A binary feedback flow control scheme using system sensitivity derivatives for congestion detection

Author

Aweya, James ; Montuno, Delfin Y. ; Zhang, Qi-Jun ; Orozco-Barbosa, Luis

Author_Institution

Nortel, Ottawa, Ont., Canada

fYear

1998

fDate

19-24 Jul 1998

Firstpage

112

Lastpage

117

Abstract

This paper presents a binary feedback flow control scheme which uses the gradient of the system performance function to generate feedback from the network to the data sources. The setting of the single bit congestion indication communicated back to the users is based upon the sign of the gradient of the system performance function. The proposed scheme uses a simple gradient optimization method and a neural model of the system dynamics to determine the gradient of the performance function. Simulation results are presented to compare the performance of the proposed scheme to the conventional queue thresholding approach

Keywords

feedback; feedforward neural nets; gradient methods; optimisation; packet switching; queueing theory; telecommunication computing; telecommunication congestion control; binary feedback flow control; congestion detection; data sources; feedforward neural network; gradient optimization method; neural model; packet switched network; queue thresholding; simulation results; single bit congestion indication; system dynamics; system performance function; system sensitivity derivatives; Communication system traffic control; Computer networks; Control systems; Feedback; ISDN; Jacobian matrices; Neural networks; Neurofeedback; Neurons; Relays;

fLanguage

English

Publisher

ieee

Conference_Titel

Modeling, Analysis and Simulation of Computer and Telecommunication Systems, 1998. Proceedings. Sixth International Symposium on

Conference_Location

Montreal, Que.

Print_ISBN

0-8186-8566-2

Type

conf

DOI

10.1109/MASCOT.1998.693683

Filename

693683