TY - GEN
T1 - Power Quality Analysis for A Solar-Grid Integrated System Using Support Vector Machine
AU - Moloi, K.
AU - Thango, B. A.
AU - Nnnachi, A. F.
AU - Jordaan, J. A.
AU - Hamam, Y.
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/1/27
Y1 - 2021/1/27
N2 - The modern electricity society has seen an increase in the integration of renewable energy sources into the power grid. This has significantly improved the electricity supply and sustainability. However, there are technical challenges related to the power quality (PQ) analysis for grid integrated systems. In this paper, we propose a PQ detection technique using the discrete wavelet transform (DWT) and support vector machine (SVM). The DWT analysis technique is used to extract statistical features, which are used as input to train the SVM classifier. The parameters of the SVM are optimised using the harris hawks optimisation (HHO) algorithm. Various scenarios of cases which may affect the quality of network performance are investigated. These events include the voltage sag, voltage swell, notch, transient fault conditions and sudden load increment. The proposed method is validated using the modified practical Eskom network. The presented results show that the proposed scheme correctly classified different cases.
AB - The modern electricity society has seen an increase in the integration of renewable energy sources into the power grid. This has significantly improved the electricity supply and sustainability. However, there are technical challenges related to the power quality (PQ) analysis for grid integrated systems. In this paper, we propose a PQ detection technique using the discrete wavelet transform (DWT) and support vector machine (SVM). The DWT analysis technique is used to extract statistical features, which are used as input to train the SVM classifier. The parameters of the SVM are optimised using the harris hawks optimisation (HHO) algorithm. Various scenarios of cases which may affect the quality of network performance are investigated. These events include the voltage sag, voltage swell, notch, transient fault conditions and sudden load increment. The proposed method is validated using the modified practical Eskom network. The presented results show that the proposed scheme correctly classified different cases.
KW - Discrete Wavelet Transform
KW - Power Quality Analysis
KW - Renewable Energy Sources
KW - Support Vector Machine
UR - http://www.scopus.com/inward/record.url?scp=85103740112&partnerID=8YFLogxK
U2 - 10.1109/SAUPEC/RobMech/PRASA52254.2021.9377221
DO - 10.1109/SAUPEC/RobMech/PRASA52254.2021.9377221
M3 - Conference contribution
AN - SCOPUS:85103740112
T3 - 2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa, SAUPEC/RobMech/PRASA 2021
BT - 2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa, SAUPEC/RobMech/PRASA 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa, SAUPEC/RobMech/PRASA 2021
Y2 - 27 January 2021 through 29 January 2021
ER -
