Skip navigation
Skip navigation

Future Wireless Networks: Towards Learning-driven Sixth-generation Wireless Communications

Saleem, Rabbia

Description

The evolution of wireless communication networks, from present to the emerging fifth-generation (5G) new radio (NR), and sixth-generation (6G) is inevitable, yet propitious. The thesis evolves around application of machine learning and optimization techniques to problems in spectrum management, internet-of-things (IoT), physical layer security, and intelligent reflecting surface (IRS). The first problem explores License Assisted Access (LAA), which leverages unlicensed resource sharing with...[Show more]

dc.contributor.authorSaleem, Rabbia
dc.date.accessioned2022-11-03T23:23:33Z
dc.date.available2022-11-03T23:23:33Z
dc.identifier.urihttp://hdl.handle.net/1885/277999
dc.description.abstractThe evolution of wireless communication networks, from present to the emerging fifth-generation (5G) new radio (NR), and sixth-generation (6G) is inevitable, yet propitious. The thesis evolves around application of machine learning and optimization techniques to problems in spectrum management, internet-of-things (IoT), physical layer security, and intelligent reflecting surface (IRS). The first problem explores License Assisted Access (LAA), which leverages unlicensed resource sharing with the Wi-Fi network as a promising technique to address the spectrum scarcity issue in wireless networks. An optimal communication policy is devised which maximizes the throughput performance of LAA network while guaranteeing a proportionally fair performance among LAA stations and a fair share for Wi-Fi stations. The numerical results demonstrate more than 75 % improvement in the LAA throughput and a notable gain of 8-9 % in the fairness index. Next, we investigate the unlicensed spectrum sharing for bandwidth hungry diverse IoT networks in 5G NR. An efficient coexistence mechanism based on the idea of adaptive initial sensing duration (ISD) is proposed to enhance the diverse IoT-NR network performance while keeping the primary Wi-Fi network's performance to a bearable threshold. A Q-learning (QL) based algorithm is devised to maximize the normalized sum throughput of the coexistence Wi-Fi/IoT-NR network. The results confirm a maximum throughput gain of 51 % and ensure that the Wi-Fi network's performance remains intact. Finally, advanced levels of network security are critical to maintain due to severe signal attenuation at higher frequencies of 6G wireless communication. Thus, an IRS-based model is proposed to address the issue of network security under trusted-untrusted device diversity, where the untrusted devices may potentially eavesdrop on the trusted devices. A deep deterministic policy gradient (DDPG) algorithm is devised to jointly optimize the active and passive beamforming matrices. The results confirm a maximum gain of 2-2.5 times in the sum secrecy rate of trusted devices and ensure Quality-of-Service (QoS) for all the devices. In conclusion, the thesis has led towards efficient, secure, and smart communication and build foundation to address similar complex wireless networks.
dc.language.isoen_AU
dc.titleFuture Wireless Networks: Towards Learning-driven Sixth-generation Wireless Communications
dc.typeThesis (PhD)
local.contributor.supervisorNi, Wei
local.contributor.supervisorcontactu1111362@anu.edu.au
dc.date.issued2023
local.identifier.doi10.25911/SHDX-1797
local.identifier.proquestYes
local.identifier.researcherIDACH-5087-2022
local.thesisANUonly.author69d3bb4c-a694-4c01-aaa8-a45b474cd68f
local.thesisANUonly.title000000019399_TC_1
local.thesisANUonly.key2f3e04d0-0f62-c4d0-fc6f-7d699b610599
local.mintdoimint
CollectionsOpen Access Theses

Download

File Description SizeFormat Image
PhD_Thesis_Rabbia_Saleem.pdfThesis Material1.71 MBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  17 November 2022/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator