Novel Technique of Sizing the Stand-Alone Photovoltaic Systems Using the Radial Basis Function Neural Networks: Application in Isolated Sites

Abstract

The objective of this work is to investigate the Radial Basis Function Neural Networks (RBFN) to identifying and modeling the optimal sizing couples of stand-alone photovoltaic (PV) system using a minimum of input data, These optimal couples allow to the users of stand-alone PV systems to determine the number of solar panel modules and storage batteries necessary to satisfy a given consumption. The advantage of this model is to estimate of the sizing PV system in any site in Algeria particularly in isolated sites, where the global solar radiation data is not always available. A RBFN has been trained by using 200 known sizing couples data corresponding to 200 locations. In this way, it was trained to accept and even handle a number of unusual case, known sizing couples were subsequently used to investigate the accuracy of prediction the training of the RBFN model was performed with adequate accuracy. Subsequently, the unknown validation sizing couples set produced very set accurate predictions with the correlation coefficient between the actual and the RBFN model identified data of 98% was obtained. This result indicates that the proposed method can be successfully used for estimating of optimal sizing couples of PV systems for any locations in Algeria, but the methodology can be generalized using different locations in the world.