A Study of Measurement-Based Traffic Models for Network Diagnostics

In this paper, the measurement and analysis of network flows are taken into account as a methodology for characterization and diagnosis of network behavior. The accuracy of flow models will be discussed, reviewing the basic underlying assumptions. A modeling approach based on multidomain analysis will be proposed, where flow measurements can be complemented by a limited amount of protocol data gathered from packet headers. By the analysis of experimental data, we argue that, in several situations, traffic may be more appropriately modeled by the superposition of multiple flows with different characteristics, which results in better measurements and improved diagnostic possibilities.