Power Quality Disturbances Identification Method Based on Novel Hybrid Kernel Function
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
A hybrid kernel function of support vector machine is proposed to improve the classification performance ofpower quality disturbances. The kernel function mathematical model of support vector machine directly affectsthe classification performance. Different types of kernel functions have different generalization ability andlearning ability. The single kernel function cannot have better ability both in learning and generalization. Toovercome this problem, we propose a hybrid kernel function that is composed of two single kernel functions toimprove both the ability in generation and learning. In simulations, we respectively used the single and multiplepower quality disturbances to test classification performance of support vector machine algorithm with theproposed hybrid kernel function. Compared with other support vector machine algorithms, the improvedsupport vector machine algorithm has better performance for the classification of power quality signals withsingle and multiple disturbances.
Abstract
A hybrid kernel function of support vector machine is proposed to improve the classification performance ofpower quality disturbances. The kernel function mathematical model of support vector machine directly affectsthe classification performance. Different types of kernel functions have different generalization ability andlearning ability. The single kernel function cannot have better ability both in learning and generalization. Toovercome this problem, we propose a hybrid kernel function that is composed of two single kernel functions toimprove both the ability in generation and learning. In simulations, we respectively used the single and multiplepower quality disturbances to test classification performance of support vector machine algorithm with theproposed hybrid kernel function. Compared with other support vector machine algorithms, the improvedsupport vector machine algorithm has better performance for the classification of power quality signals withsingle and multiple disturbances.
참고문헌 (16)
- W. G. Morsi, "Power quality evaluation in smart grids considering modern distortion in electric power systems", Electric Power Systems Research, 81(5), pp.1117~1123 (2011)
- Z. Liu, "Review of power quality mixed disturbances identification", Power System Protection and Control, 41(13), pp.146~153 (2013)
- D. De Yong, "An effective power quality classifier using wavelet transform and support vector machines", Expert Systems with Applications, 42(15-16), pp.6075~6081 (2015)
- Y. Wu, "Feature extraction method of power quality disturbance signals based on modified S-transform", Proceedings of the Chinese Society of Electrical Engineering, 36(10), pp.2682~2689 (2016)
- F. Xu, "Classification for power quality short duration disturbances based on generalized S-transform", Proceedings of the Chinese Society of Electrical Engineering, 32(4), pp.77~84 (2012)
- Y. Wang, "The classification of power quality disturbance based on PSO-MP algorithm and RBF neural network", Electrical Measurement & Instrumentations, 53(13), pp.54~58 (2016)
- H. Chen, "Power quality disturbance identification based on decision tree and support vector machine", Power Grid Technology, 37(5), pp.1272~1278 (2013)
- G. Han, "Power quality disturbance classification based on multi-features combination and optimazing parameters of SVM", Proceedings of the CSU-EPSA, 27(8), pp.71~76 (2015)
- X. Yang, "Short-term wind speed forecasting based on support vector machine with similar data", Proceedings of the Chinese Society of Electrical Engineering, 32(4), pp.35~41 (2012)
- Z. Liu, "A classification method for complex power quality disturbances using EEMD and rank wavelet SVM", IEEE Transactions on Smart Grid, 6(4), pp.1678~1685 (2015)
- G. Liu, "Support vector machine with mixed kernel function", Microcomputer & Applications, 36(11), pp.19~22 (2017)
- L. Zhao, "Classification of power quality composite disturbance based on improved SVM", Advanced Technology of Electrical Engineering and Energy, 35(10), pp.63~68 (2016)
- Z. Chen, "PQD recognition based on wavelet energy difference distribution and SVM", Computer Engineering and Applications, 47(20), pp.241~244 (2011)
- D. Wang, "Fault location for distribution network with distributed power based on improved genetic algorithm", Journal of Northeast Dianli University(Natural Science Edition), 36(1), pp.1~7 (2016)
- F. J. Kuang, "A novel network intrusion detection based on support vector machine and tent chaos artificial bee colony algorithm", Journal of Network Intelligence, 36(1), pp.1~7 (2016)
- W. Qian. L, "Planning of distributed energy storage system for improving low voltage and network loss in rural network", Journal of Northeast Electric Power University, 37(5), pp.19~24 (2017)