A Reconstruction Method for Missing Data in Power System Measurement Using an Improved Generative Adversarial Network

被引：0
|
作者：
Wang S. [1 ]
Chen H. [1 ]
Pan Z. [2 ]
Wang J. [2 ]
机构：
[1] Key Laboratory of Smart Grid of Ministry of Education (Tianjin University), Nankai District, Tianjin
[2] State Grid Jiangsu Electric Power Research Institute, Nanjing, 210024, Jiangsu Province
来源：
Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2019年 / 39卷 / 01期
关键词：
Convolution neural network; Generating adversarial networks; Missing data reconstruction; Power system measarement; Time series characteristics;
D O I：
10.13334/j.0258-8013.pcsee.181282
中图分类号：
学科分类号：
摘要：
The collection, transmission and conversion of measured data may be interrupted or disturbed, leading to the loss of data. The traditional reconstruction method only considers the distribution of single data, ignores the correlation between measurement points, measured variables and the historical load change in power system. In this paper, an improved Wasserstein generating adversarial networks (WGAN) method for the reconstruction of missing value was proposed, and a WGAN network structure was designed. Through the unsupervised training of WGAN, the neural network could automatically learn the complex space-time relation which was difficult to model explicitly, such as the correlation between measurement and load fluctuation rule. The hidden variables were optimized by using the real constraint and context similarity constraint, so that the generator after training could generate high precision reconstruction data. The method in this paper is completely data-driven and does not involve explicit modeling steps. It still has high reconstruction accuracy when a large number of measurements are missing. In the calculation example, the relationship between the number of measurements missing and the reconstruction error is analyzed in the example, and it's proved that the data reconstructed can reflect the real time sequence characteristics of the measurement for the long term missing specific measurement. © 2019 Chin. Soc. for Elec. Eng.
引用
收藏
页码：56 / 64
页数：8
相关论文
共 22 条
  • [1] Ding H., Gao Z., Su D., Et al., Solution to bad data problem of phase angle reference bus for state estimation with hybrid measurement, Automation of Electric Power Systems, 38, 9, pp. 132-136, (2014)
  • [2] Yan Y., Sheng G., Chen Y., Et al., Cleaning method for big data of power transmission and transformation equipment state based on time sequence analysis, Automation of Electric Power Systems, 39, 7, pp. 138-144, (2015)
  • [3] Wang D., Sun Z., Big data analysis and parallel load forecasting of electric power user side, Proceedings of the CSEE, 35, 3, pp. 527-537, (2015)
  • [4] Zhang S., Zhao B., Wang F., Et al., Short-term power load forecasting based on big data, Proceedings of the CSEE, 35, 1, pp. 37-42, (2015)
  • [5] Zhang D., Li W., Liu Y., Et al., Reconstruction method of active power historical operating data for wind farm, Automation of Electric Power Systems, 38, 5, (2014)
  • [6] Long J., Liu W., Yin S., Research on abnormal diagnosis for power grid equipment archival data based on machine learning, Electric Power Information and Communication Technology, 16, 7, pp. 21-27, (2018)
  • [7] Miranda V., Krstulovic J., Keko H., Et al., Reconstructing missing data in state estimation with autoencoders, IEEE Transactions on Power Systems, 27, 2, pp. 604-611, (2012)
  • [8] 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)
  • [9] Wang K., Gou C., Duan Y., Et al., Generative adversarial networks: The state of the art and beyond, Acta Automatica Sinica, 43, 3, pp. 321-332, (2017)
  • [10] Yao N., Guo Q., Qiao F., Et al., Robust facial expression recognition with generative adversarial networks, Acta Automatica Sinica, 44, 5, pp. 865-877, (2018)
123