| KEYWORD |
Energy Center Lab
Deep learning techniques to forecast solar radiation
keywords ARTIFICIAL INTELLIGENCE, ARTIFICIAL NEURAL NETWORK, DEEP NEURAL NETWORKS, FORECAST, RENEWABLE ENERGY SOURCES, SOLAR RADIATION
Reference persons EDOARDO PATTI
External reference persons Alessandro Aliberti (alessandro.aliberti@polito.it), Marco Castangia (marco.castangia@polito.it)
Research Groups DAUIN - GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ELECTRONIC DESIGN AUTOMATION - EDA, Energy Center Lab, GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ICT4SS - ICT FOR SMART SOCIETIES
Thesis type EXPERIMENTAL
Description The accurate prediction of solar radiation in the short-term can finally enable the full penetration of renewable energy sources into the smart grids. The correlation between solar radiation and meteorological factors has been already investigated by scientists, showing that variables like cloud coverage, water vapours and atmospheric aerosols can significantly attenuate the amount of solar radiation reaching the Earth's surface.
This thesis aims at developing an innovative methodology to forecast solar irradiation by taking advantage of advanced deep learning techniques to implement a statistical model for solar radiation forecasting. In detail, the model should leverage images/scans from satellites in order to improve the state-of-the-art in solar radiation forecasting, taking into account both spatial and temporal information influencing solar variations. The ideal candidate should be familiar with Python.
Required skills Python
Deadline 25/01/2025
PROPONI LA TUA CANDIDATURA