To address the problems of network congestion, Active queue management (AQM) is advocated to improve the quality of services (QoS) for Internet. Random early detective (RED) algorithm is one of notably AQM mechanism, because it could reduce the high drop rate of bursty flows, avoid global synchronization among flows and reduces network latency (“ping time”). However, RED requires careful tuning of its parameters in order to provide good performance. For solving this problem, this paper proposes a new mechanism to improve RED algorithm, which is named BO-ARED (An Adaptive RED Algorithm Combined With Buffer Occupation). By matching router's buffer occupation with wq, minth, maxth and Pmax parameter settings, to make BO-ARED adapt to network environment variation automatically. The simulations take comparisons of the BO-ARED with RED, ARED and BORED. It is shown in the simulation results that BO-ARED algorithm maintains the great performance while network environment varies. It has low drop rate, low average delay time and high throughput with it adaptive parameters.
[1]
Sally Floyd,et al.
Adaptive RED: An Algorithm for Increasing the Robustness of RED's Active Queue Management
,
2001
.
[2]
Hong Chen,et al.
An algorithm of enhancing RED fairness
,
2008,
2008 7th World Congress on Intelligent Control and Automation.
[3]
Hans-Peter Schwefel,et al.
Transient analysis of RED queues: A quantitative analysis of buffer-occupancy fluctuations and relevant time-scales
,
2006,
Perform. Evaluation.
[4]
QUTdN QeO,et al.
Random early detection gateways for congestion avoidance
,
1993,
TNET.
[5]
Xiaobo Zhou,et al.
Packet Scheduling with Buffer Management for Fair Bandwidth Sharing and Delay Differentiation
,
2007,
2007 16th International Conference on Computer Communications and Networks.
[6]
Mohammed Atiquzzaman,et al.
A framework to determine bounds of maximum loss rate parameter of RED queue for next generation routers
,
2008,
J. Netw. Comput. Appl..