Probabilistic analysis of solar cell optical performance using Gaussian processes

TL;DR

This paper explores machine learning methods, especially Gaussian processes, to predict and analyze the optical performance of silicon solar cells, including reflection and generation profiles, with an emphasis on uncertainty quantification.

Contribution

It introduces the use of Gaussian processes for solar cell performance prediction and incorporates confidence bounds to improve estimation accuracy and design optimization.

Findings

Gaussian processes accurately estimate reflection and optical generation profiles.

Confidence bounds provide reliable uncertainty quantification.

Cell design parameters can be optimized for target performance metrics.

Abstract

This work investigates application of different machine learning based prediction methodologies to estimate the performance of silicon based textured cells. Concept of confidence bound regions is introduced and advantages of this concept are discussed in detail. Results show that reflection profiles and depth dependent optical generation profiles can be accurately estimated using Gaussian processes with exact knowledge of uncertainty in the prediction values.It is also shown that cell design parameters can be estimated for a desired performance metric.