Reinforcement learning based distributed multiagent sensing policy for cognitive radio networks

Jarmo Lundén, Visa Koivunen, Sanjeev R. Kulkarni, H. Vincent Poor

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

28 Scopus citations

Abstract

In this paper a distributed multiagent, multiband reinforcement learning based sensing policy for cognitive radio ad hoc networks is proposed. The proposed sensing policy employs secondary user (SU) collaboration through local interactions. The goal is to maximize the amount of available spectrum found for secondary use given a desired diversity order, i.e. a desired number of SUs sensing simultaneously each frequency band. The SUs in the cognitive radio network make local decisions based on their own and their neighbors' local test statistics or decisions to identify unused spectrum locally. Thus, the network builds a locally available map of spectrum occupancy of its geographical area. Simulation results show that the proposed sensing policy provides a significant increase in the amount of available spectrum found for secondary use compared to a random sensing policy.

Original languageEnglish (US)
Title of host publication2011 IEEE International Symposium on Dynamic Spectrum Access Networks, DySPAN 2011
Pages642-646
Number of pages5
DOIs
StatePublished - 2011
Event2011 IEEE International Symposium on Dynamic Spectrum Access Networks, DySPAN 2011 - Aachen, Germany
Duration: May 3 2011May 6 2011

Publication series

Name2011 IEEE International Symposium on Dynamic Spectrum Access Networks, DySPAN 2011

Other

Other2011 IEEE International Symposium on Dynamic Spectrum Access Networks, DySPAN 2011
CountryGermany
CityAachen
Period5/3/115/6/11

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Reinforcement learning based distributed multiagent sensing policy for cognitive radio networks'. Together they form a unique fingerprint.

Cite this