TY - GEN
T1 - Fault Classification in Photovoltaic Arrays Using Graph Signal Processing
AU - Fan, Jie
AU - Rao, Sunil
AU - Muniraju, Gowtham
AU - Tepedelenlioglu, Cihan
AU - Spanias, Andreas
N1 - Funding Information:
† These authors contributed equally. The authors from Arizona State University are funded in part by the NSF CPS award 1646542 and the SenSIP Center, School of ECEE, Arizona State University.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/6/10
Y1 - 2020/6/10
N2 - In this paper, we address the problem of fault classification in PhotoVoltaic (PV) arrays using a semi-supervised graph signal processing approach. Traditional fault detection and classification methods require large amounts of labeled data for training. In utility scale solar arrays, obtaining labeled data for different fault classes is resource intensive. We propose a graph based classification technique that relies on a limited amount of labeled data. We compare our results with the well known supervised machine learning classifiers such as the K-nearest neighbour classifier, random forest classifier, support vector machines, and artificial neural networks. We also show that the graph-based classifiers require lower training computational cost compared to the standard supervised machine learning algorithms. The proposed method also achieves good classification performance with unseen data. We validate our method on a real-time dataset and show significant improvements over existing approaches.
AB - In this paper, we address the problem of fault classification in PhotoVoltaic (PV) arrays using a semi-supervised graph signal processing approach. Traditional fault detection and classification methods require large amounts of labeled data for training. In utility scale solar arrays, obtaining labeled data for different fault classes is resource intensive. We propose a graph based classification technique that relies on a limited amount of labeled data. We compare our results with the well known supervised machine learning classifiers such as the K-nearest neighbour classifier, random forest classifier, support vector machines, and artificial neural networks. We also show that the graph-based classifiers require lower training computational cost compared to the standard supervised machine learning algorithms. The proposed method also achieves good classification performance with unseen data. We validate our method on a real-time dataset and show significant improvements over existing approaches.
KW - Graph Signal Processing
KW - Machine Learning
KW - Photovoltaic Array
KW - Solar Array Fault Classification
UR - http://www.scopus.com/inward/record.url?scp=85096201682&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096201682&partnerID=8YFLogxK
U2 - 10.1109/ICPS48405.2020.9274763
DO - 10.1109/ICPS48405.2020.9274763
M3 - Conference contribution
AN - SCOPUS:85096201682
T3 - Proceedings - 2020 IEEE Conference on Industrial Cyberphysical Systems, ICPS 2020
SP - 315
EP - 319
BT - Proceedings - 2020 IEEE Conference on Industrial Cyberphysical Systems, ICPS 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd IEEE Conference on Industrial Cyberphysical Systems, ICPS 2020
Y2 - 10 June 2020 through 12 June 2020
ER -