Periodic autoregressive forecasting of global solar irradiation without knowledge-based model implementation

Reliable forecasting methods increase the integration level of stochastic production and reduce cost of intermittence of photovoltaic production. This paper proposes a solar forecasting model for short time horizons, i.e. one to six hours ahead. In this time-range, machine learning methods have proven their efficiency. But their application requires that the solar irradiation time series is stationary which can be realized by calculating the clear sky global horizontal solar irradiance index (CSI), depending on certain meteorological parameters. This step is delicate and often generates additional uncertainty if conditions underlying the calculation of the CSI are not well-defined and/or unknown. As a novel alternative, we introduce a so-called periodic autoregressive (PAR) model. We discuss the computation of post-sample point forecasts and forecast intervals. We show the forecasting accuracy of the model via a real data set, i.e., the global horizontal solar irradiation (GHI) measured at two meteorological stations located at Corsica Island, France. In particular, and as opposed to methods based on CSI, a PAR model helps to improve forecast accuracy, especially for short forecast horizons. In all the cases, PAR is more appropriate than persistence, and smart persistence. Moreover, smart persistence based on the typical meteorological year gives more reliable results than when based on CSI.