International Journal of Computational and Electronics Aspects in Engineering
Volume 7 · Issue 1 · March 2026 · pp. 100-114
Review Article · Peer Reviewed
Received: December 28, 2025 · Accepted: February 28, 2026 · Published: March 08, 2026
DOI: 10.26706/ijceae.7.1.20260111
Open Access · CC BY 4.0

AI for Solar PV Forecasting, MPPT, and Energy Management: A Comprehensive Review

Hussain Ali Mutar1*, Israa J. Mohammed1, Ibtihal Razaq Niama ALRubeei2
1Computer Department, College of Computer Science and Information Technology, Wasit University, Wasit, Iraq.

2Electrical Engineering Department, College of Engineering, Wasit University, Wasit, Iraq.

*Corresponding author: hmutar@uowasit.edu.iq
Download PDF Cite this article Certificate Volume 7 Issue 1

Abstract

With sub-millisecond latency, 10 million devices per square kilometer of connectivity, and terabit Photovoltaic (PV) systems are becoming increasingly important in today’s electricity networks. The fast growth of these installations is moving the focus from simply putting up the solar panels to ways to predict how much electricity they will produce in the future, ways to get the maximum generation from the panels (maximum power point tracking or MPPT), and ways to intelligently manage energy. At the same time, several different research articles demonstrate that artificial intelligence (AI) is becoming a fundamental part of three interrelated functions of PV: predicting future PV production, rapidly and stably extracting available power, and scheduling the interactions between PVs, batteries, loads, and the grid. The majority of reviews focus only on one of three areas: forecasting, MPPT, or energy management, while actual PV systems increasingly require those functions to be simultaneously optimized.

This review establishes a common technical framework across all three areas. It provides an overview of recent work on AI-based PV forecasting, smart and hybrid MPPT, and AI-enabled energy management; compares separate and hybrid approaches to all three processes; establishes a comprehensive benchmark and simulation framework from the literature reviewed; and identifies a number of key research areas needing attention, including benchmarks being established, quantifying uncertainties in the results, transferability of the results to other applications, battery aging considerations, explainability of the models being produced by the algorithms, and deployment based on digital twins.

The primary conclusion is that hybrid AI approaches currently represent a significant amount of the future direction for intelligent PV systems. In forecasting, applications of hybrid and physics-based deep-learning techniques lead to improved spatiotemporal characterizations of forecast uncertainty and improved robustness in their ability to forecast; in MPPT, the use of hybrid methods leads to better overall balancing of global vs. local searches for maximum power in partially shaded scenarios; and in energy management, the combination of forecast-based reinforcement learning methods and hybrid predictive control strategies provide the best overall balance between adaptability and operational constraints.

Keywords

Power Optimization Photovoltaic Forecasting Maximum Power Point Tracking Energy Management Deep Learning Reinforcement Learning Hybrid Intelligent Systems

References

  1. O. S. Popel’ and A. B. Tarasenko, "Modern Development Trends in Photovoltaics (Review)," Thermal Engineering, vol. 68, no. 11, pp. 807-825, Nov. 2021, doi: 10.1134/S0040601521100037.
  2. N. M. Haegel and S. R. Kurtz, "Global Progress Toward Renewable Electricity: Tracking the Role of Solar (Version 4)," IEEE Journal of Photovoltaics, vol. 15, no. 2, pp. 206-214, 2025, doi: 10.1109/JPHOTOV.2024.3450020.
  3. P. Omid, A. Soares, and P. Moura, "A Review of Methodologies for Photovoltaic Energy Generation Forecasting in the Building Sector," Energies, vol. 18, no. 18, p. 5007, 2025, doi: 10.3390/en18185007.
  4. H. F. Carlak and K. Karabanova, "Integration of Machine-Learning Weather Forecasts into Photovoltaic Power Plant Modeling: Analysis of Forecast Accuracy and Energy Output Impact," Energies, vol. 19, no. 2, p. 318, doi: 10.3390/en19020318.
  5. C. Rodriguez-Aburto et al., "Machine Learning for Photovoltaic Power Forecasting Integrated with Energy Storage Systems: A Scientometric Analysis, Systematic Review, and Meta-Analysis," Energies, vol. 18, no. 23, p. 6291, doi: 10.3390/en18236291.
  6. H. Li, W. Wu, W. Chen, and M. Zhang, "RTI-Net: Physics-informed deep learning for photovoltaic power forecasting," Renewable Energy, vol. 256, p. 124152, Jan. 2026, doi: https://doi.org/10.1016/j.renene.2025.124152.
  7. Y. Nie et al., "SKIPP’D: A SKy Images and Photovoltaic Power Generation Dataset for short-term solar forecasting," Solar Energy, vol. 255, pp. 171-179, May 2023, doi: https://doi.org/10.1016/j.solener.2023.03.043.
  8. E. J. Kim et al., "Evaluation of Photovoltaic Generation Forecasting Using Model Output Statistics and Machine Learning," Energies, vol. 19, no. 2, p. 486, doi: 10.3390/en19020486.
  9. F. Aksan, A. Pawlica, V. Suresh, and P. Janik, "A Comparative Study of Machine Learning Models for PV Energy Prediction in an Energy Community," Energies, vol. 18, no. 22, p. 5980, doi: 10.3390/en18225980.
  10. H. Mutar et al., "AI-Based Model for Home Waste Separation Using Raspberry Pi 5 AI Kit," Physics and Chemistry of Solid State, vol. 27, pp. 44-51, Feb. 2026, doi: 10.15330/pcss.27.1.44-51.
  11. V. Suresh, "Benchmarking Transformer Variants for Hour-Ahead PV Forecasting: PatchTST with Adaptive Conformal Inference," Energies, vol. 18, no. 18, p. 5000, doi: 10.3390/en18185000.
  12. J. Chandola et al., "Recent advances in MPPT techniques for photovoltaic systems: A review of classical (P&O, IC), intelligent (ANN), optimization (PSO) and hybrid (ANN-PSO) methods," Results in Engineering, vol. 29, p. 109395, Mar. 2026, doi: https://doi.org/10.1016/j.rineng.2026.109395.
  13. D. Latoń, J. Grela, and A. Ożadowicz, "Applications of Deep Reinforcement Learning for Home Energy Management Systems: A Review," Energies, vol. 17, no. 24, p. 6420, doi: 10.3390/en17246420.
  14. R. Tu et al., "Reviews of Photovoltaic and Energy Storage Systems in Buildings for Sustainable Power Generation and Utilization," Energies, vol. 18, no. 11, p. 2683, doi: 10.3390/en18112683.
  15. J. Li et al., "A systematic review of reinforcement learning in Building-Integrated Photovoltaic (BIPV) optimization," Advances in Applied Energy, vol. 19, p. 100239, Sep. 2025, doi: https://doi.org/10.1016/j.adapen.2025.100239.
  16. U. Hussan et al., "Transformer-based renewable energy forecasting: A comprehensive review," Renewable and Sustainable Energy Reviews, vol. 226, p. 116356, Jan. 2026, doi: https://doi.org/10.1016/j.rser.2025.116356.
  17. H. A. Mutar et al., "Auto-PPA: An Adaptive Deep RL Agent for VLSI Physical Design Optimization," Journal of VLSI Circuits and Systems, vol. 8, no. 1, pp. 9-19, 2026, doi: https://doi.org/10.31838/JCVS/08.01.02.
  18. H. A. Mutar and I. R. N. ALRubeei, "AI-Driven Power Optimization in 6G Networks: A Comprehensive Review," International Journal of Computational and Electronics Aspects in Engineering, vol. 7, no. 1, pp. 45-57, 2026, doi: 10.26706/ijceae.7.1.20260104.
  19. S. J. Yaqoob et al., "Advanced Maximum Power Point Tracking in Photovoltaic Systems: A Comprehensive Review," Engineering Reports, vol. 7, no. 9, p. e70404, 2025, doi: https://doi.org/10.1002/eng2.70404.
  20. E. Saloux et al., "From theory to practice: A critical review of model predictive control field implementations in the built environment," Applied Energy, vol. 393, p. 126091, Sep. 2025, doi: https://doi.org/10.1016/j.apenergy.2025.126091.
  21. J. Wu et al., "Deep reinforcement learning-based multi-objective energy management system for microgrids under flexible energy market," Applied Energy, vol. 406, p. 127223, Mar. 2026, doi: https://doi.org/10.1016/j.apenergy.2025.127223.
  22. H. Meng et al., "Enhanced reinforcement learning-model predictive control for distributed energy systems," Building Simulation, vol. 18, no. 3, pp. 547-567, Mar. 2025, doi: 10.1007/s12273-024-1227-9.
  23. X. Wang et al., "Safe deep reinforcement learning for building energy management," Applied Energy, vol. 377, p. 124328, Jan. 2025, doi: https://doi.org/10.1016/j.apenergy.2024.124328.
  24. G. Chenxiao et al., "Reinforcement learning-based control of residential energy storage systems for electric bill minimization," in Proc. IEEE Consumer Communications and Networking Conference (CCNC), 2015, pp. 637-642, doi: 10.1109/CCNC.2015.7158054.
  25. A. Ali et al., "Dynamic Multi-Objective Optimization of Grid-Connected Distributed Resources Along With Battery Energy Storage Management," IEEE Access, vol. 12, pp. 58972-58992, 2024, doi: 10.1109/ACCESS.2024.3392911.