Article Sidebar

pdf
Issue: Vol. 3 No. 102 (2025)
Section: Articles
Date Published: 22/05/2026
Views 0
Downloads 0
How to Cite
Nguyen, D. T., Bui, C. G., Ho, V. C., & Huynh, L. M. T. (2026). Applying Deep Learning in Active Power Filter Control to Enhance High-Order Harmonic Filtering Efficiency. Scientific Journal of Saigon University, 3(102), 3-18. https://sj.sgu.edu.vn/index.php/sjsgu/article/view/416

Applying Deep Learning in Active Power Filter Control to Enhance High-Order Harmonic Filtering Efficiency

Duc Thịn Nguyen1, Cong Giao Bui2, Van Cuu Ho2, , Le Minh Thien Huynh2
1 Trường Đại học Tài chính - Marketing
2 Saigon University

Main Article Content

Abstract

The Active Power Filter (APF) plays a crucial role in improving power quality by reducing Total Harmonic Distortion (THD) and balancing active and reactive power. However, traditional control methods such as PID, Fuzzy Logic Control (FLC), or Model Predictive Control (MPC) often face limitations in nonlinear and rapidly changing load conditions. Recently, Deep Learning has emerged as a powerful approach, enabling APF to automatically learn and adapt to variations in the power system.
This paper introduces applications of Deep Learning in APF control, including harmonic detection and classification, optimal compensation current prediction using Artificial Neural Networks (ANNs), and control strategy optimization via Deep Reinforcement Learning (DRL). Additionally, it discusses challenges in implementing Deep Learning in APF, such as training data requirements, real-time computational capabilities, and model reliability. Finally, the paper proposes potential research directions to enhance the effectiveness of Deep Learning in this field.

Keywords

Active Power Filter (APF), Deep Learning, Intelligent Control, Harmonics, Total Harmonic Distortion (THD), Artificial Neural Network (ANN), Deep Reinforcement Learning (DRL)

Article Details

References

Atherton, Derek P. and Somanath Majhi. “Limitations of PID controllers.” Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251) 6 (1999): 3843-3847 vol.6.
Tang Y, Chen R, Xia B. VSFCM: A Novel Viewpoint-Driven Subspace Fuzzy C-Means Algorithm. Applied Sciences. 2023; 13(10):6342. https://doi.org/10.3390/app13106342
Rodríguez, José Cristian Lozano. “Predictive Control in Power Electronics and Drives.” IEEE Transactions on Industrial Electronics, Institute of Electrical and Electronics Engineers (IEEE), 2008.
Mantach S, Ashraf A, Janani H, Kordi B. “A Convolutional Neural Network-Based Model for Multi-Source and Single-Source Partial Discharge Pattern Classification Using Only Single-Source Training Set”. Energies. 2021; 14(5):1355. https://doi.org/10.3390/en14051355
Muneer, Amgad, et al. "Short-term residential load forecasting using long short-term memory recurrent neural network." International Journal of Electrical & Computer Engineering (2088-8708) 12.5 (2022).
D. C. Park, M. A. El-Sharkawi, R. J. Marks, L. E. Atlas and M. J. Damborg, "Electric load forecasting using an artificial neural network," in IEEE Transactions on Power Systems, vol. 6, no. 2, pp. 442-449, May 1991, doi: 10.1109/59.76685.
K. J. Åström and T. Hägglund, "The future of PID control," Control Eng. Pract., vol. 9, pp. 1163–1175, 2001. doi: 10.1016/S0967-0661(01)00062-4.
H. X. Li and H. B. Gatland, “Conventional Fuzzy Control and its Enhancement,” IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 26, No. 5, 1996, pp. 791-797. doi:10.1109/3477.537321 E. F. Camacho and C. Bordons Alba, Model Predictive Control, 2nd ed. Cham: Springer Science & Business Media, 2013.
K. R. Sugavanam, K. Mohana Sundaram, R. Jeyabharath, and P. Veena, "Convolutional Neural Network-Based Harmonic Mitigation Technique for an Adaptive Shunt Active Power Filter," Automatika, vol. 62, no. 3–4, pp. 471–485, 2021. doi: 10.1080/00051144.2021.1985703.
L. Liu, J. Fei and C. An, "Adaptive Sliding Mode Long Short-Term Memory Fuzzy Neural Control for Harmonic Suppression," in IEEE Access, vol. 9, pp. 69724-69734, 2021, doi: 10.1109/ACCESS.2021.3077646.
T. Santhosh Kumar and J. Shanmugam, "ANN Application of the APF Improved for DG Unit System Reliability," in Proc. I3CAC, 2021. doi: 10.4108/eai.7-6-2021.2308861.
Wang, X., Chen, C., Lei, and L. Yang, "Artificial Potential Field-Enhanced Deep Reinforcement Learning for Motion Planning," 2024 8th International Conference on Robotics, Control and Automation (ICRCA), Shanghai, China, 2024, pp. 459-465, doi: 10.1109/ICRCA60878.2024.10649312.
Z. A. Akhond, M. M. Hasan, M. T. Islam, and S. Biswas, "Comprehensive Analysis of AI- Enhanced Performance for Three-Phase Two-Level IGBT Inverters," Thesis, June 2024. doi: 10.13140/RG.2.2.26963.39206.
Suleiman M. Sharkh; Mohammad A. Abu-Sara; Georgios I. Orfanoudakis; Babar Hussain, "Digital Control of a Three-Phase Two-Level Grid-Connected Inverter," in Power Electronic Converters for Microgrids, IEEE, 2014, pp.109-129, doi: 10.1002/9780470824054.ch6.
Chahine K. “Machine Learning in Active Power Filters: Advantages, Limitations, and Future Directions”. AI. 2024; 5(4):2433-2460. https://doi.org/10.3390/ai5040119
R. L. Iglesias, R. L. Arantegui, and M. A. Alonso, "Power electronics evolution in wind turbines - A market-based analysis," Renew. Sustain. Energy Rev., vol. 15, no. 9, pp. 4982-4993, 2011. doi: 10.1016/j.rser.2011.07.056.
Huynh Le Minh Thien, Ho Van Cuu, Tran Thanh Vu, and Do Dang Trinh, “Investigating the combination between LCL filter and Phase-Locked Loop (PLL) to control positive filter grid connection quickly”, Journal of Science of Saigon University, Issue 60 (8/2018)