| FAULT IDENTIFICATION IN HETEROGENEOUS NETWORKS USING TIME SERIES ANALYSIS |
| |
| 作者姓名： | 孙钦东 张德运 孙朝晖 |
| |
| 作者单位： | [1]InstituteofNetwork,Xi＇anJiaotongUniversity,Xi＇an710049,China [3]InstituteofNetwork,Xi＇anJiaotongUniversity,Xi＇an710049,China |
| |
| 基金项目： | ThisworkwassupportedbytheNationalComputerNetworkandInformationSecurityFoundationofChina(No.2001-1-0100) |
| |
| 摘 要： | Fault management is crucial to provide quality of service grantees for the future networks, and fault identification is an essential part of it. A novel fault identification algorithm is proposed in this paper, which focuses on the anomaly detection of network traffic. Since the fault identification has been achieved using statistical information in management information base, the algorithm is compatible with the existing simple network management protocol framework. The network traffic time series is verified to be non-stationary. By fitting the adaptive autoregressive model, the series is transformed into a multidimensional vector. The training samples and identifiers are acquired from the network simulation. A k-nearest neighbor classifier identifies the system faults after being trained. The experiment results are consistent with the given fault scenarios, Which prove the accuracy of the algorithm. The identification errors are discussed to illustrate that the novel fault identification algorithm is adaptive in the fault scenarios with network traffic change.
|
| 关 键 词： | 故障管理 故障识别 时间序列分析 自回归 网络管理 |
FAULT IDENTIFICATION IN HETEROGENEOUS NETWORKS USING TIME SERIES ANALYSIS |
| |
| Sun Qindong,Zhang Deyun,Sun Zhaohui Institute of Network,Xi'an Jiaotong University,Xi'an ,China..FAULT IDENTIFICATION IN HETEROGENEOUS NETWORKS USING TIME SERIES ANALYSIS[J].Academic Journal of Xi’an Jiaotong University,2004,16(2):101-105. |
| |
| Authors: | Sun Qindong Zhang Deyun Sun Zhaohui Institute of Network Xi'an Jiaotong University Xi'an China |
| |
| Institution: | Institute of Network, Xi'an Jiaotong University, Xi'an 710049, China. |
| |
| Abstract: | Fault management is crucial to pro vi de quality of service grantees for the future networks, and fault identification is an essential part of it. A novel fault identification algorithm is proposed in this paper, which focuses on the anomaly detection of network traffic. Since the fault identification has been achieved using statistical information in mana gement information base, the algorithm is compatible with the existing simple ne twork management protocol framework. The network traffic time series is verified to be non-stationary. By fitting the adaptive autoregressive model, the series is transformed into a multidimensional vector. The training samples and identif iers are acquired from the network simulation. A k-nearest neighbor classif ier identifies the system faults after being trained. The experiment results are consistent with the given fault scenarios, which prove the accuracy of the algo rithm. The identification errors are discussed to illustrate that the novel faul t identification algorithm is adaptive in the fault scenarios with network traff ic change. |
| |
| Keywords: | fault management fault identification time seri es analysis adaptive autoregressive |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
