Using Bayesian Optimization to Increase the Efficiency of III‐V Multijunction Solar Cells

Technology Computer‐Aided Design (TCAD) modeling is a vital tool for the design of complex optoelectronic devices such as III‐V multijunction solar cells. In this work, Bayesian optimization is proposed as a robust framework that is able to tackle difficulties that arise in the optimization of expensive to evaluate black‐box functions, such as TCAD solvers. This method is applied to a lattice‐matched GaInP/Ga(In)As/Ge triple junction solar cell, which incorporates a distributed Bragg reflector for space applications. The results show a path to increase the efficiency of current commercial space triple junction solar cells.