Joint channel selection and cluster-based routing scheme based on reinforcement learning for cognitive radio networks

Abstract

Cognitive radio network (CRN) has emerged as a promising solution to solve the problem of underutilization of licensed spectrum. It allows opportunistic access of unutilized spectrum (or white spaces) by unlicensed users (or secondary users, SUs) whilst minimizing interference to licensed users (or primary users, PUs). The dynamicity of channel availability has imposed additional challenges for routing in CRNs. Besides providing optimal routes to SUs for communication, one of the key requirements of routing in CRNs is to minimize interference to PUs. In this paper, we propose a joint channel selection and cluster-based routing scheme called SMART (SpectruM-Aware cluster-based RouTing) for CRNs. SMART enables SUs to form clusters in the network, and subsequently, it enables SU source node to search for a route to its destination node in the underlying clustered network. SMART applies an artificial intelligence approach called reinforcement learning in order to maximize network performance, such as SU-PU interference and packet delivery ratio. Simulation results show that SMART reduces significant interference to PUs without significance degradation of packet delivery ratio when compared to clustered scheme without cluster maintenance (i.e., SMART-NO-MNT) and non-clustered scheme (i.e., spectrum-aware AODV or SA-AODV).