RT Conference Proceedings
T1 Characterisation of hourly temperature of a thin-film module from weather conditions by artificial intelligence techniques
A1 Piliougine, Michel
A1 Mora-López, Llanos
A1 Carretero-Rubio, Jesús Eduardo
A1 Sidrach-de-Cardona-Ortin, Mariano
K1 Células solares
K1 Termometría
AB The aim of this paper is the use and validation of artificial intelligence techniques to predict thetemperature of a thin-film module based on tandem CdS/CdTe technology. The cell temperature of a module isusually tens of degrees above the air temperature, so that the greater the intensity of the received radiation, the greaterthe difference between these two temperature values. In practice, directly measuring the cell temperature is verycomplicated, since cells are encapsulated between insulation materials that do not allow direct access. In the literaturethere are several equations to obtain the cell temperature from the external conditions. However, these models usesome coefficients which do not appear in the specification sheets and must be estimated experimentally. In this work,a support vector machine and a multilayer perceptron are proposed as alternative models to predict the celltemperature of a module. These methods allow us to achieve an automatic way to learn only from the underlyinginformation extracted from the measured data, without proposing any previous equation. These proposed methodswere validated through an experimental campaign of measurements. From the obtained results, it can be concludedthat the proposed models can predict the cell temperature of a module with an error less than 1.5 °C.
YR 2015
FD 2015-09-21
LK http://hdl.handle.net/10630/10280
UL http://hdl.handle.net/10630/10280
LA eng
NO Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 24 ene 2026