Conditional drop probability of RED mechanism with UDP and TCP traffic

In this paper, we apply the matrix-analytic approach to explore the conditional drop behavior of router with UDP and TCP traffic under RED scheme. We constructed a simple queuing model for RED mechanism with UDP and TCP traffic, which follow a continuous-time Markovian arrival process (MAP). The queueing model of the router with RED scheme is modeled as MAP/M/1/K. With the numerical results, we find that as the traffic intensity of UDP traffic increases, the conditional drop probability of TCP traffic will also increase under RED scheme. In practice, this effect causes TCP congestion control protocol to reduce the transmission rate of TCP traffic. This is an unfair effect for providing multimedia applications on the Internet. Based on this observation, the router in the Internet must implement some mechanisms to suppress this effect.

[1]  Jean-Yves Le Boudec,et al.  Global fairness of additive-increase and multiplicative-decrease with heterogeneous round-trip times , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[2]  David M. Lucantoni,et al.  New results for the single server queue with a batch Markovian arrival process , 1991 .

[3]  Richard Bellman,et al.  Introduction to Matrix Analysis , 1972 .

[4]  Christoph Lindemann,et al.  Modeling IP traffic using the batch Markovian arrival process , 2003, Perform. Evaluation.

[5]  E. Seneta.  Non-negative Matrices and Markov Chains (Springer Series in Statistics) , 1981 .

[6]  Vishal Misra,et al.  Fluid-based analysis of a network of AQM routers supporting TCP flows with an application to RED , 2000, SIGCOMM.

[7]  B. Conolly.  Structured Stochastic Matrices of M/G/1 Type and Their Applications , 1991 .

[8]  Raj Jain,et al.  Analysis of the Increase and Decrease Algorithms for Congestion Avoidance in Computer Networks , 1989, Comput. Networks.

[9]  Alexander Graham,et al.  Kronecker Products and Matrix Calculus: With Applications , 1981 .

[10]  V. Jacobson,et al.  Congestion avoidance and control , 1988, CCRV.

[11]  QUTdN QeO,et al.  Random early detection gateways for congestion avoidance , 1993, TNET.

[12]  Victor Firoiu,et al.  A study of active queue management for congestion control , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[13]  Philippe Nain,et al.  Upper and Lower Bounds for the Multiplexing of Multiclass Markovian on/off Sources , 1996, Perform. Evaluation.

[14]  Marcel F. Neuts,et al.  Matrix-geometric solutions in stochastic models - an algorithmic approach , 1982 .

[15]  Yung-Chung Wang.  Loss Information of Random Early Detection Mechanism , 2003 .

[16]  Martin May,et al.  Analytic evaluation of RED performance , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[17]  Marcel F. Neuts.  Models Based on the Markovian Arrival Process , 1992 .

[18]  Frank Kelly,et al.  Rate control for communication networks: shadow prices, proportional fairness and stability , 1998, J. Oper. Res. Soc..

[19]  Kenji Nakagawa.  The Importance Sampling Simulation of MMPP/D/1 Queueing , 1997 .

[20]  Robert Tappan Morris,et al.  Dynamics of random early detection , 1997, SIGCOMM '97.

[21]  Richard Bellman,et al.  Introduction to matrix analysis (2nd ed.) , 1997 .