|Title:||Call admission control for video sources in ATM networks using neural networks|
|Subject:||Telecommunication -- Traffic|
Neural networks (Computer science)
Asynchronous transfer mode
Hong Kong Polytechnic University -- Dissertations
|Pages:||79 leaves : ill. ; 30 cm|
|Abstract:||The role of the call admission control (CAC) in Asynchronous Transfer Mode (ATM) networks becomes more and more important in order to allocate the network resources in a more efficient way yet at the same time, maintain the desired QoS for all the connections. Since there is a large bit-rate variation of digitized video data, the characterization of the video traffic and hence the CAC for such sources are in general difficult in such a dynamic environment. Neural networks are usually employed as an adaptive controller for dynamically changing situations. This project investigates the application of neural networks in CAC in ATM networks. Video sources are modeled by a first order autoregressive process. Training patterns are obtained based on delay requirement for video transmission and are used to train a feedforward neural network using mean, variance and peak values. The performance of the neural CAC is compared with those of other CAC algorithms. The proposed neural CAC is shown to outperform other CAC algorithms in term of average throughput. The adaptive nature of the neural CAC may be particularly suitable for heterogeneous sources.|
|Rights:||All rights reserved|
Files in This Item:
|b14211294.pdf||For All Users (off-campus access for PolyU Staff & Students only)||2.89 MB||Adobe PDF||View/Open|
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item: