PROJECT TITLE :

Instantaneous Electromechanical Dynamics Monitoring in Smart Transmission Grid

ABSTRACT:

Measurement sensors installed in the smart transmission system will acquire huge information for electromechanical dynamics monitoring. The time-series data obtained carry info of instantaneous relationship of system oscillation modes with respect to operating conditions. To extract this information, this paper proposes a parallel processed online supervised learning algorithm known as k-nearest neighbors “locally weighted linear regression” (KNN-LWLR), which is an extensive combination of 2 famous machine-learning algorithms: 1) the KNN learning; and 2) LWLR learning. Its mathematical derivation, implementation, parameter tuning, and application to electromechanical oscillation mode prediction are 1st described. The proposed algorithm is then validated primarily based on an 8-generator thirty six-node system with the $64000 operations information.