Stability analysis of a novel exponential-RED model with heterogeneous delays
Computer Communications
A fuzzy logic-based AQM for real-time traffic over internet
Computer Networks: The International Journal of Computer and Telecommunications Networking
Reduction of queue oscillation in the next generation Internet routers
Computer Communications
| Hi-index | 0.00 |
In recent years, AQM (Active Queue Management)mechanisms, which support the end-to-end congestion controlmechanism ofTCP by performing congestion control ata router, have been actively studied by many researchers.AQM mechanisms usually have several control parameters,and their effectiveness depend on a setting of those controlparameters. Therefore, issues on parameter tuning of severalAQM mechanisms have been extensively studied usingsimulation experiments. However, in most of those studies,only a small number of simulation experiments are performedfor investigating the effect of control parameters onthe performance of AQM mechanisms. In this paper, wetherefore statistically analyze a large number of simulationexperiments using multivariate analysis, and quantitativelyshow how the performance of AQM mechanisms is affectedby a setting of control parameters. In particular, we analyzethe performance of three AQM mechanisms: GRED(Gentle RED), DRED (Dynamic-RED), and SRED (StabilizedRED), all of which are varitmts of RED (Random EarlyDetection). Through several numerical examples, we clarifyhow control parameters of GRED, DRED, and SRED haveimpact on their steady state performance measures such asthe average queue length and the packet loss probability.We present a few guidelines for configuring control parametersof those AQM mechanisms.