Efficiency Improvement of Ingan Solar Cell Based on Bayesian Optimization

Indium gallium nitride (InGaN) solar cells have garnered significant attention due to their tunable bandgap, high absorption coefficient, and robust thermal stability. However, achieving optimal efficiency in these devices remains challenging due to the complex interplay of material properties and device design parameters. Traditional optimization methods are often computationally expensive or inefficient when exploring the multidimensional parameter space. In this work, we propose a data-driven approach using improved Bayesian Optimization (BO) to enhance the efficiency of InGaN solar cells. By systematically optimizing key parameters such as layer thicknesses, indium composition, and doping concentrations, BO identifies configurations that maximize power conversion efficiency (PCE). Our results demonstrate a significant improvement in PCE compared to conventional optimization techniques, showcasing the potential of BO as a powerful tool for advancing InGaN solar cell technology.