eduzhai > Applied Sciences > Engineering >

Deep Neural Network based Wide-Area Event Classification in Power Systems

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 6 pages

Abstract: This paper presents a wide-area event classification in transmission powergrids. The deep neural network (DNN) based classifier is developed based on theavailability of data from time-synchronized phasor measurement units (PMUs).The proposed DNN is trained using Bayesian optimization to search for the besthyperparameters. The effectiveness of the proposed event classification isvalidated through the real-world dataset of the U.S. transmission grids. Thisdataset includes line outage, transformer outage, frequency event, andoscillation events. The validation process also includes different PMU outputs,such as voltage magnitude, angle, current magnitude, frequency, and rate ofchange of frequency (ROCOF). The simulation results show that ROCOF as inputfeature gives the best classification performance. In addition, it is shownthat the classifier trained with higher sampling rate PMUs and a larger datasethas higher accuracy.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×