基于GAN的异构无线网络故障检测与诊断算法

朱晓荣; 张佩佩

doi:10.11959/j.issn.1000-436x.2020165

您当前的位置：

首页 >

文章列表页 >

基于GAN的异构无线网络故障检测与诊断算法

学术论文 | 更新时间：2024-06-05

- 基于GAN的异构无线网络故障检测与诊断算法
- Fault detection and diagnosis method for heterogeneous wireless network based on GAN
- 通信学报 2020年41卷第8期页码：110-119
- 作者机构：
  
  南京邮电大学江苏省无线通信重点实验室，江苏南京 210003
- 作者简介：
  
  [ "朱晓荣（1977- ），女，山东临沂人，博士，南京邮电大学教授、博士生导师，主要研究方向为5G通信系统、异构网络、物联网等关键技术及系统研发" ]
  [ "张佩佩（1995- ），女，山东菏泽人，南京邮电大学硕士生，主要研究方向为 4G/5G网络故障诊断、网络故障预测等" ]
- 基金信息：
  
  国家自然科学基金资助项目(61871237);江苏省高校“青蓝工程”和江苏省重点研发计划基金资助项目(BE2019017)
- DOI：10.11959/j.issn.1000-436x.2020165
  中图分类号： TN915.81
- 网络出版日期：2020-08，
  
  纸质出版日期：2020-08-25
- 稿件说明：
移动端阅览
朱晓荣, 张佩佩. 基于GAN的异构无线网络故障检测与诊断算法[J]. 通信学报, 2020,41(8):110-119.

Xiaorong ZHU, Peipei ZHANG. Fault detection and diagnosis method for heterogeneous wireless network based on GAN[J]. Journal on communications, 2020, 41(8): 110-119.
朱晓荣, 张佩佩. 基于GAN的异构无线网络故障检测与诊断算法[J]. 通信学报, 2020,41(8):110-119. DOI： 10.11959/j.issn.1000-436x.2020165.

Xiaorong ZHU, Peipei ZHANG. Fault detection and diagnosis method for heterogeneous wireless network based on GAN[J]. Journal on communications, 2020, 41(8): 110-119. DOI： 10.11959/j.issn.1000-436x.2020165.

摘要

针对异构无线网络故障检测与诊断过程中，如何基于小数据量样本进行准确的故障检测与诊断模型的训练的问题，提出了基于生成对抗网络的异构无线网络故障检测与诊断算法。首先，分析了异构无线网络环境下的常见网络故障来源，通过 GAN 算法，在小数据量的网络故障样本的基础上，得到大量可靠数据集。然后，基于这些数据，利用极端梯度提升算法选择故障检测阶段输入参数的最优特征组合，并完成故障检测与诊断。仿真结果表明，所提算法可以实现对异构无线网络更加准确而高效的故障检测与诊断，准确率可达98.18%。

Abstract

Aiming at the problem that in the process of network fault detection and diagnosis

how to train the precise fault diagnosis and detection model based on small data volume

a fault diagnosis and detection algorithm based on generative adversarial networks (GAN) for heterogeneous wireless networks was proposed.Firstly

the common network fault sources in heterogeneous wireless network environment was analyzed

and a large number of reliable data sets was obtained based on a small amount of network fault samples through GAN algorithm.Then

the extreme gradient boosting (XGBoost) algorithm was used to select the optimal feature combination of input parameters in the fault detection stage and completed fault diagnosis and detection based on these data.Simulation results show that the algorithm can achieve more accurate and efficient fault detection and diagnosis for heterogeneous wireless networks

with an accuracy of 98.18%.

关键词

Keywords

references

STEINDER M , SETHI A . A survey of fault localization techniques in computer networks [J ] . Science of Computer Programming , 2004 , 53 ( 2 ): 165 - 194 .

SZILAGYI P , NOVACZKI S . An automatic detection and diagnosis framework for mobile communication systems [J ] . IEEE Transactions on Network and Service Management , 2012 , 9 ( 2 ): 184 - 197 .

BARCO R , LAZARO P , DIEZ L , et al . Continuous versus discrete model in autodiagnosis systems for wireless networks [J ] . IEEE Transactions on Mobile Computing , 2008 , 7 ( 2 ): 673 - 681 .

KHANAFER R M , SOLANA B , TRIOLA J , et al . Automated diagnosis for UMTS networks using Bayesian network approach [J ] . IEEE Transactions on Vehicular Technology , 2008 , 57 ( 4 ): 2451 - 2461 .

BARCO R , WILLE V , DÍEZ V , et al . Learning of model parameters for fault diagnosis in wireless networks [J ] . Wireless Networks , 2010 , 16 ( 1 ): 255 - 271 .

KHATIB E J , BARCO R , ANDRADES A G , et al . Diagnosis based on genetic fuzzy algorithms for LTE self-healing [J ] . IEEE Transactions on Vehicular Technology , 2015 , 65 ( 3 ):1.

5G Alliance . Description of network slicing concept [R ] . NGMN ,(2016-01)[2020-01-14 ] .

ETSI . Network functions virtualisation (NFV); architectural framework:ETSI GS NFV 002 V1.2.1 [R ] .(2014-12)[2020-01-14 ] .

KUKLIŃSKI S , TOMASZEWSKI L . Key performance indicators for 5G network slicing [C ] // 2019 IEEE Conference on Network Softwarization . Piscataway:IEEE Press , 2019 : 464 - 471 .

MFULA H , NURMINEN J . Adaptive root cause analysis for self-healing in 5G networks [C ] // 2017 International Conference on High Performance Computing ＆ Simulation . Piscataway:IEEE Press , 2017 : 136 - 143 .

GOODFELLOW I J , POUGET-ABADIE J , MIRZA M ， et al . Generative adversarial nets [C ] // International Conference on Neural Information Processing Systems . Massachusetts:MIT Press , 2014 : 2672 - 2680 .

ARJOVSKY M , BOTTOU L . Towards principled methods for training generative adversarial networks [J ] . arXiv Preprint,arXiv:1701.04862 , 2017

LIU H , GU X , SAMARAS D . Wasserstein GAN with quadratic transport cost [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway:IEEE Press , 2019 : 4831 - 4840 .

WILLE V , BRIMER A , DAVIES G , et al . A simple and fast method for identification of missing adjacencies in WCDMA networks [C ] // IEEE International Conference on 3G ＆ Beyond . Piscataway:IEEE Press , 2005 : 132 - 139 .

BETTSTETTER C , FITZEK F , HARTENSTEIN H , et al . Special issue on self-organization in mobile networking [J ] . European Transactions on Telecommunications , 2005 , 16 ( 5 ): 371 - 373 .

GULRAJANI I , AHMED F , ARJOVSKY M , et al . Improved training of Wasserstein GANs [C ] // Advances in Neural Information Processing Systems . Massachusetts:MIT Press , 2017 : 5767 - 5777 .

CHEN T , GUESTRIN C . XGBoost:a scalable tree boosting system [C ] // ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York:ACM Press , 2016 : 785 - 794 .

FRIEDMAN J H . Greedy function approximation:a gradient boosting machine [J ] . Annals of Statistics , 2001 , 29 ( 5 ): 1189 - 1232 .

浏览量

1003

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于Nadam-TimeGAN和XGBoost的时序信号故障诊断方法

面向6G的跨模态信号重建技术

动态广义主成分分析及其在故障子空间建模中的应用

基于生成对抗网络的僵尸网络检测

基于DA优化模糊神经网络的异构无线网络接入选择算法