Affiliation:
1. Yuncheng University, Yuncheng 044000, Shanxi, P.R. China
Abstract
In order to improve the effect of fault location, this paper proposes an accurate fault location method for wireless sensor networks based on random matrix theory. The standard non Hermite matrix is used to extract accurate fault location data. Considering the volatility of the original data, the original random matrix is preprocessed. Based on the real-time sliding time window method, the space-time characteristic data of network faults are determined, and the precise fault location of wireless sensor networks based on random matrix theory is realized.Experimental results show that the false positive rate of the proposed method is only 2%. The average fault location accuracy is as high as 96.4% and the fault location time is only 15.1 s, which shows that the proposed method has a good location effect.
Subject
Artificial Intelligence,Computer Networks and Communications,Software
Reference18 articles.
1. Location in power distribution systems via deep graph convolutional networks;Chen;IEEE Journal on Selected Areas in Communications,2020
2. Evaluation of cyber-physical power systems in cascading failure: Node vulnerability and systems connectivity;Chen;IET Generation, Transmission & Distribution,2020
3. A provably correct and robust algorithm for convolutive nonnegative matrix factorization;Degleris;IEEE Transactions on Signal Processing,2020
4. Security and privacy in the Internet of Things;Fawaz;Computer,2019
5. Localization algorithm for wireless sensor networks based on iterative segmentation;Jing;Journal of Changchun University of Technology (Natural Science Edition),2019