A short note on the effect of randomization for active queue management congestion avoidance

Authors:
Thomas Ziegler;Erich Plasser
Affiliations:
Telecommunications Research Center Vienna (ftw.), Donaucitystr. 1, 1220 Vienna, Austria;Telecommunications Research Center Vienna (ftw.), Donaucitystr. 1, 1220 Vienna, Austria
Venue:
ICCC '02 Proceedings of the 15th international conference on Computer communication
Year:
2002

Citing 5
Cited 0

Connections with multiple congested gateways in packet-switched networks part 1: one-way traffic

ACM SIGCOMM Computer Communication Review
Random early detection gateways for congestion avoidance

IEEE/ACM Transactions on Networking (TON)
Generating representative Web workloads for network and server performance evaluation

SIGMETRICS '98/PERFORMANCE '98 Proceedings of the 1998 ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems
On Averaging for Active Queue Management Congestion Avoidance

ISCC '02 Proceedings of the Seventh International Symposium on Computers and Communications (ISCC'02)
Comparison of Tail Drop and Active Queue Management Performance for Bulk-Data and Web-Like Internet Traffic

ISCC '01 Proceedings of the Sixth IEEE Symposium on Computers and Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper investigates the effect of randomization on RED's ability to avoid a bias against bursty traffic, to minimize queue size oscillation, and to optimize the distribution of packet drops over time in order to avoid global synchronization. We find that random dropping does not improve performance compared to deterministic packet dropping but causes some overhead. This finding results in a recommendation for deterministic packet dropping in active queue management.