一种基于趋势分析的网络性能异常检测方法

A Network Performance Anomaly Detection Method Based on Trend Analysis

计算机网络的规模越来越大,结构越来越复杂,网络负担过重,导致网络性能下降,网络性能监控备受关注。提出一种基于趋势分析的网络性能异常检测方法,通过建立历史RTT性能数据的正常模型,根据模型得到的随机变化分量采用滑动窗口平均的方法用实测RTT数据进行性能异常检测。OPNET仿真实验和实际数据监测表明,方法具有高检测率和较低的误警率。

[Abstract ] With the increasing scale and complexity of computer network, the more and more heavier network burden and the descending of network performance, network performance detection are playing an increasingly important role. A network performance anomaly detection method based on trend analysis is put forward. Firstly, the process sets up normal model based on the RTI＂ historical data, and then uses slipping windows to detect random variety data got from actual measurement data based on normal model. Using the network simulation tool OPNET the process is evaluated and the result indicates that the method has high accuracy detection rate and low false alarm rate.