Active Learning of Microgrid Frequency Dynamics Using Neural Ordinary Differential Equations

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

doi:10.1049/esi2.70020

Active Learning of Microgrid Frequency Dynamics Using Neural Ordinary Differential Equations

Journal Article · Sat Oct 18 00:00:00 EDT 2025 · IET Energy Systems Integration

DOI:https://doi.org/10.1049/esi2.70020· OSTI ID:3001121

^[1]; ^[1]; Bhujel, Niranjan ^[2]; Rekabdarkolaee, Hossein Moradi ^[3]; Fu, Kaiqun ^[4]; Wang, Zongjie ^[5]; Hansen, Timothy M. ^[5]

South Dakota State Univ., Brookings, SD (United States)
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Bowling Green State Univ., OH (United States)
Texas Christian Univ., Fort Worth, TX (United States)
Colorado State Univ., Fort Collins, CO (United States)

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 10^-6 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.

View Accepted Manuscript (DOE)

Research Organization:: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Sponsoring Organization:: National Science Foundation (NSF); USDOE Office of Electricity (OE); USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office; USDOE Office of Science (SC)

Grant/Contract Number:: NA0003525; SC0020281

OSTI ID:: 3001121

Report Number(s):: SAND--2025-13968J; 1766783

Journal Information:: IET Energy Systems Integration, Journal Name: IET Energy Systems Integration Journal Issue: 1 Vol. 7; ISSN 2516-8401

Publisher:: Institution of Engineering and Technology (IET)Copyright Statement

Country of Publication:: United States

Language:: English

References (41)

Dynamic modeling, stability analysis and control of interconnected microgrids: A review Naderi, Mobin; Khayat, Yousef; Shafiee, Qobad Applied Energy, Vol. 334 https://doi.org/10.1016/j.apenergy.2023.120647	journal	March 2023
Microgrid modelling: A comprehensive survey Sen, Sachidananda; Kumar, Vishal Annual Reviews in Control, Vol. 46 https://doi.org/10.1016/j.arcontrol.2018.10.010	journal	January 2018
Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios Xu, Chen; Cao, Ba Trung; Yuan, Yong Computer Methods in Applied Mechanics and Engineering, Vol. 405 https://doi.org/10.1016/j.cma.2022.115852	journal	February 2023
What does the GB power outage on 9 August 2019 tell us about the current state of decarbonised power systems? Bialek, Janusz Energy Policy, Vol. 146 https://doi.org/10.1016/j.enpol.2020.111821	journal	November 2020
Gradient-enhanced physics-informed neural networks for power systems operational support Mohammadian, Mostafa; Baker, Kyri; Fioretto, Ferdinando Electric Power Systems Research, Vol. 223 https://doi.org/10.1016/j.epsr.2023.109551	journal	October 2023
Machine-learned security assessment for changing system topologies Bellizio, Federica; Cremer, Jochen L.; Strbac, Goran International Journal of Electrical Power & Energy Systems, Vol. 134 https://doi.org/10.1016/j.ijepes.2021.107380	journal	January 2022
Elementary changes in topology and power transmission capacity can induce failures in power grids Lacerda, Juliana C.; Freitas, Celso; Macau, Elbert E. N. Physica A: Statistical Mechanics and its Applications, Vol. 590 https://doi.org/10.1016/j.physa.2021.126704	journal	March 2022
Effect of Model Plant Mismatch on MPC Performance and Mismatch Threshold Determination Tufa, Lemma Dendena; Ka, Chong Zhi Procedia Engineering, Vol. 148 https://doi.org/10.1016/j.proeng.2016.06.518	journal	January 2016
Smooth Mathematical Representation of the DER_A Aggregated Model Vasquez-Plaza, Jesus D.; Scarpetta, Jose M. Ramirez; Hansen, Timothy M. IEEE Access, Vol. 11 https://doi.org/10.1109/ACCESS.2023.3315245	journal	January 2023
Implementation of Model Predictive Control for Frequency Support in a Real-time Digital Simulator Rai, Astha; Bhujel, Niranjan; Hansen, Timothy M. 2022 IEEE Electrical Energy Storage Application and Technologies Conference (EESAT) https://doi.org/10.1109/EESAT55007.2022.9998027	conference	November 2022
Evaluation of Probing Signals for Implementing Moving Horizon Inertia Estimation in Microgrids Rauniyar, Manisha; Berg, Sterling; Subedi, Sunil 2020 52nd North American Power Symposium (NAPS) https://doi.org/10.1109/NAPS50074.2021.9449811	conference	April 2021
Application of Neural Ordinary Differential Equations to Power System Frequency Dynamics Aryal, Tara; Aslami, Pooja; Bhujel, Niranjan 2023 North American Power Symposium (NAPS) https://doi.org/10.1109/NAPS58826.2023.10318565	conference	October 2023
A Real-Time Digital Simulator Accelerated Reinforcement Learning Training Environment for Power System Frequency Dynamics Aslami, Pooja; Aryal, Tara; Bhujel, Niranjan 2024 56th North American Power Symposium (NAPS) https://doi.org/10.1109/NAPS61145.2024.10741737	conference	October 2024
Physics-Informed Neural Networks for Power Systems Misyris, George S.; Venzke, Andreas; Chatzivasileiadis, Spyros 2020 IEEE Power & Energy Society General Meeting (PESGM) https://doi.org/10.1109/PESGM41954.2020.9282004	conference	August 2020
Dynamic Parameter Estimation with Physics-based Neural Ordinary Differential Equations Kong, Xianghao; Yamashita, Koji; Foggo, Brandon 2022 IEEE Power & Energy Society General Meeting (PESGM) https://doi.org/10.1109/PESGM48719.2022.9916840	conference	July 2022
Learning Power System Dynamics with Noisy Data Using Neural Ordinary Differential Equations Zhang, Shaorong; Yamashita, Koji; Yu, Nanpeng 2024 IEEE Power & Energy Society General Meeting (PESGM) https://doi.org/10.1109/PESGM51994.2024.10689132	conference	July 2024
Comparative Analysis of State and Parameter Estimation Techniques for Power System Frequency Dynamics Poudel, Bidur; Aslami, Pooja; Aryal, Tara 2022 International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM) https://doi.org/10.1109/SPEEDAM53979.2022.9842272	conference	June 2022
State-Space Modeling, Analysis, and Distributed Secondary Frequency Control of Isolated Microgrids Doost Mohammadi, Farideh; Keshtkar Vanashi, Hessam; Feliachi, Ali IEEE Transactions on Energy Conversion, Vol. 33, Issue 1 https://doi.org/10.1109/TEC.2017.2757012	journal	March 2018
Acceleration of Power System Dynamic Simulations Using a Deep Equilibrium Layer and Neural ODE Surrogate Bossart, Matthew; Lara, Jose Daniel; Roberts, Ciaran IEEE Transactions on Energy Conversion https://doi.org/10.1109/TEC.2025.3563142	journal	January 2025
Model for Frequency Dynamics in an Islanded Microgrid and Primary Frequency Control Based on Disturbance Compensation Hussain, Amir; Shireen, Wajiha IEEE Access, Vol. 9 https://doi.org/10.1109/access.2021.3069769	journal	January 2021
Review of Methods to Accelerate Electromagnetic Transient Simulation of Power Systems Subedi, Sunil; Rauniyar, Manisha; Ishaq, Saima IEEE Access, Vol. 9 https://doi.org/10.1109/access.2021.3090320	journal	January 2021
Real-Time Estimation of Microgrid Inertia and Damping Constant Tamrakar, Ujjwol; Copp, David A.; Nguyen, Tu A. IEEE Access, Vol. 9 https://doi.org/10.1109/access.2021.3104516	journal	January 2021
Data-Driven Modeling of Grid-Forming Inverter Dynamics Using Power Hardware-in-the-Loop Experimentation Guruwacharya, Nischal; Chakraborty, Soham; Saraswat, Govind IEEE Access, Vol. 12 https://doi.org/10.1109/access.2024.3383323	journal	January 2024
Experimentation in Exploring Photovoltaic Inverter Dynamics Under Different Irradiance Levels Through a Data-Driven Approach Poudel, Bidur; Guruwacharya, Nischal; Subedi, Sunil IEEE Access, Vol. 12 https://doi.org/10.1109/access.2024.3488493	journal	January 2024
Modeling and Design of $df/dt$ -Based Inertia Control for Power Converters Duckwitz, Daniel; Fischer, Boris IEEE Journal of Emerging and Selected Topics in Power Electronics, Vol. 5, Issue 4 https://doi.org/10.1109/jestpe.2017.2703814	journal	December 2017
Multiarea Inertia Estimation Using Convolutional Neural Networks and Federated Learning Poudyal, Abodh; Tamrakar, Ujjwol; Trevizan, Rodrigo D. IEEE Systems Journal, Vol. 16, Issue 4 https://doi.org/10.1109/jsyst.2021.3134599	journal	December 2022
An Optimal Primary Frequency Control Based on Adaptive Dynamic Programming for Islanded Modernized Microgrids Davari, Masoud; Gao, Weinan; Jiang, Zhong-Ping IEEE Transactions on Automation Science and Engineering, Vol. 18, Issue 3 https://doi.org/10.1109/tase.2020.2996160	journal	July 2021
Optimization-Based Fast-Frequency Estimation and Control of Low-Inertia Microgrids Tamrakar, Ujjwol; Copp, David A.; Nguyen, Tu IEEE Transactions on Energy Conversion, Vol. 36, Issue 2 https://doi.org/10.1109/tec.2020.3040107	journal	June 2021
Nonlinear System Identification Using Exponential Swept-Sine Signal Novák, Antonín; Simon, L.; Kadlec, F. IEEE Transactions on Instrumentation and Measurement, Vol. 59, Issue 8 https://doi.org/10.1109/tim.2009.2031836	journal	August 2010
Assessing Gaussian Assumption of PMU Measurement Error Using Field Data Wang, Shaobu; Zhao, Junbo; Huang, Zhenyu IEEE Transactions on Power Delivery, Vol. 33, Issue 6 https://doi.org/10.1109/tpwrd.2017.2762927	journal	December 2018
Roles of Dynamic State Estimation in Power System Modeling, Monitoring and Operation Zhao, Junbo; Netto, Marcos; Huang, Zhenyu IEEE Transactions on Power Systems, Vol. 36, Issue 3 https://doi.org/10.1109/tpwrs.2020.3028047	journal	May 2021
Neuro-Reachability of Networked Microgrids Zhou, Yifan; Zhang, Peng IEEE Transactions on Power Systems, Vol. 37, Issue 1 https://doi.org/10.1109/tpwrs.2021.3085706	journal	January 2022
Feasibility Study of Neural ODE and DAE Modules for Power System Dynamic Component Modeling Xiao, Tannan; Chen, Ying; Huang, Shaowei IEEE Transactions on Power Systems, Vol. 38, Issue 3 https://doi.org/10.1109/tpwrs.2022.3194570	journal	May 2023
Physics-Aware Neural Dynamic Equivalence of Power Systems Shen, Qing; Zhou, Yifan; Zhang, Qiang IEEE Transactions on Power Systems, Vol. 39, Issue 1 https://doi.org/10.1109/tpwrs.2023.3328162	journal	January 2024
Intelligent Multi-Microgrid Energy Management Based on Deep Neural Network and Model-Free Reinforcement Learning Du, Yan; Li, Fangxing IEEE Transactions on Smart Grid, Vol. 11, Issue 2 https://doi.org/10.1109/tsg.2019.2930299	journal	March 2020
Microgrid Dynamic Modeling and Islanding Control With Synchrophasor Data Konakalla, Sai Akhil Reddy; Valibeygi, Amir; de Callafon, Raymond A. IEEE Transactions on Smart Grid, Vol. 11, Issue 1 https://doi.org/10.1109/tsg.2019.2948815	journal	January 2020
An Adaptive Approach for Dynamic Load Modeling in Microgrids Chavarro-Barrera, L.; Perez-Londono, S.; Mora-Florez, J. IEEE Transactions on Smart Grid, Vol. 12, Issue 4 https://doi.org/10.1109/tsg.2021.3064046	journal	July 2021
Power System Frequency Dynamics Modeling, State Estimation, and Control using Neural Ordinary Differential Equations (NODEs) and Soft Actor-Critic (SAC) Machine Learning Approaches Aslami, Pooja; Aryal, Tara; Rai, Astha ACM SIGAPP Applied Computing Review, Vol. 24, Issue 1 https://doi.org/10.1145/3663652.3663655	journal	March 2024
Topological Machine Learning Methods for Power System Responses to Contingencies Bush, Brian; Chen, Yuzhou; Ofori-Boateng, Dorcas Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, Issue 17 https://doi.org/10.1609/aaai.v35i17.17791	journal	May 2021
On Small Signal Frequency Stability under Virtual Inertia and the Role of PLLs Khan, Sohail; Bletterie, Benoit; Anta, Adolfo Energies, Vol. 11, Issue 9 https://doi.org/10.3390/en11092372	journal	September 2018
Dynamic Modeling of Multiple Microgrid Clusters Using Regional Demand Response Programs Rostami, Ziba; Ravadanegh, Sajad Najafi; Kalantari, Navid Taghizadegan Energies, Vol. 13, Issue 16 https://doi.org/10.3390/en13164050	journal	August 2020

Similar Records

An ODE-Enabled Distributed Transient Stability Analysis for Networked Microgrids

Journal Article · Tue Dec 15 19:00:00 EST 2020 · IEEE Power & Energy Society General Meeting (Online) · OSTI ID:1668662

Grid Resiliency with a 100% Renewable Microgrid

Technical Report · Tue Sep 30 00:00:00 EDT 2025 · OSTI ID:2589920

Active Learning of Microgrid Frequency Dynamics Using Neural Ordinary Differential Equations

Citation Formats

References (41)

Similar Records

Related Subjects