Supplementary data: "Physics-informed machine learning for power grid frequency modelling"

This repository contains result files for the paper "Physics-informed machine learning for power grid frequency modelling" (Preprint). The code for producing the processed data and the results is available at github. Results The result folder comprises the results of hyper-parameter optimisation, scaling variation and interpretation via SHAP. In particular, it contains these sub-folders and files: tuning : Results of hyper-parameter tuning. best_model : Weights of the trained model with best hyper-parameters. best_model_ : Weights of the trained models with best hyper-parameters but with a variation of the parameter scaling. fixed_model_hps.pkl : Hyper-parameters that are not optimised. shap_values__long.h5 : SHAP values for the prediction of the system parameters.