Reconfigurable intelligent surfaces-aided smart wireless environments for 6G systems

Al-Senwi, Madyan

Reconfigurable intelligent surfaces-aided smart wireless environments for 6G systems

Al-Senwi, Madyan

Permalink

Publication Type:: Thesis
Issue Date:: 2024

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (2.47 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Al-Senwi, Madyan
dc.date.accessioned	2025-04-03T02:36:32Z
dc.date.available	2025-04-03T02:36:32Z
dc.date.issued	2024
dc.identifier.uri	http://hdl.handle.net/10453/186550
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	The 6th Generation (6G) wireless networks are expected to evolve toward intelligence and openness with re-programmable components and disaggregated architecture paradigms and be capable of controlling and optimizing wireless environments. Recently, Reconfigurable Intelligent Surfaces (RISs) have emerged as a promising technology capable of manipulating wireless environments to enhance network coverage and capacity. Furthermore, the Open Radio Access Networks (O-RAN) Alliance has proposed a new vision for 6G wireless systems, including standardized interfaces designed to enable operators to utilize shared infrastructure from various vendors. Additionally, recent advancements in Unmanned Aerial Vehicles (UAVs) have been utilized to improve wireless networks. This thesis comprehensively explores 6G wireless networks enabling technologies, focusing on the synergistic integration of RISs, O-RAN, and UAVs and their roles in enhancing network performance. Specifically, in the first contribution of this thesis, an RIS-aided Millimeter Wave (mmWave) vehicular wireless network is considered, where the RIS assists in reflecting the mmWave signals from the base station (BS) towards vehicular users who experience link blockages. A two-phase framework is proposed, comprising: 1) the Base Station (BS) precoding optimization phase, wherein a decomposition and relaxation-based optimization algorithm is developed; and 2) the RIS phase shift control phase, wherein a Deep Reinforcement Learning (DRL) algorithm is introduced to fine-tune the signal reflection. Next, in the second contribution, the network model is extended to a multi-cell network scenario, where multiple roadside units (RSU) are deployed to serve vehicular users. A federated learning framework based on the multi-agent DRL is proposed following the network architecture presented by the O-RAN to optimize the RIS phase shifts and precoding of each associated RSU. In the third contribution, we study the beamforming and trajectory design in UAV-assisted networks, where an RIS-equipped UAV is used to enhance connectivity for users with blocked links. A dual computational DRL framework is proposed that combines extensive offline training on a central server with real-time decision-making on an edge server for efficient optimization of UAV trajectories and RIS phase shifts. In the last contribution, a novel approach is proposed to enhance the performance of RIS-aided mmWave wireless networks for Extended Reality (XR) applications, incorporating a channel prediction model based on Gaussian Process Regression (GPR) and an optimization algorithm for adjusting RIS phase shifts. Extensive simulations validate the effectiveness of the proposed algorithms under various network configurations, demonstrating superior performance through comparative analyses with state-of-the-art techniques.	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/186550/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2024 Madyan Al-Senwi
dc.rights	au.edu.uts.lib/nph
dc.title	Reconfigurable intelligent surfaces-aided smart wireless environments for 6G systems	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

The 6th Generation (6G) wireless networks are expected to evolve toward intelligence and openness with re-programmable components and disaggregated architecture paradigms and be capable of controlling and optimizing wireless environments. Recently, Reconfigurable Intelligent Surfaces (RISs) have emerged as a promising technology capable of manipulating wireless environments to enhance network coverage and capacity. Furthermore, the Open Radio Access Networks (O-RAN) Alliance has proposed a new vision for 6G wireless systems, including standardized interfaces designed to enable operators to utilize shared infrastructure from various vendors. Additionally, recent advancements in Unmanned Aerial Vehicles (UAVs) have been utilized to improve wireless networks. This thesis comprehensively explores 6G wireless networks enabling technologies, focusing on the synergistic integration of RISs, O-RAN, and UAVs and their roles in enhancing network performance. Specifically, in the first contribution of this thesis, an RIS-aided Millimeter Wave (mmWave) vehicular wireless network is considered, where the RIS assists in reflecting the mmWave signals from the base station (BS) towards vehicular users who experience link blockages. A two-phase framework is proposed, comprising: 1) the Base Station (BS) precoding optimization phase, wherein a decomposition and relaxation-based optimization algorithm is developed; and 2) the RIS phase shift control phase, wherein a Deep Reinforcement Learning (DRL) algorithm is introduced to fine-tune the signal reflection. Next, in the second contribution, the network model is extended to a multi-cell network scenario, where multiple roadside units (RSU) are deployed to serve vehicular users. A federated learning framework based on the multi-agent DRL is proposed following the network architecture presented by the O-RAN to optimize the RIS phase shifts and precoding of each associated RSU. In the third contribution, we study the beamforming and trajectory design in UAV-assisted networks, where an RIS-equipped UAV is used to enhance connectivity for users with blocked links. A dual computational DRL framework is proposed that combines extensive offline training on a central server with real-time decision-making on an edge server for efficient optimization of UAV trajectories and RIS phase shifts. In the last contribution, a novel approach is proposed to enhance the performance of RIS-aided mmWave wireless networks for Extended Reality (XR) applications, incorporating a channel prediction model based on Gaussian Process Regression (GPR) and an optimization algorithm for adjusting RIS phase shifts. Extensive simulations validate the effectiveness of the proposed algorithms under various network configurations, demonstrating superior performance through comparative analyses with state-of-the-art techniques.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/186550