Accurate predictions of photovoltaic generation are essential for effectively managing power system resources, particularly in the face of high variability in solar radiation. This is especially crucial in microgrids and grids, where the proper operation of generation, load, and storage resources is necessary to avoid grid imbalance conditions. Therefore, the availability of reliable prediction models is of utmost importance. Authors address this issue investigating the potential benefits of a machine learning approach in combination with photovoltaic power forecasts generated using weather models. Several machine learning methods have been tested for the combined approach (linear model, Long Short-Term Memory, eXtreme Gradient Boosting, and the Light Gradient Boosting Machine). Among them, the linear models were demonstrated to be the most effective with at least an RMSE improvement of 3.7% in photovoltaic production forecasting, with respect to two numerical weather prediction based baseline methods. The conducted analysis shows how machine learning models can be used to refine the prediction of an already established PV generation forecast model and highlights the efficacy of linear models, even in a low-data regime as in the case of recently established plants.

Solar irradiance data provided by the Copernicus program are crucial for several scientific, environmental, and energy management applications, but their validation by means of ground-based measurements may be necessary, especially if daily and hourly data resolutions are required. The validation process not only ensures that reliable information is available for solar energy resource planning, power plant performance assessment, and grid integration, but also contributes to the improvement of the Copernicus system itself. Ground-based stations offer site-specific data, allowing for comprehensive assessments of the system’s performance. This work presents a comparative statistical analysis of solar irradiance data provided by the Copernicus system and ground-based measurements on a seasonal basis at three specific Italian reference sites, showing a maximum average relative error of less than 7% for hourly horizontal global irradiance in the irradiance range defined by the IEC 61724-2.