English

Physics-Informed Neural Networks for Non-linear System Identification for Power System Dynamics

Systems and Control 2021-04-16 v2 Machine Learning Systems and Control

Abstract

Varying power-infeed from converter-based generation units introduces great uncertainty on system parameters such as inertia and damping. As a consequence, system operators face increasing challenges in performing dynamic security assessment and taking real-time control actions. Exploiting the widespread deployment of phasor measurement units (PMUs) and aiming at developing a fast dynamic state and parameter estimation tool, this paper investigates the performance of Physics-Informed Neural Networks (PINN) for discovering the frequency dynamics of future power systems. PINNs have the potential to address challenges such as the stronger non-linearities of low-inertia systems, increased measurement noise, and limited availability of data. The estimator is demonstrated in several test cases using a 4-bus system, and compared with state of the art algorithms, such as the Unscented Kalman Filter (UKF), to assess its performance.

Keywords

Cite

@article{arxiv.2004.04026,
  title  = {Physics-Informed Neural Networks for Non-linear System Identification for Power System Dynamics},
  author = {Jochen Stiasny and George S. Misyris and Spyros Chatzivasileiadis},
  journal= {arXiv preprint arXiv:2004.04026},
  year   = {2021}
}

Comments

6 pages, 8 figures, accepted at IEEE PES PowerTech 2021 Madrid

R2 v1 2026-06-23T14:44:20.481Z