Novel neural-analytical method for determining silicon/plastic solar cells and modules characteristics

Abstract In this paper, a novel method is proposed to determine the characteristics of silicon solar cell, module and plastic solar cell. Feed-forward artificial neural network together with Lambert W function are used to determine the characteristics. The current–voltage (I–V) and power–voltage (P–V) curves of silicon/plastic solar cells and module are determined. Five model parameters of the solar cell and module are calculated using the proposed technique which compares the Lambert W function representation of the current–voltage characteristic with the learned feed-forward neural network model of the current–voltage relation. Simulation results show a very good agreement between the calculated characteristic curves and experimental data. Also errors are calculated to evaluate the accuracy of the proposed method. The accuracy of the proposed method is compared with other related methods to validate the superiority of the proposed method. As will be shown, the novel contributions of the proposed method can be summarized as: firstly, the proposed method has the accuracy which is much better than other methods and secondly, the current and power errors in the proposed method are generally very lower than these errors in other methods even at the Maximum Power Point (MPP).