Machine learning based Call Admission Control approaches: A comparative study

Abul Basher, Gerard Parr, Sally McClean, Scotney Bryan, Detlef Nauck

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

The importance of providing guaranteed Quality of Service (QoS) cannot be overemphasised, especially in the NGN environment which supports converged services on a common IP transport network. Call Admission Control (CAC) mechanisms do provide QoS to class-based services in a proactive manner. However, due to the factors of complexity, scale and dynamicity of NGN, Machine Learning techniques are favoured to analytical approaches for providing autonomous CAC. This paper is an effort to compare the performance of two such approaches - Neural Networks (NN) and Bayesian Networks (BN), to model the network behaviour and to estimate QoS metrics to be used in the CAC algorithm. It provides a way to find the optimum model training size for accurate predictions. Performance comparison is based on a wide range of experiments through a simulated network in Opnet. The outcome of this comparative study provides some interesting insights into the behaviour of NN and BN models and how they can be utilised for better CAC implementations.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages431-434
Number of pages4
DOIs
Publication statusPublished - 25 Oct 2010
EventInternational Conference on Network and Service Management (CNSM), 2010 - Niagara Falls, ON, Canada
Duration: 25 Oct 2010 → …

Conference

ConferenceInternational Conference on Network and Service Management (CNSM), 2010
Period25/10/10 → …

Fingerprint

Congestion control (communication)
Learning systems
Quality of service
Bayesian networks
Neural networks
Experiments

Cite this

Basher, Abul ; Parr, Gerard ; McClean, Sally ; Bryan, Scotney ; Nauck, Detlef. / Machine learning based Call Admission Control approaches: A comparative study. Unknown Host Publication. 2010. pp. 431-434
@inproceedings{3a74e04dffb443f0b8cd08848056dd92,
title = "Machine learning based Call Admission Control approaches: A comparative study",
abstract = "The importance of providing guaranteed Quality of Service (QoS) cannot be overemphasised, especially in the NGN environment which supports converged services on a common IP transport network. Call Admission Control (CAC) mechanisms do provide QoS to class-based services in a proactive manner. However, due to the factors of complexity, scale and dynamicity of NGN, Machine Learning techniques are favoured to analytical approaches for providing autonomous CAC. This paper is an effort to compare the performance of two such approaches - Neural Networks (NN) and Bayesian Networks (BN), to model the network behaviour and to estimate QoS metrics to be used in the CAC algorithm. It provides a way to find the optimum model training size for accurate predictions. Performance comparison is based on a wide range of experiments through a simulated network in Opnet. The outcome of this comparative study provides some interesting insights into the behaviour of NN and BN models and how they can be utilised for better CAC implementations.",
author = "Abul Basher and Gerard Parr and Sally McClean and Scotney Bryan and Detlef Nauck",
year = "2010",
month = "10",
day = "25",
doi = "10.1109/CNSM.2010.5691261",
language = "English",
isbn = "978-1-4244-8910-7",
pages = "431--434",
booktitle = "Unknown Host Publication",

}

Basher, A, Parr, G, McClean, S, Bryan, S & Nauck, D 2010, Machine learning based Call Admission Control approaches: A comparative study. in Unknown Host Publication. pp. 431-434, International Conference on Network and Service Management (CNSM), 2010, 25/10/10. https://doi.org/10.1109/CNSM.2010.5691261

Machine learning based Call Admission Control approaches: A comparative study. / Basher, Abul; Parr, Gerard; McClean, Sally; Bryan, Scotney; Nauck, Detlef.

Unknown Host Publication. 2010. p. 431-434.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Machine learning based Call Admission Control approaches: A comparative study

AU - Basher, Abul

AU - Parr, Gerard

AU - McClean, Sally

AU - Bryan, Scotney

AU - Nauck, Detlef

PY - 2010/10/25

Y1 - 2010/10/25

N2 - The importance of providing guaranteed Quality of Service (QoS) cannot be overemphasised, especially in the NGN environment which supports converged services on a common IP transport network. Call Admission Control (CAC) mechanisms do provide QoS to class-based services in a proactive manner. However, due to the factors of complexity, scale and dynamicity of NGN, Machine Learning techniques are favoured to analytical approaches for providing autonomous CAC. This paper is an effort to compare the performance of two such approaches - Neural Networks (NN) and Bayesian Networks (BN), to model the network behaviour and to estimate QoS metrics to be used in the CAC algorithm. It provides a way to find the optimum model training size for accurate predictions. Performance comparison is based on a wide range of experiments through a simulated network in Opnet. The outcome of this comparative study provides some interesting insights into the behaviour of NN and BN models and how they can be utilised for better CAC implementations.

AB - The importance of providing guaranteed Quality of Service (QoS) cannot be overemphasised, especially in the NGN environment which supports converged services on a common IP transport network. Call Admission Control (CAC) mechanisms do provide QoS to class-based services in a proactive manner. However, due to the factors of complexity, scale and dynamicity of NGN, Machine Learning techniques are favoured to analytical approaches for providing autonomous CAC. This paper is an effort to compare the performance of two such approaches - Neural Networks (NN) and Bayesian Networks (BN), to model the network behaviour and to estimate QoS metrics to be used in the CAC algorithm. It provides a way to find the optimum model training size for accurate predictions. Performance comparison is based on a wide range of experiments through a simulated network in Opnet. The outcome of this comparative study provides some interesting insights into the behaviour of NN and BN models and how they can be utilised for better CAC implementations.

U2 - 10.1109/CNSM.2010.5691261

DO - 10.1109/CNSM.2010.5691261

M3 - Conference contribution

SN - 978-1-4244-8910-7

SP - 431

EP - 434

BT - Unknown Host Publication

ER -