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

摘要

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.