Meteorological data of the city of N'Djamena

In order to enable an efficient and reliable integration of photovoltaic power plants into power
grids in sub-Saharan Africa in general and Chad in particular, which is committed to massively exploiting
solar energy to address its energy deficit, this work aims to forecast hourly temperature and global horizontal
irradiation (GHI). In this study, we employ ensemble methods represented by random forest (RF) and extreme
boosting gradient (XGB) model. Their performances are then compared with the support vector regression
(SVR) model. As the initial dataset consisted of daily statistics to make hourly previsions, we introduced an
original approach for discretising variables taking into account the nature of the meteorological parameters
with a set of assumptions about their daily trends