Artificial Intelligence–Based Maximum Power Point Tracking in Smart Photovoltaic Systems: A Systematic Review

The efficiency of solar photovoltaic (PV) systems depends on the ability to track the Maximum
Power Point (MPP) under varying environmental conditions. Conventional Maximum Power Point
Tracking (MPPT) methods, such as Perturb & Observe (P&O) and Incremental Conductance (IC), suffer
from slow convergence, steady-state oscillations, and poor performance under partial shading. To address
these limitations, Artificial Intelligence (AI)-based MPPT techniques, including Artificial Neural
Networks (ANN), Reinforcement Learning (RL), and hybrid AI-metaheuristic models, have been
developed. This study reviews 110 peer-reviewed research papers and finds that AI-driven MPPT methods
achieve tracking efficiencies of up to 99.5%, improve energy yield by 36%, and outperform conventional
methods by 20–30%. Hybrid AI models, such as PSO-ANN and RL-PSO, demonstrate superior
adaptability and precision in dynamic conditions. However, challenges such as high computational costs,
limited real-world validation, and smart grid integration constraints remain. To overcome these barriers,
future research should focus on developing energy-efficient AI architectures for embedded MPPT
controllers, exploring blockchain-based MPPT for secure energy management, and conducting large-scale
experimental validation in operational PV systems. This study highlights the potential of AI-driven MPPT
to enhance solar energy conversion, improve system reliability, and support the transition to more
intelligent and sustainable energy solutions.
Keywords: MPPT, Artificial Intelligence, Optimization, Solar, Efficiency.