Fault prediction method and device for 5G slices and computing equipment

Abstract

The invention discloses a 5G slice fault prediction method and device and computing equipment, and the method comprises the steps: collecting to-be-predicted network slice data, and dividing a slice physical connection graph and a slice resource logic relation graph; converting the slice physical connection graph into a first adjacency matrix and a first feature matrix, and converting the slice resource logic relation graph into a second adjacency matrix and a second feature matrix; inputting the first adjacency matrix, the first feature matrix, the second adjacency matrix and the second feature matrix into a space-time multi-graph convolutional network model, and predicting fault information of the historical network slice data. Through the above mode, potential faults of 5G slices can be predicted by using the space-time multi-graph convolutional network model, and the space-time relationship of the slice topology network is considered, so that the faults can be found automatically and accurately.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a fault prediction method, device and computing equipment for 5G slices. Background technique [0002] Network slice (Network Slice) is a collection of end-to-end logical functions and the required physical or virtual resources, including access network, transmission network, core network, etc. Network slice can be regarded as a virtualized "private network" in 5G network ; Network slicing is based on the unified infrastructure of NFV to achieve low-cost and efficient operation. Network slicing technology can achieve logical isolation of communication networks, allowing network elements and functions to be configured and reused in each network slice to meet specific industry application requirements. At the same time, network slicing may also have various failures. [0003] However, in the existing technology, slice potential failure prediction is mainly realized...

AI Technical Summary

Problems solved by technology

[0003] However, in the existing technology, slice potential failure prediction is mainly realized by setting thresholds for each KPI in the slice network through expert experience, the prediction accuracy is low, and the spatio-temporal relationship of the slice topology network is not considered, and the slice network There are many nodes, there are various dependencies between nodes, the temporal and spatial correlation of slices is complicated, and the automatic prediction is difficult. At present, there is no good slice fault prediction method

Images