Adaptive UAV-Assisted Hierarchical Federated Learning: Optimizing Energy, Latency, and Resilience for Dynamic Smart IoT

• URL: http://arxiv.org/abs/2503.06145v2
• Date: Mon, 24 Mar 2025 13:05:25 GMT
• Title: Adaptive UAV-Assisted Hierarchical Federated Learning: Optimizing Energy, Latency, and Resilience for Dynamic Smart IoT
• Authors: Xiaohong Yang, Minghui Liwang, Liqun Fu, Yuhan Su, Seyyedali Hosseinalipour, Xianbin Wang, Yiguang Hong,
• Abstract summary: Key application of HFL lies in smart Internet of Things systems, including remote monitoring and battlefield operations.<n>In such scenarios, UAVs can act as mobile aggregators, dynamically providing connectivity to terrestrial IoT devices.<n>This paper investigates an HFL architecture enabled by energy-constrained, dynamically deployed UAVs.
• Score: 21.859332138454928
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: A key application of HFL lies in smart Internet of Things (IoT) systems, including remote monitoring and battlefield operations, where cellular connectivity is often unavailable. In such scenarios, UAVs can act as mobile aggregators, dynamically providing connectivity to terrestrial IoT devices. Subsequently, this paper investigates an HFL architecture enabled by energy-constrained, dynamically deployed UAVs that are susceptible to communication disruptions. We propose a novel approach to minimize global training costs in such environments by formulating a joint optimization problem that integrates learning configuration, bandwidth allocation, and IoT device-to-UAV association, ensuring timely global aggregation before UAV disconnections and redeployments. The problem explicitly captures the dynamic nature of IoT devices and their intermittent connectivity to UAVs and is shown to be NP-hard. To address its complexity, we decompose the problem into three interrelated subproblems. First, we optimize learning configuration and bandwidth allocation using an augmented Lagrangian function to reduce training costs. Second, we introduce a device fitness score that accounts for data heterogeneity (via Kullback-Leibler divergence), device-to-UAV proximity, and computational resources, leveraging a Twin Delayed Deep Deterministic Policy Gradient (TD3)-based algorithm for adaptive device-to-UAV assignment. Third, we develop a low-complexity two-stage greedy strategy for UAV redeployment and global aggregator selection, ensuring efficient model aggregation despite UAV disconnections.

Related papers

• When UAV Meets Federated Learning: Latency Minimization via Joint Trajectory Design and Resource Allocation [47.20867891501245]
  Federated learning (FL) has emerged as a pivotal solution for training machine learning models over wireless networks.<n>We introduce an innovative approach by deploying an unmanned aerial vehicle (UAV) as a mobile FL server to enhance the training process of FL.<n>To improve the overall training efficiency, we formulate a latency problem by jointly optimizing the bandwidth allocation, computing frequencies, transmit power for both the UAV and IoT devices, and the UAV's trajectory.
  arXiv  Detail & Related papers  (2024-12-10T11:39:27Z)
• Meta Reinforcement Learning for Strategic IoT Deployments Coverage in Disaster-Response UAV Swarms [5.57865728456594]
  Unmanned Aerial Vehicles (UAVs) have grabbed the attention of researchers in academia and industry for their potential use in critical emergency applications. These applications include providing wireless services to ground users and collecting data from areas affected by disasters. UAVs' limited resources, energy budget, and strict mission completion time have posed challenges in adopting UAVs for these applications.
  arXiv  Detail & Related papers  (2024-01-20T05:05:39Z)
• UAV Swarm-enabled Collaborative Secure Relay Communications with Time-domain Colluding Eavesdropper [115.56455278813756]
  Unmanned aerial vehicles (UAV) as aerial relays are practically appealing for assisting Internet Things (IoT) network. In this work, we aim to utilize the UAV to assist secure communication between the UAV base station and terminal terminal devices.
  arXiv  Detail & Related papers  (2023-10-03T11:47:01Z)
• Multi-Objective Optimization for UAV Swarm-Assisted IoT with Virtual Antenna Arrays [55.736718475856726]
  Unmanned aerial vehicle (UAV) network is a promising technology for assisting Internet-of-Things (IoT) Existing UAV-assisted data harvesting and dissemination schemes require UAVs to frequently fly between the IoTs and access points. We introduce collaborative beamforming into IoTs and UAVs simultaneously to achieve energy and time-efficient data harvesting and dissemination.
  arXiv  Detail & Related papers  (2023-08-03T02:49:50Z)
• RIS-assisted UAV Communications for IoT with Wireless Power Transfer Using Deep Reinforcement Learning [75.677197535939]
  We propose a simultaneous wireless power transfer and information transmission scheme for IoT devices with support from unmanned aerial vehicle (UAV) communications. In a first phase, IoT devices harvest energy from the UAV through wireless power transfer; and then in a second phase, the UAV collects data from the IoT devices through information transmission. We formulate a Markov decision process and propose two deep reinforcement learning algorithms to solve the optimization problem of maximizing the total network sum-rate.
  arXiv  Detail & Related papers  (2021-08-05T23:55:44Z)
• Trajectory Design for UAV-Based Internet-of-Things Data Collection: A Deep Reinforcement Learning Approach [93.67588414950656]
  In this paper, we investigate an unmanned aerial vehicle (UAV)-assisted Internet-of-Things (IoT) system in a 3D environment. We present a TD3-based trajectory design for completion time minimization (TD3-TDCTM) algorithm. Our simulation results show the superiority of the proposed TD3-TDCTM algorithm over three conventional non-learning based baseline methods.
  arXiv  Detail & Related papers  (2021-07-23T03:33:29Z)
• 3D UAV Trajectory and Data Collection Optimisation via Deep Reinforcement Learning [75.78929539923749]
  Unmanned aerial vehicles (UAVs) are now beginning to be deployed for enhancing the network performance and coverage in wireless communication. It is challenging to obtain an optimal resource allocation scheme for the UAV-assisted Internet of Things (IoT) In this paper, we design a new UAV-assisted IoT systems relying on the shortest flight path of the UAVs while maximising the amount of data collected from IoT devices.
  arXiv  Detail & Related papers  (2021-06-06T14:08:41Z)
• Privacy-Preserving Federated Learning for UAV-Enabled Networks: Learning-Based Joint Scheduling and Resource Management [45.15174235000158]
  Unmanned aerial vehicles (UAVs) are capable of serving as flying base stations (BSs) for supporting data collection, artificial intelligence (AI) model training, and wireless communications. It is impractical to send raw data of devices to UAV servers for model training. In this paper, we develop an asynchronous federated learning framework for multi-UAV-enabled networks.
  arXiv  Detail & Related papers  (2020-11-28T18:58:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.