In order to solve the problem of accurately mining the power consumption characteristic data of power users, this paper proposes a research on power user network data mining algorithms based on multi-information fusion. In the past, the mining methods based on neural networks and cure algorithms were affected by noise data, resulting in low mining accuracy. To solve this problem, this paper proposes a user-complex power consumption feature mining method based on the K-means clustering algorithm. In the K-means clustering algorithm, the principle of mining complex power consumption characteristics of users is studied, and the data are cleaned, integrated, and preprocessed by protocol transformation to avoid noise interference. The information entropy principle is used to cluster the matrix to regularize the feature points. According to the complex power consumption characteristics, the power consumption feature points are determined through the cluster, the distance between the clusters is calculated, the power consumption feature information gain is obtained, and the user complex power consumption feature mining is completed. The experimental results show that the mining accuracy of this method is up to 99%, providing users with better quality services. Conclusion. The automatic control performance of the system is good, and the acquisition results are accurate and reliable.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.