constraint of requiring detailed knowledge of the underlying dynamic models. This work also establishes key requirements needed to integrate the surrogate into existing simulation workflows; the proposed surrogate is initialized to a steady state operating point that matches the power flow solution by design.