In this paper, we present a dynamic congestion management mechanism called DWRED (Dynamic Weighted RED) that enhances the well-known congestion avoidance Random Early Detection (RED) algorithm, by providing service for multiple classes of traffic as well as dynamic parameters modifications using the communicating agents concepts of MultiAgents Systems. We also propose a simple DWRED prototype i...

We consider the adaptation of random early detection (RED) as an active queue management algorithm for multimedia traffic in wireless networks. We studied features of RED, multimedia data and point out a weakness in both. We show that an appropriate RED algorithm can improve multimedia data performance.

This paper introduces a technique for applying packet arrival rate based queue management to class based scheduling algorithms. This enables a DiffServ architecture with very low packet latency, loss, and high link utilisation. Simulation results demonstrate that the proposed technique outperforms the current weighted random early drop (WRED) and weighted fair queue (WFQ) architecture.

TCP Vegas version is expected to achieve higher throughput than TCP Tahoe and Reno versions, which are currently used in the Internet. However, we need to consider a migration path of TCP Vegas when it is deployed in the Internet. In this paper, we focus on the situation where multiple TCP Reno and Vegas connections coexist at the bottleneck router, by which the fairness property is investigate...

あらまし 近年、エンド–エンド間で動作する TCPの輻輳制御機構を補助し、ルータにおいて積極的に輻輳制御を行 う、アクティブキュー管理機構が注目を浴びている。アクティブキュー管理機構には制御パラメータが存在するが、そ の有効性はこれらの制御パラメータの設定に依存する。そのため、アクティブキュー管理機構の制御パラメータ設定 方法に関しては、これまでさまざまな研究が行われてきた。しかし、そのほとんどは、少数のシミュレーション結果か ら、制御パラメータがアクティブキュー管理機構の性能に与える影響を調べているにすぎない。そこで本稿では、多 変量解析手法を用いることにより、膨大な数のシミュレーション結果を統計的に解析し、アクティブキュー管理機構の 制御パラメータが、その性能にどのような影響を与えるかを定量的に明らかにする。本稿では、代表的なアクティブ キュー管理機構である RED (Rando...

We use a discrete-time dynamical feedback system model of TCP/RED to study the performance of Random Early Detection RED for different values of control parameters. Our analysis shows that the queue length is able to keep stable at a given target if the maximum probability pmax and exponential averaging weight w satisfy some conditions. From the mathematical analysis, a new self-tuning RED is p...

The Active Queue Management algorithms stabilize the instantaneous queue length through mapping the congestion measurement into packet drop probability to achieve high throughput and low average delay. Random Early Detection [RED] is widely used AQM mechanism detecting and avoiding the incipient congestion. The detection of congestion is based on priori estimation of congestion and calculation ...

We investigate the effect of TCP Explicit Congestion Notification (ECN) with a new response strategy that is more aggressive in the short term, but preserves TCP long term behavior, without modifying the router marking rate. A less aggressive ECN decrease gives more incentives for end systems to become ECN-compliant, as ECN serves as an early warning sign in this case. Our analysis and simulati...

Random Early Detection (RED) has been introduced as a congestion avoidance algorithm for the Internet. RED detects congestion by estimating the average queue size. It drops packets probabilistically before buuer overrow, with the drop probability depending on the average queue size. In this paper, we analyse the innuence of RED on the packet loss ratio and the throughput of a system consisting ...

Several gateway-based congestion control mechanism have been proposed to support an end-to-end congestion control mechanism of TCP (Transmission Control Protocol). One of promising gateway-based congestion control mechanisms is a RED (Random Early Detection) gateway. Although a number of researches on the steady state performance of the RED gateway have been performed, the transient behavior of...