Explainable AI

Current research on explainability and interpretability of machine learning algorithms

This site is a community effort by the Explainable AI members. Please join the group and reach out to the administrators if you have any questions.

Made with Jekyll and Hyde. Idea and base code for the website adapted from ml4code.

Large-scale Interconnection Power System Model Sanity Check, Tuning, and Validation for Frequency Response Study

Shutang You, Yilu Liu. 2020

[ArXiv]    

The quality and accuracy of power system models is critical for simulation-based studies, especially for studying actual stability issues in large-scale systems. With the deployment of wide-area monitoring systems (WAMSs), the high-reporting-rate frequency measurement provides a trustworthy ground truth for validating models in frequency response studies. This paper documented an effort to check, tune, and validate the U.S. power system model based on a WAMS called FNET/GridEye. Four metrics are used to quantitatively compare the simulation results and the actual measurement, including frequency nadir, RoCoF, settling frequency and settling time. After tuning governor deadband and the governor ratio, the model frequency response shows significant improvement and matches well with the event measurement data. This work serves as an example for tuning and validating large-scale power system models.