Advertisement

Denoising SOM: An Improved Fault Diagnosis Method for Quantum Power Communication Network

  • Xi ChenEmail author
  • Wenjing Li
  • Shangjun He
  • Gonghua Hou
  • Lifan Yang
  • Lin Lin
  • Xiao Feng
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 905)

Abstract

With the continuous expansion of quantum power grids, big data analysis of the power grid has become an important issue in the management of smart grid operation and maintenance. Due to the complexity of the power grid system and the limitations of software and hardware environmental conditions, frequent faults in the power grid are very important for the processing of alarm data. This article analyzed the characteristics of power grid alarm data and proposes an improved fault diagnosis method, Denoising SOM. This method uses the self-organizing map (SOM) neural network as a basis, and proposes the idea of denoising the alarm data sample to improve the robustness of the model. In addition, this method also optimizes the Euclidean distance calculation and the neighbourhood function setting of the SOM neural network. The results of comparative experiments show that the fault diagnosis method proposed in this paper has higher accuracy in the task of multi-source fault diagnosis and reduces the time consumption.

Keywords

Quantum SOM Neural network Fault diagnosis Power communication network 

Notes

Acknowledgement

The project is supported by Science and Technology Project “Research and Development of Quantum Cryptography Equipment and Terminal Modules for Power Distribution Grid” in State Grid Corporation of China (536800170042).

References

  1. 1.
    Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: International Conference on Machine Learning, pp. 1096–1103. ACM (2008)Google Scholar
  2. 2.
    Kohonen, T.: Self-Organizing Maps. Series in Information Science, vol. 30(4), pp. 266–270. Springer, Heidelberg (1997)CrossRefGoogle Scholar
  3. 3.
    Niwa, T, Miyazawa, M, Hayashi, M., Stadler, R.: Universal fault detection for NFV using SOM-based clustering. In: Network Operations and Management Symposium, pp. 315–320. IEEE (2015)Google Scholar
  4. 4.
    Li, J., Meng, G., Xie, G.: Sensor fault diagnosis based on wavelet packet and SOM neural network. Chin. J. Sens. Actuators 30(7), 1035–1039 (2017). (in Chinese)Google Scholar
  5. 5.
    Qiu, L., Ye, Y., Jiang, C.: Fault diagnostic method for micro-grid based on wavelet singularity entropy and SOM neural network. J. Shandong Univ. 47(5), 118–122 (2017). (in Chinese)Google Scholar
  6. 6.
    Li, M., Du, W., Qian, F.: Performance recognition method based on multi-index and multi-layer DAE-SOM algorithm. CIESC J. 69(2), 769–778 (2018). (in Chinese)Google Scholar
  7. 7.
    Ntalampiras, S.N.: Fault diagnosis for smart grids in pragmatic conditions. IEEE Trans. Smart Grid 9(3), 1964–1971 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Xi Chen
    • 1
    Email author
  • Wenjing Li
    • 2
  • Shangjun He
    • 1
  • Gonghua Hou
    • 1
  • Lifan Yang
    • 1
  • Lin Lin
    • 1
  • Xiao Feng
    • 3
  1. 1.State Grid Fujian Electric Power Co., Ltd., Fuzhou Power Supply CompanyFuzhouChina
  2. 2.State Grid Information and Telecommunication Group Co., Ltd.BeijingChina
  3. 3.State Grid Xintong Yili Technology Co., Ltd.BeijingChina

Personalised recommendations