On control parameters tuning for active queue management mechanisms using multivariate analysis

In recent years, AQM (Active Queue Management) mechanisms, which support the end-to-end congestion control mechanism of TCP by performing congestion control at a router have been actively studied by many researchers. AQM mechanisms usually have several control parameters, and their effectiveness depend on a setting of those control parameters. Therefore, issues on parameter tuning of several AQM mechanisms have been extensively studied using simulation experiments. However in most of those studies, only a small number of simulation experiments are performed for investigating the effect of control parameters on the performance of AQM mechanisms. In this paper, we therefore statistically analyze a large number of simulation experiments using multivariate analysis, and quantitatively show how the performance of AQM mechanisms is affected by a setting of control parameters. In particular we analyze the performance of three AQM mechanisms: GRED (Gentle RED), DRED (Dynamic-RED), and SRED (Stabilized RED), all of which are variants of RED (Random Early Detection). Through several numerical examples, we clarify how control parameters of GRED, DRED, and SRED have impact on their steady state performance measures such as the average queue length and the packet loss probability. We present a few guidelines for configuring control parameters of those AQM mechanisms.