Research Article
Abnormal Traffic Detection Method of Educational Network Based on Cluster Analysis Technology
@INPROCEEDINGS{10.1007/978-3-031-21161-4_55, author={Lei Ma and Jianxing Yang and Fayue Zheng}, title={Abnormal Traffic Detection Method of Educational Network Based on Cluster Analysis Technology}, proceedings={e-Learning, e-Education, and Online Training. 8th EAI International Conference, eLEOT 2022, Harbin, China, July 9--10, 2022, Proceedings, Part I}, proceedings_a={ELEOT}, year={2023}, month={3}, keywords={Cluster analysis Network flow Anomaly detection Standardization of specifications Median deviation Minimum covariance}, doi={10.1007/978-3-031-21161-4_55} }- Lei Ma
Jianxing Yang
Fayue Zheng
Year: 2023
Abnormal Traffic Detection Method of Educational Network Based on Cluster Analysis Technology
ELEOT
Springer
DOI: 10.1007/978-3-031-21161-4_55
Abstract
Due to the long detection time of the existing education network abnormal traffic detection methods, the detection accuracy of individual abnormal traffic information is relatively low, which is easy to threaten the operation security of the education network. Therefore, an education network abnormal traffic detection method based on cluster analysis technology is proposed. According to the standardization principle, the key abnormal traffic information is processed, and then according to the definition of subspace clustering, the specific numerical results of the cluster similarity index are calculated to complete the clustering and analysis of the abnormal traffic of the education network. On this basis, execute the abnormal flow information extraction instruction, combine the known median absolute deviation measurement conditions, analyze the minimum covariance results of the detection results, and realize the smooth application of the education network abnormal flow detection method based on the cluster analysis technology. The experimental results show that, compared with traditional detection methods, under the effect of cluster analysis technology, the maximum value of abnormal traffic information of education network can reach 14.1 × 10−7T per unit time, which is in line with the reality of rapid detection of abnormal traffic information of education network Application requirements can better avoid the threat and impact of abnormal information parameters on the security of the education network.
