## Liquan Zhao* and Meijiao Gai*## |

Disturbance type | Classification accuracy (%) | ||||

Radial basis kernel function | Polynomial kernel function | Method [13] | Method [11] | Hybrid kernel function | |

Voltage swell | 99.1667 | 98.3333 | 100 | 100 | 100 |

Voltage sag | 70 | 84.1667 | 93.3333 | 99.1667 | 85 |

Voltage interruption | 80 | 72.5 | 94.1667 | 96.6667 | 81.1667 |

Harmonic | 100 | 100 | 100 | 100 | 100 |

Transient pulse | 96.6667 | 97.5 | 80.8333 | 70.6667 | 99.1667 |

Transient oscillation | 100 | 100 | 100 | 100 | 100 |

Voltage flicker | 99.1667 | 100 | 83.1667 | 89.1667 | 100 |

Voltage swell with harmonic | 98.3333 | 100 | 100 | 99.1667 | 100 |

Voltage sag with harmonic | 99.1667 | 97.5 | 97.5 | 96.1667 | 98.3333 |

Voltage swell with flicker | 97.5 | 97.5 | 98.3333 | 99.1667 | 99.1667 |

Voltage sag with flicker | 98.3333 | 95.8333 | 99.1667 | 100 | 95 |

Average classification accuracy | 94.3939 | 94.8485 | 95.13636364 | 95.46971818 | 96.2121 |

The average classification accuracies that are obtained by using the SVM algorithms with different kernel functions are shown in Fig. 5. From this figure, we can see that the average classification accuracy that is obtained by using the SVM algorithm with the proposed kernel function is higher than the SVM algorithms with the other kernel function.

In feature extraction, this paper used the wavelet energy difference between the standard signal and the PQD signal to construct the feature vector. In feature vector classification, this paper used the improved SVM with proposed hybrid kernel function to improve the classification accuracy of PQDs. The proposed SVM method has higher generalization and learning abilities than the others, and its classification accuracy is greatly improved.

- 1 W. G. Morsi, M. E. El-Hawary, "Power quality evaluation in smart grids considering modern distortion in electric power systems,"
*Electric Power Systems Research*, vol. 81, no. 5, pp. 1117-1123, 2011.doi:[[[10.1016/j.epsr.2010.12.013]]] - 2 Z. Liu, Q. Zhang, Y. Zhang, "Review of power quality mixed disturbances identification,"
*Power System Protection and Control*, vol. 41, no. 13, pp. 146-153, 2013.custom:[[[-]]] - 3 D. De Yong, S. Bhowmik, F. Magnago, "An effective power quality classifier using wavelet transform and support vector machines,"
*Expert Systems with Applications*, vol. 42, no. 15-16, pp. 6075-6081, 2015.doi:[[[10.1016/j.eswa.2015.04.002]]] - 4 Y. Wu, Q. Tang, Z. Teng, N. Li, X. Wang, "Feature extraction method of power quality disturbance signals based on modified S-transform," in
*Proceedings of the Chinese Society of Electrical Engineering*, 2016;vol. 36, no. 10, pp. 2682-2689. custom:[[[-]]] - 5 F. Xu, H. Yang, M. Ye, Y. Liu, J. Hui, "Classification for power quality short duration disturbances based on generalized S-transform," in
*Proceedings of the Chinese Society of Electrical Engineering*, 2012;vol. 32, no. 4, pp. 77-84. custom:[[[-]]] - 6 Y. Wang, Y. Li, Z. Qu, S. Liu, "The classification of power quality disturbance based on PSO-MP algorithm and RBF neural network,"
*Electrical Measurement & Instrumentations*, vol. 53, no. 13, pp. 54-58, 2016.custom:[[[-]]] - 7 H. Chen, G. Zhang, "Power quality disturbance identification based on decision tree and support vector machine,"
*Power Grid Technology*, vol. 37, no. 5, pp. 1272-1278, 2013.custom:[[[-]]] - 8 G. Han, X. Chu, "Power quality disturbance classification based on multi-features combination and optimazing parameters of SVM," in
*Proceedings of the CSU-EPSA*, 2015;vol. 27, no. 8, pp. 71-76. custom:[[[-]]] - 9 X. Yang, B. Sun, X. Zhang, L. Li, "Short-term wind speed forecasting based on support vector machine with similar data," in
*Proceedings of the Chinese Society of Electrical Engineering*, 2012;vol. 32, no. 4, pp. 35-41. custom:[[[-]]] - 10 Z. Liu, Y. Cui, W. Li, "A classification method for complex power quality disturbances using EEMD and rank wavelet SVM,"
*IEEE Transactions on Smart Grid*, vol. 6, no. 4, pp. 1678-1685, 2015.doi:[[[10.1109/TSG.2015.2397431]]] - 11 G. Liu, X. Yang, "Support vector machine with mixed kernel function,"
*Microcomputer & Applications*, vol. 36, no. 11, pp. 19-22, 2017.custom:[[[-]]] - 12 L. Zhao, Y. Long, "Classification of power quality composite disturbance based on improved SVM,"
*Advanced Technology of Electrical Engineering and Energy*, vol. 35 no.10, no. vol.35 10, pp. 63-68, 2016.custom:[[[-]]] - 13 Z. Chen, M. Ouyang, H. Liu, "PQD recognition based on wavelet energy difference distribution and SVM,"
*Computer Engineering and Applications*, vol. 47, no. 20, pp. 241-244, 2011.custom:[[[-]]] - 14 D. Wang, X. Wu, Z. Wang, "Fault location for distribution network with distributed power based on improved genetic algorithm,"
*Journal of Northeast Dianli University (Natural Science Edition)*, vol. 36, no. 1, pp. 1-7, 2016.custom:[[[-]]] - 15 F. J. Kuang, S. Y. Zhang, "A novel network intrusion detection based on support vector machine and tent chaos artificial bee colony algorithm,"
*Journal of Network Intelligence*, vol. 36, no. 1, pp. 1-7, 2016.custom:[[[-]]] - 16 W. Qian. L, Lina. X. Bei, C. Houhe, "Planning of distributed energy storage system for improving low voltage and network loss in rural network,"
*Journal of Northeast Electric Power University*, vol. 37, no. 5, pp. 19-24, 2017.custom:[[[-]]]