The widespread deployment of photovoltaics (PV) systems has emerged as a key element in the global shift toward a carbon-neutral and sustainable energy systems. Driven by a combination of supportive regulatory frameworks, government incentive programs, technical developments, and increasing environmental awareness, the adoption of PV technologies has witnessed remarkable growth in recent years. However, the rapid integration of distributed PV systems into existing electricity grid infrastructure introduces new challenges, particularly concerning voltage regulation, reverse power flow, and congestion within the electricity grid. These issues are intensified when PV systems are integrated without proper strategy. In this context, solar PV power forecasting has become an essential tool for ensuring the reliable and efficient integration of solar PV systems into power systems. Artificial intelligence (AI) and machine learning (ML) offer means to forecast PV power and energy generation based on historical data of PV generation, meteorological data, and/or weather forecasts.

• Chapter 1: Introduction to solar photovoltaics generation forecast
• Chapter 2: Data, data collection, and pre-processing for solar photovoltaics forecast
• Chapter 3: Statistical time-series based solar photovoltaics forecast
• Chapter 4: Machine learning based solar photovoltaics forecast
• Chapter 5: Deep learning based solar photovoltaics forecast
• Chapter 6: Ensemble and hybrid approaches for solar photovoltaics forecast
• Chapter 7: Probabilistic approaches for solar photovoltaics forecast
• Chapter 8: Model optimisation, hyperparameter tuning, and performance evaluation of AI-based solar photovoltaics forecast
• Chapter 9: Sky imager based solar photovoltaics forecast
• Chapter 10: Solar photovoltaics forecasting for energy system integration and control