Title: Falsified data filtering method for smart grid wireless communication based on SVM

Authors: Fen Liu; Zheng Yu; Yixi Wang; Hao Feng; Zhiyong Zha; Rongtao Liao; Ying Zhang

Addresses: Information and Communication Branch of Hubei EPC, Wuhan, Hubei 430077, China ' Information and Communication Branch of Hubei EPC, Wuhan, Hubei 430077, China ' Information and Communication Branch of Hubei EPC, Wuhan, Hubei 430077, China ' Information and Communication Branch of Hubei EPC, Wuhan, Hubei 430077, China ' Information and Communication Branch of Hubei EPC, Wuhan, Hubei 430077, China ' Information and Communication Branch of Hubei EPC, Wuhan, Hubei 430077, China ' Scientific Research Institute of Electric Power, Guizhou Power Grid Company Ltd., Guiyang 550002, China

Abstract: In order to solve the problems of long filter time, low filter efficiency and low utilisation rate of filtered information in traditional data filtering methods, a method of falsified data filtering in smart grid wireless communication based on SVM is proposed. In the initial stage of population search, chaos model is introduced to increase the diversity of individuals, adaptive factors are added into the updating mechanism to increase the global search capability, and falsified feature data is introduced into the fitness function to adjust the classification accuracy and the number of features by using penalty factors. At the later stage of iteration, with the classification accuracy as the objective function. The experimental results show that the filtering accuracy of the proposed method is as high as 99.89%, and the filter time is greatly reduced. The utilisation rate of the filtered information is about 90%, and the overall filter efficiency and accuracy are high.

Keywords: smart grid; wireless communication; falsified data filtering method.

DOI: 10.1504/IJIPT.2020.110304

International Journal of Internet Protocol Technology, 2020 Vol.13 No.4, pp.177 - 183

Received: 04 Dec 2018
Accepted: 23 Mar 2019

Published online: 14 Oct 2020 *

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