Machine Learning Based State Estimation for Transmission and Distribution Grids
Fast timescale state estimation for a large power system can be challenging if the sensors producing the measurements are not spread across the system. This is particularly true for performing time-synchronized state estimation for a transmission system that does not have complete phasor measurement unit (PMU) coverage. Similarly, time-synchronized state estimation for distribution networks is challenging because of the sheer size of the system. This talk will first introduce the limitations of conventional supervisory control and data acquisition (SCADA)-based state estimation and of PMU-based linear state estimation, and will then describe how the use of machine learning can help overcome the observability challenges associated with performing time-synchronized state estimation in transmission and distribution grids.
Webinar presenters:
Evangelos Farantatos and Professor Anamitra Pal
Date: August 31, 2022
Time: 11:00am PT / 2:00pm ET (1 hour).