Power System Machine Learning Applications: From Physics-Informed Learning for Decision Support to Inference at the Edge for Control

Authors: Dr. Luigi Vanfretti, Dr. Tetiana Bogodorova and Sergio A. Dorado-Rojas.

Links and Information

The material for this tutorial is available below:

)

The code for Part 1: Synthetic Data for ML Decision Making Applications, can be found here. For Part 2, check the supplementary video here:

Cite this work

If you find this work useful, please cite one (or all!) of the following papers:

• Bogodorova, T; Osipov, D; Vanfretti, L. Automated Design of Realistic Contingencies for Big Data Generation. In IEEE Transactions on Power Systems. doi: 10.1109/TPWRS.2020.3020726

• Dorado-Rojas, SA; de Castro Fernandes, M; Vanfretti, L. Synthetic Training Data Generation for ML-based Small-Signal Stability Assessment. In IEEE SmartGridComm 2020.. Presentation here.

• Ayachi, M; Vanfretti, L; Ahmed, S. A PMU-Based Machine Learning Application for Fast Detection of Forced Oscillations from Wind Farms.

Errata

In the video tutorial for Part 2, we forgot to save the normalized eigenvalues in a pickle file. This was added to the notebook afterwards.