Performance Prediction of Hybrid Energy Harvesting Devices Using Machine Learning

Yoonbeom Park; Kyoungah Cho; Sangsig Kim

doi:10.1021/acsami.1c21856

Performance Prediction of Hybrid Energy Harvesting Devices Using Machine Learning

ACS Appl Mater Interfaces. 2022 Mar 9;14(9):11248-11254. doi: 10.1021/acsami.1c21856. Epub 2022 Feb 25.

Authors

Yoonbeom Park¹, Kyoungah Cho¹, Sangsig Kim¹

Affiliation

¹ Department of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea.

PMID: 35213134
DOI: 10.1021/acsami.1c21856

Abstract

In this study, we used machine learning to predict the output power of hybrid energy devices (HEDs) comprising photovoltaic cells (PVCs) and thermoelectric generators (TEGs). For the five types of HEDs, eight different machine learning models were trained and tested with experimental data; the HED each had different interface materials between the PVCs and the TEGs. An artificial neural network (ANN) model, which is the most appropriate model, predicted the correlation between HED performance and interface material properties. The ANN model demonstrated that the output power of the HED with a carbon paste interface material at an irradiance of 1000 W/m² was 2.6% higher than that of a PVC alone.

Keywords: hybrid energy device; interface; machine learning; photovoltaic cell; thermoelectric generator.