Unsupervised Anomaly Detection via DBSCAN for KPIs Jitters in Network Managements

作     者：Haiwen Chen Guang Yu Fang Liu Zhiping Cai Anfeng Liu Shuhui Chen Hongbin Huang Chak Fong Cheang 

作者机构：College of Computer ScienceNational University of Defense TechnologyChangshaChina School of Data Science and Computer ScienceSun Yat-sen UniversityGuangzhouChina College of Information and EngineeringCentral South UniversityChangshaChina Faculty of Information TechnologyMacao University of Science and TechnologyMacao 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2020年第62卷第2期

页      面：917-927页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Anomaly detection KPIs unsupervised learning algorithm 

摘      要：For many Internet companies,a huge amount of KPIs(e.g.,server CPU usage,network usage,business monitoring data)will be generated every *** to closely monitor various KPIs,and then quickly and accurately detect anomalies in such huge data for troubleshooting and recovering business is a great challenge,especially for unlabeled *** generated KPIs can be detected by supervised learning with labeled data,but the current problem is that most KPIs are *** is a time-consuming and laborious work to label anomaly for company *** an unsupervised model to detect unlabeled data is an urgent need at *** this paper,unsupervised learning DBSCAN combined with feature extraction of data has been used,and for some KPIs,its best F-Score can reach about 0.9,which is quite good for solving the current problem.