Inverse design of intermediate band solar cell via a joint drift-diffusion simulator and deep reinforcement learning scheme

Abstract

In this work, we developed an efficient inverse design approach for optimal intermediate band solar cells (IBSC) device design given a target performance by using a joint drift-diffusion simulator and deep reinforcement learning scheme.GaAs quantum well embedded AlGaAs IBSC was used as the test candidate to verify the performance of the AI based inverse design approach. Maximum efficiency of was reached for the device with optimal structure parameters searched by the AI agent, which exceeds the target efficiency of 30%. Our work presented here demonstrate for the first time that a well-trained AI agent can fulfill the target efficiency by searching the optimal parameters with sound physical meaning for solar cell device. The AI-based inverse design approach shows promising potential to serve as an efficient device design tool by greatly reduce the number of trial-and-error experiment demonstrations and replacing laborious human guided device design.

Drift–Diffusion Simulation of Intermediate Band Solar Cell: Effect of Intermediate Band Continuity Constraint

“…Our work demonstrated for the first time the appropriate band potential profile and the device performance for drift-diffusion based IBSC device simulation. All the results verified in this work will have significant impact on the proper device design of IBSC for better IB material candidate screening, efficiency improvement, optical management for both the III-V compoundbased IBSC as well as the emerging state of the art perovskite solar cell, perovskite-based IBSC, and other state-of-the art silicon-based photovlotaics [24][25][26][27][28].…”