基于组合模型的网络业务流多重分形建模

Network Traffic Multi-fractal Modeling Based on Combination Model

研究表明网络业务流具有长相关、短相关特性以及小尺度上的多重分形特性的特点。将可以描述网络业务流波动情况的GARCH模型和可以描述网络业务流长相关特性和短相关特性的FARIMA模型引入网络业务流的多重分形建模中。提出了一种FARIMA/GARCH组合模型。数值仿真对比结果表明提出的FARIMA/GARCH组合模型对网络业务流多重分形谱描述更为准确,实现了对网络业务流多重分形特性的有效建模。

Recent research has discovered that network traffic model has the property of long-range dependence,short-range dependence and multi-fractal.It is known that GARCH model could analyze the volatility of time series,and FARIMA model could describe the long range dependent and short range dependent of time series.So a FARIMA / GARCH combination model is developed to the modeling of network traffic.Numerical results prove that the combination model could effectively describe the multi-fractal nature of network traffic comparing with other models.