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

<p>This repository contains result files for the paper &quot;Physics-informed machine learning for power grid frequency modelling&quot; <a href="https://doi.org/10.48550/arXiv.2211.01481">(Preprint)</a>.&nbsp; The code for producing the processed data and the results is <a href="https://github.com/johkruse/PIML-for-grid-frequency-modelling">available at github</a>.</p> <p><strong>Results</strong></p> <p>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:</p> <ul> <li><em>tuning </em>: Results of hyper-parameter tuning.</li> <li><em>best_model </em>: Weights of the trained model with best hyper-parameters.</li> <li><em>best_model_&lt;scaling-variation&gt; </em>: Weights of the trained models with best hyper-parameters but with a variation of the parameter scaling.</li> <li><em>fixed_model_hps.pkl </em>: Hyper-parameters that are not optimised.</li> <li><em>shap_values_&lt;parameter&gt;_long.h5</em> : SHAP values for the prediction of the system parameters.</li> </ul>