A reinforcement learning-based routing scheme for cognitive radio ad hoc networks

Hasan A.A. Al-Rawi, Kok Lim Alvin Yau, Hafizal Mohamad, Nordin Ramli, Wahidah Hashim

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

9 Citations (Scopus)

Abstract

Cognitive radio (CR) has been proposed to enable unlicensed users (or secondary users, SUs) to exploit the underutilized licensed channels (or white spaces) owned by the licensed users (or primary users, PUs). This article presents a simple and pragmatic reinforcement learning (RL)-based routing scheme called Cognitive Radio Q-routing (CRQ-routing). CRQ-routing is a spectrum-Aware scheme that finds least-cost routes taking into account the dynamicity and unpredictability of channel availability and channel quality, as well as interference to PUs. RL is applied to enable each SU node to observe, learn and make action selection that maximizes network performance as time goes by; and this is essential as it may not be feasible to define actions for all possible sets of network conditions. Simulation results show that CRQ-routing minimizes SUs' interference to PUs, SUs' end-to-end delay, SUs' packet loss rate, as well as maximizes SUs' throughput.

Original languageEnglish
Title of host publication2014 7th IFIP Wireless and Mobile Networking Conference, WMNC 2014
PublisherIEEE Computer Society
ISBN (Print)9781479930609
DOIs
Publication statusPublished - 2014
Event7th IFIP Wireless and Mobile Networking Conference, WMNC 2014 - Vilamoura, Portugal
Duration: 20 May 201422 May 2014

Other

Other7th IFIP Wireless and Mobile Networking Conference, WMNC 2014
CountryPortugal
CityVilamoura
Period20/05/1422/05/14

Fingerprint

Reinforcement learning
Cognitive radio
Ad hoc networks
Packet loss
Network performance
Throughput
Availability
Costs

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Al-Rawi, H. A. A., Yau, K. L. A., Mohamad, H., Ramli, N., & Hashim, W. (2014). A reinforcement learning-based routing scheme for cognitive radio ad hoc networks. In 2014 7th IFIP Wireless and Mobile Networking Conference, WMNC 2014 [6878881] IEEE Computer Society. https://doi.org/10.1109/WMNC.2014.6878881
Al-Rawi, Hasan A.A. ; Yau, Kok Lim Alvin ; Mohamad, Hafizal ; Ramli, Nordin ; Hashim, Wahidah. / A reinforcement learning-based routing scheme for cognitive radio ad hoc networks. 2014 7th IFIP Wireless and Mobile Networking Conference, WMNC 2014. IEEE Computer Society, 2014.
@inproceedings{5789b62faed0431a86d0cc5906d3448e,
title = "A reinforcement learning-based routing scheme for cognitive radio ad hoc networks",
abstract = "Cognitive radio (CR) has been proposed to enable unlicensed users (or secondary users, SUs) to exploit the underutilized licensed channels (or white spaces) owned by the licensed users (or primary users, PUs). This article presents a simple and pragmatic reinforcement learning (RL)-based routing scheme called Cognitive Radio Q-routing (CRQ-routing). CRQ-routing is a spectrum-Aware scheme that finds least-cost routes taking into account the dynamicity and unpredictability of channel availability and channel quality, as well as interference to PUs. RL is applied to enable each SU node to observe, learn and make action selection that maximizes network performance as time goes by; and this is essential as it may not be feasible to define actions for all possible sets of network conditions. Simulation results show that CRQ-routing minimizes SUs' interference to PUs, SUs' end-to-end delay, SUs' packet loss rate, as well as maximizes SUs' throughput.",
author = "Al-Rawi, {Hasan A.A.} and Yau, {Kok Lim Alvin} and Hafizal Mohamad and Nordin Ramli and Wahidah Hashim",
year = "2014",
doi = "10.1109/WMNC.2014.6878881",
language = "English",
isbn = "9781479930609",
booktitle = "2014 7th IFIP Wireless and Mobile Networking Conference, WMNC 2014",
publisher = "IEEE Computer Society",
address = "United States",

}

Al-Rawi, HAA, Yau, KLA, Mohamad, H, Ramli, N & Hashim, W 2014, A reinforcement learning-based routing scheme for cognitive radio ad hoc networks. in 2014 7th IFIP Wireless and Mobile Networking Conference, WMNC 2014., 6878881, IEEE Computer Society, 7th IFIP Wireless and Mobile Networking Conference, WMNC 2014, Vilamoura, Portugal, 20/05/14. https://doi.org/10.1109/WMNC.2014.6878881

A reinforcement learning-based routing scheme for cognitive radio ad hoc networks. / Al-Rawi, Hasan A.A.; Yau, Kok Lim Alvin; Mohamad, Hafizal; Ramli, Nordin; Hashim, Wahidah.

2014 7th IFIP Wireless and Mobile Networking Conference, WMNC 2014. IEEE Computer Society, 2014. 6878881.

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

TY - GEN

T1 - A reinforcement learning-based routing scheme for cognitive radio ad hoc networks

AU - Al-Rawi, Hasan A.A.

AU - Yau, Kok Lim Alvin

AU - Mohamad, Hafizal

AU - Ramli, Nordin

AU - Hashim, Wahidah

PY - 2014

Y1 - 2014

N2 - Cognitive radio (CR) has been proposed to enable unlicensed users (or secondary users, SUs) to exploit the underutilized licensed channels (or white spaces) owned by the licensed users (or primary users, PUs). This article presents a simple and pragmatic reinforcement learning (RL)-based routing scheme called Cognitive Radio Q-routing (CRQ-routing). CRQ-routing is a spectrum-Aware scheme that finds least-cost routes taking into account the dynamicity and unpredictability of channel availability and channel quality, as well as interference to PUs. RL is applied to enable each SU node to observe, learn and make action selection that maximizes network performance as time goes by; and this is essential as it may not be feasible to define actions for all possible sets of network conditions. Simulation results show that CRQ-routing minimizes SUs' interference to PUs, SUs' end-to-end delay, SUs' packet loss rate, as well as maximizes SUs' throughput.

AB - Cognitive radio (CR) has been proposed to enable unlicensed users (or secondary users, SUs) to exploit the underutilized licensed channels (or white spaces) owned by the licensed users (or primary users, PUs). This article presents a simple and pragmatic reinforcement learning (RL)-based routing scheme called Cognitive Radio Q-routing (CRQ-routing). CRQ-routing is a spectrum-Aware scheme that finds least-cost routes taking into account the dynamicity and unpredictability of channel availability and channel quality, as well as interference to PUs. RL is applied to enable each SU node to observe, learn and make action selection that maximizes network performance as time goes by; and this is essential as it may not be feasible to define actions for all possible sets of network conditions. Simulation results show that CRQ-routing minimizes SUs' interference to PUs, SUs' end-to-end delay, SUs' packet loss rate, as well as maximizes SUs' throughput.

UR - http://www.scopus.com/inward/record.url?scp=84906773162&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906773162&partnerID=8YFLogxK

U2 - 10.1109/WMNC.2014.6878881

DO - 10.1109/WMNC.2014.6878881

M3 - Conference contribution

SN - 9781479930609

BT - 2014 7th IFIP Wireless and Mobile Networking Conference, WMNC 2014

PB - IEEE Computer Society

ER -

Al-Rawi HAA, Yau KLA, Mohamad H, Ramli N, Hashim W. A reinforcement learning-based routing scheme for cognitive radio ad hoc networks. In 2014 7th IFIP Wireless and Mobile Networking Conference, WMNC 2014. IEEE Computer Society. 2014. 6878881 https://doi.org/10.1109/WMNC.2014.6878881