Proceedings Article10.1109/ISCC.2004.1358630
Design a robust controller for active queue management in large delay networks
Fengyuan Ren,Chuang Lin,Bo Wei +2 more
- 28 Jun 2004
- Vol. 2, pp 748-754
38
TL;DR: The novel algorithm restrains the negative effect on queue stability caused by large delay and the integrated performance of the proposed algorithm is obviously superior to that of several well-known schemes when the connections have large delay.
read more
Abstract: AQM (active queue management) can maintain the smaller queuing delay and higher throughput by the purposefully dropping the packets at the intermediate nodes. Almost all the existed schemes for AQM neglect the impact of large delay on performance. In this study, we firstly verify a fact through simulation experiments, which is the queues controlled by the several popular AQM schemes, including RED, PI controller and REM, appear the dramatic oscillations in large delay networks, which decreases the utilization of the bottleneck link and introduces the avoidable delay jitter. After some appropriate model approximation, we design a robust AQM controller to compensate the delay using the principle of internal mode compensation in control theory. The novel algorithm restrains the negative effect on queue stability caused by large delay. The simulation results show that the integrated performance of the proposed algorithm is obviously superior to that of several well-known schemes when the connections have large delay, at the same time, the buffers keep at small queue length.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Active Queue Management: A Survey
TL;DR: This survey attempts to travel the trajectory of AQM research from 1993 with the first algorithm, Random Early Detection (RED), to current work in 2011, and discusses the general attributes of AQm schemes, and the design approaches taken such as heuristic, control-theoretic and deterministic optimization.
299
Optimal Control for Bufferbloat Queue Management Using Indirect Method with Parametric Optimization
TL;DR: This article designs a forward-backward optimal control queue algorithm based on an indirect approach with parametric optimization that has advantages of scalability and accuracy compared to direct approaches, while still maintaining good throughput and shorter queue length than several existing queue management algorithms.
Cascade Probability Control to Mitigate Bufferbloat under Multiple Real-World TCP Stacks
TL;DR: In this paper, a cascade probability control scheme using margin optimal method was proposed to address the problem of bufferbloat in TCP stacks and guarantee the measured round trip time tracking to a low value of delay.
•Journal Article
A Fairness Investigation on Active Queue Management Schemes in Wireless Local Area Network
TL;DR: This paper provides an experimental evaluation of different AQM schemes in WLAN environment with presence of two different types of flows (TCP flows and UDP flows) to study the behavior of these AQm schemes which might punish some flows unfairly.
1
Queue Management using Optimal Margin method to Improve Bottleneck Link Per formance
TL;DR: A novel framework which exploits two-loop control method, e.g. queue-length and congestion window size, combined with optimal margin method to facilitate parameter choices is proposed.
References
Random early detection gateways for congestion avoidance
Sally Floyd,Van Jacobson +1 more
TL;DR: Red gateways are designed to accompany a transport-layer congestion control protocol such as TCP and have no bias against bursty traffic and avoids the global synchronization of many connections decreasing their window at the same time.
Rate control for communication networks: shadow prices, proportional fairness and stability
TL;DR: This paper analyses the stability and fairness of two classes of rate control algorithm for communication networks, which provide natural generalisations to large-scale networks of simple additive increase/multiplicative decrease schemes, and are shown to be stable about a system optimum characterised by a proportional fairness criterion.
5.8K
TCP Vegas: end to end congestion avoidance on a global Internet
TL;DR: The three key techniques employed by Vegas are described, and the results of a comprehensive experimental performance study, using both simulations and measurements on the Internet, of the Vegas and Reno implementations of TCP are presented.
Internal model control: PID controller design
TL;DR: For a large number of single input-single output (SISO) models typically used in the process industries, the Internal Model Control design procedure is shown to lead to PID controllers, occaslonally augmented with a first-order lag.
Related Papers (5)
Ren Fengyuan,Lin Chuang,Ren Yong,Shan Xiu-Ming +3 more
- 01 Jan 2003
Jinsheng Sun,Moshe Zukerman,Marimuthu Palaniswami +2 more
- 24 Jun 2007