通信学报 ›› 2020, Vol. 41 ›› Issue (8): 110-119.doi: 10.11959/j.issn.1000-436x.2020165

• 学术论文 • 上一篇    下一篇

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   

  1. 南京邮电大学江苏省无线通信重点实验室,江苏 南京 210003
  • 修回日期:2020-04-13 出版日期:2020-08-25 发布日期:2020-09-05
  • 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
  • 基金资助:
    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)

Fault detection and diagnosis method for heterogeneous wireless network based on GAN

Xiaorong ZHU,Peipei ZHANG   

  1. Jiangsu Key Laboratory of Wireless Communications,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
  • Revised:2020-04-13 Online:2020-08-25 Published:2020-09-05
  • Supported by:
    The National Natural Science Foundation of China(61871237);Program to Cultivate Middle-aged and Young Science Leaders of Universities of Jiangsu Province and Key Research and Development Plan of Jiangsu Province(BE2019017)

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%。

关键词: 异构无线网络, 生成对抗网络, 极端梯度提升, 故障检测, 故障诊断

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%.

Key words: heterogeneous wireless network, GAN, XGBoost, fault detection, fault diagnosis

中图分类号: 

No Suggested Reading articles found!