Logo image
Back
PINNs-Based Uncertainty Quantification for Transient Stability Analysis
Conference proceeding   Open access

PINNs-Based Uncertainty Quantification for Transient Stability Analysis

Ren Wang, Ming Zhong, Kaidi Xu, Lola Giraldez Sanchez-Cortes and Ignacio De Cominges Guerra
2026 9th International Conference on Electrical Engineering and Green Energy (CEEGE), pp 397-401
15 May 2026
DOI: https://doi.org/10.1109/CEEGE70076.2026.11637840
url
https://doi.org/10.48550/arXiv.2311.12947View
Submitted Open arXiv.org - Non-exclusive license to distribute

Abstract

ensemble PINNs Equations Generators Modeling Neural networks physicsinformed neural networks Power systems Printing Stability stability analysis Transient analysis Uncertainty Physics
This paper addresses the challenge of transient stability in power systems characterized by missing parameters and the propagation of uncertainty in swing equations. We introduce a novel application of Physics-Informed Neural Networks (PINNs), specifically, an Ensemble of PINNs (E-PINNs), to solve the swing equations and estimate critical parameters, such as the inertia coefficient, in noisy environments. E-PINNs leverage the underlying physical principles of swing equations to provide a robust solution. Our approach not only facilitates efficient parameter estimation but also quantifies uncertainties, thereby delivering probabilistic insights into system behavior. The efficacy of E-PINNs is demonstrated through the analysis of 1-bus, 2-bus, and 14-bus systems, highlighting the model's ability to handle parameter variability and data scarcity. This study advances the application of machine learning in power system stability, paving the way for reliable and computationally efficient transient stability analysis.

Metrics

1 Record Views

Related content

Has preprint

Details

Logo image