Optimizing the Performance of Perovskite Solar Cells through Triple-Diode Model: Achieving Maximum Power Conversion Efficiency and Minimizing Statistical Errors

Third-generation photovoltaic systems utilize various hybrid organic-inorganic perovskite materials to convert solar energy into electrical power. A key advantage of these cells is their lower cost, resulting from inexpensive raw materials as well as manufacture techniques. However, they also face several challenges, including the hysteresis phenomenon and limited stability.To overcome these, this manuscript presents a triple-diode model (TDM) for Perovskite solar cells (PSCs). The main objective of the work is to design an optimal structure for a PSC to achieve the maximal power conversion efficiency (PCE) and reducing the statistical errors. The Proposed method utilizes an Artificial Rabbits Optimized Neural Network (ARONN) to predict the parameters of the triple-diode method for PSCs. To validate the proposed ARONN approach, it is implemented in the MATLAB Simulink platform. The simulation results show better performance and robustness of the proposed ARONN approach against existing approaches such as Artificial Neural Network (ANN), Particle Swarm Optimization (PSO), and Fire Hawk Optimizer (FHO). The proposed ARONN approach significantly reduces the parameter estimation error, achieving approximately 70%, 75%, and 89% improvement compared with FHO, ANN, and PSO, respectively, demonstrating the superior prediction capability of the proposed model. The results demonstrate detecting the parameters of the TDM for PSCs, where the proposed ARONN method attained a lower value compared to the existing approach.