Modeling climate parameters for renewable energy applications in the UAE using neural networks

This paper aims to create prediction models for both global solar radiation and wind speed for the city of Abu Dhabi in the United Arab Emirates. To do so neural network techniques using feed-forward back propagation were deployed and samples for the month of January for such models are presented. The results confirm the accuracy of the models and compare the measured output with the neural network trained outputs. Such models will then be used for estimating power generation using photovoltaics and/or wind turbines.