English

A Physics Informed Machine Learning Method for Power System Model Parameter Optimization

Systems and Control 2023-09-29 v1 Systems and Control

Abstract

This paper proposes a gradient descent based optimization method that relies on automatic differentiation for the computation of gradients. The method uses tools and techniques originally developed in the field of artificial neural networks and applies them to power system simulations. It can be used as a one-shot physics informed machine learning approach for the identification of uncertain power system simulation parameters. Additionally, it can optimize parameters with respect to a desired system behavior. The paper focuses on presenting the theoretical background and showing exemplary use-cases for both parameter identification and optimization using a single machine infinite busbar system. The results imply a generic applicability for a wide range of problems.

Keywords

Cite

@article{arxiv.2309.16579,
  title  = {A Physics Informed Machine Learning Method for Power System Model Parameter Optimization},
  author = {Georg Kordowich and Johann Jaeger},
  journal= {arXiv preprint arXiv:2309.16579},
  year   = {2023}
}

Comments

7 pages, 8 figures

R2 v1 2026-06-28T12:35:08.441Z