An Improved Random Early Detection Algorithm Based on Flow Prediction

Author

Enhai, Liu ; Yan, Liu ; Ruimin, Pan

Author_Institution

Sch. of Comput. Sci. & Eng., Hebei Univ. of Technol., Tianjin, China

fYear

2009

fDate

1-3 Nov. 2009

Firstpage

425

Lastpage

428

Abstract

Random early detection (RED) is a network congestion control algorithm which calculates the packet-loss ratio according to current length of average queue. This paper describes an improved RED algorithm: Firstly, predicts network flows with RBF neural network in order to forecast queue length much earlier, and then, fits the packet-loss-ratio of RED algorithm according to some special points using curve fitting method, therefore, controls nonlinear network congestion. From our simulation, it can be concluded that the algorithm avoids congestion more efficiently.

Keywords

computer network management; computer networks; neural nets; prediction theory; queueing theory; telecommunication computing; telecommunication congestion control; RBF neural network; average queue length; flow prediction; network congestion control algorithm; nonlinear network congestion; packet loss ratio; queue length forecasting; random early detection; Artificial neural networks; Computer science; Control systems; Curve fitting; Detection algorithms; Equations; Intelligent networks; Intelligent systems; Neural networks; Prediction algorithms; Active Queue Management; RBFNN; curve fitting; random early detection (RED);

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Networks and Intelligent Systems, 2009. ICINIS '09. Second International Conference on

Conference_Location

Tianjin

Print_ISBN

978-1-4244-5557-7

Electronic_ISBN

978-0-7695-3852-5

Type

conf

DOI

10.1109/ICINIS.2009.115

Filename

5363317