Machine Learning For Frequency Regulation In Islanded Microgrids With Renewable Integration
DOI:
https://doi.org/10.29284/e1c51b67Keywords:
Machine learning, deep reinforcement learning, islanded microgrid, frequency regulation, load frequency control, renewable energy integration, secondary control.Abstract
The growing penetration of renewable energy sources (RES) such as photovoltaic (PV) and wind generation into islanded microgrids has introduced significant frequency-stability challenges due to the intermittent, low-inertia nature of power-electronic-interfaced generation. Conventional droop-based and Proportional–Integral (PI) secondary controllers, while structurally simple, struggle to maintain frequency within acceptable limits under fast, stochastic disturbances. This paper investigates the application of machine learning (ML), and specifically deep reinforcement learning (DRL), for adaptive frequency regulation in islanded microgrids with high renewable integration. A single-area islanded microgrid model comprising diesel generation, wind, PV, and battery energy storage is developed, and an actor–critic DRL-based secondary controller is designed to adaptively adjust regulation commands in response to load and renewable disturbances. The proposed controller is benchmarked in simulation against conventional Droop+PI, Fuzzy-PI, and Artificial Neural Network (ANN)-based controllers using metrics including peak frequency deviation, settling time, overshoot, root-mean-square error (RMSE), and the integral of time-weighted absolute error (ITAE). Results show that the proposed ML-based controller reduces peak frequency deviation by approximately 68% and settling time by nearly 73% relative to the conventional Droop+PI scheme, while also improving robustness under stochastic renewable fluctuations. These findings support the practical viability of ML-based frequency regulation for next-generation islanded and remote microgrids.
References
1. Abazari, A., Monsef, H., & Wu, B. (2019). Coordination strategies of distributed energy resources including FESS, DEG, FC and WTG in load frequency control (LFC) scheme of hybrid isolated micro-grid. International Journal of Electrical Power & Energy Systems, 109, 535–547.
2. Aziz, A., Oo, A. T., & Stojcevski, A. (2018). Frequency regulation capabilities in wind power plant. Sustainable Energy Technologies and Assessments, 26, 47–76.
3. Bevrani, H. (2014). Robust power system frequency control (2nd ed.). Springer.
4. Deng, W., Zhong, J., Huang, M., Zhang, J., & Zhang, Z. (2022). Adaptive control strategy with threshold of virtual inertia and virtual damping for virtual synchronous generator. Journal of Physics: Conference Series, 2203(1), 012039. https://doi.org/10.1088/1742-6596/2203/1/012039
5. Du, W., Huang, X., Zhu, Y., Wang, L., & Deng, W. (2024). Deep reinforcement learning for adaptive frequency control of island microgrid considering control performance and economy. Frontiers in Energy Research, 12, 1361869. https://doi.org/10.3389/fenrg.2024.1361869
6. Guerrero, J. M., Vasquez, J. C., Matas, J., de Vicuña, L. G., & Castilla, M. (2011). Hierarchical control of droop-controlled AC and DC microgrids—A general approach toward standardization. IEEE Transactions on Industrial Electronics, 58(1), 158–172.
7. Kundur, P. (1994). Power system stability and control. McGraw-Hill.
8. Li, J., & Zhou, T. (2023). Evolutionary multi-agent deep meta reinforcement learning method for swarm intelligence energy management of isolated multi-area microgrid with Internet of Things. IEEE Internet of Things Journal, 10(14), 12923–12937. https://doi.org/10.1109/JIOT.2023.3253693
9. Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533. https://doi.org/10.1038/nature14236
10. Olivares, D. E., Mehrizi-Sani, A., Etemadi, A. H., Cañizares, C. A., Iravani, R., Kazerani, M., Hajimiragha, A. H., Gomis-Bellmunt, O., Saeedifard, M., Palma-Behnke, R., Jiménez-Estévez, G. A., & Hatziargyriou, N. D. (2014). Trends in microgrid control. IEEE Transactions on Smart Grid, 5(4), 1905–1919. https://doi.org/10.1109/TSG.2013.2295514
11. Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.
12. Zhang, X., Yu, T., Yang, B., & Jiang, L. (2021). A random forest-assisted fast distributed auction-based algorithm for hierarchical coordinated power control in a large-scale PV power plant. IEEE Transactions on Sustainable Energy, 12(4), 2471–2481. https://doi.org/10.1109/TSTE.2021.3101520
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
