Call admission control in ATM networks using neural networks trained with virtual cell loss probability method
In this paper, we propose a Neural Network (NN) approach to estimate Virtual cell loss probability (VCLP) of bursty sources for Call Admission Control (CAC) purpose in Asynchronous Transfer Mode (ATM) environment. Based on this approach, we have presented two schemes of estimating cell loss probabil...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| _version_ | 1825925812825620480 |
|---|---|
| author | Khalil, Ibrahim Bidin, Abdul Rahman Mukerjee, Malay R. |
| author_facet | Khalil, Ibrahim Bidin, Abdul Rahman Mukerjee, Malay R. |
| author_sort | Khalil, Ibrahim |
| collection | UPM |
| description | In this paper, we propose a Neural Network (NN) approach to estimate Virtual cell loss probability (VCLP) of bursty sources for Call Admission Control (CAC) purpose in Asynchronous Transfer Mode (ATM) environment. Based on this approach, we have presented two schemes of estimating cell loss probability (CLP). For both the schemes training data set are obtained from VCLP methods advocated by, and this training is done off-line to estimate CLP in real time environment. While the first method performs consistently well to withstand changes in burst duration parameters, the second one is also suitable from the point of view of individual call quality. In order to discuss performance aspects the methods have been compared with other cell loss estimation methods. Our simulation shows that NN approach outperforms the conventional methods in terms of accuracy. |
| first_indexed | 2024-03-06T08:03:19Z |
| format | Conference or Workshop Item |
| id | upm.eprints-25632 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-03-06T08:03:19Z |
| record_format | dspace |
| spelling | upm.eprints-256322019-12-09T08:59:05Z http://psasir.upm.edu.my/id/eprint/25632/ Call admission control in ATM networks using neural networks trained with virtual cell loss probability method Khalil, Ibrahim Bidin, Abdul Rahman Mukerjee, Malay R. In this paper, we propose a Neural Network (NN) approach to estimate Virtual cell loss probability (VCLP) of bursty sources for Call Admission Control (CAC) purpose in Asynchronous Transfer Mode (ATM) environment. Based on this approach, we have presented two schemes of estimating cell loss probability (CLP). For both the schemes training data set are obtained from VCLP methods advocated by, and this training is done off-line to estimate CLP in real time environment. While the first method performs consistently well to withstand changes in burst duration parameters, the second one is also suitable from the point of view of individual call quality. In order to discuss performance aspects the methods have been compared with other cell loss estimation methods. Our simulation shows that NN approach outperforms the conventional methods in terms of accuracy. Conference or Workshop Item PeerReviewed Khalil, Ibrahim and Bidin, Abdul Rahman and Mukerjee, Malay R. Call admission control in ATM networks using neural networks trained with virtual cell loss probability method. In: International Symposium on Information Theory & Its Applications, 20-24 Nov. 1994, Sydney, Australia. (pp. 653-658). |
| spellingShingle | Khalil, Ibrahim Bidin, Abdul Rahman Mukerjee, Malay R. Call admission control in ATM networks using neural networks trained with virtual cell loss probability method |
| title | Call admission control in ATM networks using neural networks trained with virtual cell loss probability method |
| title_full | Call admission control in ATM networks using neural networks trained with virtual cell loss probability method |
| title_fullStr | Call admission control in ATM networks using neural networks trained with virtual cell loss probability method |
| title_full_unstemmed | Call admission control in ATM networks using neural networks trained with virtual cell loss probability method |
| title_short | Call admission control in ATM networks using neural networks trained with virtual cell loss probability method |
| title_sort | call admission control in atm networks using neural networks trained with virtual cell loss probability method |
| work_keys_str_mv | AT khalilibrahim calladmissioncontrolinatmnetworksusingneuralnetworkstrainedwithvirtualcelllossprobabilitymethod AT bidinabdulrahman calladmissioncontrolinatmnetworksusingneuralnetworkstrainedwithvirtualcelllossprobabilitymethod AT mukerjeemalayr calladmissioncontrolinatmnetworksusingneuralnetworkstrainedwithvirtualcelllossprobabilitymethod |