Daily global solar radiation estimation for Gran Canaria Island using artificial neural networks

Abstract

Forecasting of global solar radiation is an important tool for power systems planning and operation, especially in island grids. The aim of this paper is the analysis of an artificial neural network as a reliable method to obtain a daily forecast for solar radiation. Some different tests are proposed to obtain the optimal ANN that will capture the underlying physical process that generates the data. In the present study, the available data come from seven measuring stations throughout the Gran Canaria Island along six years. ANN was trained and tested only with past ground measurement solar radiation and other meteorological data available at measurement stations as inputs.