Investigating the effect of cloud cover on radiative cooling potential with artificial neural network modeling
Radiative cooling is a novel and promising technology in which, heat is radiated through the infrared wavelength (8–13 μm) to the cold outer space, while the incident solar radiation (0.3–4 μm) is reflected. This leads to a temperature reduction in the material that can be utilized as a free and renewable resource of cooling for different applications. For the sake of increasing the efficiency and the cooling potential of these systems, scientists have precisely studied the affecting parameters and developed analytical equations. The sky cloud coverage is one of the major affecting parameters that is challenging to model due to its inherent complexity and diversity. Therefore, in this article, we investigated the effect of cloud cover on the radiative cooling potential by utilizing machine learning techniques. In this regard, a non-linear autoregressive with exogenous feedback (NARX) neural network has been developed to predict the temperature of the system in different climate conditions by taking cloud coverage into account. Results of this investigation indicate that there is an intensely indirect relationship between cloud coverage and the performance of the system. Accordingly, a cloudy sky can lead to 15°C inaccuracy in the modeling of the system and may even lead to a temperature increase relative to the ambient, which inhibits the applicability of the system. It was eventually concluded that the cloud cover, as one of the major parameters that determine the performance of the system, must be taken into account in radiative cooling system designs.
Artificial neural networks , Cloud cover , Daytime radiative cooling , Machine learning , Radiative sky cooling
Mokhtari, R., Fakouriyan, S. and Ghasempour, R. (2021) ‘Investigating the effect of cloud cover on radiative cooling potential with artificial neural network modeling’, Frontiers in Energy Research, 9, 658338 (14 pp). https://doi.org/10.3389/fenrg.2021.658338
© 2021 Mokhtari, Fakouriyan and Ghasempour. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.