University of Khartoum

Implementation Of Neural Network Call Admission Control Strategies In Broadband Networks

Implementation Of Neural Network Call Admission Control Strategies In Broadband Networks

Show full item record

Title: Implementation Of Neural Network Call Admission Control Strategies In Broadband Networks
Author: Ibrahim, Sayed Gotb Ibrahim Hassan
Abstract: Call Admission Control (CAC) has been accepted as a potential solution for supporting diverse, heterogeneous traffic sources demanding different quality of services in broadband network (e.g. Asynchronous Transfer Mode (ATM) or broadband integrated services digital network (B-ISDN)) networks. Besides, CAC is required to consume a minimum of time and space to make call acceptance decisions. One important issue in broadband networks is the design of an efficient traffic control architecture that guarantees quality of service (QoS) for all network users. And that, applying the traditional methodology to judge Accepting or rejecting the incoming call request is difficult to apply. A Neural Network technique is introduced. In this project, we present an efficient neural-network-based CAC (NNCAC) mechanism for broadband network node with m-channels of equal capacity and two types of customer arrivals. This mechanism makes call acceptance decisions and guarantees quality of services. The results conclusively indicate that under ANN based Call Admission Control is superior in performance to conventional CAC schemes. The conventional controller also proved to be not as robust as the ANN scheme under statistically varied traffic scenarios.
URI: http://khartoumspace.uofk.edu/handle/123456789/18594
Date: 2005


Files in this item

Files Size Format View

This item appears in the following Collection(s)

Show full item record

Share

Search DSpace


Browse

My Account