Solar energy is becoming one of the most promising power sources in residential, commercial, and industrial applications. Solar photovoltaic (PV) facilities use PV cells that convert solar irradiation into electric power. PV cells can be used in either standalone or grid-connected systems to supply power for home appliances, lighting, and commercial and industrial equipment.
Managing uncertainty and fluctuations in energy production is a key challenge in integrating PV systems into power grids and using them as steady, standalone power sources. For this reason, it is very important to forecast solar energy power output.
In this paper, we analyze and compare various methods to predict the production of photovoltaic energy for individual installations and network areas around the world, using statistical methods for time series and different machine learning techniques.