Microservices have become popular in enterprises because of their excellent scalability and timely update capabilities . However, while fine-grained modularity and service-orientation decrease the complexity of system development, the complexity of system operation and maintenance has been greatly increased, on the contrary. Multiple types of system failures occur frequently, and it is hard to detect and diag-nose failures in time. Furthermore, microservices are updated frequently. Existing anomaly detection models depend on offline training and cannot adapt to the frequent updates of microservices. This paper proposes an anomaly detection approach for microservice systems with multi-source data streams. This approach realizes online model construction and online anomaly detection, and is capable of self-updating and self-adapting. Experimental results show that this approach can correctly identify 78.85％of faults of different types.

ZHANG Qixun;HAN Jing;CHENG Li;ZHANG Baisheng;GONG Zican

Peking University, Beijing 100091, China;ZTE Corporation, Shenzhen 518057, China

中兴通讯技术（英文版）

[1]ZHANG Qixun;HAN Jing;CHENG Li;ZHANG Baisheng;GONG Zican-.Approach to Anomaly Detection in Microservice System with Multi-Source Data Streams)[J].中兴通讯技术（英文版）,2022(03):85-92

Microservice,Streams,Microservices,microservices,microservice

Approach,Anomaly,Detection,System,Source,Data,have,become,popular,enterprises,because,their,excellent,scalability,timely,capabilities,However,while,fine,grained,modularity,orientation,decrease,complexity,development,operation,maintenance,has,been,greatly,increased,contrary,Multiple,types,failures,occur,frequently,hard,diag,nose,Furthermore,are,updated,Existing,anomaly,detection,models,depend,offline,training,cannot,updates,This,paper,proposes,approach,systems,multi,source,data,streams,realizes,online,construction,capable,self,updating,adapting,Experimental,results,show,that,this,correctly,identify,faults,different

0.606405