Service Fault Location Algorithm based on Network Characteristics under 5G Network Slicing

摘要

In order to solve the problem of long diagnosis time for fault diagnosis algorithms in large-scale environments, this paper proposes a service fault location algorithm based on network characteristics. First, based on the virtual network mapping data, the service is associated with the underlying resources to build a Bayesian fault location model. Second, by analyzing the network topology and the running status of each service, the probability of network node failure is calculated based on the multi-attribute characteristics. Finally, the fault location is achieved by calculating the set of suspected faults with the strongest ability to explain abnormal symptoms. The experimental part compares the algorithm of this paper with the classical algorithm, and verifies that the algorithm of this paper improves the accuracy of fault diagnosis and reduces the time cost of fault diagnosis.