Discrete event fluid modeling of background TCP traffic

TCP is the most widely used transport layer protocol used in the Internet today. A TCP session adapts the demands it places on the network to observations of bandwidth availability on the network. Because TCP is adaptive, any model of its behavior that aspires to be accurate must be influenced by other network traffic. This point is especially important in the context of using simulation to evaluate some new network algorithm of interest (e.g., reliable multicast) in an environment where the background traffic affects---and is affected by---its behavior. We need to generate background traffic efficiently in a way that captures the salient features of TCP, while the reference and background traffic representations interact with each other. This article describes a fluid model of TCP and a switching model that has flows represented by fluids interacting with packet-oriented flows. We describe conditions under which a fluid model produces exactly the same behavior as a packet-oriented model, and we quantify the performance advantages of the approach both analytically and empirically. We observe that very significant speedups may be attained while keeping high accuracy.

[1]  George Kesidis,et al.  Feasibility of fluid event-driven simulation for ATM networks , 1996, Proceedings of GLOBECOM'96. 1996 IEEE Global Telecommunications Conference.

[2]  David M. Nicol.  Discrete event fluid modeling of TCP , 2001, Proceeding of the 2001 Winter Simulation Conference (Cat. No.01CH37304).

[3]  Donald F. Towsley,et al.  A study of networks simulation efficiency: fluid simulation vs. packet-level simulation , 2001, Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213).

[4]  Matthew Mathis,et al.  The stationary behavior of ideal TCP congestion avoidance , 1996 .

[5]  David M. Nicol.  Fluid simulation: discrete event fluid modeling of TCP , 2001, WSC '01.

[6]  W. Gong,et al.  Fluid Simulation for High Speed Networks 1 , 1996 .

[7]  Jean C. Walrand,et al.  Quick simulation of ATM buffers with on-off multiclass Markov fluid sources , 1993, TOMC.

[8]  Mineo Takai,et al.  Integration of fluid-based analytical model with packet-level simulation for analysis of computer networks , 2001, SPIE ITCom.

[9]  Donald F. Towsley,et al.  Fluid Simulation of Large Scale Networks: Issues and Tradeoffs , 1999, PDPTA.

[10]  David M. Nicol,et al.  Fluid-based Simulation of Communication Networks using SSF , 1999 .

[11]  Ad Ridder.  Fast simulation of Markov fluid models , 1993 .

[12]  Debasis Mitra,et al.  Performance and fluid simulations of a novel shared buffer management system , 2001, TOMC.

[13]  Vishal Misray,et al.  Stochastic Differential Equation Modeling and Analysis of TCP-Windowsize Behavior , 2005 .

[14]  Wei-Bo Gong,et al.  Time-driven fluid simulation for high-speed networks , 1999, IEEE Trans. Inf. Theory.

[15]  Donald F. Towsley,et al.  Fluid models and solutions for large-scale IP networks , 2003, SIGMETRICS '03.

[16]  Eitan Altman,et al.  A stochastic model of TCP/IP with stationary random losses , 2005, TNET.

[17]  Peter B. Danzig,et al.  Packet network simulation: speedup and accuracy versus timing granularity , 1996, TNET.

[18]  Donald F. Towsley,et al.  Time-stepped hybrid simulation (TSHS) for large scale networks , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).