Dynamics of TCP over BoD satellite networks

Bandwidth-on-Demand (BoD) mechanisms are used by most next generation satellite systems to efficiently share a limited radio spectrum among a large number of users. BoD design needs to consider a range of engineering issues: the anticipated number of users, interactions with other subsystems, and the contradictory design goals of optimising system utilization and delay/capacity offered to the network traffic. A BoD system may provide a range of quality of service classes to support different user classes and allow optimisation of allocation efficiency. Each class may have different delay and delay variation characteristics. The performance achieved by a TCP flow using such a BoD satellite network is highly dependent on the delay and the variation of the delay experienced by TCP. This paper describes the BoD mechanisms, and their expected impact on TCP behaviour. This discussion is supplemented by simulation results using an implementation of TCP combined with a model of some simple satellite BoD access schemes to characterize the performance and efficiency of BoD algorithms. Copyright © 2003 John Wiley & Sons, Ltd.

[1]  Scott Shenker,et al.  Observations on the dynamics of a congestion control algorithm: the effects of two-way traffic , 1991, SIGCOMM 1991.

[2]  Donald F. Towsley,et al.  Modeling TCP Reno performance: a simple model and its empirical validation , 2000, TNET.

[3]  George Kesidis,et al.  ATM via satellite: A framework and implementation , 1998, Wirel. Networks.

[4]  H KatzRandy,et al.  The Eifel algorithm , 2000 .

[5]  Mark Allman,et al.  Enhancing TCP Over Satellite Channels using Standard Mechanisms , 1999, RFC.

[6]  Godred Fairhurst,et al.  Performance issues in asymmetric TCP service provision using broadband satellite , 2001 .

[7]  Matthew Mathis,et al.  The macroscopic behavior of the TCP congestion avoidance algorithm , 1997, CCRV.

[8]  Allan Kuchinsky,et al.  Integrating user-perceived quality into Web server design , 2000, Comput. Networks.

[9]  Matthew Mathis,et al.  Automatic TCP buffer tuning , 1998, SIGCOMM '98.

[10]  Antonio Pietrabissa,et al.  Resource management for ATM-based geostationary satellite networks with on-board processing , 2002, Comput. Networks.

[11]  Vern Paxson,et al.  TCP Congestion Control , 1999, RFC.

[12]  William C. Fenner,et al.  Known TCP Implementation Problems , 1999, RFC.

[13]  Reiner Ludwig,et al.  The Eifel Detection Algorithm for TCP , 2003, RFC.

[14]  Godred Fairhurst,et al.  Reinforcement of TCP error recovery for wireless communication , 1998, CCRV.

[15]  Randy H. Katz,et al.  The Eifel algorithm: making TCP robust against spurious retransmissions , 2000, CCRV.

[16]  Roy T. Fielding,et al.  Hypertext Transfer Protocol - HTTP/1.1 , 1997, RFC.

[17]  Gorry Fairhurst,et al.  Advice for Internet Subnetwork Designers , 2004, RFC.

[18]  Catherine Rosenberg,et al.  Weighted fair bandwidth-on-demand (WFBoD) for geostationary satellite networks with on-board processing , 2002, Comput. Networks.

[19]  Gabriel Montenegro,et al.  Performance Enhancing Proxies Intended to Mitigate Link-Related Degradations , 2001, RFC.

[20]  Vern Paxson,et al.  Computing TCP's Retransmission Timer , 2000, RFC.

[21]  Mahesh Sooriyabandara,et al.  TCP Performance Implications of Network Path Asymmetry , 2002, RFC.