Gap filling for power generation time series data of PV (Photovoltaic) systems.
- Clone or download this repository to your local machine.
- Install the required dependencies.
pip install -r requirements.txt- Move to root directory and run the script using the following command:
python source/impute.py path_to_meteo_data.csv path_to_pv_data.csv output_path.csv modelReplace path_to_meteo_data.csv, path_to_pv_data.csv, and output_path.csv with the actual file paths you want to use.
Choose the gap filling method by replacing model with 'xgb' or 'lstm'.
If model is not specified
'xgb'will be used.
Note that the xgb model performs best.
test-data directory contains the meteo data and PV data of December 2022 collected at GEP. These datasets can be utilized for testing as follows:
python source/impute.py test-data/meteo_data_12_22.csv test-data/System_117_12_22.csv saves/df_imputed.csv 'xgb'
