Reinforcement learning for dynamic aerial base station positioning

Lee, Isabella

Permalink

https://hdl.handle.net/2142/108184 Copy

Description

Title

Reinforcement learning for dynamic aerial base station positioning

Author(s)

Lee, Isabella

Issue Date

2020-05-12

Director of Research (if dissertation) or Advisor (if thesis)

Caesar, Matthew

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• UAV relay network
• reinforcement learning
• IoT network
• emergency relief
• disaster response
• aerial base station

Abstract

Reliable communication infrastructure plays an extremely important role in peoples' everyday lives and the lack of sufficient communication means could have severe negative consequences. In the case of a post-disaster situation, it could be the difference in an emergency responder's ability to rescue a trapped victim. In the case of a state-wide stay-at-home order, it could be the difference in a parent's ability to continue their work remotely and in a student's ability to receive a proper education. In the case of a remote region, it could be the difference in someone's ability to connect with the outside world. Unfortunately, in many of these cases, the number of functioning communication network infrastructure is actually limited. In such scenarios, unmanned aerial vehicles (UAVs) can be used as aerial base stations or relays to help form a connected network amongst users. Since users are likely to be constantly mobile, the problem of where these UAVs are placed and how they move in response to the changing environment could have a large effect on the number of connections this UAV relay network is able to maintain. In this work, we propose DroneDR, a reinforcement learning framework for UAV positioning that uses information about connectivity requirements and user node positions to decide how to move each UAV in the network while maintaining connectivity between UAVs. The proposed approach is shown to outperform other baseline methods across a broad range of scenarios and demonstrates the potential in using reinforcement learning techniques to aid in communication efforts.

Graduation Semester

2020-05

Type of Resource

Thesis

Permalink

http://hdl.handle.net/2142/108184

Copyright and License Information

Copyright 2020 Isabella Lee

Owning Collections