Modeling and traffic analysis of the adaptive rate transport protocol

Authors:
Igor V. Alekseev;Valery A. Sokolov
Affiliations:
Yaroslavl State University, Sovetskaya Street 14, Yaroslavl 150000, Russia;Yaroslavl State University, Sovetskaya Street 14, Yaroslavl 150000, Russia
Venue:
Future Generation Computer Systems - Parallel computing technologies (PaCT-2001)
Year:
2002

Citing 5
Cited 1

On the self-similar nature of Ethernet traffic (extended version)

IEEE/ACM Transactions on Networking (TON)
TCP Vegas: new techniques for congestion detection and avoidance

SIGCOMM '94 Proceedings of the conference on Communications architectures, protocols and applications
Self-similarity through high-variability: statistical analysis of Ethernet LAN traffic at the source level

IEEE/ACM Transactions on Networking (TON)
Internetworking with TCP/IP: Principles, Protocols, and Architecture

Internetworking with TCP/IP: Principles, Protocols, and Architecture
Congestion control for best-effort service: why we need a new paradigm

IEEE Network: The Magazine of Global Internetworking

An approach to the implementation of the dynamical priorities method

PaCT'05 Proceedings of the 8th international conference on Parallel Computing Technologies

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a new algorithm (adaptive rate transmission control protocol (ARTCP)) for rate control in transport protocols of packet switching networks, such as Internet. The protocol based on ARTCP uses scheduling mechanism to smoothly transmit data flow and avoids overloading the network by considering temporal characteristics of its flow and adjusting its rate to the available network capacity. ARTCP utilizes inter-segment spacing and round trip time measurements to control the rate of the flow.We provide an imitational model to study characteristics of the ARTCP, such as efficiency, loss probabilities and statistical properties of simulated traffic. Results of our simulation studies, performed with ARTCP on our model, display substantial advantages, which ARTCP has over standard transmission control protocol (TCP) algorithms. Statistical analysis of ARTCP traffic traces yields the self-similar property of ARTCP traffic, which is in line with other studies of traffic traces in network systems.