基于径向基函数神经网络的配电网参数估计

Abstract
Figure/Table
References
Related Citation (1)

Download: PDF (8218 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The effect of temperature, surrounding environment, skin effect and many other factors can contribute to the difference of distribution lines. A big error happened in distribution system analysis when distribution line parameter for calculation is much different from actual parameter data. To address parameter issue, this paper introduces a novel parameter estimation method based on radial basis function neural network (RBFNN) for three-phase unbalanced distribution line to map the nonlinear relation between measured values of branch power and node voltage and line parameter which is deduced from accurate equivalent distribution line three-phase unbalanced model. For a well trained RBFNN, accurate distribution line parameter can be obtained directly from measurement at two end of distribution line which can decrease the error caused by ill-conditioned matrix in parameter estimation.

Key words： radial basis function neural network three-phase unbalanced distribution system parameter estimation nonlinear relation

Received: 29 September 2018 Published: 17 April 2019

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Huang Rui
	Guo Moufa
	Chen Yongwang

Cite this article:

Huang Rui,Guo Moufa,Chen Yongwang. Parameter estimation of distribution system based on radial basis neural network[J]. Electrical Engineering, 2019, 20(4): 42-46.

URL:

http://dqjs.cesmedia.cn/EN/Y2019/V20/I4/42

[1] Acharya Janak R, Wang Yunfei, Xu Wilsun.Temporary overvoltage and GPR characteristics of distribution feeders with multigrounded neutral[J]. IEEE Transa- ctions on Power Delivery, 2010, 25(2): 1036-1044.
[2] McCotter R E, Smolleck H A, Ranade S J, et al. An investigation of the fundamental-frequency impedance of a single-phase distribution lateral[J]. Power Engineering Review, IEEE, 1986, (1): 56-57.
[3] PANDIAN S S. Various considerations for estimating steady-state voltage drop in low voltage AC power distribution systems[C]//proceedings of the2006 IEEE Industrial and Commercial Power Systems Technical Conference-Conference Record, 2006(5): 1-6.
[4] 薛安成, 张兆阳, 毕天姝. 基于自适应抗差最小二乘的线路正序参数在线辨识方法[J]. 电工技术学报, 2015, 30(8): 202-209.
[5] 牛胜锁, 梁志瑞, 张建华, 等. 基于多时段同步测量信息的T接线路参数在线测量[J]. 电工技术学报, 2012, 27(5): 238-244.
[6] 宁辽逸, 孙宏斌, 吴文传, 等. 基于状态估计的电网支路参数估计方法[J]. 中国电机工程学报, 2009, 29(1): 7-13.
[7] JIA D, SHENG W, SONG X, et al.A system identification method for smart distribution grid[C]// Proceedings of the 2014 International Conference on Power System Technology, 2014: 20-22.
[8] Prostejovsky A M, Gehrke O, Kosek A M, et al.Distribution line parameter estimation under consideration of measurement tolerances[J]. IEEE Transactions on Industrial Informatics, 2016, 12(2): 726-735.
[9] 刘小江, 廖文龙, 姚晓, 等. 配变三相不平衡整治策略分析[J]. 电气技术, 2017, 18(11): 87-90.
[10] Vicol B, Gavrilas M, Ivanov O, et al.Synchrophasor measurement method for overhead line parameters estimation in MV distribution networks[C]//2014 IEEE 16th International Conference on Harmonics and Quality of Power (ICHQP), 2014: 862-865.
[11] Das B.Estimation of parameters of a Three-Phase distribution feeder[J]. IEEE Transactions on Power Delivery, 2011, 26(4): 2267-2276.
[12] 尹东阳, 盛义发, 李永胜, 等. 基于EMD和RBFNN的短期风速预测[J]. 电气技术, 2014, 15(6): 44-47.
[13] Demuth H, Beale M.Neural network toolbox[J]. Mathworks, 2007, 21(15): 1225-1233.
[14] Yang N C.Three-phase power flow calculations using direct Z (BUS) method for large-scale unbalanced distribution networks[J]. IET Generation Transmission & Distribution, 2016, 10(4): 1048-1055.
[15] Kersting W H.Radial distribution test feeders[J]. IEEE Transactions on Power Systems, 1991, 6(3): 975-985.