Authors : Ramanantsihoarana Harisoa Nathalie; Rastefano Elisée

Volume/Issue : Volume 10 - 2025, Issue 7 - July

Google Scholar : https://tinyurl.com/7tmj47sp

DOI : https://doi.org/10.38124/ijisrt/25jul480

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : This paper presents a novel approach to controlling non-inverting buck-boost converters using Proximal Policy Optimization (PPO) algorithm for renewable energy applications, particularly photovoltaic systems. Traditional PID controllers face significant limitations when dealing with the complex nonlinear dynamics, external disturbances, and varying operating conditions inherent in renewable energy systems. The proposed PPO-based control strategy addresses these challenges by providing adaptive and intelligent control capabilities. Through comprehensive simulation and experimental validation, we demonstrate that the PPO algorithm successfully learned optimal control policies within 10,000 episodes, maintain excellent voltage regulation under various operating conditions. The results confirm the effectiveness of the proposed approach in maintaining stable output voltage regulation under varying load conditions, input voltage fluctuations, and temperature variations.

Keywords : Buck-Boost Converter, Proximal Policy Optimization, Deep Reinforcement Learning, Power Electronics Control, Renewable Energy Systems.

References :

1. Mahafzah, K. A., et al. "Enhanced photovoltaic panel diagnostics through AI integration with experimental DC to DC Buck Boost converter implementation." Scientific Reports, vol. 14, 2024.
2. Recent developments of multiport DC/DC converter topologies, control strategies, and applications: A comparative review and analysis. ScienceDirect, 2023.
3. Sun, Y., et al. "Optimizing intelligent startup strategy of power system using PPO algorithm." Intelligent Decision Technologies, 2024.
4. Deep learning based buck-boost converter for PV modules. Heliyon, vol. 10, no. 5, 2024.
5. Proximal policy optimization-based reinforcement learning approach for DC-DC boost converter control: A comparative evaluation against traditional control techniques. PMC, 2024.
6. A Deep Reinforcement Learning Approach to DC-DC Power Electronic Converter Control with Practical Considerations. Energies, vol. 17, no. 14, 2024.
7. Reinforcement Learning-Based Control of a Power Electronic Converter. Mathematics, vol. 12, no. 5, 2024.
8. Learning-Based Model Predictive Control of DC-DC Buck Converters in DC Microgrids: A Multi-Agent Deep Reinforcement Learning Approach. Energies, vol. 15, no. 15, 2022.
9. Model predictive control of DC/DC boost converter with reinforcement learning. PMC, 2022.
10. A Novel Nonlinear Deep Reinforcement Learning Controller for DC–DC Power Buck Converters. IEEE Transactions, 2020.
11. Deep learning based buck-boost converter for PV modules. PMC, 2024.
12. Enhanced photovoltaic panel diagnostics through AI integration with experimental DC to DC Buck Boost converter implementation. Scientific Reports, 2024.
13. A review of machine learning applications in power system protection and emergency control: opportunities, challenges, and future directions. Frontiers in Smart Grids, 2024.
14. Overview of Control Algorithm Verification Methods in Power Electronics Systems. Energies, vol. 14, no. 14, 2021.
15. A Deep Reinforcement Learning Approach to DC-DC Power Electronic Converter Control with Practical Considerations. Energies, vol. 17, no. 14, 2024.
16. A review of machine learning applications in power system protection and emergency control: opportunities, challenges, and future directions. Frontiers in Smart Grids, 2024.
17. Machine learning for modern power distribution systems: Progress and perspectives. Journal of Renewable and Sustainable Energy, vol. 15, no. 3, 2023.
18. Proximal Policy Optimization — Spinning Up documentation. OpenAI, 2024.
19. Proximal policy optimization - Wikipedia. Accessed 2024.
20. Machine learning for modern power distribution systems: Progress and perspectives. Journal of Renewable and Sustainable Energy, 2023.