EUVIMEDEUVIMED entdecken
Crossref

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

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

ACM SIGAPP Applied Computing Review · 2024-03 · 24 (1) · 24-39

DOI: 10.1145/3663652.3663655 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM SIGAPP Applied Computing Review, online erschienen am 03.05.2024. Verfasst von Pooja Aslami und 8 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 38 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 energy sources (RES), the system dynamics are changing, causing traditional power system dynamic modeling with swing equation-based modeling approaches to fail. Additionally, the converter-dominated power grid is decreasing the system inertia, making the power system more fragile to the frequency swings. This paper first investigates and compares the application of a model-based Kalman filter state estimation approach with (i) a model-free machine learning approach --- neural ordinary differential equations (NODEs) --- and (ii) a data-driven system identification (SysId) approach to model and infer critical state values of the power system frequency dynamics. Then a model predictive control (MPC) framework is compared to a model-free Soft Actor-Critic (SAC) reinforcement learning (RL) control algorithm in providing efficient fast frequency response (FFR) to the power system frequency dynamics. The approaches are compared in terms of their performance goals as well as their per-timestep computational efficiency. The comparative study for state estimation shows that for the model-free requirement, both NODEs and SysId can provide accurate state estimates; however, with increasing model complexity, NODEs can be a better choice for model identification. Similarly, the results from the FFR comparative study show that the SAC RL-based FFR, once trained, outperforms MPC with better control signals and faster computation time, making the SAC RL-based FFR better option for providing FFR to the power system.

Zitieren

APA

Aslami, P., Aryal, T., Rai, A., Bhujel, N., Rekabdarkolaee, H. M., Fu, K., Tonkoski, R., Wang, Z., & Hansen, T. M. (2024). Power System Frequency Dynamics Modeling, State Estimation, and Control using Neural Ordinary Differential Equations (NODEs) and Soft Actor-Critic (SAC) Machine Learning Approaches. ACM SIGAPP Applied Computing Review, 24(1), 24-39. https://doi.org/10.1145/3663652.3663655

Vancouver

Aslami P, Aryal T, Rai A, Bhujel N, Rekabdarkolaee HM, Fu K, et al. Power System Frequency Dynamics Modeling, State Estimation, and Control using Neural Ordinary Differential Equations (NODEs) and Soft Actor-Critic (SAC) Machine Learning Approaches. ACM SIGAPP Applied Computing Review. 2024;24(1):24-39. doi:10.1145/3663652.3663655

BibTeX
@article{Aslami2024,
  author = {Aslami, Pooja and Aryal, Tara and Rai, Astha and Bhujel, Niranjan and Rekabdarkolaee, Hossein Moradi and Fu, Kaiqun and Tonkoski, Reinaldo and Wang, Zongjie and Hansen, Timothy M.},
  title = {Power System Frequency Dynamics Modeling, State Estimation, and Control using Neural Ordinary Differential Equations (NODEs) and Soft Actor-Critic (SAC) Machine Learning Approaches},
  journal = {ACM SIGAPP Applied Computing Review},
  year = {2024},
  volume = {24},
  number = {1},
  pages = {24--39},
  doi = {10.1145/3663652.3663655}
}
Kostenlos starten →