Benmouiza Mohammed Said / University of Laghouat, Algeria. / Algeria
BENMOUIZA MOHAMMED SAID / UNIVERSITY AMAR TELIDJI OF LAGHOUAT / ALGERIA
HACHANI LAKHDER / UNIVERSITY AMAR TELIDJI OF LAGHOUAT / ALGERIA
BENMOUIZA KHALIL / UNIVERSITY AMAR TELIDJI OF LAGHOUAT / ALGERIA
Recent The application of solar energy at a given site requires the complete and detailed knowledge of solar radiation of the site. This is generally easy when the site is provided with a radiometric measurement station running regularly for several years. However, in most areas of the world, these measurements are not easily available due to financial, technical, or institutional limitations. Estimation models are used to determine the amount of solar radiation at given place, among them Angstrom model that used a linear relation to determine the amount of ground solar radiation based on sunshine hours. However, this model suffers from drawbacks because it does not take into consideration the seasonal variations and the nonlinearity of the measured data. Hence, we propose in this paper a clustering method to enhance the old Angstrom-Prescott model in order to get an accurate estimation model. The proposed idea consists of using clustering k-means algorithm to classify the measured sunshine hours and reconstructing a new Angstrom model parameter based on the results of clusters. The proposed model is tested and validated for the Region of Oran, Algeria.