Skip to main content

BRIEF RESEARCH REPORT article

Front. Comms. Net.
Sec. IoT and Sensor Networks
Volume 6 - 2025 | doi: 10.3389/frcmn.2025.1529453

UAV-Assisted Federated Learning with Hybrid LoRa P2P/LoRaWAN for Sustainable Biosphere

Provisionally accepted
Mehran Behjati Mehran Behjati 1*Haider A.H. Alobaidy Haider A.H. Alobaidy 2*Rosdiadee Nordin Rosdiadee Nordin 1Nor Fadzilah Abdullah Nor Fadzilah Abdullah 3
  • 1 Department of Computing and Information Systems, School of Engineering & Technology, Sunway University, Bandar Sunway, Selangor Darul Ehsan, Malaysia
  • 2 Department of Information and Communications Engineering, College of Information Engineering, Al-Nahrain University, Baghdad, Iraq
  • 3 Department of Electrical, Electronic & Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia

The final, formatted version of the article will be published soon.

    The increasing amount of data sensors generate, and the dynamic nature of climate and environment pose challenges for conventional smart environmental monitoring systems. These systems encounter difficulties in long-distance data communication, accurate data processing, and generalized prediction modeling, particularly in large-scale, remote, and hard-to-reach areas. Moreover, they are costly, complex, and inefficient, especially in regions with limited telecommunications infrastructure. Consequently, there is a pressing need for more efficient and effective monitoring techniques to safeguard natural resources and ecosystems. To address these challenges, we propose the concept of a novel environmental monitoring system that integrates aerial access networks (AAN), federated learning (FL), and hybrid LoRa Point-to-Point (P2P)/LoRaWAN technologies. This integration offers a reliable and efficient solution for monitoring remote regions. We provide an overview of the AAN, FL, and aerial FL paradigms and discuss the benefits and challenges of their integration. Preliminary simulation results demonstrated the proposed system's feasibility and effectiveness. Lastly, we outline open challenges and potential research directions to advance this field.

    Keywords: Federated learning, Aerial access network, UAV, LORA, Wireless Sensor Networks, Environmental conservation

    Received: 16 Nov 2024; Accepted: 07 Jan 2025.

    Copyright: © 2025 Behjati, Alobaidy, Nordin and Abdullah. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Mehran Behjati, Department of Computing and Information Systems, School of Engineering & Technology, Sunway University, Bandar Sunway, 47500, Selangor Darul Ehsan, Malaysia
    Haider A.H. Alobaidy, Department of Information and Communications Engineering, College of Information Engineering, Al-Nahrain University, Baghdad, Iraq

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.