Verification and Validation of Physics-Informed Surrogate Component Models for Dynamic Power-System Simulation

TL;DR

This paper develops a framework for verifying and validating physics-informed surrogate models in power system simulations, emphasizing the importance of in-simulator accuracy over standalone performance, with a focus on neural-network surrogates of synchronous machines.

Contribution

It introduces a finite-horizon bound linking component output errors to system sensitivity, and studies model-based and data-based validation methods for physics-informed neural surrogates in power systems.

Findings

Good standalone accuracy does not ensure in-simulator accuracy.

Discrepancies are concentrated in stressed operating regions.

Small residuals do not guarantee small trajectory errors.

Abstract

Physics-informed machine learning surrogates are increasingly explored to accelerate dynamic simulation of generators, converters, and other power grid components. The key question, however, is not only whether a surrogate matches a stand-alone component model on average, but whether it remains accurate after insertion into a differential-algebraic simulator, where the surrogate outputs enter the algebraic equations coupling the component to the rest of the system. This paper formulates that in-simulator use as a verification and validation (V\&V) problem. A finite-horizon bound is derived that links allowable component-output error to algebraic-coupling sensitivity, dynamic error amplification, and the simulation horizon. Two complementary settings are then studied: model-based verification against a reference component solver, and data-based validation through conformal calibration of the component-output variables exchanged with the simulator. The framework is general, but the case study focuses on physics-informed neural-network surrogates of second-, fourth-, and sixth-order synchronous-machine models. Results show that good stand-alone surrogate accuracy does not by itself guarantee accurate in-simulator behavior, that the largest discrepancies concentrate in stressed operating regions, and that small equation residuals do not necessarily imply small state-trajectory errors.