An adaptive wavenet model for sizing of stand-alone photovoltaic systems

Abstract

In this paper, an application to sizing of stand-alone photovoltaic (PV) systems design method of an unknown optimal sizing combination is presented. These optimal sizing combinations 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, especially in isolated sites where the global solar radiation data is not always available. A developed model combines between multi-layer perceptron (MLP), wavelet and infinite impulse response (UR) filter. The wavenet model has been trained by using 200 known sizing coefficients data corresponding to 200 locations. In this way, the adaptive model was trained to accept and even handle a number of unusual cases. Known sizing coefficients were subsequently used to investigate the accuracy of estimation, the unknown validation sizing coefficients set produced very set accurate estimation with the correlation coefficient between the actual and the wavenet model estimated data of 98% was obtained. This result indicates that the proposed method can be successfully used for estimating of optimal sizing coefficients of stand-alone PV systems for any locations in Algeria, but the methodology can be generalized using different locations in the world.