EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Active Learning of Microgrid Frequency Dynamics Using Neural Ordinary Differential Equations

Tara Aryal, Pooja Aslami, Niranjan Bhujel, Hossein Moradi Rekabdarkolaee, Kaiqun Fu, Zongjie Wang, Timothy M. Hansen

IET Energy Systems Integration · 2025-01 · 7 (1)

DOI: 10.1049/esi2.70020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Energy Systems Integration, online erschienen am 18.10.2025. Verfasst von Tara Aryal und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, Office of Electricity.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate frequency modelling of inverter‐based resource (IBR)‐dominated power systems is crucial for ensuring stable, reliable and resilient operations, particularly given their inherent low‐inertia characteristics and fast dynamics that traditional swing equation‐based models inadequately capture. This paper explores neural ordinary differential equations (Neural ODEs) as a computationally efficient, data‐driven framework for modelling power system frequency dynamics, specifically within microgrids integrating high penetrations of distributed energy resources (DERs). The developed neural ODEs framework incorporates a neural network architecture designed to capture input dynamics. By actively perturbing the system with a known signal, the Python‐based neural ODEs framework was trained using measured system states and inputs, without the need for detailed system information. The framework, tested on a model of the Cordova, AK, microgrid, achieved a goodness of fit ranging from 60% to 99% across different state variables and maintained a mean square error in the p.u. range under square and step excitation signals. The proposed approach demonstrated robustness to measurement noise and initial condition variations while maintaining low computational complexity suitable for real‐time power system control applications. Furthermore, transfer learning enabled the neural ODEs model to adapt to the following changes in system topology or generator dispatch, highlighting its effectiveness for dynamic microgrids with frequently evolving configurations and diverse DERs.

Förderung

  • National Science Foundation
  • Office of Electricity

Zitieren

APA

Aryal, T., Aslami, P., Bhujel, N., Rekabdarkolaee, H. M., Fu, K., Wang, Z., & Hansen, T. M. (2025). Active Learning of Microgrid Frequency Dynamics Using Neural Ordinary Differential Equations. IET Energy Systems Integration, 7(1). https://doi.org/10.1049/esi2.70020

Vancouver

Aryal T, Aslami P, Bhujel N, Rekabdarkolaee HM, Fu K, Wang Z, et al. Active Learning of Microgrid Frequency Dynamics Using Neural Ordinary Differential Equations. IET Energy Systems Integration. 2025;7(1). doi:10.1049/esi2.70020

BibTeX
@article{Aryal2025,
  author = {Aryal, Tara and Aslami, Pooja and Bhujel, Niranjan and Rekabdarkolaee, Hossein Moradi and Fu, Kaiqun and Wang, Zongjie and Hansen, Timothy M.},
  title = {Active Learning of Microgrid Frequency Dynamics Using Neural Ordinary Differential Equations},
  journal = {IET Energy Systems Integration},
  year = {2025},
  volume = {7},
  number = {1},
  doi = {10.1049/esi2.70020}
}
Kostenlos starten →