When supplying energy into the electricity grid, it is important to know the expected output from solar energy systems. While a point forecast of the expected output is valuable, it is only the expected value, whereas a probabilistic forecast gives a range of the most likely values of the output. A probabilistic forecast provides information about all expected outputs and allows one to asses a wide range of uncertainties and then can in turn improve decision making. A probabilistic forecast can be thought of as the error bounds of the forecast. These error bounds are also known as prediction intervals.
Probabilistic forecasting is becoming more prevalent in the renewable energy forecasting literature. Note also that one of the priorities of the International Energy Agency Task 16 on Solar resource for high penetration and large scale applications is developing the best methods for probabilistic forecasting of solar radiation.
Previous work by Boland, Grantham et al. has developed procedures for conditional probabilistic forecasting of solar radiation, incorporating bootstrapping. There are subtle but significant differences between forecasting solar radiation and output from solar farms. The latter, at least in the Australian milieu, tends to reach the maximum capacity of the farm for significant periods. Thus, alteration of the methods previously developed need to be undertaken. Additionally, there is the ability to enhance the forecast skill by blending the statistical tools used in these previous works with sky camera and satellite-based forecast methods.
Key topics: Solar radiation, Forecasting, Probalistic forecasting, Nonparametric