TY - GEN
T1 - Supervised machine learning-based protection for transmission line connected to PV plant
AU - Kharusi, Khalfan Al
AU - Haffar, Abdelsalam El
AU - Mesbah, Mostefa
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/10/7
Y1 - 2021/10/7
N2 - This paper presents a supervised machine learning (ML)-based protection approach for identifying different types of transmission lines' faults, including faults during power swing, at several locations and variable fault resistances. Descriptive statistical features used in classification were extracted from spectrograms of measured signals at the relay point. Decision trees (DT)., support vector machines (SVM), k-nearest neighbors (k-NN), boosted and bagged ensemble tree classifiers were used for classification. Four feature selection algorithms, namely neighborhood component analysis (NCA), minimum redundancy maximum relevance (mRMR), sequential feature selection (SFS), and fit ensemble of learners, were applied to reduce the number of features. The synthetic minority class oversampling technique (SMOTE) balances the data to prevent biases toward the majority (non-fault) class. The results show that ensemble bagged trees with SMOTE achieve the maximum accuracy and the minimum false-negative rates. Feature selection algorithms show no improvement in the performance of the classifiers. The best classifier was then tested using data from an unseen scenario and showed accurate detection of the fault events. The classifier, however, was not able to detect faults during power swing after integrating a photovoltaic (PV) plant behind the relay point in the protected line.
AB - This paper presents a supervised machine learning (ML)-based protection approach for identifying different types of transmission lines' faults, including faults during power swing, at several locations and variable fault resistances. Descriptive statistical features used in classification were extracted from spectrograms of measured signals at the relay point. Decision trees (DT)., support vector machines (SVM), k-nearest neighbors (k-NN), boosted and bagged ensemble tree classifiers were used for classification. Four feature selection algorithms, namely neighborhood component analysis (NCA), minimum redundancy maximum relevance (mRMR), sequential feature selection (SFS), and fit ensemble of learners, were applied to reduce the number of features. The synthetic minority class oversampling technique (SMOTE) balances the data to prevent biases toward the majority (non-fault) class. The results show that ensemble bagged trees with SMOTE achieve the maximum accuracy and the minimum false-negative rates. Feature selection algorithms show no improvement in the performance of the classifiers. The best classifier was then tested using data from an unseen scenario and showed accurate detection of the fault events. The classifier, however, was not able to detect faults during power swing after integrating a photovoltaic (PV) plant behind the relay point in the protected line.
KW - Feature selection
KW - ML-based protection
KW - PV integration
KW - SMOTE
KW - Spectrogram
UR - http://www.scopus.com/inward/record.url?scp=85119436223&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119436223&partnerID=8YFLogxK
U2 - 10.1109/ICECCME52200.2021.9590956
DO - 10.1109/ICECCME52200.2021.9590956
M3 - Conference contribution
AN - SCOPUS:85119436223
T3 - International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021
BT - International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021
Y2 - 7 October 2021 through 8 October 2021
ER -