A Method of Alarm Correlation and Root Cause Analysis in 5G Core Network

5G core network realizes three-layer decoupling based on virtualization technology, and the architecture is more flexible and complex. However, once various interfaces and network elements generate alarms, alarm correlation and root cause analysis are difficult, which brings challenges to operation and maintenance. This paper proposes a method of alarm correlation and root cause analysis. We establish the three-layer correlation relationship of resource and alarm data, and set up the alarm correlation rule base based on expert experience and graph neural network algorithm. In the method, the alarm data can be compressed, and the resource topology and alarm root cause can be viewed. The method can greatly improve operation and maintenance efficiency.