Title: An adaptable transport protocol based on Genetic Algorithms

Authors: Sheng-Uei Guan, Chek Liang Dominic Boh, Fei Liu

Addresses: Department of Computer Science and Software Engineering, Xian Jiatong-Liverpool University, China. ' Department of Electrical and Computer Engineering, National University of Singapore. ' School of Computer Science and Computer Engineering, La Trobe University, Australia

Abstract: In this paper, we present an adaptable protocol, Genetic Algorithm Transport Protocol (GATP) based on Genetic Algorithms (GAs), which evolves and adapts to the network environment to achieve best-effort user-configurable Quality of Services (QoS). The networking environment is an evolutionary playground for data packets that are evolved using a fitness level of QoS achievement. Different fitness functions of weighted, single objectives, and finally multi-objectives are applied to understand the network problem. Experiments are conducted to provide the performance analysis of GATP in an actual network environment. Experimental results also show how this proposed protocol compares with Transmission Control Protocol (TCP) and User Datagram Protocol (UDP).

Keywords: modelling; adaptable protocols; configurable protocols; genetic algorithms; GAs; quality of service; QoS; multi-objectiveness; networking; GA transport protocol.

DOI: 10.1504/IJICT.2008.019103

International Journal of Information and Communication Technology, 2008 Vol.1 No.2, pp.199 - 223

Published online: 28 Jun 2008 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article