- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Faculty Research and Publications /
- Validation of Machine Learning-Aided and Power Line...
Open Collections
UBC Faculty Research and Publications
Validation of Machine Learning-Aided and Power Line Communication-Based Cable Monitoring Using Measurement Data Huo, Yinjia; Wang, Kevin; Lampe, Lutz; Victor Chung Ming, 1955-
Abstract
The implementation of power line communications (PLC) in smart electricity grids provides us with exciting opportunities for real-time cable monitoring. In particular, effective fault classification and estimation methods employing machine learning (ML) models have been proposed in the recent past. Often, the research works presenting PLC for ML-aided cable diagnostics are based on the study of synthetically generated channel data. In this work, we validate ML-aided diagnostics by integrating measured channels. Specifically, we consider the concatenation of clustering as a data pre-processing procedure and principal component analysis (PCA)-based dimension reduction for cable anomaly detection. Clustering and PCA are trained with measurement data when the PLC network is working under healthy conditions. A possible cable anomaly is then identified from the analysis of the PCA reconstruction error for a test sample. For the numerical evaluation of our scheme, we apply an experimental setup in which we introduce degradations to power cables. Our results show that the proposed anomaly detector is able to identify a cable degradation with high detection accuracy and low false alarm rate.
Item Metadata
Title |
Validation of Machine Learning-Aided and Power Line Communication-Based Cable Monitoring Using Measurement Data
|
Creator | |
Publisher |
Multidisciplinary Digital Publishing Institute
|
Date Issued |
2024-01-05
|
Description |
The implementation of power line communications (PLC) in smart electricity grids provides us with exciting opportunities for real-time cable monitoring. In particular, effective fault classification and estimation methods employing machine learning (ML) models have been proposed in the recent past. Often, the research works presenting PLC for ML-aided cable diagnostics are based on the study of synthetically generated channel data. In this work, we validate ML-aided diagnostics by integrating measured channels. Specifically, we consider the concatenation of clustering as a data pre-processing procedure and principal component analysis (PCA)-based dimension reduction for cable anomaly detection. Clustering and PCA are trained with measurement data when the PLC network is working under healthy conditions. A possible cable anomaly is then identified from the analysis of the PCA reconstruction error for a test sample. For the numerical evaluation of our scheme, we apply an experimental setup in which we introduce degradations to power cables. Our results show that the proposed anomaly detector is able to identify a cable degradation with high detection accuracy and low false alarm rate.
|
Subject | |
Genre | |
Type | |
Language |
eng
|
Date Available |
2024-02-07
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
CC BY 4.0
|
DOI |
10.14288/1.0439620
|
URI | |
Affiliation | |
Citation |
Sensors 24 (2): 335 (2024)
|
Publisher DOI |
10.3390/s24020335
|
Peer Review Status |
Reviewed
|
Scholarly Level |
Faculty
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
CC BY 4.0