Hybrid Fuzzy–DDPG Approach for Efficient MPPT in Partially Shaded Photovoltaic Panels
Source abstract
Abstract
Partial shading conditions reduce the efficiency of photovoltaic (PV) systems by introducing multiple local maxima in the power–voltage curve, complicating Maximum Power Point Tracking (MPPT). Traditional MPPT methods, such as Perturb and Observe (P&O) and Incremental Conductance (IC), frequently converge to local maxima, leading to suboptimal power extraction. This study proposes a hybrid reinforcement learning-based MPPT approach that combines fuzzy techniques with Deep Deterministic Policy Gradient (DDPG) to enhance tracking accuracy under partial shading. The method integrates fuzzy membership functions into the actor–critic structure, improving state representation and convergence speed. The proposed algorithm is evaluated in a simulated PV environment under various shading scenarios and benchmarked against conventional Perturb and Observe P&O and IC methods. Experimental results demonstrate that the Fuzzy–DDPG approach outperforms these classical techniques by achieving a higher tracking efficiency of 95%, compared to 85% for P&O and 88% for IC in average, while also minimizing steady-state oscillations. Additionally, the proposed method reduces tracking errors by up to 7.9% compared to conventional MPPT algorithms. These findings indicate that the combination of fuzzy logic and deep reinforcement learning provides a more adaptive and efficient MPPT solution, ensuring improved energy harvesting in dynamically changing conditions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Photovoltaic System Optimization Techniques · solar cell performance optimization · Solar Thermal and Photovoltaic Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Departamento de Ingeniería Industrial y Manufactura, Universidad Autonoma de Ciudad Juarez, Juárez 32315, Mexico
Funding
Mexico SECIHTI
References (47)
Show source-provided references
1. JAYA Algorithm Based on Lévy Flight for Global MPPT Under Partial Shading in Photovoltaic System
2. Ngo, S., Chiu, C., and Shao, W.E. (2019, January 20–21). MPPT Design for a DC Stand-Alone Solar Power System with Partial Shaded PV Modules. Proceedings of the 2019 International Conference on System Science and Engineering (ICSSE), Dong Hoi, Vietnam.
3. Rapid and Robust Adaptive Jaya (Ajaya) Based Maximum Power Point Tracking of a PV-Based Generation System
4. Global MPPT based on flower pollination and differential evolution algorithms to mitigate partial shading in building integrated PV system10.1016/j.solener.2017.08.024 ↗
5. A review of global maximum power point tracking techniques of photovoltaic system under partial shading conditions10.1016/j.rser.2018.04.094 ↗
6. EL-Din, A.H., Mekhamer, S., and EL-Helw, H.M. (2018, January 4–7). Maximum power point tracking under partial shading condition using particle swarm optimization with DC-DC boost converter. Proceedings of the 2018 53rd International Universities Power Engineering Conference (UPEC), Glasgow, UK.10.1109/UPEC.2018.8542041 ↗
7. A Novel Hybrid Whale Optimization Algorithm Differential Evolution Algorithm-Based Maximum Power Point Tracking Employed Wind Energy Conversion Systems for Water Pumping Applications: Practical Realization10.1109/TIE.2023.3260345 ↗
8. Nie, L., Mao, M., Wan, Y., Cui, L., Zhou, L., and Zhang, Q. (2019, January 18–20). Maximum Power Point Tracking Control Based on Modified ABC Algorithm for Shaded PV System. Proceedings of the 2019 AEIT International Annual Conference (AEIT), Florence, Italy.
9. An Improved Particle Swarm Optimization(PSO)-Based MPPT Strategy for PV System
10. Development of maximum power point tracking algorithm based on Improved Optimized Adaptive Differential Conductance Technique for renewable energy generation10.1016/j.heliyon.2024.e41344 ↗
11. A novel maximum power point tracking approach based on fuzzy logic control and optimizable Gaussian Process Regression for solar systems under complex environment conditions10.1016/j.engappai.2024.109780 ↗
12. Sahbani, S., Mahmoudi, H., Hasnaoui, A., Kchikach, M., and Redouane, A. (2020, January 29–30). A Novel MPPT Strategy with Only One Current Sensor Using Predictive Control Technique. Proceedings of the 2020 5th International Conference on Renewable Energies for Developing Countries (REDEC), Marrakech, Morocco.10.1109/REDEC49234.2020.9163846 ↗
13. A review on maximum power point tracking for photovoltaic systems with and without shading conditions10.1016/j.rser.2016.09.013 ↗
14. Khelif, M., M’Raoui, A., and Hassaine, L. (2016, January 22–24). A detailed design and optimization process of a stand-alone photovoltaic AC transformer-less regulated three-phase voltage generator. Proceedings of the 2016 7th International Renewable Energy Congress (IREC), Hammamet, Tunisia.10.1109/IREC.2016.7478956 ↗
15. Tracking Power Photovoltaic System with Sliding Mode Control Strategy10.1016/j.egypro.2013.07.025 ↗
16. Dehedkar, M.N., and Murkute, S.V. (2018, January 23–24). Optimization of PV System using Distributed MPPT Control. Proceedings of the 2018 International Conference on System Modeling & Advancement in Research Trends (SMART), Moradabad, India.10.1109/SYSMART.2018.8746931 ↗
17. Hu, P., Jiang, K., Ji, X., Tan, D., Liu, D., Cao, K., and Wang, W. (2022). A Novel Grid-Forming Strategy for Voltage-Source Controlled PV Under Nearly 100 Renewable Electricity. Front. Media, 10.10.3389/fenrg.2022.915763 ↗
18. Saleh, E., and Karami, N. (2023, January 20–23). A Fast and Efficient MPPT Technique For PV Systems Using Divide and Conquer. Proceedings of the 2023 Advances in Science and Engineering Technology International Conferences (ASET), Dubai, United Arab Emirates.10.1109/ASET56582.2023.10180727 ↗
19. Hayder, W., Abid, A., Sbita, L., and Hamed, M.B. (2020, January 20–23). MPPT based on P&O method under partially shading. Proceedings of the 2020 17th International Multi-Conference on Systems, Signals & Devices (SSD’20), Sfax, Tunisia.10.1109/SSD49366.2020.9364107 ↗
20. A New MPPT Technique for Fast and Efficient Tracking under Fast Varying Solar Irradiation and Load Resistance10.1155/2020/6535372 ↗
21. Conventional and artificial intelligence based maximum power point tracking techniques for efficient solar power generation10.1002/eng2.12963 ↗
22. Ramakrishna, B., Gopala Krishna Rao, C., Harshavardhan, L., and Raghu Krishna, V. (2024, January 18–20). Maximum Power Tracking Using Machine Learning Technique in Hybrid Solar-Wind Renewable Energy Power Generation. Proceedings of the 2024 Third International Conference on Power, Control and Computing Technologies (ICPC2T), Raipur, India.10.1109/ICPC2T60072.2024.10474801 ↗
23. Bi-objective reinforcement learning for PV array dynamic reconfiguration under moving clouds10.1016/j.epsr.2025.111579 ↗
24. Yang, M., Wu, J., Wang, Y.-X., Wang, Z.-G., and Lan, S.-H. (2025). An optimally improved entropy weight method integrated with a fuzzy comprehensive evaluation for complex environment systems. Environmental and Ecological Statistics, Springer.10.1007/s10651-025-00654-w ↗
25. Siddique, M.A.B., Zhao, D., Rehman, A.U., Ouahada, K., and Hamam, H. (2024). An adapted model predictive control MPPT for validation of optimum GMPP tracking under partial shading conditions. Sci. Rep., 14.10.1038/s41598-024-59304-z ↗
26. A reinforcement learning approach for MPPT control method of photovoltaic sources10.1016/j.renene.2017.03.008 ↗
27. Kesilmiş, Z., Karabacak, M.A., and Aksoy, M. (2019, January 11–13). Investigation of MPPT Algorithms under Partial Shading and Changing Atmospheric Conditions in PSIM Environment. Proceedings of the 2019 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Ankara, Turkey.10.1109/ISMSIT.2019.8932799 ↗
28. Phan, B.C., Lai, Y.C., and Lin, C.E. (2020). A Deep Reinforcement Learning-Based MPPT Control for PV Systems under Partial Shading Condition. Sensors, 20.10.3390/s20113039 ↗
29. A compromise solution for comparison photovoltaic tracking systems: A 7E and uncertainty analysis assisted by machine learning algorithm10.1016/j.enconman.2024.119242 ↗
30. Artetxe, E., Uralde, J., Barambones, O., Calvo, I., and Martin, I. (2023). Maximum Power Point Tracker Controller for Solar Photovoltaic Based on Reinforcement Learning Agent with a Digital Twin. Mathematics, 11.10.3390/math11092166 ↗
31. Cheng, H., Luo, H., Zhi, L., Sun, W., Li, W., and Li, Q. (2024). Reinforcement Learning Based Robust Volt/Var Control in Active Distribution Networks with Imprecisely Known Delay. arXiv.
32. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., and Klimov, O. (2017). Proximal Policy Optimization Algorithms. arXiv.
33. A Reinforcement Learning-Based Maximum Power Point Tracking Method for Photovoltaic Array10.1155/2015/496401 ↗
34. Approximate dynamic programming with a fuzzy parameterization10.1016/j.automatica.2010.02.006 ↗
35. Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, MIT Press. [2nd ed.].
36. Schaul, T., Horgan, D., Gregor, K., and Silver, D. (2015, January 7–9). Universal Value Function Approximators. Proceedings of the 32nd International Conference on Machine Learning, Lille, France.
37. Shi, T., Wu, Y., Song, L., Zhou, T., and Zhao, J. (2025). Efficient Reinforcement Finetuning via Adaptive Curriculum Learning. arXiv.
38. Q-learning10.1007/BF00992698 ↗
39. Afshar, R.R., Zhang, Y., Vanschoren, J., and Kaymak, U. (2022). Automated Reinforcement Learning: An Overview. arXiv.
40. Deep reinforcement learning approach for MPPT control of partially shaded PV systems in Smart Grids10.1016/j.asoc.2020.106711 ↗
41. Thrun, S., and Schwartz, A. (2014). Issues in using function approximation for reinforcement learning. Proceedings of the 1993 Connectionist Models Summer School, Psychology Press.
42. Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., and Riedmiller, M. (2014, January 21–26). Deterministic Policy Gradient Algorithms. Proceedings of the International Conference on Machine Learning, Beijing, China.
43. Lillicrap, T., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., and Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv.
44. Busoniu, L., Babuska, R., Schutter, B.D., and Ernst, D. (2010). Reinforcement Learning and Dynamic Programming Using Function Approximators, CRC Press. [1st ed.].
45. Li, C., Jin, C., and Sharma, R. (2019). Coordination of PV Smart Inverters Using Deep Reinforcement Learning for Grid Voltage Regulation. arXiv.10.1109/ICMLA.2019.00310 ↗
46. Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., and Torgo, L. (2005). Neural Fitted Q Iteration–First Experiences with a Data Efficient Neural Reinforcement Learning Method. Proceedings of the Machine Learning: ECML 2005, Springer.
47. Fuzzy Sets in Data Analysis: From Statistical Foundations to Machine Learning10.1109/MCI.2018.2881642 ↗