Analysis of User Power Characteristic Weight Based on Improved ReliefF and FCM Clustering

In view of the problem of low accuracy in the selection of users' power load characteristics in the analysis of user behavior in smart community, an improved ReliefF algorithm is proposed. Through the improved ReliefF algorithm model, a large number of user power data is processed. Then the FCM clustering algorithm is used for cluster analysis. The improved ReliefF algorithm is combined with the FCM algorithm to verify the effectiveness of the improved ReliefF algorithm for the model of power users. The experimental data come from an intelligent park that has been able to collect data. The improved ReliefF algorithm and FCM clustering algorithm are used to classify users. The accuracy of the result is 95.43%. It is proved that the improved ReliefF model is more reliable.