Title: An abnormal data screening method of digital power distribution device based on gSpan

Authors: Keyan Liu; Hui Zhou

Addresses: China Electric Power Research Institute, Haidian District, Beijing, 100192, China ' School of Electrical Engineering, Beijing Jiaotong University, Haidian District, Beijing, 100044, China

Abstract: In order to improve the accuracy and efficiency of abnormal data screening and reduce the data missing rate, a gSpan-based abnormal data screening method for digital power distribution devices is proposed. Under the cloud computing platform, fuzzy association rules are introduced to collect abnormal data of digital power distribution devices. Wavelet threshold denoising method is used to denoise the collected data. According to the data denoising results, the abnormal data is screened by the gSpan algorithm, and according to the preliminary screening results, the data with strong correlation is selected for secondary screening to obtain the final screening results. The experimental results show that the minimum data screening time of the proposed method is 6.2 s, the screening error is always lower than 0.2, and the data missing rate is low, indicating that the data screening effect of the method is good.

Keywords: gSpan; power distribution device; abnormal data screening; fuzzy association rules; wavelet threshold denoising.

DOI: 10.1504/IJPEC.2022.128199

International Journal of Power and Energy Conversion, 2022 Vol.13 No.2, pp.170 - 181

Received: 22 Jun 2022
Accepted: 03 Oct 2022
Published online: 11 Jan 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article