AMI-enabled Distribution Network Line Outage Identification via Multi-label SVM

Authors

Zohreh S. Hosseini, University of Denver
Mohsen Mahoor, University of Denver
Amin Khodaei, University of Denver

Publication Date

9-2018

Document Type

Article

Organizational Units

Daniel Felix Ritchie School of Engineering and Computer Science, Electrical and Computer Engineering

Keywords

Kernel, Support vector machines, Smart meters, Power system reliability, Companies, Meteorology, Network topology

Abstract

This letter proposes an effective data mining method for identifying distribution network line outages by leveraging data collected through Advanced Metering Infrastructure (AMI). The line outage identification method is developed based on a Multi-Label Support Vector Machine (ML-SVM) classification scheme that utilizes the status of customers' smart meters as input data and accordingly identifies the outage/operational status of distribution lines. The F β -score is proposed to validate the performance of the classifier through numerical simulations.

Publication Statement

Copyright held by author or publisher. User is responsible for all copyright compliance.

Recommended Citation

Hosseini, Zohreh S, et al. “AMI-Enabled Distribution Network Line Outage Identification via Multi-Label SVM.” IEEE Transactions on Smart Grid, vol. 9, no. 5, 2018, pp. 5470–5472. doi: 10.1109/tsg.2018.2849845.