NEURAL NETWORK TRAINING BY MODIFIED GENETIC ALGORITHMS AND ITS APPLICATION IN MODELING THE GLOBAL SOLAR RADIATION IN AMMAN
A. Al-Salaymeh, R. Al_Tarawneh and D. Popovic
Mechanical Engineering Department, Faculty of Engineering and Technology, University of Jordan, Amman 11942 Jordan,
E-mail: email@example.com , Fax:+962 6 53 555 88
Institut für Automatisierungstechnik (IAT), Universität Bremen, Otto-Hahn-Allee,
Gebäude NW1, D-28359 Bremen,
Artificial neural networks (ANNs) are powerful tools that can be used to model and investigate various highly complex and nonlinear phenomena. In this study, ANNs were used to model the daily global solar radiation on horizontal surfaces at Amman city in Jordan. An ANN model was built to develop an algorithm using the solar data measurements. The neural network training was achieved using Hybrid Genetic Algorithm. The utilization of solar energy is very attractive because it is nondepletable source of energy and it is relatively pollution free. The daily average values of the three-years measured global solar radiation data on horizontal surfaces at Amman city which has 32? 1' latitude angle were used for the model assessment. One of the applications for the prediction models is to calculate the solar radiation on horizontal surfaces for solar collector system designs. The present research showed that the predicted results were in a very good agreement with the tabulated data, and the expected solar radiation behaviour.
Index Artificial neural networks, Solar Energy, Global Solar Radiation.
do so for
2000-2007 Professor F.R. Hall & Dr I. Oraifige, University of