A Tensor Completion Method of Missing Data in Transformer District

被引：0

作者：

Zhao H. ^{[1
]}

Shou P. ^{[1
]}

Ma L. ^{[1
]}

机构：

[1] Hebei Key Laboratory of Distributed Energy Storage and Micro-grid, North China Electric Power University, Baoding

来源：

Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2020年 / 40卷 / 22期

关键词：

Missing data completion; Smart distribution systems; Tensor completion; Transformer district;

D O I：

10.13334/j.0258-8013.pcsee.191738

中图分类号：

学科分类号：

摘要：

The calculation of the theoretical line loss in the transformer district is significant for the distribution system to reduce the loss and improve the power quality. However, due to the loss of power consumption data in the collection, transmission and other links, it is impossible to accurately calculate the line loss. In order to obtain the complete data required for the theoretical line loss calculation, a tensor-based multi-user missing data completion model was proposed. Firstly, the paper analyzed the characteristics of the missing data in the station area and constructed the normalized missing tensor in the station area. Then, considering the characteristics of user data and the multi-dimensional intrinsic correlation of multi-user data, the model was established by the low rank of the complement tensor, and the alternating direction method of multipliers (ADMM) was used to solve the model iteratively. Finally, the missing data completion was performed by the proposed method for the random element loss and all day loss of the user data in the district. The results of the example show that the method is suitable for the actual missing situation and can accurately fill the missing data in the low-voltage station area. © 2020 Chin. Soc. for Elec. Eng.

引用

页码：7328 / 7336

页数：8

共 23 条

[1]

Peng Yuwen, Liu Kewen, A distribution network theoretical line loss calculation method based on improved core vector machine, Proceedings of the CSEE, 31, 34, pp. 120-126, (2011)

[2]

Niu Yingshui, Application and case analysis of power grid loss reduction and energy saving technology, pp. 65-110, (2013)

[3]

Li Ya, Liu Liping, Li Baiqing, Et al., Calculation of line loss rate in transformer district based on improved K-Means clustering algorithm and BP neural network, Proceedings of the CSEE, 36, 17, pp. 4543-4551, (2016)

[4]

Zhang Kaikai, Yang Xiuyuan, Bu Congrong, Et al., Theoretical analysis on distribution network loss based on load measurement and countermeasures to reduce the loss, Proceedings of the CSEE, 33, S1, pp. 92-97, (2013)

[5]

Yang Xiutai, Theoretical calculation and analysis of power network line loss, pp. 135-214, (1985)

[6]

Fu Xueqian, Chen Haoyong, Energy losses estimation using equivalent time of average current loss method, Transactions of China Electrotechnical Society, 30, 12, pp. 377-382, (2015)

[7]

Hippert H S, Pedreira C E, Souza R C., Neural networks for short-term load forecasting: a review and evaluation, IEEE Transactions on Power Systems, 16, 1, pp. 44-55, (2001)

[8]

Li Xueping, Liu Yiran, Lu Zhigang, Et al., Phase theoretical line loss calculation and analysis based on clustering theory, Transactions of China Electrotechnical Society, 30, 12, pp. 367-376, (2015)

[9]

Wang Shouxiang, Chen Haiwen, Pan Zhixin, Et al., A reconstruction method for missing data in power system measurement using an improved generative adversarial network, Proceedings of the CSEE, 39, 1, pp. 56-64, (2019)

[10]

Azarkhail M, Woytowitz P., Uncertainty management in model-based imputation for missing data, Proceedings of 2013 Proceedings Annual Reliability and Maintainability Symposium, pp. 1-7, (2013)

← 1 2 3 →