Artificial intelligent power prediction for efficient resource management of WCDMA mobile network

Y. K. Tee, S. K. Tinng, Johnny Siaw Paw Koh, Y. David

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

Abstract

This paper presents a method of predicting changes of power consumption at Node B of a wideband code division multiple access (WCDMA) mobile network due to dynamic resource allocation such as movement of unit equipment (UE), handover call from adjacent cell and accommodation of new service request. The method learns the mapping of power consumption at Node B by monitoring power changes that response to previous performed resource allocation. Estimation of the unknown function is implemented with support vector regression (SVR). The output of SVR will be used by WCDMA mobile network to decide on new service admission. Genetic algorithm (GA) is then applied to form optimal beams to cover all UEs in a cell with minimum power. This artificial intelligent call admission control (CAC) was validated using a dynamic WCDMA mobile network simulator. A few comparative results in downlink have shown that our integrated support vector regression assists genetic algorithm (SVRaGA) is capable of predicting next interval power consumption at Node B with low prediction error and improving the quality of service (QoS) by reducing dropped calls.

Original languageEnglish
Title of host publication2008 14th Asia-Pacific Conference on Communications, APCC 2008
Publication statusPublished - 01 Dec 2008
Event2008 14th Asia-Pacific Conference on Communications, APCC 2008 - Akihabara, Tokyo, United States
Duration: 14 Oct 200816 Oct 2008

Publication series

Name2008 14th Asia-Pacific Conference on Communications, APCC 2008

Other

Other2008 14th Asia-Pacific Conference on Communications, APCC 2008
CountryUnited States
CityAkihabara, Tokyo
Period14/10/0816/10/08

Fingerprint

Code division multiple access
Wireless networks
Electric power utilization
Resource allocation
Genetic algorithms
management
resources
Congestion control (communication)
regression
Quality of service
Simulators
Monitoring
accommodation
monitoring

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Communication

Cite this

Tee, Y. K., Tinng, S. K., Koh, J. S. P., & David, Y. (2008). Artificial intelligent power prediction for efficient resource management of WCDMA mobile network. In 2008 14th Asia-Pacific Conference on Communications, APCC 2008 [4773836] (2008 14th Asia-Pacific Conference on Communications, APCC 2008).
Tee, Y. K. ; Tinng, S. K. ; Koh, Johnny Siaw Paw ; David, Y. / Artificial intelligent power prediction for efficient resource management of WCDMA mobile network. 2008 14th Asia-Pacific Conference on Communications, APCC 2008. 2008. (2008 14th Asia-Pacific Conference on Communications, APCC 2008).
@inproceedings{146f07ce9ce747debd6bf39182934308,
title = "Artificial intelligent power prediction for efficient resource management of WCDMA mobile network",
abstract = "This paper presents a method of predicting changes of power consumption at Node B of a wideband code division multiple access (WCDMA) mobile network due to dynamic resource allocation such as movement of unit equipment (UE), handover call from adjacent cell and accommodation of new service request. The method learns the mapping of power consumption at Node B by monitoring power changes that response to previous performed resource allocation. Estimation of the unknown function is implemented with support vector regression (SVR). The output of SVR will be used by WCDMA mobile network to decide on new service admission. Genetic algorithm (GA) is then applied to form optimal beams to cover all UEs in a cell with minimum power. This artificial intelligent call admission control (CAC) was validated using a dynamic WCDMA mobile network simulator. A few comparative results in downlink have shown that our integrated support vector regression assists genetic algorithm (SVRaGA) is capable of predicting next interval power consumption at Node B with low prediction error and improving the quality of service (QoS) by reducing dropped calls.",
author = "Tee, {Y. K.} and Tinng, {S. K.} and Koh, {Johnny Siaw Paw} and Y. David",
year = "2008",
month = "12",
day = "1",
language = "English",
isbn = "4885522323",
series = "2008 14th Asia-Pacific Conference on Communications, APCC 2008",
booktitle = "2008 14th Asia-Pacific Conference on Communications, APCC 2008",

}

Tee, YK, Tinng, SK, Koh, JSP & David, Y 2008, Artificial intelligent power prediction for efficient resource management of WCDMA mobile network. in 2008 14th Asia-Pacific Conference on Communications, APCC 2008., 4773836, 2008 14th Asia-Pacific Conference on Communications, APCC 2008, 2008 14th Asia-Pacific Conference on Communications, APCC 2008, Akihabara, Tokyo, United States, 14/10/08.

Artificial intelligent power prediction for efficient resource management of WCDMA mobile network. / Tee, Y. K.; Tinng, S. K.; Koh, Johnny Siaw Paw; David, Y.

2008 14th Asia-Pacific Conference on Communications, APCC 2008. 2008. 4773836 (2008 14th Asia-Pacific Conference on Communications, APCC 2008).

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

TY - GEN

T1 - Artificial intelligent power prediction for efficient resource management of WCDMA mobile network

AU - Tee, Y. K.

AU - Tinng, S. K.

AU - Koh, Johnny Siaw Paw

AU - David, Y.

PY - 2008/12/1

Y1 - 2008/12/1

N2 - This paper presents a method of predicting changes of power consumption at Node B of a wideband code division multiple access (WCDMA) mobile network due to dynamic resource allocation such as movement of unit equipment (UE), handover call from adjacent cell and accommodation of new service request. The method learns the mapping of power consumption at Node B by monitoring power changes that response to previous performed resource allocation. Estimation of the unknown function is implemented with support vector regression (SVR). The output of SVR will be used by WCDMA mobile network to decide on new service admission. Genetic algorithm (GA) is then applied to form optimal beams to cover all UEs in a cell with minimum power. This artificial intelligent call admission control (CAC) was validated using a dynamic WCDMA mobile network simulator. A few comparative results in downlink have shown that our integrated support vector regression assists genetic algorithm (SVRaGA) is capable of predicting next interval power consumption at Node B with low prediction error and improving the quality of service (QoS) by reducing dropped calls.

AB - This paper presents a method of predicting changes of power consumption at Node B of a wideband code division multiple access (WCDMA) mobile network due to dynamic resource allocation such as movement of unit equipment (UE), handover call from adjacent cell and accommodation of new service request. The method learns the mapping of power consumption at Node B by monitoring power changes that response to previous performed resource allocation. Estimation of the unknown function is implemented with support vector regression (SVR). The output of SVR will be used by WCDMA mobile network to decide on new service admission. Genetic algorithm (GA) is then applied to form optimal beams to cover all UEs in a cell with minimum power. This artificial intelligent call admission control (CAC) was validated using a dynamic WCDMA mobile network simulator. A few comparative results in downlink have shown that our integrated support vector regression assists genetic algorithm (SVRaGA) is capable of predicting next interval power consumption at Node B with low prediction error and improving the quality of service (QoS) by reducing dropped calls.

UR - http://www.scopus.com/inward/record.url?scp=66149134740&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=66149134740&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:66149134740

SN - 4885522323

SN - 9784885522321

T3 - 2008 14th Asia-Pacific Conference on Communications, APCC 2008

BT - 2008 14th Asia-Pacific Conference on Communications, APCC 2008

ER -

Tee YK, Tinng SK, Koh JSP, David Y. Artificial intelligent power prediction for efficient resource management of WCDMA mobile network. In 2008 14th Asia-Pacific Conference on Communications, APCC 2008. 2008. 4773836. (2008 14th Asia-Pacific Conference on Communications, APCC 2008).