Bandwidth allocation in ATM networks using neural networks.
Item
-
Title
-
Bandwidth allocation in ATM networks using neural networks.
-
Identifier
-
AAI9924857
-
identifier
-
9924857
-
Creator
-
Youssef, Sameh Ahmed.
-
Contributor
-
Adviser: Tarek Saadawi
-
Date
-
1999
-
Language
-
English
-
Publisher
-
City University of New York.
-
Subject
-
Engineering, Electronics and Electrical
-
Abstract
-
ATM network architecture are capable of supporting a wide range of connections with different quality of service requirements and traffic characteristics. This dynamic environment creates difficult traffic control problems when trying to achieve efficient use of network resources. One of such problem is bandwidth allocation. In this thesis, we suggest the neural network (NN) as a new approach to handle the bandwidth allocation problem in ATM. The proposed algorithms employ neural network to calculate the bandwidth required to support multimedia traffic with multiple quality of service (QoS) requirements. Two types of neural network have been used to design the bandwidth allocation controllers, backpropagation neural network and radial basis function neural network. The hierarchical structure has been used to simplify the design of the neural network controllers and to extend the ability of the neural network to learn a huge number of patterns. The NN controllers calculate the bandwidth required per call using on-line measurements of the traffic via its count process, instead of relying on simple parameters such as the peak, average bit rate and burst length. Furthermore, to enhance the statistical multiplexing gain, the controllers calculate the gain obtained from multiplexing multiple streams of traffic supported on separate virtual paths (i.e., class multiplexing). In this thesis, we will explain the design of the controllers have been used and also we will compare the results from neural network controllers with the results from the traditional methods.
-
Type
-
dissertation
-
Source
-
PQT Legacy CUNY.xlsx
-
degree
-
Ph.D.
