2D-interval forecasts for solar power production. (December 2015)

• Record Type: Journal Article
• Authors: Rana, Mashud; Koprinska, Irena; Agelidis, Vassilios G.
• Is Part Of: Solar energy. Volume 122(2015)
• Page Start: 191
• Page End: 203
• Publication Date: 2015-12
• Subjects: Interval forecasts -- Solar power forecasting -- Support vector regression -- Neural networks; Solar energy -- Periodicals; Solar engines -- Periodicals; 621.47
• DOI: 10.1016/j.solener.2015.08.018
• Languages: English
• ISSNs: 0038-092X

Abstract

Highlights: We generate 2D-interval forecasts for solar power produced by PV systems. At time t we predict the lower and upper bound of the PV power for [ t + 1, t + k ]. We predict the PV power directly, from previous PV power and weather data. Prediction algorithm: support vector regression. Evaluation: Australian PV data for 2 years; 1, 5 & 30 min; various interval lengths. Abstract: Accurate prediction of the power generated from solar energy is required for the successful integration of solar energy into the power grid. In this paper we consider forecasting the electricity power produced by a photovoltaic solar system. While previous research has been concerned with point forecasts, we focus on interval forecasts which are more suitable for the highly variable nature of the solar data. We consider a special type of interval forecasts, called 2D-interval forecasts, where the goal is to predict a range of expected values for the solar power output, for a future time interval. We present a new approach called SVR2D which directly computes the 2D-interval forecasts from previous historical solar power and meteorological data, using support vector regression as a prediction algorithm. We evaluate its performance using Australian photovoltaic data for two years sampled every 1, 5 and 30 min, for various interval lengths. The results show that SVR2D provides accurate predictions, outperforming a number of baselines and other methods used for comparison.