Performance Prediction of Hybrid Energy Harvesting Devices Using Machine Learning
Yoonbeom Park, Kyoungah Cho, Sangsig Kim
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.
Topics & Concepts
Materials scienceArtificial neural networkInterface (matter)Energy (signal processing)Photovoltaic systemEnergy harvestingPower (physics)Thermoelectric generatorComputer scienceAutomotive engineeringMachine learningThermoelectric effectComposite materialElectrical engineeringPhysicsThermodynamicsEngineeringQuantum mechanicsCapillary numberStatisticsCapillary actionMathematicsAdvanced Thermoelectric Materials and DevicesEnergy Harvesting in Wireless NetworksInnovative Energy Harvesting Technologies