Synchronizing UAV Teams for Timely Data Collection and Energy Transfer by Deep Reinforcement Learning

Omar Sami Oubbati, Mohammed Atiquzzaman, Hyotaek Lim, Abderrezak Rachedi, Abderrahmane Lakas

Research output: Contribution to journalArticlepeer-review

28 Citations (Scopus)

Abstract

Due to their promising applications and intriguing characteristics, Unmanned Aerial Vehicles (UAVs) can be dispatched as flying base stations to serve multiple energy-constrained Internet-of-Things (IoT) sensors. Moreover, to ensure fresh data collection while providing sustainable energy support to a large set of IoT devices, a required number of UAVs should be deployed to carry out these two tasks efficiently and promptly. Indeed, the data collection requires that UAVs first make Wireless Energy Transfer (WET) to supply IoT devices with the necessary energy in the downlink. Then, IoT devices perform Wireless Information Transmission (WIT) to UAVs in the uplink based on the harvested energy. However, it turns out that when the same UAV performs WIT and WET, its energy usage and the data collection time are severely penalized. Worse yet, it is difficult to efficiently coordinate between UAVs to improve the performance in terms of WET and WIT. This work proposes to divide UAVs into two teams to behave as data collectors and energy transmitters, respectively. A Multi-Agent Deep Reinforcement Learning (MADRL) method, called TEAM, is leveraged to jointly optimize both teams' trajectories, minimize the expected Age of Information (AoI), maximize the throughput of IoT devices, minimize the energy utilization of UAVs, and enhance the energy transfer. Simulation results depict that TEAM can effectively synchronize UAV teams and adapt their trajectories while serving a large-scale dynamic IoT environment.

Original languageEnglish
Pages (from-to)6682-6697
Number of pages16
JournalIEEE Transactions on Vehicular Technology
Volume71
Issue number6
DOIs
Publication statusPublished - Jun 1 2022

Keywords

  • Multi-Agent Deep Reinforcement Learning (MADRL)
  • Trajectory optimization
  • UAV
  • Wireless Powered Communication Network (WPCN)

ASJC Scopus subject areas

  • Aerospace Engineering
  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Automotive Engineering

Fingerprint

Dive into the research topics of 'Synchronizing UAV Teams for Timely Data Collection and Energy Transfer by Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this