In this study a new method for design optimization is proposed that is based on “transfer learning”. The proposed framework improves the accuracy and efficiency of surrogate-based optimization. A surrogate model is an approximation to a costly black-box function that can be used for more efficient search of optimal points. When design specifications change, the objective function changes too. Therefore, there is a need for a new surrogate model. However, the concept of transfer learning can be applied to refit the new surrogate more efficiently. In other words insights from previous experiences can be applied to learning and optimizing the new function. We use the proposed method in a particular problem pertaining to the design of “thin film multilayer solar cells”, where the goal is to maximize the external quantum efficiency of photoelectric conversion. The results show that the accuracy of the surrogate model is improved by 2–3 times using the transfer learning approach, using only half as many training data points as the original model. In addition, by transferring the design knowledge from one particular set of materials to another similar set of materials in the thin film structure, the surrogate-based optimization is improved, and is it obtained with far less computational time.
This paper uses surrogate modeling for very fast design of thin film solar cells with improved solar-to-electricity conversion efficiency. We demonstrate that the wavelength-specific optical absorptivity of a thin film multi-layered amorphous-silicon-based solar cell can be modeled accurately with Neural Networks and can be efficiently approximated as a function of cell geometry and wavelength. Consequently, the external quantum efficiency can be computed by averaging surrogate absorption and carrier recombination contributions over the entire irradiance spectrum in an efficient way. Using this framework, we optimize a multi-layer structure consisting of ITO front coating, metallic back-reflector and oxide layers for achieving maximum efficiency. Our required computation time for an entire model fitting and optimization is 5 to 20 times less than the best previous optimization results based on direct Finite Difference Time Domain (FDTD) simulations, therefore proving the value of surrogate modeling. The resulting optimization solution suggests at least 50% improvement in the external quantum efficiency compared to bare silicon, and 25% improvement compared to a random design.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.