RT Journal Article
T1 Using a multi-view convolutional neural network to monitor solar irradiance
A1 Huertas Tato, Javier
A1 Galván, Inés M.
A1 Aler, Ricardo
A1 Rodríguez Benítez, Francisco J.
A1 Pozo Vázquez, David
AB In the last years, there is an increasing interest for enhanced method for assessing and monitoring the level of the globalhorizontal irradiance (GHI) in photovoltaic (PV) systems, fostered by the massive deployment of this energy. Thermopileor photodiode pyranometers provide point measurements, which may not be adequate in cases when areal information isimportant (as for PV network or large PV plants monitoring). The use of All Sky Imagers paired convolutional neuralnetworks, a powerful technique for estimation, has been proposed as a plausible alternative. In this work, a convolutionalneural network architecture is presented to estimate solar irradiance from sets of ground-level Total Sky Images. Thisneural network is capable of combining images from three cameras. Results show that this approach is more accurate thanusing only images from a single camera. It has also been shown to improve the performance of two other approaches: acloud fraction model and a feature extraction model.
PB Springer
SN 0941-0643
YR 2021
FD 2021-04-21
LK https://hdl.handle.net/10016/34139
UL https://hdl.handle.net/10016/34139
LA eng
NO This work has been made possible by the Ministerio de Economia y Empresa of Spain, under the project PROSOL (ENE2014-56126-C2). Authors from the University of Jaen are supported by the Junta de Andalucía (Research group TEP-220) and by FEDER funds. This work has been made possible by projects funded by Agencia Estatal de Investigación (PID2019-107455RB-C21 and PID2019-107455RB-C22 / AEI / 10.13039/501100011033).
DS e-Archivo
RD 27 jul. 2024