A Prediction-Guided and Local-Execution Collaborative MPPT Method for Dynamic Environments: Mechanism Insights and Performance Validation

Authors

  • Xia Wei Kuala Lumpur University of Science and Technology, School of Information Technology Block 11, De Centrum City, Jalan Ikram-Uniten, 43000 Kajang, Selangor Darul Ehsan, Malaysia Author
  • Tadiwa Elisha Nyamasvisva Kuala Lumpur University of Science and Technology, School of Information Technology Block 11, De Centrum City, Jalan Ikram-Uniten, 43000 Kajang, Selangor Darul Ehsan, Malaysia Author
  • Liu Pan Kuala Lumpur University of Science and Technology, School of Information Technology Block 11, De Centrum City, Jalan Ikram-Uniten, 43000 Kajang, Selangor Darul Ehsan, Malaysia Author

DOI:

https://doi.org/10.66525/ijictt92

Keywords:

Photovoltaic systems, Maximum power point tracking, Gated recurrent unit, Incremental conductance, Collaborative control, Dynamic environments

Abstract

Dynamic irradiance variations, temperature disturbances, and partial shading conditions continuously shift the maximum power point (MPP) of photovoltaic (PV) systems, increasing the difficulty of maximum power point tracking (MPPT). Conventional MPPT methods mainly rely on real-time feedback and lack the ability to perceive MPP migration trends under dynamic environments, while existing intelligent MPPT studies primarily focus on prediction accuracy rather than the effective integration of predictive information into control processes. To address this issue, a collaborative MPPT method combining gated recurrent unit (GRU)-based prediction guidance and incremental conductance (INC)-based local execution is proposed. The GRU model provides operating-point trend information, while the INC algorithm ensures feedback-based regulation and stable convergence. The proposed method is evaluated under dynamic irradiance variations, temperature disturbances, partial shading conditions, and composite dynamic conditions. Results show that the GRU–INC framework achieves higher tracking efficiency, lower tracking error, and more stable operating trajectories than the conventional INC-based approach, particularly under partial shading and composite dynamic conditions. Ablation studies further demonstrate that the performance improvement mainly originates from the collaboration between prediction guidance and real-time feedback rather than from the prediction module alone. The results confirm the effectiveness of the proposed collaborative mechanism for MPPT under dynamic environments and highlight the benefit of integrating prediction guidance with feedback regulation

Downloads

Download data is not yet available.

References

Esram T, Chapman P L. Comparison of photovoltaic array maximum power point tracking techniques. IEEE Transactions on Energy Conversion, 2007, 22(2): 439-449. https://doi.org/10.1109/TEC.2006.874230

Ram J P, Pillai D S, Rajasekar N. A comprehensive review on solar PV maximum power point tracking techniques. Renewable and Sustainable Energy Reviews, 2017, 67: 826-847. https://doi.org/10.1016/j.rser.2016.09.076

Ahmed J, Salam Z. A modified P&O maximum power point tracking method with reduced steady-state oscillation and improved tracking efficiency. IEEE Transactions on Sustainable Energy, 2015, 7(4): 1506-1515. https://doi.org/10.1109/TSTE.2015.2472273

Mellit A, Kalogirou S A. Artificial intelligence techniques for photovoltaic applications: A review. Progress in Energy and Combustion Science, 2008, 34(5): 574-632. https://doi.org/10.1016/j.pecs.2008.01.001

Abdel-Nasser M, Mahmoud K. Accurate photovoltaic power forecasting models using deep LSTM-RNN. Neural Computing and Applications, 2019, 31(7): 2727-2740. https://doi.org/10.1007/s00521-017-3225-z

Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation, 1997, 9(8): 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735

Cho K, Van Merrienboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078, 2014. https://doi.org/10.48550/arXiv.1406.1078

Priyadarshi N, Padmanaban S, Holm-Nielsen J B, et al. An experimental estimation of hybrid ANFIS-PSO-based MPPT for PV grid integration under fluctuating sun irradiance. IEEE Systems Journal, 2020, 14(1): 1218-1229. https://doi.org/10.1109/JSYST.2019.2918181

Wang H, Zhou Z, Liu Y, et al. Intelligent maximum power point tracking methods for photovoltaic systems under complex atmospheric conditions: A review. Renewable and Sustainable Energy Reviews, 2021, 145: 111151.

Qin S, Sun Y, Hao X, et al. Adaptive intelligent control for renewable energy systems under dynamic uncertainty: A review. Renewable and Sustainable Energy Reviews, 2022, 158: 112143. https://doi.org/10.1016/j.rser.2022.112143

Chung J, Gulcehre C, Cho K, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555, 2014.

Goodfellow I, Bengio Y, Courville A. Deep Learning. Cambridge: MIT Press, 2016.

Blaabjerg F, Yang Y, Yang D, Wang X. Distributed power-generation systems and protection. Proceedings of the IEEE, 2017, 105(7): 1311-1331. https://doi.org/10.1109/JPROC.2017.2696878

Lund H, Østergaard P A, Connolly D, et al. Smart energy and smart energy systems. Energy, 2017, 137: 556-565. https://doi.org/10.1016/j.energy.2017.05.123

Zheng H, Li S, Peng J, et al. Data-driven adaptive energy management under uncertainty for renewable energy systems. Applied Energy, 2021, 282: 116170. https://doi.org/10.1016/j.apenergy.2020.116170

Heidari A, Abbaspour R A, Chen H, et al. Dynamic adaptation mechanisms in intelligent optimization systems: A review. Information Sciences, 2021, 571: 117-145. https://doi.org/10.1016/j.ins.2021.04.059

Yang B, Yu T, Shu H, et al. Perturbation observation and machine learning hybrid MPPT methods under complex environmental conditions. Solar Energy, 2020, 208: 1159-1172. https://doi.org/10.1016/j.solener.2020.08.051

Li H, Yang D, Su W, et al. An overall distribution particle swarm optimization MPPT algorithm for photovoltaic system under partial shading. IEEE Transactions on Industrial Electronics, 2019, 66(1): 265-275. https://doi.org/10.1109/TIE.2018.2829693

Yap K Y, Sarimuthu C R, Lim J M Y. Artificial intelligence based MPPT techniques for solar power system: A review[J]. Journal of Modern Power Systems and Clean Energy, 2020, 8(6): 1043-1059. DOI:10.35833/MPCE.2020.000159.

Endiz M S, Gökkuş G, Coşgun A E, Demir H. A review of traditional and advanced MPPT approaches for PV systems under uniformly insolation and partially shaded conditions. Applied Sciences, 2025, 15(3): 1031. https://doi.org/10.3390/app15031031

Badawi A, Abdelkader M, El-Naggar M, et al. A State-of-the-Art Comprehensive Review on Maximum Power Point Tracking Techniques for Solar Photovoltaic Systems. Energies, 2025, 18(24): 6555. https://doi.org/10.3390/en18246555

Hu J, Li Y, Mohd Zainuri M A, et al. A comprehensive review of artificial intelligence applications in photovoltaic power generation systems. CAAI Artificial Intelligence Research, 2024, 3(3): 9150031. https://doi.org/10.26599/AIR.2024.9150031

Rezk H, Fathy A. Performance improvement of photovoltaic system during partial shading using particle swarm optimization. Applied Soft Computing, 2017, 57: 382-394. https://doi.org/10.1016/j.asoc.2017.03.017

Koad R B A, Zobaa A F, El-Shahat A. A novel MPPT algorithm based on particle swarm optimization for photovoltaic systems. IEEE Transactions on Sustainable Energy, 2017, 8(2): 468-476. https://doi.org/10.1109/TSTE.2016.2606423

Kumar N, Hussain I, Singh B, et al. Rapid MPPT for uniformly and partial shaded photovoltaic system by using intelligent techniques. IEEE Transactions on Industrial Informatics, 2018, 14(3): 1066-1076. https://doi.org/10.1109/TII.2017.2752690

Kumar K, Singh B, Alammari R, et al. Artificial intelligence-based maximum power point tracking techniques for photovoltaic systems under partial shading conditions: A review. IEEE Access, 2023, 11: 51234-51261. https://doi.org/10.1109/ACCESS.2023.3271452

Li C, Zhou D, Yang M, et al. Deep reinforcement learning-based MPPT control for photovoltaic systems under partial shading conditions. Energy Conversion and Management, 2021, 229: 113731. https://doi.org/10.1016/j.enconman.2020.113731

Priyadarshi N, Padmanaban S, Blaabjerg F, et al. Artificial intelligence applications for solar photovoltaic systems: A comprehensive review. IEEE Access, 2021, 9: 73356-73385. https://doi.org/10.1109/ACCESS.2021.3079642

Priya P, Rajesh R, Kumar A, et al. Advancements in Maximum Power Point Tracking (MPPT) Techniques for Solar Photovoltaic Applications: A Comprehensive Review. Energy Conversion and Management: X, 2026, 29: 101438. https://doi.org/10.1016/j.ecmx.2025.101438

Guanghua L, et al. Maximum Power Point Tracking Strategies for Solar PV Systems: A Comprehensive Review of Classical, Adaptive and Hybrid Methods. Solar Compass, 2025. https://doi.org/10.1016/j.solcom.2025.100066

Villalva M G, Gazoli J R, Filho E R. Comprehensive approach to modeling and simulation of photovoltaic arrays. IEEE Transactions on Power Electronics, 2009, 24(5): 1198-1208. https://doi.org/10.1109/TPEL.2009.2013862

Downloads

Published

2026-06-28