Current studentsExisting staffContact us
 

Distributed dynamic call admission control and channel allocation using SARSA

Simple item page
dc.contributor.authorLilith, N.
dc.contributor.authorDogancay, K.
dc.contributor.conference11th Asia-Pacific Conference on Communications (3 Oct 2005 - 5 Oct 2005 : Perth, Western Australia, Australia)
dc.date.issued2005
dc.description.abstractThis paper introduces novel reinforcement learning agent-based solutions to the problems of call admission control (CAC) and dynamic channel allocation (DCA) in multi-cellular telecommunications environments featuring multi-class traffic and intercell handoffs. Both agents providing the CAC and DCA functionality make use of an on-policy reinforcement learning technique known as SARSA and are designed to be implemented at the cellular level in a distributed manner. Furthermore, both are capable of on-line learning without any initial training period. Both of the reinforcement learning agents are examined via computer simulations and are shown to provide superior results in terms of call blocking probabilities and revenue raised under a variety of traffic conditions. © 2005 IEEE.
dc.identifier.citation2005 Asia-Pacific conference on communications, 2005, vol.2005, pp.376-380
dc.identifier.doi10.1109/APCC.2005.1554084
dc.identifier.isbn0-7803-9132-2
dc.identifier.isbn9780780391321
dc.identifier.orcidDogancay, K. [0000-0003-3373-6295]
dc.identifier.urihttps://hdl.handle.net/1959.8/27446
dc.language.isoen
dc.publisherIEEE
dc.publisher.placeUSA
dc.rightsCopyright IEEE 2005
dc.source.urihttps://doi.org/10.1109/APCC.2005.1554084
dc.titleDistributed dynamic call admission control and channel allocation using SARSA
dc.typeConference paper
pubs.publication-statusPublished
ror.fileinfo12143356030001831 13143351090001831 9915912014601831_53109379390001831.pdf
ror.mmsid9915912014601831

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
9915912014601831_53109379390001831.pdf
Size:
207.81 KB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections