At present, photovoltaic (PV) systems are becoming the core of low-carbon power systems, but their large-scale integration is still limited by weather-driven intermittency, heterogeneous data, equipment failures, operational uncertainty, and life-cycle sustainability requirements. Unlike specific task reviews that only focus on photovoltaic forecasting, fault diagnosis, or general artificial intelligence applications in renewable energy, this review develops an integrated data-driven perspective for machine learning and artificial intelligence in photovoltaic power generation systems. It links data governance, feature engineering, prediction, and uncertainty quantification, fault diagnosis and predictive maintenance, energy management, market participation, and carbon-aware optimization within a framework for photovoltaic systems. This review indicates that traditional machine learning, deep learning, graph learning, reinforcement learning, generative artificial intelligence, and physics-based artificial intelligence are suitable for different photovoltaic tasks based on data structure, time range, operational constraints, and deployment maturity. The main contribution is cross-task integration, which links the output of artificial intelligence models, including scheduling, storage scheduling, maintenance planning, virtual power plant operation, and low-carbon management, with actual decision-making. The review further identified the most critical deployment barriers, such as incomplete benchmarks, weak cross-site generalization, insufficient uncertainty calibration, limited interpretability, network security risks, and computational costs. The resulting methodological approach emphasizes data management, uncertainty awareness, physical constraints, decision orientation, and sustainability-driven photovoltaic intelligence.
Wu et al. (Thu,) studied this question.