[HTML][HTML] Training stiff neural ordinary differential equations in data-driven wastewater process modelling

X Huang, K Kandris, E Katsou - Journal of Environmental Management, 2025‏ - Elsevier
Neural ordinary differential equations (NODEs) have emerged as a powerful tool for data-
driven modelling of dynamical systems (R. Chen et al., 2018). Unlike traditional machine …

Learning Power System Dynamics with Noisy Data Using Neural Ordinary Differential Equations

S Zhang, K Yamashita, N Yu - 2024 IEEE Power & Energy …, 2024‏ - ieeexplore.ieee.org
The ability to learn complex system dynamics is crucial to enhancing the reliability and
stability of power systems. In this paper, we develop a novel neural ordinary differential …

Power System Frequency Dynamics Modeling, State Estimation, and Control using Neural Ordinary Differential Equations (NODEs) and Soft Actor-Critic (SAC) …

P Aslami, T Aryal, A Rai, N Bhujel… - ACM SIGAPP Applied …, 2024‏ - dl.acm.org
With the global energy transition of the electric power system, grid control, supervision, and
protection is becoming more challenging. With the increasing integration of renewable …

Learning power system dynamics with nearly-Hamiltonian neural network

S Zhang, N Yu - 2023 IEEE Power & Energy Society General …, 2023‏ - ieeexplore.ieee.org
The ability to learn power system dynamic model and predict transient trajectories using
data is crucial to realizing closed-loop control of the system with artificial intelligence. This …

Application of Neural Ordinary Differential Equations to Power System Frequency Dynamics

T Aryal, P Aslami, N Bhujel… - 2023 North …, 2023‏ - ieeexplore.ieee.org
Electric power system control, supervision, and protection actions require an accurate
system dynamics model. The swing equation-based modeling approach does not properly …

Financial Time Series Prediction via Neural Ordinary Differential Equations Approach

J Li, W Zhu, Z Chen, C Pei - 2023 International Annual …, 2023‏ - ieeexplore.ieee.org
This paper considers the prediction problem of financial time series, namely, the prediction
of exchange rate for four currencies with the Chinese Yuan (CNY). A novel approach is …

Modeling Power Systems Dynamics with Symbolic Physics-Informed Neural Networks

HTT Tran, HT Nguyen - 2024 IEEE Power & Energy Society …, 2024‏ - ieeexplore.ieee.org
In recent years, scientific machine learning, particularly physic-informed neural networks
(PINNs), has introduced new innovative methods to understanding the differential equations …

Parameter Estimation of Synchronous Generator Using Neural Controlled Differential Equations

Z Yin, H Wang, ZP Jiang - 2024 IEEE 18th International …, 2024‏ - ieeexplore.ieee.org
This paper introduces a synchronous generator modeling method based on neural
controlled differential equations (neural CDEs) using online sampled data. This method …

Parameter identification through gradient flow on latent variables

M Boulakia, H Liu, D Lombardi - 2023‏ - inria.hal.science
In this article, we consider a system of parametric ODEs which involves unknown
parameters and we seek to identify the values of the parameters associated to a given …

[PDF][PDF] Physics-informed ML for power grids

VJ Nair - 2023‏ - raw.githubusercontent.com
In this project, I explore the use of physics-informed machine learning for simulating and
analyzing transmission grids, to aid planning as well as real-time operations. Scientific …