CyL_GHI

This repository contains a solar irradiance dataset for solar forecasting with research propose. 
The goal with this release is to provide a dataset, that allows other authors to use it with their models, without having to make the effort we have made in its elaboration and cleaning, and comparisons can be established between models using the same dataset. In addition can be used with emerging trends (deep learning) in data science.

The dataset have 18 years between January 1st, 2002 and December 31, 2019 with a temporal resolution of 30 minutes of global horizontal irradiance, astronomical variables and ground measurements in Castile and Leon Community, Spain.

1. “CyL_raw.zip” contains the original data in raw format.
2. “CyL_GHI_ast.csv" contains refined data of the Global Horizontal Irradiance (GHI) and the following astronomical variables for each station: Top of Atmosphere Radiation (“toa”), solar elevation angle (“sun_elev”), and azimuth angle (“sun_azim”). The label of a variable is represented by the union of its name with the code of the station (e.g. “GHI_AV01”, “sun_elev_AV01”, “sun_azim_AV01”).
3. “CyL_meteo.csv” contains refined data of the following meteorological variables: temperature (“air_temp”), humidity, wind speed (“wind_sp”), wind direction (“wind_dir”) and precipitation for each station and applies the same procedure for naming variables as the “CyL_GHI_ast.csv” file (e.g. “air_temp_AV01”, “wind_dir_AV01”, “wind_sp_AV01”, etc.).
4. “CyL_geo.csv” contains geographic variables and information related to the stations, namely the code (“station_code”), the name, the coordinates, and the altitude of each station.
5. “CyL_by_stations.zip” contains refined data separated (grouped) by stations—for each station, there is a csv file containing astronomical, meteorological, and geographic variables.