[Paper Review] Analysis and Simulation of Delay and Buffer Requirements of satellite-ATM Networks for TCP/IP Traffic

Rohit Goyal, Sastri Kota+4 more|ArXiv.org|Sep 23, 1998

Network Traffic and Congestion Control12 references19 citations

TL;DR

This paper analyzes and simulates end-to-end delay and buffer requirements in satellite-ATM networks for TCP/IP traffic, focusing on propagation and buffering delays in GEO and LEO constellations. It models LEO routing for optimal paths and evaluates buffering delays under ATM ABR and UBR service categories, showing that buffering delay dominates in LEO systems and significantly impacts TCP performance.

ABSTRACT

In this paper we present a model to study the end-to-end delay performance of a satellite-ATM netowrk. We describe a satellite-ATM network architecture. The architecture presents a trade-off between the on-board switching/processing features and the complexity of the satellite communication systems. The end-to-end delay of a connection passing through a satellite constellation consists of the transmission delay, the uplink and downlink ground terminal-satellite propagation delay, the inter-satellite link delays, the on-board switching, processing and buffering delays. In a broadband satellite network, the propagation and the buffering delays have the most impact on the overall delay. We present an analysis of the propagation and buffering delay components for GEO and LEO systems. We model LEO constellations as satellites evenly spaced in circular orbits around the earth. A simple routing algorithm for LEO systems calculates locally optimal paths for the end-to-end connection. This is used to calculate the end-to-end propagation delays for LEO networks. We present a simulation model to calculate the buffering delay for TCP/IP traffic over ATM ABR and UBR service categories. We apply this model to calculate total end-to-end delays for TCP/IP over satellite-ATM networks.

Motivation & Objective

• To analyze the end-to-end delay performance in satellite-ATM networks for TCP/IP traffic.
• To evaluate the impact of propagation and buffering delays in both GEO and LEO satellite constellations.
• To model a routing algorithm for LEO systems that computes locally optimal paths.
• To simulate buffering delays for TCP/IP traffic over ATM ABR and UBR service categories.
• To quantify total end-to-end delay and identify dominant delay components in satellite-ATM networks.

Proposed method

• Models LEO constellations as satellites evenly spaced in circular orbits around Earth.
• Develops a simple routing algorithm to compute locally optimal end-to-end paths in LEO networks.
• Analyzes propagation delay based on satellite geometry and orbital parameters for both GEO and LEO systems.
• Models buffering delay for TCP/IP traffic using ATM's ABR and UBR service categories.
• Simulates end-to-end delay by combining propagation delay, switching/processing delays, and buffering delays.
• Uses a simulation model to compute total end-to-end delay, emphasizing buffering delay contributions.

Experimental results

Research questions

• RQ1 What is the contribution of propagation delay to end-to-end delay in GEO and LEO satellite-ATM networks?
• RQ2 How do buffering delays in ATM ABR and UBR service categories affect TCP/IP traffic performance?
• RQ3 What is the impact of satellite constellation geometry on end-to-end delay in LEO systems?
• RQ4 Which delay component—propagation or buffering—dominates in LEO satellite-ATM networks for TCP/IP traffic?
• RQ5 How does the choice of routing algorithm affect end-to-end delay in LEO constellations?

Key findings

• Buffering delay is the dominant contributor to end-to-end delay in LEO satellite-ATM networks for TCP/IP traffic.
• Propagation delay is significant in both GEO and LEO systems, but LEO systems exhibit lower overall propagation delay due to lower orbital altitude.
• The simulation results show that ABR service category results in more predictable buffering delays compared to UBR, which is more sensitive to traffic load.
• End-to-end delay in LEO networks is primarily determined by the number of hops and the buffering behavior at each satellite.
• The proposed routing algorithm effectively minimizes end-to-end path length and thus reduces propagation delay in LEO constellations.
• The total end-to-end delay in LEO systems is significantly higher than in terrestrial networks due to cumulative buffering and propagation delays.