Publication:
Deep Reinforcement Learning For Distributed Fog Network Probing

Simple item page
dc.contributor.advisorBeatriz Lorenzo
dc.contributor.authorGuan, Xiaoding
dc.contributor.departmentUniversity of Massachusetts Amherst
dc.contributor.departmentElectrical & Computer Engineering
dc.date2024-03-28T20:00:53.000
dc.date.accessioned2024-04-26T18:37:05Z
dc.date.available2024-04-26T18:37:05Z
dc.date.issued2020-09-01
dc.date.submittedSeptember
dc.date.submitted2020
dc.description.abstractThe sixth-generation (6G) of wireless communication systems will significantly rely on fog/edge network architectures for service provisioning. To satisfy stringent quality of service requirements using dynamically available resources at the edge, new network access schemes are needed. In this paper, we consider a cognitive dynamic edge/fog network where primary users (PUs) may temporarily share their resources and act as fog nodes for secondary users (SUs). We develop strategies for distributed dynamic fog probing so SUs can find out available connections to access the fog nodes. To handle the large-state space of the connectivity availability that includes availability of channels, computing resources, and fog nodes, and the partial observability of the states, we design a novel distributed Deep Q-learning Fog Probing (DQFP) algorithm. Our goal is to develop multi-user strategies for accessing fog nodes in a distributed manner without any centralized scheduling or message passing. By using cooperative and competitive utility functions, we analyze the impact of the multi-user dynamics on the connectivity availability and establish design principles for our DQFP algorithm.
dc.description.degreeMaster of Science in Electrical and Computer Engineering (M.S.E.C.E.)
dc.identifier.doihttps://doi.org/10.7275/19085701
dc.identifier.orcidhttps://orcid.org/0000-0002-2648-4985
dc.identifier.urihttps://hdl.handle.net/20.500.14394/34039
dc.relation.urlhttps://scholarworks.umass.edu/cgi/viewcontent.cgi?article=2037&context=masters_theses_2&unstamped=1
dc.source.statuspublished
dc.subjectcognitive wireless network
dc.subjectfog probing
dc.subjectdynamic network access
dc.subjectdeep reinforcement learning
dc.subjectmulti-agent learning
dc.subjectSystems and Communications
dc.titleDeep Reinforcement Learning For Distributed Fog Network Probing
dc.typecampusfive
dc.typearticle
dc.typethesis
digcom.contributor.authorisAuthorOfPublication|email:gxiaoding@umass.edu|institution:University of Massachusetts Amherst|Guan, Xiaoding
digcom.identifiermasters_theses_2/967
digcom.identifier.contextkey19085701
digcom.identifier.submissionpathmasters_theses_2/967
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
master_thesis_xiaoding_guan_10_20.pdf
Size:
2.29 MB
Format:
Adobe Portable Document Format
Name: master_thesis_xiaoding_guan_10_20.pdf
Size: 2.29 MB
Kind: Adobe PDF
Collections
Masters Theses