Cause identification of electromagnetic transient events using spatiotemporal feature learning

Document Type

Article

Publication Date

12-1-2020

Department

Electrical Engineering

Abstract

This paper presents a spatiotemporal feature learning method for cause identification of electromagnetic transient events in power grids. The proposed method is formulated based on the availability of time-synchronized high-frequency measurements and using the convolutional neural network as the spatiotemporal feature representation along with softmax function for the classification. Despite the existing threshold-based, or energy-based events analysis methods, such as support vector machine autoencoder, and tapered multi-layer perceptron neural network, the proposed feature learning is carried out with respect to both time and space. The effectiveness of the proposed feature learning and the subsequent cause identification is validated through the Electromagnetic Transients Program (EMTP) simulation of different events such as line energization, capacitor bank energization, lightning, fault, and high-impedance fault in the IEEE 30-bus, and the real-time digital simulation of the Western System Coordinating Council (WSCC) 9-bus system. © 2020 Elsevier Ltd

DOI

10.1016/j.ijepes.2020.106255

Publication Title

International Journal of Electrical Power and Energy Systems

This document is currently not available here.

Share

COinS