Stochastic approach for modeling random early detection gateways in TCP/IP networks

Author

Alazemi, Hamed M. ; Mokhtar, Ahmed ; Azizoglu, Murat

Author_Institution

Dept. of Comput. Eng., Kuwait Univ., Safat, Kuwait

Volume

8

fYear

2001

fDate

2001

Firstpage

2385

Abstract

This paper considers the random early detection (RED) active queue management algorithm in TCP/IP networks. A stochastic framework for modeling the performance of the RED algorithm is presented. We introduce a two-dimensional second-order discrete-time Markov chain to model the feedback effect of packet dropping on the incoming traffic. The mean system occupancy, packet drop probability, and system throughput are computed from the analytical model for both marking and dropping policies. The effects of RED parameters on a selected set of performance metrics are studied

Keywords

Markov processes; feedback; internetworking; network servers; packet switching; probability; queueing theory; signal detection; stochastic processes; telecommunication congestion control; telecommunication network management; transport protocols; 2D second-order discrete-time Markov chain; RED algorithm algorithm; RED parameters; TCP/IP networks; active queue management algorithm; analytical model; dropping policy; feedback effect; incoming traffic; marking policy; mean system occupancy; network congestion; packet drop probability; packet dropping; performance metrics; random early detection gateways; steady state system performance; stochastic approach; system throughput; system transition probabilities; Analytical models; Feedback; IP networks; Intelligent networks; Internet; Performance analysis; Stochastic processes; Switches; TCPIP; Traffic control;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications, 2001. ICC 2001. IEEE International Conference on

Conference_Location

Helsinki

Print_ISBN

0-7803-7097-1

Type

conf

DOI

10.1109/ICC.2001.936566

Filename

936566