An An inverse artificial neural network algorithm for retrieval of sunshine hours from ground-based global solar irradiation measurements

Main Article Content

Nicholas Nzala
Dennis Muyimbwa
Nicolausi Ssenyonga
Taddeo Ssebiyonga

Keywords

Algorithms; Neural Networks; Artificial intelligence; direct sunshine duration; renewable energy; prediction

Abstract

Availability of meteorological parameter values is important in applications that require solar irradiation. Meteorological parameters such as sunshine hours are best provided by measuring equipment mainly stationed at weather stations. The cost of purchasing the measuring equipment, and setting up and maintaining weather stations is enormous and cannot be easily afforded by many developing countries like Uganda. Furthermore, in Uganda, we have some weather stations which have been measuring global horizontal solar irradiation for quite some time but lacked sunshine duration sensors, and at some others, the sunshine measuring equipment malfunctioned. In this work we present an inverse artificial neural network algorithm that predicts sunshine hours based on horizontal global solar irradiation, the algorithm caters to cases where global horizontal solar irradiation is present but sunshine hour measuring equipment is missing or malfunctioned. A radial basis function neural network (RBF-NN) was trained for forward computation of global horizontal solar irradiation from sunshine hour values.  The inverse modelling algorithm employs multidimensional unconstrained non-linear optimization to retrieve sunshine hours. The correlation coefficient (r) between the measured sunshine hour values and those predicted by the inverse artificial neural network algorithm was found to be 0.924.  The average value of the ratios of the inverse artificial neural network algorithm computed values to the sunshine duration sensor measurements was 1.043. The algorithm predicted sunshine hour values with a mean bias and relative root mean square error of 0.043 and 0.394, respectively. The algorithm developed provides an affordable, fast and reliable method for determining sunshine hour values based on global horizontal solar irradiation. However, sunshine hour values prediction for low values of global horizontal solar irradiation was less precise, and this could be attributed to high levels of cloudiness. It is recommended that an inverse algorithm that retrieves sunshine hours under cloudy conditions be constructed

Abstract 158 | PDF Downloads 0