Deep-Learning-Based Koopman Modeling for Online Control Synthesis of Nonlinear Power System Transient Dynamics

Zhao, Tianqiao; Yue, Meng; Wang, Jianhui

doi:10.1109/tii.2023.3240939

Deep-Learning-Based Koopman Modeling for Online Control Synthesis of Nonlinear Power System Transient Dynamics

Journal Article · Tue Jan 31 00:00:00 EST 2023 · IEEE Transactions on Industrial Informatics

DOI:https://doi.org/10.1109/tii.2023.3240939· OSTI ID:2396604

^[1]; ^[1]; ^[2]

Brookhaven National Laboratory (BNL), Upton, NY (United States)
Southern Methodist Univ., Dallas, TX (United States)

Power system stability and control have become more challenging due to the increasing uncertainty associated with renewable generation. Here, the performance of conventional control is highly driven by the physics-based offline-developed dynamic models that can deviate from the actual system characteristics under different operating conditions and/or configurations. Data-driven approaches based on online measurements can be a better solution to addressing these issues by capturing real-time operation conditions. This article describes a novel fully data-driven probabilistic framework to derive a linear representation of postcontingency grid dynamics and online prescribe control based on the derived model to enhance transient stability. The complex nonlinear power system dynamics is approximated by a linear model by using multiple neural network modules that infer distributions of the observations and introducing a Koopman layer to sample possible Koopman linear models from the inferred distributions. The trained model features linearity that can be easily incorporated into the existing linear control design paradigm and ease the controller design process. The effectiveness of Koopman-based control designs is validated through comparative case studies, which demonstrate increased prediction accuracy and control performance when applied to a power system with heterogeneous generator dynamics.

View Accepted Manuscript (DOE)

Research Organization:: Brookhaven National Laboratory (BNL), Upton, NY (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office; USDOE Laboratory Directed Research and Development (LDRD) Program

Grant/Contract Number:: SC0012704; EE0009341; 21-032

OSTI ID:: 2396604

Report Number(s):: BNL-225798-2024-JAAM

Journal Information:: IEEE Transactions on Industrial Informatics, Vol. 19, Issue 10; ISSN 1551-3203

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (24)

Deep Variational Koopman Models: Inferring Koopman Observations for Uncertainty-Aware Dynamics Modeling and Control Morton, Jeremy; Witherden, Freddie D.; Kochenderfer, Mykel J. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence https://doi.org/10.24963/ijcai.2019/440	conference	August 2019
Deep learning for universal linear embeddings of nonlinear dynamics Lusch, Bethany; Kutz, J. Nathan; Brunton, Steven L. Nature Communications, Vol. 9, Issue 1 https://doi.org/10.1038/s41467-018-07210-0	journal	November 2018
Power grid transient stabilization using Koopman model predictive control Korda, Milan; Susuki, Yoshihiko; Mezić, Igor IFAC-PapersOnLine, Vol. 51, Issue 28 https://doi.org/10.1016/j.ifacol.2018.11.718	journal	January 2018
Deep Koopman model predictive control for enhancing transient stability in power grids Ping, Zuowei; Yin, Zhun; Li, Xiuting International Journal of Robust and Nonlinear Control, Vol. 31, Issue 6 https://doi.org/10.1002/rnc.5043	journal	June 2020
Lyapunov-Regularized Reinforcement Learning for Power System Transient Stability Cui, Wenqi; Zhang, Baosen IEEE Control Systems Letters, Vol. 6 https://doi.org/10.1109/LCSYS.2021.3088068	journal	January 2022
Secondary Frequency and Voltage Control of Islanded Microgrids via Distributed Averaging Simpson-Porco, John W.; Shafiee, Qobad; Dorfler, Florian IEEE Transactions on Industrial Electronics, Vol. 62, Issue 11 https://doi.org/10.1109/TIE.2015.2436879	journal	November 2015
Koopman Invariant Subspaces and Finite Linear Representations of Nonlinear Dynamical Systems for Control Brunton, Steven L.; Brunton, Bingni W.; Proctor, Joshua L. PLOS ONE, Vol. 11, Issue 2 https://doi.org/10.1371/journal.pone.0150171	journal	February 2016
Hamiltonian Systems and Transformation in Hilbert Space Koopman, B. O. Proceedings of the National Academy of Sciences, Vol. 17, Issue 5 https://doi.org/10.1073/pnas.17.5.315	journal	May 1931
Improvement of First Swing Stability Limit by Utilizing Full Benefit of Shunt FACTS Devices Haque, M. H. IEEE Transactions on Power Systems, Vol. 19, Issue 4 https://doi.org/10.1109/TPWRS.2004.836243	journal	November 2004
An Intelligent Transient Stability Assessment Framework With Continual Learning Ability Li, Xin; Yang, Zeguo; Guo, Panfeng IEEE Transactions on Industrial Informatics, Vol. 17, Issue 12 https://doi.org/10.1109/TII.2021.3064052	journal	December 2021
Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control Korda, Milan; Mezić, Igor Automatica, Vol. 93 https://doi.org/10.1016/j.automatica.2018.03.046	journal	July 2018
Frequency Stability Using Inverter Power Control in Low-Inertia Power Systems Ademola-Idowu, Atinuke; Zhang, Baosen IEEE Transactions on Power Systems https://doi.org/10.1109/TPWRS.2020.3019998	journal	January 2020
Optimal Load-Side Control for Frequency Regulation in Smart Grids Mallada, Enrique; Zhao, Changhong; Low, Steven IEEE Transactions on Automatic Control, Vol. 62, Issue 12 https://doi.org/10.1109/TAC.2017.2713529	journal	December 2017
Linearly Recurrent Autoencoder Networks for Learning Dynamics Otto, Samuel E.; Rowley, Clarence W. SIAM Journal on Applied Dynamical Systems, Vol. 18, Issue 1 https://doi.org/10.1137/18M1177846	journal	January 2019
MPC-Based Fast Frequency Control of Voltage Source Converters in Low-Inertia Power Systems Stanojev, Ognjen; Markovic, Uros; Aristidou, Petros IEEE Transactions on Power Systems, Vol. 37, Issue 4 https://doi.org/10.1109/TPWRS.2020.2999652	journal	July 2022
A Neural Lyapunov Approach to Transient Stability Assessment of Power Electronics-Interfaced Networked Microgrids Huang, Tong; Gao, Sicun; Xie, Le IEEE Transactions on Smart Grid, Vol. 13, Issue 1 https://doi.org/10.1109/TSG.2021.3117889	journal	January 2022
Enhanced Transient Angle Stability Control of Grid-Forming Converter Based on Virtual Synchronous Generator Chen, Meng; Zhou, Dao; Blaabjerg, Frede IEEE Transactions on Industrial Electronics, Vol. 69, Issue 9 https://doi.org/10.1109/TIE.2021.3114723	journal	September 2022
Distributed Model Predictive Frequency Control of Inverter-Based Networked Microgrids Liu, Kun; Yang, Luwei; Liu, Tao IEEE Transactions on Energy Conversion, Vol. 36, Issue 4 https://doi.org/10.1109/TEC.2021.3102074	journal	December 2021
Neural Lyapunov Control for Power System Transient Stability: A Deep Learning-Based Approach Zhao, Tianqiao; Wang, Jianhui; Lu, Xiaonan IEEE Transactions on Power Systems, Vol. 37, Issue 2 https://doi.org/10.1109/TPWRS.2021.3102857	journal	March 2022
Power and Frequency Regulation of Synchronverters Using a Model Free Neural Network-Based Predictive Controller Saadatmand, Sepehr; Shamsi, Pourya; Ferdowsi, Mehdi IEEE Transactions on Industrial Electronics, Vol. 68, Issue 5 https://doi.org/10.1109/TIE.2020.2984419	journal	May 2021
A power system nonlinear adaptive decentralized controller design Yan, Rui; Dong, ZhaoYang; Saha, T. K. Automatica, Vol. 46, Issue 2 https://doi.org/10.1016/j.automatica.2009.10.020	journal	February 2010
An Eigenstructure-Based Performance Index and Its Application to Control Design for Damping Inter-Area Oscillations in Power Systems Ke, D. P.; Chung, C. Y. IEEE Transactions on Power Systems, Vol. 26, Issue 4 https://doi.org/10.1109/TPWRS.2011.2123119	journal	November 2011
Structural Scheduling of Transient Control Under Energy Storage Systems by Sparse-Promoting Reinforcement Learning Sun, Jian; Qi, Guanqiu; Mazur, Neal IEEE Transactions on Industrial Informatics, Vol. 18, Issue 2 https://doi.org/10.1109/TII.2021.3084139	journal	February 2022
Deep Belief Network Enabled Surrogate Modeling for Fast Preventive Control of Power System Transient Stability Su, Tong; Liu, Youbo; Zhao, Junbo IEEE Transactions on Industrial Informatics, Vol. 18, Issue 1 https://doi.org/10.1109/TII.2021.3072594	journal	January 2022

Similar Records

Sensor enabled data-driven predictive analytics for modeling and control with high penetration of DERs in distribution systems

Technical Report · Sat May 29 00:00:00 EDT 2021 · OSTI ID:1785126

Ajjarapu, Venkataramana; Vaidya, Umesh; Govindarasu, Manimaran; +6 more

Data-driven modeling and control of dynamical systems using Koopman and Perron-Frobenius operators

Other · Fri Sep 04 00:00:00 EDT 2020 · OSTI ID:1693451

Huang, Bowen

Koopman-based Differentiable Predictive Control for the Dynamics-Aware Economic Dispatch Problem

Conference · Mon Sep 05 00:00:00 EDT 2022 · OSTI ID:1894496

King, Ethan; Drgona, Jan; Tuor, Aaron R.; +4 more

Related Subjects

24 POWER TRANSMISSION AND DISTRIBUTION

Deep-Learning-Based Koopman Modeling for Online Control Synthesis of Nonlinear Power System Transient Dynamics

Citation Formats

References (24)

Similar Records

Related Subjects