ATM congestion control using Minimal Resource Allocation Networks (MRAN)

Abstract

This paper presents a congestion control scheme for ATM traffic using a minimal radial basis function neural network referred to as Minimal Resource Allocation Network (MRAN). Earlier studies have shown that MRAN is well suited for online adaptive control of nonlinear time varying systems as it can adjust its size by adding and pruning the hidden neurons based on the input data. Since ATM traffic is nonlinear and time varying performance of MRAN as a congestion controller is investigated here. These studies are carried out using OPNET to model the ATM traffic. The ATM traffic model consists of bursty, Variable BitRate (VBR) and custom traffic in a multiplexed form so as to generate a heavily congested traffic situation. For this scenario, the controller has to minimize the congestion episodes and maintain the Quality of Service (QoS) requirements. This paper compares the performance of the MRAN congestion controller with that of a modified Explicit Rate Indication with Congestion Avoidance (ERICA) scheme and a Back-Propagation (BP) neural controller. Simulation results indicate that MRAN controller performs better than the modified ERICA and BP controller in reducing the congestion episodes and maintaining the desirable QoS.

A Survey on Study of Various Machine Learning Methods for Classification

“…More or less all the existing machine algorithms have been executed in this field. The improved classified efficiency is proved in [5][6][7][8][9].It also proves its betterment in the field of image processing by generating high resolution images from low resolution input [3,[10][11].ELM also entered in the field of system modeling and prediction [12][13].…”