流量模型是流量预测和网络性能评价的核心基础。好的流量模型必须能够准确描述网络实际流量的特征情况,才能准确预测流量状况。随着网络业务类型不断增加,实际网络中业务流特性越来越复杂,表现为长相关性和自相似性等。本文重点分析了当前广泛使用的几种自相似模型,对自相似业务的分析和处理具有一定的指导意义。 Traffic model is the core of traffic forecasting and network performance evaluation. Good traffic model must be able to accurately describe the characteristics of the actual network traffic conditions, in order to accurately predict traffic conditions. As the types of network services continue to increase, the characteristics of service flows in an actual network become more and more complex, showing long-term correlation and self-similarity. This article focuses on the analysis of several self-similar models widely used at present, which is of guiding significance for the analysis and processing of self-similar services.