Bounding Machine Learning Model Errors in Power Grid Analysis

Wednesday, September 25, 2019 - 4:00pm to 4:30pm

Event Calendar Category

LIDS & Stats Tea

Speaker Name

Yuxiao Liu



Building and Room Number

LIDS Lounge


Machine learning methods analysis power grids under incomplete physical information, and their accuracy has been mostly validated empirically using excessive testing datasets. We explore error bounds for machine learning methods under all possible scenarios, and propose an evaluation implementation base on Rademacher complexity theory. We answer key questions in learning practices: how much training data is required to guarantee a certain bound on inaccuracy, and how partial physical knowledge can be utilized to reduce the required amount of data. Our results are crucial for the secure and explanatory application of data-driven methods in power grid analysis. We demonstrate the proposed method by finding generalization error bounds in branch flow linearization and external network equivalent under different degree of physical knowledge.


Yuxiao Liu received the B.E. degree in Electrical Engineering from Tsinghua University, China, where he is currently starting his fourth year of the Ph.D. on the topic of “data analytics in power grid modeling and optimization”. His advisor is Prof. Chongqing Kang. He is now a visiting Ph.D. student in the Laboratory for Information and Decision Systems at MIT with Audun Botterud.