An Efficient Connected Swarm Deployment via Deep Learning

Kiril Danilchenko, Michael Segal

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, an unmanned aerial vehicles (UAVs) deployment framework based on machine learning is studied. It aims to maximize the sum of the weights of the ground users covered by UAVs while UAVs forming a connected communication graph. We focus on the case where the number of UAVs is not necessarily enough to cover all ground users. We develop an UAV Deployment Deep Neural network (UD-DNNet) as a UAV's deployment deep network method. Simulation results demonstrate that UDDNNet can serve as a computationally inexpensive replacement for traditionally expensive optimization algorithms in real-time tasks and outperform the state-of-the-art traditional algorithms.

Original languageEnglish
Title of host publicationProceedings of the 16th Conference on Computer Science and Intelligence Systems, FedCSIS 2021
EditorsMaria Ganzha, Leszek Maciaszek, Marcin Paprzycki, Dominik Slezak
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-7
Number of pages7
ISBN (Electronic)9788395918384
DOIs
StatePublished - 2 Sep 2021
Event16th Conference on Computer Science and Intelligence Systems, FedCSIS 2021 - Virtual, Sofia, Bulgaria
Duration: 2 Sep 20215 Sep 2021

Publication series

NameProceedings of the 16th Conference on Computer Science and Intelligence Systems, FedCSIS 2021

Conference

Conference16th Conference on Computer Science and Intelligence Systems, FedCSIS 2021
Country/TerritoryBulgaria
CityVirtual, Sofia
Period2/09/215/09/21

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Information Systems
  • Information Systems and Management
  • Control and Optimization

Fingerprint

Dive into the research topics of 'An Efficient Connected Swarm Deployment via Deep Learning'. Together they form a unique fingerprint.

Cite this