A fault diagnosis method for carrier network based on dynamic Bayesian network

Abstract

The invention discloses a carrier network fault diagnosis method based on a dynamic Bayesian network, and relates to the technical field of carrier network management. The method includes constructing a fault propagation model according to the relationship between faults and symptoms; constructing a dynamic Bayesian fault propagation model according to a set of abnormal symptom nodes and a set of abnormal fault nodes, and according to the dynamic Bayesian fault propagation model, two The fault diagnosis model on two time slices; according to the fault diagnosis model on two time slices, the maximum possible fault node state set in the previous stage is obtained; according to the maximum possible fault node state set in the previous stage, the maximum possible fault node state set in the current stage is obtained collection of states. The present invention models the fault diagnosis problem under the dynamic network environment as a dynamic Bayesian fault diagnosis model, and proposes a carrier network fault diagnosis method based on the dynamic Bayesian network, which can effectively reduce the impact of the dynamic network environment on the fault diagnosis model. Noise problem.

Description

technical field [0001] The invention relates to the technical field of carrier network management, in particular to a carrier network fault diagnosis method based on a dynamic Bayesian network. Background technique [0002] In the field of smart grid, in order to meet the needs of more and more IoT devices for the network, the carrier network has gradually become the basic network resource that power companies focus on building. In order to further improve the utilization rate of carrier network resources, network slicing technology is applied to the construction of carrier networks. Under the technology of network slicing, the traditional carrier network is divided into basic network and virtual network. Basic network resources include underlying nodes and underlying link resources, which are responsible for providing basic resources for virtual networks. Virtual network resources include virtual nodes and virtual link resources, which are responsible for providing users ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a carrier network fault diagnosis method based on a dynamic Bayesian network to solve the problem of low performance of the fault diagnosis algorithm caused by inaccurate fault diagnosis models in the carrier network environment

Images