A DIGITAL IMPLEMENTATION OF ADAPTIVE PI CONTROLLER FOR DC–DC BOOST CONVERTER BASED ON REINFORCEMENT LEARNING
DOI:
https://doi.org/10.62985/j.huit_ojs.vol26.no2E.376Từ khóa:
Adaptive controller, boost DC-DC converter, reinforcement learningTóm tắt
DC–DC boost converters are widely applied in various industrial power electronics applications, such as motor drive systems and voltage step-up stages in grid-connected renewable energy systems, due to their simple and compact circuit topology combined with high voltage gain. However, because of the inherent right-half-plane zero in their dynamic characteristics, feedback control of DC–DC boost converters is regarded as one of the most challenging nonlinear control problems. To date, numerous efforts have been devoted to improving the performance of boost converters. Among modern approaches, reinforcement learning has attracted significant attention for its potential in designing adaptive controllers through the automatic tuning of conventional control structures, including PID, PI, and LQR controllers. This paper proposes an implementation pipeline for a DC–DC boost converter based on an ESP32 microcontroller platform and a 16-bit ADS1115 ADC for constructing the training environment of an adaptive RL-PI controller. In addition, control performance evaluation indices are established based on standard criteria, including steady-state error, overshoot, and output voltage ripple, enabling a quantitative and objective comparison among different control strategies. The controllers investigated in this study include a conventional PI controller, a cascaded PI controller with voltage and inductor current feedback, and the proposed adaptive RL-PI controller, all evaluated under varying load conditions. Experimental results demonstrate that the reinforcement learning–based approach exhibits strong potential for adaptive control of boost converters, achieving output voltage ripple below 2% and steady-state error below 5%.
Tài liệu tham khảo
[1] S. M. Ghamari, M. Hajihosseini, D. Habibi, and A. Aziz, “Design of an Adaptive Robust PI Controller for DC/DC Boost Converter Using Reinforcement-Learning Technique and Snake Optimization Algorithm,” IEEE Access, vol. 12, pp. 141814–141829, 2024, doi: https://doi.org/10.1109/ACCESS.2024.3440580.
[2] G. Nethaji and J. Kathirvelan, "Performance comparison between PID and fuzzy logic controllers for the hardware implementation of traditional high-voltage DC-DC boost converter," Heliyon, vol. 10, no. 17, Art. no. e36750, Sep. 2024, doi: https://doi.org/10.1016/j.heliyon.2024.e36750.
[3] S. W. Seo and H. H. Choi, “Digital implementation of fractional order PID-Type controller for boost DC-DC converter,” IEEE Access, vol. 7, pp. 142652–142662, 2019, doi: https://doi.org/10.1109/ACCESS.2019.2945065.
[4] W. R. Liou et al., “A Programmable Controller IC for DC/DC Converter and Power Factor Correction Applications,” IEEE Trans. Ind. Informat., vol. 9, no. 4, pp. 2105–2113, 2013, doi: https://doi.org/10.1109/TII.2012.2235845.
[5] O. Djamel, G. Dhaouadi, S. Youcef, and M. Mahmoud, “Hardware Implementation of Digital PID Controller for DC-DC Boost Converter,” in Proc. 4th Int. Conf. Power Electron. Appl. (ICPEA), Elazig, Turkey, 2019, pp. 1–4, doi: https://doi.org/10.1109/ICPEA1.2019.8911129.
[6] D. C. Meena and A. Devanshu, ‘‘Genetic algorithm tuned PID controller for process control,’’ in Proc. Int. Conf. Inventive Syst. Control (ICISC), Coimbatore, India, Jan. 2017, pp. 1–6, doi: https://doi.org/10.1109/ICISC.2017.8068639.
[7] K. J. Rathi and M. S. Ali, “Neural Network Controller for Power Electronics Circuits,” IAES Int. J. Artif. Intell., vol. 6, no. 2, pp. 49–55, Jun. 2017, doi: https://doi.org/10.11591/ijai.v6.i2.pp49-55.
[8] M. H. Demir and M. Demirok, “Designs of Particle-Swarm-Optimization-Based Intelligent PID Controllers and DC/DC Buck Converters for PEM Fuel-Cell-Powered Four-Wheeled Automated Guided Vehicle,” Appl. Sci., vol. 13, no. 5, Mar. 2023, doi: https://doi.org/10.3390/app13052919.
[9] M. Algreer, M. Armstrong, and D. Giaouris, “Adaptive PD+I control of a switch-mode DC-DC power converter using a recursive FIR predictor,” IEEE Trans. Ind. Appl., vol. 47, no. 5, pp. 2135–2144, Sep. 2011, doi: https://doi.org/10.1109/TIA.2011.2161856.
[10] L. Ren, D. Wang, and Y. Zhang, “Adaptive Neural Network Control of Four-Switch Buck–B oost Converters,” Actuators, vol. 13, no. 9, Sep. 2024, doi: https://doi.org/10.3390/act13090375.
[11] . M. Cheng et al., “A Back Propagation Neural Network with Double Learning Rate for PID Controller in Phase-Shifted Full-Bridge Soft-Switching Power Supply,” J. Electr. Eng. Technol., vol. 15, no. 6, pp. 2811–2822, Nov. 2020, doi: https://doi.org/10.1007/s42835-020-00523-5.
[12] N. T. T. Vu, H. D. Nguyen, and A. T. Nguyen, “Reinforcement Learning-Based Adaptive Optimal Fuzzy MPPT Control for Variable Speed Wind Turbine,” IEEE Access, vol. 10, pp. 95771–95780, 2022, doi: https://doi.org/10.1109/ACCESS.2022.3205124.
[13] N. P. Lawrence, M. G. Forbes, P. D. Loewen, D. G. McClement, J. U. Backstrom, and R. B. Gopaluni, “Deep Reinforcement Learning with Shallow Controllers: An Experimental Application to PID Tuning,” Control Eng. Pract., vol. 118, Jan. 2022, doi: https://doi.org/10.1016/j.conengprac.2021.105046.
[14] Z. Guan and T. Yamamoto, “Design of a Reinforcement Learning PID Controller,” in Proc. Int. Joint Conf. Neural Netw. (IJCNN), Glasgow, U.K., 2020, pp. 1–6, doi: https://doi.org/10.1109/IJCNN48605.2020.9207641.
[15] H. Song, Y. Liu, J. Zhao, J. Liu, and G. Wu, “Prioritized Replay Dueling DDQN Based Grid-Edge Control of Community Energy Storage System,” IEEE Trans. Smart Grid, vol. 12, no. 6, pp. 4950–4961, Nov. 2021, doi: https://doi.org/10.1109/TSG.2021.3099133.
[16] S. Shahnooshi, J. Ebrahimi, and A. Bakhshai, “A Reinforcement Learning Controller Based on Double DQN for DC Microgrids with Constant Power Loads,” in Proc. Can. Conf. Electr. Comput. Eng. (CCECE), 2024, pp. 376–380, doi: https://doi.org/10.1109/CCECE59415.2024.10667207.
[17] P. Kofinas and A. I. Dounis, “Fuzzy Q-learning agent for online tuning of PID controller for DC motor speed control,” Algorithms, vol. 11, no. 10, Oct. 2018, doi: https://doi.org/10.3390/a11100148.
