Minimizing Congestion in Neuro Fuzzy System

Main Article Content

Priya Kasana
Sunita Parashar

Abstract

This paper presents a Fuzzy and Neural based congestion control in Diff-Services network. Congestion control in a dynamic
environment remains a critical and high priority issue. Diff-Services is a new architecture for the time – sensitive voice and video application.
The RED (Random Early Detection) algorithm is used for controlling congestion in Diff-Services. RED is one of the AQM (Active Queue
Management) algorithms. RED (Random Early deduction) and its variants are one of these alternatives to provide QoS (Quality of Service) in
Diff-Services networks. RED also defines some maximum threshold and minimum threshold in each class of router queue. The proposed fuzzy
and neural based approach for congestion control allows us to reduce the PDP (Packet drop probability) in Diff-Services network when the AQL
(Average Queue Length) of buffer exceeds the minimum Q.

 

 

Key Words: Fuzzy, Neural Networks, RED (Random Early Detection)

Downloads

Download data is not yet available.

Article Details

Section
Articles