Random early detection with flow number estimation and queue length feedback control

In order to achieve high throughput and low average delay in computer network, it is necessary to stabilize the queue length and avoid oscillation or chaos phenomenon. In this paper, based on Adaptive Random Early Detection (ARED), an improved algorithm is proposed, which dynamically changes the range of maximum drop probabilitypmaxaccording to different network scenarios and adjustspmaxto limit average queue sizeqavein a steady range. Moreover, exponential averaging weightwis adjusted based on linear stability condition to stabilizeqave. A number of simulations show that the improved ARED algorithm can effectively stabilize the queue length and perform better than other algorithms in terms of stability and chaos control.

Download Full-text

Modeling discrete-time analytical models based on random early detection: Exponential and linear

International Journal of Modeling Simulation and Scientific Computing ◽

10.1142/s1793962315500282 ◽

2015 ◽

Vol 06 (03) ◽

pp. 1550028 ◽

Cited By ~ 2

Author(s):

Hussein Abdel-Jaber ◽

Fadi Thabtah ◽

Mike Woodward

Keyword(s):

Early Detection ◽

Discrete Time ◽

Queue Length ◽

Computer Network ◽

Arrival Rate ◽

Analytical Models ◽

Random Early Detection ◽

Queueing Delay ◽

Threshold Position ◽

Mean Queue Length

Congestion control is among primary topics in computer network in which random early detection (RED) method is one of its common techniques. Nevertheless, RED suffers from drawbacks in particular when its "average queue length" is set below the buffer's "minimum threshold" position which makes the router buffer quickly overflow. To deal with this issue, this paper proposes two discrete-time queue analytical models that aim to utilize an instant queue length parameter as a congestion measure. This assigns mean queue length (mql) and average queueing delay smaller values than those for RED and eventually reduces buffers overflow. A comparison between RED and the proposed analytical models was conducted to identify the model that offers better performance. The proposed models outperform the classic RED in regards to mql and average queueing delay measures when congestion exists. This work also compares one of the proposed models (RED-Linear) with another analytical model named threshold-based linear reduction of arrival rate (TLRAR). The results of the mql, average queueing delay and the probability of packet loss for TLRAR are deteriorated when heavy congestion occurs, whereas, the results of our RED-Linear were not impacted and this shows superiority of our model.

Download Full-text

Self-Tuning Random Early Detection Algorithm to Improve Performance of Network Transmission

Mathematical Problems in Engineering ◽

10.1155/2011/872347 ◽

2011 ◽

Vol 2011 ◽

pp. 1-17 ◽

Cited By ~ 6

Author(s):

Jianyong Chen ◽

Cunying Hu ◽

Zhen Ji

Keyword(s):

Early Detection ◽

Queue Length ◽

Feedback System ◽

Detection Algorithm ◽

Random Early Detection ◽

Maximum Probability ◽

History Information ◽

Self Tuning ◽

Fluctuation Amplitude ◽

Network Transmission

We use a discrete-time dynamical feedback system model of TCP/RED to study the performance of Random Early Detection (RED) for different values of control parameters. Our analysis shows that the queue length is able to keep stable at a given target if the maximum probabilitypmax⁡and exponential averaging weightwsatisfy some conditions. From the mathematical analysis, a new self-tuning RED is proposed to improve the performance of TCP-RED network. The appropriatepmax⁡is dynamically obtained according to history information of bothpmax⁡and the average queue size in a period of time. Andwis properly chosen according to a linear stability condition of the average queue length. From simulations withns-2, it is found that the self-tuning RED is more robust to stabilize queue length in terms of less deviation from the target and smaller fluctuation amplitude, compared to adaptive RED, Random Early Marking (REM), and Proportional-Integral (PI) controller.

Download Full-text

IGRED: An Improved Gentle Random Early Detection Method for Management of Congested Networks

Journal of Interconnection Networks ◽

10.1142/s021926591950004x ◽

2019 ◽

Vol 19 (02) ◽

pp. 1950004

Author(s):

HUSSEIN ABDEL-JABER ◽

ABDULAZIZ SHEHAB ◽

MOHAMED BARAKAT ◽

MAGDI RASHAD

Keyword(s):

Early Detection ◽

Queue Length ◽

Detection Method ◽

Random Early Detection ◽

Queuing Delay ◽

Packet Dropping ◽

Dropping Probability ◽

Maximum Value ◽

Congested Networks ◽

Mean Queue Length

Controlling congested router buffers of a network has a crucial role in improving network’s performance. This paper proposes a novel Active Queue Management (AQM) method named Improved Gentle Random Early Detection (IGRED) that based on GRED algorithm, which counted as one of the popular AQM methods. The proposed is mainly developed to overcome the problems faced with classic GRED. The initial packet-dropping probability depends on several parameters such as the average queue length, maximum value of packet dropping probability, minimum and maximum thresholds, etc. IGRED reduces its reliance on the GRED’s parameters through shrinking these parameters. The results shows, when congestion is taken place, the proposed IGRED provides more satisfactory performance with reference to mean queue length, average queuing delay, and overflow packet loss probability.

Download Full-text