Network fault diagnosis method based on deep learning in virtual network environment

Abstract

The invention discloses a network fault diagnosis method based on deep learning in a network virtualization environment. The network fault diagnosis method comprises the steps of: dividing a network into a physical network and a virtual network, combining the characteristics of occurrence of network faults, considering the time influencing factor, network topological connection characteristics and a mapping relation between the virtual network and the physical network, and comprehensively evaluating the network faults by means of a fault severity grading probability; regarding network characteristic parameters with influence degrees as a model learning resource, paying attention to the correspondence between variation trend of network historical data and fault tags, establishing a network fault diagnosis model with multiple fault grading probabilities in the network virtualization environment based on a viewing angle of deep learning, and training network parameters by using the network fault diagnosis model; and adjusting a fault prediction model in the training process, and utilizing an optimized and adjusted deep learning network to realize fault diagnosis in the network virtualization environment. The network fault diagnosis method can carry out deep analysis on the network parameters in the network virtualization environment, therefore the network fault diagnosis method has higher precision in predicting the network faults.

Description

technical field [0001] The invention relates to a network fault diagnosis method based on deep learning in a virtual network environment, and belongs to the field of network fault diagnosis. Background technique [0002] Network virtualization is an important method to solve network rigidity. The main work of network virtualization is to realize the fine segmentation of traditional networks through reasonable abstraction, allocation and isolation of underlying physical infrastructure resources. Compared with traditional networks, the security, flexibility and manageability of networks and energy efficiency are more promising. Network virtualization divides a traditional network into a Substrate Network (SN for short) and a Virtual Network (VN for short). The underlying network is maintained and operated by Infrastructure Providers (InPs for short), and the virtual network is operated by Service Providers (SPs for short). InPs provide SPs with underlying network resources ...

AI Technical Summary

Problems solved by technology

[0003] With the continuous generation of various SPs, more and more applications and network services run on the virtual network, and the new mapping mechanism also makes the resource utilization of the virtual network higher and higher, which makes the virtual network on the underlying network The mapping is more complicated; the underlying network virtualization and dynamic virtual network make it easier for the underlying network resources corresponding to various virtual networks to interfere with each other; the underlying network is transparent to the upper virtual network, and virtual network operators cannot obtain the underlying infrastructure Fault data and mapping information for

The complexity of resource relationships and the mutual influence between resources in the network virtualization environment lead to the fact that once a fault occurs somewhere in the virtual network or the underlying network, the fault will be rebroadcast and spread, which may eventually lead to the paralysis of the entire network

Images