This review paper provides a comprehensive overview of solar energy forecasting techniques, with a particular focus on advancements in forecasting methods and the role of Artificial Intelligence (AI). The study highlights the importance of solar energy forecasting for integrating renewable energy sources into electricity grids and managing renewable energy resources effectively. It covers a wide range of time horizons, from ultrashort intervals (1 minute to 1 hour) to extended durations (up to 24 hours), and emphasizes the integration of satellite imagery, weather predictions, and historical data to enhance forecasting accuracy. The paper reviews various AI techniques, including Neural Networks, supervised learning, regression, ensembles, and physics-based methods, and discusses their application in solar energy forecasting. It also addresses the significance of standardized datasets and benchmark methods for accurate evaluations and meaningful comparisons with naive forecasts. Key aspects of the review include: 1. **Data Sources**: Satellite Images, All-Sky Imagers, Sensor Networks, and Numerical Weather Predictions are discussed for their roles in collecting input data. 2. **AI Techniques**: Neural Networks, support vector machines, k-Nearest Neighbor algorithms, intelligent optimization algorithms, and Markov Chains are highlighted for their effectiveness in solving complex problems. 3. **Performance Metrics**: Common metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Bias Error (MBA), Relative RMSE (rRMSE), Forecast Skill (FS), and Continuous Ranked Probability Score (CRPS) are explained and used to assess forecasting accuracy. 4. **Ramp Events and Timing Errors**: Special attention is given to the Temporal Distortion Index (TDI) and Temporal Distortion Mix (TDM) for detecting and measuring ramp events. 5. **Current Research Trends**: The review identifies trends in solar forecasting research, noting an increase in publications using AI techniques over the last few years. The paper concludes by emphasizing the importance of standardization and the need for further research to address key gaps in the existing literature, particularly in the integration of AI techniques and the development of accurate models for renewable energy planning.This review paper provides a comprehensive overview of solar energy forecasting techniques, with a particular focus on advancements in forecasting methods and the role of Artificial Intelligence (AI). The study highlights the importance of solar energy forecasting for integrating renewable energy sources into electricity grids and managing renewable energy resources effectively. It covers a wide range of time horizons, from ultrashort intervals (1 minute to 1 hour) to extended durations (up to 24 hours), and emphasizes the integration of satellite imagery, weather predictions, and historical data to enhance forecasting accuracy. The paper reviews various AI techniques, including Neural Networks, supervised learning, regression, ensembles, and physics-based methods, and discusses their application in solar energy forecasting. It also addresses the significance of standardized datasets and benchmark methods for accurate evaluations and meaningful comparisons with naive forecasts. Key aspects of the review include: 1. **Data Sources**: Satellite Images, All-Sky Imagers, Sensor Networks, and Numerical Weather Predictions are discussed for their roles in collecting input data. 2. **AI Techniques**: Neural Networks, support vector machines, k-Nearest Neighbor algorithms, intelligent optimization algorithms, and Markov Chains are highlighted for their effectiveness in solving complex problems. 3. **Performance Metrics**: Common metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Bias Error (MBA), Relative RMSE (rRMSE), Forecast Skill (FS), and Continuous Ranked Probability Score (CRPS) are explained and used to assess forecasting accuracy. 4. **Ramp Events and Timing Errors**: Special attention is given to the Temporal Distortion Index (TDI) and Temporal Distortion Mix (TDM) for detecting and measuring ramp events. 5. **Current Research Trends**: The review identifies trends in solar forecasting research, noting an increase in publications using AI techniques over the last few years. The paper concludes by emphasizing the importance of standardization and the need for further research to address key gaps in the existing literature, particularly in the integration of AI techniques and the development of accurate models for renewable energy planning.