Applying regression techniques to determine mathematical equations of exergy, electricity, and energy values of photovoltaic thermal collector

Abstract

The highlight of this study is to produce mathematical equations that can calculate the electricity, energy, and exergy efficiency values of an air-type photovoltaic-thermal (PV-T) solar collector with the help of a regression-based artificial intelligence method. Contrary to classical predictive artificial intelligence models, the Elastic.Net regression method, which can produce a linear equation for the modeled parameter, was used. Six different data sets were obtained, with the trials carried out in two months for the PV-T efficiency values. The Elastic Net algorithm produced energy, electrical, and exergy efficiency equations with the first, third, and fifth datasets. Comparisons were made between experimental thermal efficiency ratings and the output of efficiency formulas. The other three data sets were then subjected to efficiency equations, and the results were contrasted with the experimental values. The thermal efficiency equations predicted the experimental data in the data sets 1, 3, 5 and, 2, 4, 6 with mean MAPEs of 2.9% and 4.16%, respectively. The experimental values in both group data sets have been said to be comparable to the efficiency values discovered using the equations. As a result, it is anticipated that the efficiency equations developed can be used in various experimental configurations or flat solar collectors. Additionally, prediction models were created utilizing datasets 1, 3, and 5 using the artificial neural network (ANN) technique. The best ANN network structure was obtained using different network types, training algorithms, transfer functions, and layer-neuron numbers in ANN models.