Analysis of the Use of Support Vector Regression and Neural Networks to Forecast Insolation for 25 Locations in Japan
Abstract
Photovoltaic systems power output are highly sensitive to variations of insolation. A sudden change in the weather or a displacement of clouds in the sky can cause a meaningful decrease in the power output of such systems. If photovoltaic systems are installed in large scale, such power output oscillations can result in control and operation issues. With a proper forecast of insolation, however, variations in the power output of photovoltaic system can be known before hand allowing for power companies to keep the supply of power stable, balancing the use of photovoltaics with the use of other energy systems for example.