%0 Journal Article
	%A Rami El-Hajj Mohamad and  Mahmoud Skafi and  Ali Massoud Haidar
	%D 2014
	%J International Journal of Computer and Information Engineering
	%B World Academy of Science, Engineering and Technology
	%I Open Science Index 86, 2014
	%T Predicting Global Solar Radiation Using Recurrent  Neural Networks and Climatological Parameters
	%U https://publications.waset.org/pdf/9997510
	%V 86
	%X Several meteorological parameters were used for the 
prediction of monthly average daily global solar radiation on 
horizontal using recurrent neural networks (RNNs). Climatological 
data and measures, mainly air temperature, humidity, sunshine 
duration, and wind speed between 1995 and 2007 were used to design 
and validate a feed forward and recurrent neural network based 
prediction systems. In this paper we present our reference system 
based on a feed-forward multilayer perceptron (MLP) as well as the 
proposed approach based on an RNN model. The obtained results 
were promising and comparable to those obtained by other existing 
empirical and neural models. The experimental results showed the 
advantage of RNNs over simple MLPs when we deal with time series 
solar radiation predictions based on daily climatological data.

	%P 331 - 334