Integration of Artificial Intelligence for the Sustainable Optimization of Photovoltaic Systems: A Comprehensive Review

Photovoltaic (PV) technology is now one of the main options for expanding the power of low-carbon electricity generation. However, in practical operation, PV systems still face several persistent difficulties, including the variability of solar irradiance, gradual performance degradation, fault occurrence, suboptimal control, and the growing complexity of grid-connected operation. These issues explain why artificial intelligence (AI) has become increasingly relevant in PV research, not only as a prediction tool, but also to improve monitoring, control, diagnosis, and decision-making. This review investigates the applications of AI in the major stages of the PV system lifecycle: solar resource assessment, power forecasting, fault detection, condition monitoring, system sizing, maximum power point tracking (MPPT), and grid integration. Rather than treating these applications as separate research topics, the review attempts to connect them through the common factors that determine their practical value: data quality, sensing configuration, model complexity, physical operating conditions, and deployment constraints. The reviewed studies indicate that AI-based MPPT methods can achieve tracking efficiencies close to 99%, while recent forecasting models, particularly LSTM, CNN–LSTM, and transformer-based architectures, can reduce prediction errors under changing weather conditions. At the same time, PV fault detection is moving beyond electroluminescence image classification toward more practical multimodal strategies that combine infrared thermography, RGB and drone imagery, electrical measurements, and SCADA/IoT data. Nevertheless, the progress reported in the literature should be interpreted with caution. Many proposed models are still evaluated on limited or non-standardized datasets, and their performance may decrease when they are transferred to different PV technologies, climates, fault severities, or operating conditions. Other recurring limitations include class imbalance, high computational cost, weak generalization, and the limited interpretability of deep-learning models. For this reason, hybrid neural networks, explainable AI, physics-informed learning, edge-AI, federated learning, and quantum machine learning are discussed as possible directions for making AI-based PV solutions more reliable and deployable. This review aims to critically synthesize recent advances and remaining gaps in order to support the practical integration of AI into efficient, reliable, and sustainable PV systems.