Fault Identification and Location of Active Distribution Network Based on SVM Classification of Voltage Data

被引：0
|
作者：
Liu K. [1 ]
Dong W. [1 ]
Xiao S. [2 ]
Wei J. [2 ]
Zhao W. [2 ]
机构：
[1] China Electric Power Research Institute, Haidian District, Beijing
[2] School of Electrical and Electronic Engineering, North China Electrical Power University, Changping District, Beijing
来源：
Dianwang Jishu/Power System Technology | 2021年 / 45卷 / 06期
关键词：
Data correlation; Fault location; Fault type discrimination; Operational state discrimination; SVM;
D O I：
10.13335/j.1000-3673.pst.2020.0516
中图分类号：
学科分类号：
摘要：
After the distributed power sources are connected to the grid, the distribution network has got a complex structure and presented weak fault characteristics.As a result, the traditional fault identification and location methods for distribution networks are no longer applicable. In this paper, a new method of fault type identification and fault location for active distribution network is proposed, which takes the fault voltage as the characteristic quantity and uses the support vector machine (SVM) to accomplish the identification tasks. Firstly, the correlations between the magnitude of each harmonic component of the measuring point voltage and the system operation states or the location of the fault, as well as the correlation between the phase voltage difference and the fault type, are analyzed. Then, the system operation state discrimination, fault type discrimination and fault location are realized based on the correlation between the real-time data and the historical data through the feature selection and the SVM classification methods. Simulation results based on IEEE33-node active power distribution network model show that SVM classification model based on the correlation between voltage and fault can achieve higher accuracy The fault state discrimination, fault type discrimination and fault location can be accurately realized based on the correlation between the real-time data and the historical data. © 2021, Power System Technology Press. All right reserved.
引用
收藏
页码：2369 / 2379
页数：10
相关论文
共 28 条
  • [1] YU Yixin, LUAN Wenpeng, Smart grid and its implementations, Proceedings of the CSEE, 29, 34, pp. 1-8, (2009)
  • [2] SHENG W, LIU K, LIU Y, Et al., Optimal Placement and Sizing of Distributed Generation via an Improved Nondominated Sorting Genetic Algorithm II, IEEE Transactions on Power Delivery, 30, 2, pp. 569-578, (2015)
  • [3] SONG Guobing, TAO Ran, LI Bin, Et al., Survey of fault analysis and protection for power system with large scale power electronic equipments, Automation of Electric Power Systems, 41, 12, pp. 2-12, (2017)
  • [4] YU Xiuyong, XIAO Liye, Overview of fault identification and location technology for DC distribution network, Advanced Technology of Electrical Engineering and Energy, pp. 1-11
  • [5] TONG Xiaoyang, ZHANG Shaoxun, Fault section location and fault type identification method of distribution network based on gray correlation degree, Automation of Electric Power Systems, 43, 4, pp. 113-118, (2019)
  • [6] ZHANG Jun, LI Xiaopeng, HE Zhengyou, Fault classification technique for power distribution network using adaptive network based fuzzy inference system, Proceedings of the CSEE, 30, 25, pp. 87-93, (2010)
  • [7] NIU Geng, ZHOU Long, PEI Wei, Et al., On-line fault section location and classification technique for low voltage active distribution network, Proceedings of the CSEE, 37, 9, pp. 2525-2539, (2017)
  • [8] JIA Qingquan, SUN Lingling, WANG Meijuan, Et al., An adaptive protection method for micro-grid based on node searching, Proceedings of the CSEE, 34, 10, pp. 1650-1657, (2014)
  • [9] SUN Jingliao, CHEN Rongzhu, CAI Shi, Et al., A new fault location scheme for distribution system with distributed generations, Power System Technology, 37, 6, pp. 1645-1650, (2013)
  • [10] ZHANG Zhihua, FENG Xingtian, YIN Mingze, Et al., Improved reverse power protective relaying for spot network with DER based on sequence current components, Power System Technology, 40, 11, pp. 3566-3573, (2016)
123