Controlling queue delay

  title={Controlling queue delay},
  author={Kathleen M. Nichols and Van Jacobson},
  journal={Communications of the ACM},
  pages={42 - 50}
A modern AQM is just one piece of the solution to bufferbloat. 

Passively measuring TCP round-trip times

A close look at round-trip time measurements with the Transmission Control Protocol.

SIR approach in modeling data packets forwarding at a leaky bucket

When network users are intensively interacting during rush hour, avoiding data loss and latency is a concern in guaranteeing segment reliability. Implementing a leaky bucket could be needed to achi...

Managing a Queue to a Soft Delay Target

This memo proposes to transplant the core idea of Curvy RED, the softened delay target, into AQMs that are better designed to deal with dynamics, such as PIE or PI2, but that suffer from the weakness

Performance of TCP with a Proportional Integral Enhanced (PIE) queue management policy

A fluid model for Compound TCP coupled with the PIE queue policy is studied and it is highlighted that it would be difficult to stabilize the system as the propagation delay, or the target queuing delay, gets large.

Trade-off queuing delay and link utilization for solving bufferbloat

  • Hao Wang
  • Computer Science
    ICT Express
  • 2020

An Adaptive AQM Algorithm Based on a Novel Information Compression Model

An innovative information compression model purely from routers’ perspective is proposed by evaluating the average effect an accepted/dropped packet has on the aggregated packet arriving rate, independent of round-trip time heterogeneity and specific endpoint protocols.

DFLOW: Low latency congestion control

  • P. O'HanlonK. Carlberg
  • Computer Science
    2013 21st IEEE International Conference on Network Protocols (ICNP)
  • 2013
An evaluation of the DFlow congestion control algorithm in a simulator shows that it can provide for self-fairness and low delay operation and it can maintain reasonable throughput against TCP Vegas and LEDBAT.

Some guidelines for queue management in high-speed networks

  • G. PatilG. Raina
  • Business
    2012 Third Asian Himalayas International Conference on Internet
  • 2012
In an intermediate buffer regime, nonlinear fluid models of TCP Reno with Drop-Tail show that the system loses stability as link capacity or the feedback delay increases, and offers some guidelines, for a threshold-based queue policy to ensure stability of the queues and low-latency in the network.

Managing fairness and application performance with active queue management in docsis-based cable networks

This work focuses on fairness and application performance capabilities of two recently proposed delay-based AQM algorithms, CoDel and PIE, in downstream DOCSIS 3.0 cable environments.

Non-Stationary Characteristics of AQM Based on the Queue Length

We performed a non-stationary analysis of a class of buffer management schemes for TCP/IP networks, in which the arriving packets were rejected randomly, with probability depending on the queue



Recommendations on Queue Management and Congestion Avoidance in the Internet

This memo presents a strong recommendation for testing, standardization, and widespread deployment of active queue management in routers, to improve the performance of today's Internet.


The conclusion is that while BLUE outperforms RED in scalability and low setup resource demand, but if not available, RED can be also hand-tuned to achieve similar or close results.

Adaptive buffer sizing for TCP flows in 802.11e WLANs

  • Tianji LiD. Leith
  • Business
    2008 Third International Conference on Communications and Networking in China
  • 2008
This work considers the provision of access point buffers in WLANs and proposes an adaptive sizing algorithms which is demonstrated to be able to maintain high throughput efficiency whilst achieving low delay.

Bufferbloat: Dark Buffers in the Internet

  • J. Gettys
  • Computer Science
    IEEE Internet Computing
  • 2011
We have conflated "speed" with "band width." As Stuart Chesire wrote in "It's the Latency, Stupid" (, "Making more bandwidth is easy. Once you

Congestion avoidance and control

In October of '86, the Internet had the first of what became a series of 'congestion collapses' during this period, the data throughput from LBL to UC Berkeley dropped from 32 Kbps to 40 bps.

The macroscopic behavior of the TCP congestion avoidance algorithm

A performance model for the TCP Congestion Avoidance algorithm that predicts the bandwidth of a sustained TCP connection subjected to light to moderate packet losses, such as loss caused by network congestion is analyzed.

Congestion control in IP/TCP internetworks

It is discovered that the Department of Defense's Internet Protocol (IP), a pure datagram protocol, and Transmission Control Protocol (TCP), a transport layer protocol, are subject to unusual congestion problems caused by interactions between the transport and datagram layers.

Netalyzr: illuminating the edge network

A detailed study of 130,000 measurement sessions that the service has recorded since it was made publicly available in June 2009 is presented, along with describing Netalyzr 's architecture and system implementation.

Characterizing residential broadband networks

This paper presents the first large-scale measurement study of major cable and DSL providers in North America and Europe, and characterizes several properties of broadband networks, including link capacities, packet round-trip times and jitter, packet loss rates, queue lengths, and queue drop policies.