Learning to optimize: Training deep neural networks for wireless resource management

dc.contributor.advisor Mingyi Hong
dc.contributor.author Sun, Haoran
dc.contributor.department Industrial and Manufacturing Systems Engineering
dc.date 2019-12-19T00:51:45.000
dc.date.accessioned 2020-06-30T03:17:38Z
dc.date.available 2020-06-30T03:17:38Z
dc.date.copyright Sun Jan 01 00:00:00 UTC 2017
dc.date.embargo 2019-07-05
dc.date.issued 2017-01-01
dc.description.abstract <p>For decades, optimization has played a central role in addressing wireless resource management problems such as power control and beamformer design. However, these algorithms often require a considerable number of iterations for convergence, which poses challenges for real-time processing. In this work, we propose a new learning-based approach for wireless resource management. The key idea is to treat the input and output of a resource allocation algorithm as an unknown non-linear mapping and to use a deep neural network (DNN) to approximate it. If the non-linear mapping can be learned accurately and effectively by a DNN of moderate size, then such DNN can be used for resource allocation in almost real time, since passing the input through a DNN to get the output only requires a small number of simple operations. In this work, we first characterize a class of `learnable algorithms' and then design DNNs to approximate some algorithms of interest in wireless communications. We use extensive numerical simulations to demonstrate the superior ability of DNNs for approximating two considerably complex algorithms that are designed for power allocation in wireless transmit signal design, while giving orders of magnitude speedup in computational time.</p>
dc.format.mimetype application/pdf
dc.identifier archive/lib.dr.iastate.edu/etd/17329/
dc.identifier.articleid 8336
dc.identifier.contextkey 15016690
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath etd/17329
dc.identifier.uri https://dr.lib.iastate.edu/handle/20.500.12876/31512
dc.language.iso en
dc.source.bitstream archive/lib.dr.iastate.edu/etd/17329/Sun_iastate_0097M_16618.pdf|||Fri Jan 14 21:20:41 UTC 2022
dc.subject.disciplines Computer Sciences
dc.subject.disciplines Electrical and Electronics
dc.subject.disciplines Industrial Engineering
dc.title Learning to optimize: Training deep neural networks for wireless resource management
dc.type article
dc.type.genre thesis
dspace.entity.type Publication
relation.isOrgUnitOfPublication 51d8b1a0-5b93-4ee8-990a-a0e04d3501b1
thesis.degree.discipline Industrial and Manufacturing Systems Engineering
thesis.degree.level thesis
thesis.degree.name Master of Science
Original bundle
Now showing 1 - 1 of 1
9.22 MB
Adobe Portable Document Format