TY  - JOUR
T1  - Artificial Neural Networks Modeling of Relation Relaying Daily Global Solar Radiation to Astronomical and Meteorological Parameters
AU - Harrag, Abdelghani AU - Messalti, Sabir 
JO  - Journal of Engineering and Applied Sciences
VL  - 12
IS  - 10
SP  - 2667
EP  - 2675
PY  - 2017
DA  - 2001/08/19
SN  - 1816-949x
DO  - jeasci.2017.2667.2675
UR  - https://makhillpublications.co/view-article.php?doi=jeasci.2017.2667.2675
KW  - Forecast solar irradiation
KW  -prediction
KW  -neural network
KW  -meteorological parameters
KW  -astronomical parameters
AB  - Algeria naturally has a significant solar potential. This qualitative constant favors the exploitation and development of this energy resource. However, the use of this energy requires knowledge of the potential of solar radiation on horizontal and inclined planes. In fact, the objective of this study is to develop a neural model that can be used to predict the daily global solar radiation average received on a horizontal surface. Several models using different meteorological and astronomical parameters were studied in order to choose the most efficient model based on error between real and predicted irradiation. The results indicate that the model using as input variables: azimuth, zenith angle, extraterrestrial solar radiation, relative humidity, precipitation and wind speed is the most efficient among the studied models.
ER  -