Research on Cross-Layer Alarm Association in 5G Core Network
Dongyue Zhang, Sai Han, Zelin Wang, Jingwei Wang, Guangquan Wang, Jieyan Yang · 2023
It is difficult to find the root cause alarms by the traditional operation and maintenance methods quickly and accurately, due to the complex architecture of the 5G core network. At present, the library of cross-layer alarm association rules for the 5G core network is not complete. Therefore, the cross-layer alarm association rules mining algorithm of 5G core network is proposed in this paper, which is based on OPTICS algorithm and the weighted FP-growth algorithm. Initially, a time-correlated alarm transaction set is generated by OPTICS algorithm, and then a spatially correlated alarm transaction set is further extracted according to the three-layer topology. Finally, the weighted FP-growth algorithm is used to generate cross-layer alarm association rules. According to the experimental results, it suggests that the alarm transaction set is effectively compressed, and the accuracy of alarm rules mining is improved greatly by this algorithm.