Abstract:
This paper investigates the effect of queue averaging on REDes ability to avoid a bias against bursty traJfic, to minimize queue size oscillation, and to optimize the distribution of packet drops over time in order to avoid global synchronization. We find that a small degree of averaging is best to optimize the performance metrics mentioned above and adapt an existing model how to set RED's queue weight parameter.
Citations
|
1681
|
Random Early Detection Gateways for Congestion Avoidance
– Floyd, Jacobson
- 1993
|
|
241
|
Connections with multiple congested gateways in packetswitched networks part 1: one-way traffic
– Floyd
- 1991
|
|
144
|
Congestion Avoidance in Computer Networks with A Connectionless Network Layer: Part IV: A Selective Binary Feedback Scheme for General Topologies
– Ramakrishnan, Jain, et al.
- 1987
|
|
120
|
A Study of active Queue Management for Congestion Control
– Firoiu, Borden
|
|
105
|
Adaptive red: An algorithm for increasing the robustness of RED
– Floyd, Gummadi, et al.
- 2001
|
|
29
|
Generating representative workloads for network and server performance evaluation
– Barford, Crovella
- 1998
|
|
14
|
et al., "Recommendations on Queue
– Braden
- 1998
|
|
8
|
Comparison of tail drop and active queue management performance for bulk-data and web-like internet traffic
– Brandauer, Iannaccone, et al.
- 2001
|
|
8
|
Red in a different light
– Jacobson, Nichols, et al.
- 1999
|
|
7
|
Discussions on setting RED parameters
– Floyd
- 1997
|
|
2
|
et al., "A Control Theoretic Analysis of RED
– Hollot
- 2001
|
|
2
|
A quantitative model of RED with TCP traffic
– Ziegler, Brandauer, et al.
- 2001
|
|
1
|
Effect of Memory on the Stability and Variability of RED Queues
– Misra, Ott
|
