Unlock instant, AI-driven research and patent intelligence for your innovation.

5G network anomaly detection method and system based on adaptive deep learning

A deep learning network and network anomaly technology, applied in the field of 5G network anomaly detection, can solve the problems of loss of detection accuracy, detection program is difficult to adapt to new requirements, etc.

Pending Publication Date: 2021-01-08
NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT +1
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The more advanced communication architecture functions and higher communication performance provided by 5G mobile communication technology bring new challenges to the existing network security defense system
New advanced features of 5G will make it difficult to adapt existing inspection procedures to new requirements
[0010] (4) End-to-end delay <1ms
[0011] These indicators make the network anomaly detection program an even greater challenge in 5G mobile networks. 5G users have a large number of user equipment, a large amount of data traffic generated by user equipment, and the reduction of connection delay. To meet the above key performance indicators, at the same time Without loss of detection accuracy, the 5G network anomaly detection system is facing new challenges

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • 5G network anomaly detection method and system based on adaptive deep learning
  • 5G network anomaly detection method and system based on adaptive deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0049] The present invention designs a 5G network anomaly detection method based on adaptive deep learning, which is used to realize traffic anomaly detection and corresponding optimization for the scenario where each terminal accesses the Internet through each radio access network (RAN); practical application Among them, the following steps A to D are specifically executed in real time.

[0050] Step A. For each radio access network (RAN) infrastructure that each terminal accesses, detect the network traffic summary in the radio access network (RAN) infrastructure, and apply the preset first deep learning network to analyze it Whether there is abnormal traffic, if yes, build a symptom package for abnormal traffic, combined with time stamp and abnormal type; otherwise, do not do anything; after completing the above opera...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a 5G network anomaly detection method and system based on adaptive deep learning, which are used for carrying out substantive expansion on the existing network anomaly detection scheme, constructing a two-stage hierarchical detection technology by applying a deep learning identification technology, and by virtue of anomaly symptom detection modules respectively arranged inradio access network infrastructures, under the condition that the 5G network rate is met, detecting the network flow, discovering abnormal flow, and constructing a symptom packet; and uploading thesymptom packet to a network anomaly detection module, performing symptom analysis and diagnosis on the symptom packet by the network anomaly detection module, obtaining operation actions of a diagnosis result through a series of measures, and optimizing resources and functions of a corresponding radio access network, so that the system has a self-adaptive capability of managing flow fluctuation. According to the invention, allocation and deployment of more computing resources can be realized when necessary, abnormal flow detection of the 5G network can be efficiently realized, and safe work ina 5G network environment is ensured.

Description

technical field [0001] The invention relates to a 5G network anomaly detection method and system based on adaptive deep learning, and belongs to the technical field of network security. Background technique [0002] The more advanced communication architecture functions and higher communication performance provided by 5G mobile communication technology bring new challenges to the existing network security defense system. As the country pays more and more attention to network security, the network security of communication infrastructure has developed rapidly in the past few years, and innovative network security defense methods have been widely used. With the emergence of 5G new technology, new problems However, it seems unclear whether existing intrusion detection and prevention procedures can effectively protect 5G network security, and whether these existing defense technologies can be adjusted accordingly with the application of 5G new technologies to meet the requiremen...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04L29/06H04W12/12G06N3/04G06N3/08G06N20/10
CPCH04L63/1425H04L63/20H04W12/12G06N3/084G06N3/088G06N20/10G06N3/045
Inventor 包秀国刘中金何跃鹰邹学强黄亮叶青李明柱吴涛郭涛
Owner NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT