Title: Service fault diagnosis method of information operation and maintenance platform based on Gaussian kernel function

Authors: Ruohan Sun; Kai Yun; Meihui Hu; Jinping Cao; Shu Cao

Addresses: Department of Information, State Grid XinJiang Electric Power Corporation Information and Telecommunication Company, Urumqi 830092, China ' Department of Information, State Grid XinJiang Electric Power Corporation Information and Telecommunication Company, Urumqi 830092, China ' Department of Information, State Grid XinJiang Electric Power Corporation Information and Telecommunication Company, Urumqi 830092, China ' Department of Information, State Grid XinJiang Electric Power Corporation Information and Telecommunication Company, Urumqi 830092, China ' Department of Information, State Grid XinJiang Electric Power Corporation Information and Telecommunication Company, Urumqi 830092, China

Abstract: In order to solve the problems of low diagnosis accuracy and long diagnosis time of existing information operation and maintenance platform service fault diagnosis methods, this paper proposes a service fault diagnosis method for information operation and maintenance platforms based on the Gaussian kernel function. Through the analysis of the service fault data density of the information operation and maintenance platform, the service fault feature extraction of information operation and maintenance platform is completed. The key noise is extracted, and the fault data is denoised. Using the kernel density of the Gaussian kernel function to estimate the kernel density of fault data, the feature data of the nearest distance of fault data is obtained, and the service fault diagnosis of information operation and maintenance platform is completed. The experimental results show that the proposed method has the highest accuracy of 97%, and the diagnosis time is less than 0.2 s.

Keywords: Gaussian kernel function; information operation and maintenance platform; fault diagnosis; average distance; kernel density.

DOI: 10.1504/IJICT.2023.132769

International Journal of Information and Communication Technology, 2023 Vol.23 No.2, pp.153 - 163

Received: 26 May 2021
Accepted: 22 Jul 2021
Published online: 09 Aug 2023 *

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