Module-Power Prediction from PL Measurements using Deep Learning

TL;DR

This paper demonstrates that deep learning can accurately predict photovoltaic module power from photoluminescence images and localize inactive regions, bridging the gap with electroluminescence-based methods.

Contribution

It introduces a deep convolutional neural network for power regression from PL images and shows how to generate localized power loss maps.

Findings

Mean absolute error of 4.4% in power prediction

Regression maps enable localization of inactive regions

Method bridges gap between EL and PL imaging techniques

Abstract

The individual causes for power loss of photovoltaic modules are investigated for quite some time. Recently, it has been shown that the power loss of a module is, for example, related to the fraction of inactive areas. While these areas can be easily identified from electroluminescense (EL) images, this is much harder for photoluminescence (PL) images. With this work, we close the gap between power regression from EL and PL images. We apply a deep convolutional neural network to predict the module power from PL images with a mean absolute error (MAE) of 4.4% or 11.7WP. Furthermore, we depict that regression maps computed from the embeddings of the trained network can be used to compute the localized power loss. Finally, we show that these regression maps can be used to identify inactive regions in PL images as well.