Optimization of MPPT in PV Systems Using Machine Learning Under Partial Shading Conditions

Shamim Hossain; Wang Lu; Li Libo; Conteh Alimamy; Ge Qiang

Authors

Shamim Hossain School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225127, China
Wang Lu School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225127, China
Li Libo School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225127, China
Conteh Alimamy School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225127, China
Ge Qiang School of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225127, China

Keywords:

Maximum Power Point Tracking (MPPT), Photovoltaic (PV) Systems, Machine Learning (ML), Partial Shading Conditions (PSC)

Abstract

Photovoltaic (PV) systems are an important solution to the increasing global demand for electricity and the declining availability of fossil fuels. However, under Partial Shading Conditions (PSC), the Power-Voltage (P-V) curve can have multiple local peaks, which leads to significant power losses and makes it harder to find the true Maximum PowerPoint (MPP). Traditional algorithms like Perturb and Observe (P&O) and Incremental Conductance (INC) often mistake these local peaks for the global ones, making it difficult to accurately track the Global Maximum PowerPoint (GMPP) during shading. To overcome this issue, Machine Learning (ML)-based Maximum Power Point Tracking (MPPT) methods are explored as a data-driven alternative. These aim to improve accuracy and reduce energy loss in PV systems affected by shading. The study evaluates several ML techniques—Artificial Neural Networks (ANN), Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF), and Weighted K-Nearest Neighbours (WK-NN) using both synthetic and real-world weather data from Johannesburg, South Africa. To test their effectiveness, the models are simulated and implemented on a hardware-based PV system. Results show that ML-based MPPT methods significantly enhance tracking performance and reliability. For example, SVM achieves an efficiency of 96.76% under normal conditions and 83.66% during heavy shading, while ANN reaches 99.58% efficiency in stable sunlight. RF and WK-NN also maintain over 95% efficiency in changing conditions due to their adaptability. Despite the promising results, some challenges remain. These include computational complexity, real-time deployment limitations, and the ability of models to generalize under varying sunlight levels. Still, this study demonstrates that AI-powered MPPT systems can greatly improve energy management and grid stability in next-generation solar technologies. Future research should focus on deep learning-based MPPT, hardware-efficient AI models, and real-time optimization to reduce processing demands and improve scalability in embedded MPPT controllers.

References

M. Yılmaz and M. F. Çorapsız, “A robust MPPT method based on optimizable Gaussian process regression and high order sliding mode control for solar systems under partial shading conditions,” Renew. Energy, vol. 239, p. 122339, 2025, doi: https://doi.org/10.1016/j.renene.2025.122339.

F. Belhachat, C. Larbes, and R. Bennia, “Empowering MPPT Efficiency in Partial Shading with Machine Learning Driven Metaheuristic Strategies: Recent Developments,” Lect. Notes Networks Syst., vol. 1238 LNNS, pp. 594–612, 2025, doi: 10.1007/978-3-031-80301-7_64.

Y. H. Liu, Y. S. Cheng, and Y. C. Huang, “A machine learning-based global maximum power point tracking technique for a photovoltaic generation system under complicated partially shaded conditions,” IEEE Trans. Sustain. Energy, 2024, doi: 10.1109/TSTE.2024.3519721.

P. V. Mahesh, S. Meyyappan, and R. K. R. Alla, “A Hybrid MPPT Technique Using Regression Machine Learning and P&O Algorithm for Solar PV Systems Under Partial Shading,” 2024 IEEE Silchar Subsect. Conf. SILCON 2024, 2024, doi: 10.1109/SILCON63976.2024.10910645.

S. M. M. & P. V. Chakarajamula Hussaian Basha, Madhu Palati, C. Dhanamjayulu, “A novel on design and implementation of hybrid MPPT controllers for solar PV systems under various partial shading conditions,” Sci. Reports Vol., vol. 14, p. 1609, 2024, doi: https://doi.org/10.1038/s41598-023-49278-9.

K. V LEELAVATHI, M.; SURESH, “Enhancing MPPT in partially shaded PV modules: a novel approach using adaptive reinforcement learning with neural network architecture,” Bull. Polish Acad. Sci. Tech. Sci., 2024.

S. Farajdadian and S. M. H. Hosseini, “DMPPT control of photovoltaic systems under partial shading conditions based on optimized neural networks,” Soft Comput., vol. 28, no. 6, pp. 4987–5014, Mar. 2024, doi: 10.1007/S00500-023-09196-4/METRICS.

X. W. & J. L. Chunliang Mai, Lixin Zhang, Xuewei Chao, Xue Hu, “A novel MPPT technology based on dung beetle optimization algorithm for PV systems under complex partial shade conditions,” Sci. Rep., vol. 14, p. 6471, 2024, doi: https://doi.org/10.1038/s41598-024-57268-8.

A. Mellit and S. A. Kalogirou, “Artificial intelligence techniques for photovoltaic applications: A review,” Prog. Energy Combust. Sci., vol. 34, no. 5, pp. 574–632, Oct. 2008, doi: 10.1016/J.PECS.2008.01.001.

S. I. P. K. H. Kim, Y. H. Kim, D. S. Kim, “Application of support vector machine and hybrid model for the prediction of maximum power point in photovoltaic systems,” Energies, vol. 12, no. 7, p. 1259, 2019.

L. Bouselham, M. Hajji, B. Hajji, and H. Bouali, “A New MPPT-based ANN for Photovoltaic System under Partial Shading Conditions,” Energy Procedia, vol. 111, pp. 924–933, 2017, doi: https://doi.org/10.1016/j.egypro.2017.03.255.

R. A. P. Venkata Mahesh, S. Meyyappan, “Support Vector Regression Machine Learning based Maximum Power Point Tracking for Solar Photovoltaic systems,” Int. J. Electr. Comput. Eng. Syst., vol. 14, no. 1, 2023, doi: https://doi.org/10.32985/ijeces.14.1.11.

M. U. N. S. Umar, M. S. Qureshi, “Thermal Imaging and AI in Solar Panel Defect Identification,” Int. J. Adv. Eng. Technol. Innov., vol. 1, no. 3, pp. 73–95, 2024.

S. N. Z. Ishrat, A. K. Gupta, “A comprehensive review of MPPT techniques based on ML applicable for maximum power in solar power systems,” J. Renew. Energy Environ., vol. 11, no. 1, p. 2837, 2024.

B. M. B. K. Nayak, A. Mohapatra, “Non linear IV curve of PV module: Impacts on MPPT and parameters estimation,” IJERT, vol. 1, no. 8, pp. 1–8, 2012.

R. G. G. T. Klise, O. Lavrova, “SANDIA REPORT PV System Component Fault and Failure Compilation and Analysis,” Sandia Natl. Lab., 2018.

Z. Zhang et al, “Deep Reinforcement Learning (DRL) for MPPT outperforms ANN and SVM,” 2023.

X. Li et al, “Transformer networks used for real-time MPPT optimization,” 2022.

G. Shankar and V. Mukherjee, “MPP detection of a partially shaded PV array by continuous GA and hybrid PSO,” Ain Shams Eng. J., vol. 6, no. 2, pp. 471–479, 2015, doi: https://doi.org/10.1016/j.asej.2014.10.017.

A. L. Karan Yadav, Bhavnesh Kumar, Josep M. Guerrero, “A hybrid genetic algorithm and grey wolf optimizer technique for faster global peak detection in PV system under partial shading,” Sustain. Comput. Informatics Syst., vol. 35, p. 100770, 2022, doi: https://doi.org/10.1016/j.suscom.2022.100770.

L. Bhukya, A. Annamraju, and S. Nandiraju, “A novel maximum power point tracking technique based on Rao-1 algorithm for solar PV system under partial shading conditions,” Int. Trans. Electr. Energy Syst., vol. 31, no. 9, p. e13028, Sep. 2021, doi: 10.1002/2050-7038.13028.

A. S. Johannes Hofer, Abel Groenewolt, Prageeth Jayathissa, Zoltan Nagy, “Parametric analysis and systems design of dynamic photovoltaic shading modules,” Energy Sci. Eng., 2016, doi: https://doi.org/10.1002/ese3.115.

R. K. Pachauri et al, “Impact of Partial Shading on Various PV Array Configurations and Different Modeling Approaches: A Comprehensive Review,” IEEE Access, vol. 8, pp. 181375–181403, 2020, doi: 10.1109/ACCESS.2020.3028473.

P. E. C. Karuppasamy, C. Senthil Kumar, R. Ganesan, “Optimizing PID control for maximum power point tracking in photovoltaic systems under variable and partial shading conditions,” Renew. Energy, vol. 246, p. 122930, 2025, doi: https://doi.org/10.1016/j.renene.2025.122930.

I. Ul Haq, S. Anwar, and T. Khan, “Machine Vision Based Predictive Maintenance for Machine Health Monitoring: A Comparative Analysis,” 2023 Int. Conf. Robot. Autom. Ind. ICRAI 2023, 2023, doi: 10.1109/ICRAI57502.2023.10089572.