Revenue-based spectrum management via Markov decision process Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/8049g856v

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • We consider the problem of wireless spectrum management in cognitive wireless networks that maximizes the revenue for a spectrum operator. Specifically, we study the problem on how a wireless spectrum operator can optimally allocate its limited spectrum to various classes users/devices who pay differently for their spectrum per unit time. We show that the problem of maximizing the revenue for the spectrum operator can be cast in the Markov Decision Process (MDP) framework. To that end, we investigate the performance of two MDP formulations: the finite-horizon and the discounted infinite-horizon models. We show that for small scenarios with known system paramters, it is feasible to obtain the optimal solution for the finite horizon MDP using the backward induction algorithm. For larger scenarios and unknown system parameters, Q-learning is used to approximate the optimal solution/policy via simulations. For real-world scenarios with many system states, it is memory inefficient to represent the optimal policy using large tables. Instead, we also show how to compactly represent the optimal policy using support vector machine (SVM). The SVM representation also allows for the prediction of the optimal actions based on the states that might not be explored during training. The existence of the compact structure of the optimal policies (SVM) for this problem motivates us to explore more efficient solutions. Specifically, under some mild assumptions, we are able to give a threshold policy, which is not only optimal but also very efficient to implement. Simulation results are used to verify our approach.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Keyword
Subject
Rights Statement
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Submitted by Pingan Zhu (zhup@onid.orst.edu) on 2014-02-04T11:46:37Z No. of bitstreams: 1 ZhuPingan2013.pdf: 1017499 bytes, checksum: 1a5851dacffe9f03df48bdec6b9052a9 (MD5)
  • description.provenance : Approved for entry into archive by Laura Wilson(laura.wilson@oregonstate.edu) on 2014-03-20T21:35:29Z (GMT) No. of bitstreams: 1 ZhuPingan2013.pdf: 1020377 bytes, checksum: 21bbab6d1c1d898c1c89bfdc69d6e02a (MD5)
  • description.provenance : Made available in DSpace on 2014-03-20T21:35:29Z (GMT). No. of bitstreams: 1 ZhuPingan2013.pdf: 1020377 bytes, checksum: 21bbab6d1c1d898c1c89bfdc69d6e02a (MD5) Previous issue date: 2013-09-23
  • description.provenance : Approved for entry into archive by Julie Kurtz(julie.kurtz@oregonstate.edu) on 2014-03-20T19:12:01Z (GMT) No. of bitstreams: 1 ZhuPingan2013.pdf: 1020377 bytes, checksum: 21bbab6d1c1d898c1c89bfdc69d6e02a (MD5)
  • description.provenance : Rejected by Julie Kurtz(julie.kurtz@oregonstate.edu), reason: Rejecting because the pretext pages doesn't reflect your dual majors and change to the commencement date. I will email you the revisions to the pretext pages to make. Once revised, log back into ScholarsArchive and go to the upload page. Replace the attached file with the revised PDF and resubmit. Thanks, Julie on 2014-03-18T18:36:45Z (GMT)
  • description.provenance : Submitted by Pingan Zhu (zhup@onid.orst.edu) on 2014-03-19T23:09:33Z No. of bitstreams: 1 ZhuPingan2013.pdf: 1020377 bytes, checksum: 21bbab6d1c1d898c1c89bfdc69d6e02a (MD5)

Relationships

Parents:

This work has no parents.

Last modified

Downloadable Content

Download PDF

Items