Establishing temporary networks for disaster relief using UAV swarms

Natural disasters can destroy communications infrastructure, introducing challenges for timely rescue. Unmanned Aerial Vehicles (UAVs) can act as aerial base stations to provide temporary communication services for ground users. In complex environments, obstacles such as trees and buildings can impede signal propagation, thus reducing communication quality. This thesis introduces an innovative approach using UAVs' observations of the surrounding obstacles to make informed decisions on the movement for improved user coverage. We use Deep Reinforcement Learning (DRL) within a multi-agent setting to optimize UAV swarm movements for establishing reliable communication networks in disaster-affected urban environments. This approach allows UAVs to dynamically adjust their positions for near-optimal user coverage, representing a significant advancement in disaster response technologies. By integrating real-time observations of obstacles and leveraging cooperative strategies among UAVs, the proposed method enhances Line-of-Sight (LoS) connections essential for effective communication coverage. Simulation results demonstrate that UAVs equipped with the proposed DRL-based decision-making framework achieve significantly improved communication coverage in urban scenarios characterized by diverse obstacles and user distributions. Additionally, our strategy enables UAVs to achieve coverage with shorter travel distances, enhancing operational efficiency.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2024

Author dc:creator

• He, Shilan

Contributors dc:contributor

• Caesar, Matthew Chapman

• Unmanned Aerial Vehicles
• Deep Reinforcement Learning
• Communication Networks
• Multi-agent Systems

Statement dc:rights

• Copyright 2024 Shilan He

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/124602

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F124602