Machine learning-based thermo-electrical performance improvement of nanofluid-cooled photovoltaic–thermal system

Abstract

Hybrid photovoltaic–thermal (hPVT) collectors are devices that allow the conversion of sun energy into useful thermal and electrical energy simultaneously. The power obtained from the photovoltaic (PV) module introduces random fluctuations into the system. While obtaining the data for PV power output in advance and for reducing the impact of random fluctuations, exact day-ahead PV power prediction is crucial. Machine learning algorithms have been proven an effective tool in PV technology for day-ahead prediction of PV-power output. This research employs the Gaussian process regression method using the Matlab environment for forecasting the hPVT collector's performance operating with pure water and Fe/water nanofluid. A one-year historical data pertaining to solar irradiance as well as ambient temperature for Roorkee (29.8543 °N, 77.8880 °E), India location has been used to validate the proposed model. This data is utilized for day-ahead forecasting of solar irradiance and ambient temperature. The outcome elucidates that as the mass-flow rate increases, the thermo-electric performance of the hPVT collector enhances. Raising the mass-flow rate of Fe/water nanofluid from 0.01 to 0.1 kg/s, the cell temperature decreases by 9.35 °C and 9.47 °C, respectively, for the actual and predicted data. The thermal, electrical, as well as overall efficiency of the hPVT collector, improves by 2.73%, 7.11%, and 9.84%, respectively, using Fe/water nanofluid ( ϕ = 2%) in contrast to the water-cooled PVT system. Finally, results demonstrate that the outcomes obtained using the forecasted data closely follow the results obtained using the actual data. In conclusion, this analysis provides a comprehensive solution for utilizing nanofluids as a coolant in the most cost-effective ways.

Application of Copper Oxide Nanofluid and Phase Change Material on the Performance of Hybrid Photovoltaic–Thermal (PVT) System

“…As represented in the thermal circuit model in Figure 1, the heat exchange that takes place in the insulation layer associates the absorber, tube assembly, and ambiance via the convective heat transfer phenomenon [36].…”

Performance evaluation of nanofluid-based photovoltaic thermal (PVT) system with regression analysis

“…Specifically, at a volume concentration of 1%, the Cu/water nanofluid demonstrated a temperature reduction of 4.1 °C, resulting in an increase in electrical efficacy of 5.98% compared to using water alone as the cooling fluid. Recently, in another study, Diwania et al [ 20 ] assessed the efficacy of a PVT system utilizing Fe/water nanofluid and day-ahead forecasting input data in Roorkee, India, using a machine learning process. Compared to a water-cooled PVT system, the hPVT collector's total efficiency was 9.84% higher when a 2% Fe/water nanofluid was used.…”

A novel FFNN-AHO hybrid predictive model for enhancing the performance of jet-cooled PVT system

“…Consequently, ANN methodologies have gained significant popularity in accurately predicting the dynamic performance of PVT systems under diverse external and internal conditions. This encompasses factors like fluid mass flow rate, climate fluctuations, and system design parameters, which have been recognized as relevant considerations [23]. Various ANN models including, radial-basis function ANN, adaptive neuro-fuzzy inference system, and FFNN, were utilized to model PVT systems incorporating nanofluids as a heat transfer fluid [24].…”

“…Other studies employed methods such as least squares support vector machine and ANN to model PVT systems and predict their thermal and electrical efficiencies [23]. The findings showed that the LS-SVM approach demonstrated superior performance in this context.…”