TY - JOUR
T1 - Clustering and Reinforcement-Learning-Based Routing for Cognitive Radio Networks
AU - Saleem, Yasir
AU - Yau, Kok-Lim Alvin
AU - Mohamad, Hafizal
AU - Ramli, Nordin
AU - Rehmani, Mubashir Husain
AU - Ni, Qiang
N1 - Funding Information:
Acknowledgment This work was supported by the Ministry of Education Malaysia (MOE) Fundamental Research Grant Scheme (FRGS) under grant number FRGS/1/2014/ICT03/SYUC/02/2, U.K. EPSRC under grant number EP/K011693/1, the European FP7 CROWN project under grant number PIRSES-GA-2013-610524, and Small Grant Scheme (Sunway-Lancaster) under grant number SGSSL-FST-CSNS-0114-05 and PVM1204.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/8/22
Y1 - 2017/8/22
N2 - The CRN is a future generation wireless communication system that allows SUs to use the underutilized or unused spectrum, known as white spaces, in licensed spectrum with minimum interference to PUs. However, the dynamic conditions of CRNs (e.g., PUs' activities and channel availability) make routing more challenging compared to traditional wireless networks. In this tutorial, we focus on solving the routing problem in CRNs with the help of a clustering mechanism. Cluster-based routing in CRNs enhances network scalability by reducing the flooding of routing overheads, as well as network stability by reducing the effects of dynamicity of channel availability. Additionally, RL, an artificial intelligence approach, is applied as a tool to further enhance network performance. We present SMART, which is a cluster-based routing scheme designed for the CRN, and evaluate its performance via simulations in order to show the effectiveness of cluster-based routing in CRNs using RL.
AB - The CRN is a future generation wireless communication system that allows SUs to use the underutilized or unused spectrum, known as white spaces, in licensed spectrum with minimum interference to PUs. However, the dynamic conditions of CRNs (e.g., PUs' activities and channel availability) make routing more challenging compared to traditional wireless networks. In this tutorial, we focus on solving the routing problem in CRNs with the help of a clustering mechanism. Cluster-based routing in CRNs enhances network scalability by reducing the flooding of routing overheads, as well as network stability by reducing the effects of dynamicity of channel availability. Additionally, RL, an artificial intelligence approach, is applied as a tool to further enhance network performance. We present SMART, which is a cluster-based routing scheme designed for the CRN, and evaluate its performance via simulations in order to show the effectiveness of cluster-based routing in CRNs using RL.
KW - Cognitive Radio Networks
KW - Wireless Networks
KW - Wireless communication
KW - Routing
KW - Reinforcement learning
KW - Cluster-based routing
UR - http://www.scopus.com/inward/record.url?scp=85028773612&partnerID=8YFLogxK
U2 - 10.1109/mwc.2017.1600117
DO - 10.1109/mwc.2017.1600117
M3 - Article
SN - 1536-1284
VL - 24
SP - 146
EP - 151
JO - IEEE Wireless Communications
JF - IEEE Wireless Communications
IS - 4
M1 - 8014298
ER -