Reconfigurable intelligent surface and UAV-assisted communications
: A deep reinforcement learning approach

Khoi Khac Nguyen

School of Electronics, Electrical Engineering and Computer Science

Student thesis: Doctoral Thesis › Doctor of Philosophy

Abstract

This thesis proposes novel methods based on the deep reinforcement learning algorithms (DRL) for maximising the energy efficiency (EE), sum-rate in reconfigurable intelligent surface (RIS) and unmanned aerieal vehicles (UAV)-aided wireless communications. The thesis carries out comprehensive optimization and evaluation of various DRL algorithms for several real-life applications including UAV's trajectory design, power allocation, data collection, wireless power transfer and RIS's phase shift matrix adjustment.

The thesis presents three major contributions. Firstly, we design a new UAV-assisted Internet-of -things (IoT) system relying on the shortest flight path of the UAVs while maximising the amount of data collected from IoT devices. then, a DRL-based technique is conceived for finding

Date of Award	Jul 2022
Original language	English
Awarding Institution	Queen's University Belfast
Supervisor	Trung Q. Duong (Supervisor)

Cite this

Documents

Reconfigurable intelligent surface and UAV-assisted communications: A deep reinforcement learning approach
File: application/pdf, 1.83 MB
Type: Thesis

Reconfigurable intelligent surface and UAV-assisted communications
: A deep reinforcement learning approach

Abstract

Cite this

Documents

Links

Related content

Research output

UAV-enabled Ultra-Reliable Low-Latency Communications for 6G: A Comprehensive Survey

Reconfigurable Intelligent Surface-assisted Multi-UAV Networks: Efficient Resource Allocation with Deep Reinforcement Learning

3D UAV Trajectory and Data Collection Optimisation via Deep Reinforcement Learning

Distributed Deep Deterministic Policy Gradient for Power Allocation Control in D2D-Based V2V Communications

Real-Time Energy Harvesting Aided Scheduling in UAV-Assisted D2D Networks Relying on Deep Reinforcement Learning

Non-Cooperative Energy Efficient Power Allocation Game in D2D Communication: A Multi-Agent Deep Reinforcement Learning Approach

Real-Time Deployment and Resource Allocation for Distributed UAV Systems in Disaster Relief

Reconfigurable intelligent surface and UAV-assisted communications: A deep reinforcement learning approach

Abstract

Cite this

Documents

Links

Related content

Research output

UAV-enabled Ultra-Reliable Low-Latency Communications for 6G: A Comprehensive Survey

Reconfigurable Intelligent Surface-assisted Multi-UAV Networks: Efficient Resource Allocation with Deep Reinforcement Learning

3D UAV Trajectory and Data Collection Optimisation via Deep Reinforcement Learning

Distributed Deep Deterministic Policy Gradient for Power Allocation Control in D2D-Based V2V Communications

Real-Time Energy Harvesting Aided Scheduling in UAV-Assisted D2D Networks Relying on Deep Reinforcement Learning

Non-Cooperative Energy Efficient Power Allocation Game in D2D Communication: A Multi-Agent Deep Reinforcement Learning Approach

Real-Time Deployment and Resource Allocation for Distributed UAV Systems in Disaster Relief

Reconfigurable intelligent surface and UAV-assisted communications
: A deep reinforcement learning approach