• Aug 09, 2018 News! Vol. 6, No. 4-No. 7, No. 3 has been indexed by EI(Inspec)!   [Click]
  • Aug 09, 2018 News!Good News! All papers from Volume 8, Number 3 have been indexed by Scopus!   [Click]
  • May 23, 2018 News![CFP] 2018 the annual meeting of IJMLC Editorial Board, ACMLC 2018, will be held in Ho Chi Minh, Vietnam, December 7-9, 2018   [Click]
General Information
Dr. Lin Huang
Metropolitan State University of Denver, USA
It's my honor to take on the position of editor in chief of IJMLC. We encourage authors to submit papers concerning any branch of machine learning and computing.
IJMLC 2013 Vol.3(4): 361-364 ISSN: 2010-3700
DOI: 10.7763/IJMLC.2013.V3.338

GA-Based PI-PD Controller for TCP Routers

R. K. Sundaram and P. K. Padhy
Abstract—Active Queue Management (AQM) is a key congestion control mechanism for reducing the packet loss and improving the network utilization in TCP/IP networks. This paper discusses previously developed PI controller for AQM and proposed a new GA-based PI-PD controller. It is able to control present congestion reactively and also avoid the incipient congestion proactively. Fast response to the changing traffic is achieved by PD to maintain a desired queue length, high link utilization and low packet loss. The optimized tuning parameters are determined by selection of an Integral Square Time Error (ISTE) as an objective/fitness function. We use ns simulation to demonstrate the practical advantage of using GA-based PI-PD controller over PI in managing constant queue length.

Index Terms—Congestion control, genetic algorithm (GA), integral square time error (ISTE), transmission control protocol (TCP).

R. K. Sundaram is with Indian Institute of Technology, Kanpur, India (e-mail: sravi@iitk.ac.in). P. K. Padhy is with PDPM-IIITDM, Jabalpur (e-mail: prabin16@iiitdmj.ac.in).


Cite:R. K. Sundaram and P. K. Padhy, "GA-Based PI-PD Controller for TCP Routers," International Journal of Machine Learning and Computing vol.3, no. 4, pp. 361-364, 2013.

Copyright © 2008-2018. International Journal of Machine Learning and Computing. All rights reserved.
E-mail: ijmlc@ejournal.net