A novel dynamic Q-learning-based scheduler technique for LTE-advanced technologies using neural networks

2.50
Hdl Handle:
http://hdl.handle.net/10547/272039
Title:
A novel dynamic Q-learning-based scheduler technique for LTE-advanced technologies using neural networks
Authors:
Comşa, Ioan-Sorin; Zhang, Sijing; Aydin, Mehmet Emin ( 0000-0002-4890-5648 ) ; Kuonen, Pierre; Wagen, Jean–Frédéric
Abstract:
The tradeoff concept between system capacity and user fairness attracts a big interest in LTE-Advanced resource allocation strategies. By using static threshold values for throughput or fairness, regardless the network conditions, makes the scheduler to be inflexible when different tradeoff levels are required by the system. This paper proposes a novel dynamic neural Q-learning-based scheduling technique that achieves a flexible throughput-fairness tradeoff by offering optimal solutions according to the Channel Quality Indicator (CQI) for different classes of users. The Q-learning algorithm is used to adopt different policies of scheduling rules, at each Transmission Time Interval (TTI). The novel scheduling technique makes use of neural networks in order to estimate proper scheduling rules for different states which have not been explored yet. Simulation results indicate that the novel proposed method outperforms the existing scheduling techniques by maximizing the system throughput when different levels of fairness are required. Moreover, the system achieves a desired throughput-fairness tradeoff and an overall satisfaction for different classes of users.
Affiliation:
University of Bedfordshire
Citation:
Sorin Comsa, I., Sijing Zhang, Aydin, M., Kuonen, P., Wagen, J., (2012) 'A novel dynamic Q-learning-based scheduler technique for LTE-advanced technologies using neural networks,' Local Computer Networks (LCN), 2012 IEEE 37th Conference on: 332-335
Publisher:
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date:
2012
URI:
http://hdl.handle.net/10547/272039
DOI:
10.1109/LCN.2012.6423642
Additional Links:
http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6423642
Type:
Conference papers, meetings and proceedings
Language:
en
ISBN:
9781467315654
Appears in Collections:
Centre for Wireless Research (CWR)

Full metadata record

DC FieldValue Language
dc.contributor.authorComşa, Ioan-Sorinen_GB
dc.contributor.authorZhang, Sijingen_GB
dc.contributor.authorAydin, Mehmet Eminen_GB
dc.contributor.authorKuonen, Pierreen_GB
dc.contributor.authorWagen, Jean–Frédéricen_GB
dc.date.accessioned2013-03-13T12:58:38Zen
dc.date.available2013-03-13T12:58:38Zen
dc.date.issued2012en
dc.identifier.citationSorin Comsa, I., Sijing Zhang, Aydin, M., Kuonen, P., Wagen, J., (2012) 'A novel dynamic Q-learning-based scheduler technique for LTE-advanced technologies using neural networks,' Local Computer Networks (LCN), 2012 IEEE 37th Conference on: 332-335en_GB
dc.identifier.isbn9781467315654en
dc.identifier.doi10.1109/LCN.2012.6423642en
dc.identifier.urihttp://hdl.handle.net/10547/272039en
dc.description.abstractThe tradeoff concept between system capacity and user fairness attracts a big interest in LTE-Advanced resource allocation strategies. By using static threshold values for throughput or fairness, regardless the network conditions, makes the scheduler to be inflexible when different tradeoff levels are required by the system. This paper proposes a novel dynamic neural Q-learning-based scheduling technique that achieves a flexible throughput-fairness tradeoff by offering optimal solutions according to the Channel Quality Indicator (CQI) for different classes of users. The Q-learning algorithm is used to adopt different policies of scheduling rules, at each Transmission Time Interval (TTI). The novel scheduling technique makes use of neural networks in order to estimate proper scheduling rules for different states which have not been explored yet. Simulation results indicate that the novel proposed method outperforms the existing scheduling techniques by maximizing the system throughput when different levels of fairness are required. Moreover, the system achieves a desired throughput-fairness tradeoff and an overall satisfaction for different classes of users.en_GB
dc.language.isoenen
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INCen_GB
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6423642en_GB
dc.subjectLTE-advanceden_GB
dc.subjectq-learningen_GB
dc.subjectneural networksen_GB
dc.titleA novel dynamic Q-learning-based scheduler technique for LTE-advanced technologies using neural networksen
dc.typeConference papers, meetings and proceedingsen
dc.contributor.departmentUniversity of Bedfordshireen_GB
All Items in UOBREP are protected by copyright, with all rights reserved, unless otherwise indicated.