Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Low-Altitude UAV-Carried Movable Antenna for Joint Wireless Power Transfer and Covert Communications

Chuang Zhang, Geng Sun, Jiahui Li, Jiacheng Wang, Qingqing Wu, Dusit Niyato, Shiwen Mao, Tony Q. S. Quek

TL;DR

The paper tackles energy-limited IoT networks by enabling joint wireless power transfer and covert communications via a low-altitude UAV carrying a movable antenna. It introduces a MoE-SAC reinforcement learning framework with an action projection module to learn trajectories, beamforming, and antenna reconfigurations under covert constraints and propulsion energy considerations. The approach achieves higher IoT energy harvesting and covert data rates while reducing UAV energy consumption, outperforming conventional baselines and standard DRL methods. This work advances secure, energy-efficient UAV-assisted wireless systems with dynamic reconfigurability and constraint-aware learning, offering practical benefits for robust, covert IoT deployments.

Abstract

The proliferation of Internet of Things (IoT) networks has created an urgent need for sustainable energy solutions, particularly for the battery-constrained spatially distributed IoT nodes. While low-altitude uncrewed aerial vehicles (UAVs) employed with wireless power transfer (WPT) capabilities offer a promising solution, the line-of-sight channels that facilitate efficient energy delivery also expose sensitive operational data to adversaries. This paper proposes a novel low-altitude UAV-carried movable antenna-enhanced transmission system joint WPT and covert communications, which simultaneously performs energy supplements to IoT nodes and establishes transmission links with a covert user by leveraging wireless energy signals as a natural cover. Then, we formulate a multi-objective optimization problem that jointly maximizes the total harvested energy of IoT nodes and sum achievable rate of the covert user, while minimizing the propulsion energy consumption of the low-altitude UAV. To address the non-convex and temporally coupled optimization problem, we propose a mixture-of-experts-augmented soft actor-critic (MoE-SAC) algorithm that employs a sparse Top-K gated mixture-of-shallow-experts architecture to represent multimodal policy distributions arising from the conflicting optimization objectives. We also incorporate an action projection module that explicitly enforces per-time-slot power budget constraints and antenna position constraints. Simulation results demonstrate that the proposed approach significantly outperforms some baseline approaches and other state-of-the-art deep reinforcement learning algorithms.

Low-Altitude UAV-Carried Movable Antenna for Joint Wireless Power Transfer and Covert Communications

TL;DR

The paper tackles energy-limited IoT networks by enabling joint wireless power transfer and covert communications via a low-altitude UAV carrying a movable antenna. It introduces a MoE-SAC reinforcement learning framework with an action projection module to learn trajectories, beamforming, and antenna reconfigurations under covert constraints and propulsion energy considerations. The approach achieves higher IoT energy harvesting and covert data rates while reducing UAV energy consumption, outperforming conventional baselines and standard DRL methods. This work advances secure, energy-efficient UAV-assisted wireless systems with dynamic reconfigurability and constraint-aware learning, offering practical benefits for robust, covert IoT deployments.

Abstract

The proliferation of Internet of Things (IoT) networks has created an urgent need for sustainable energy solutions, particularly for the battery-constrained spatially distributed IoT nodes. While low-altitude uncrewed aerial vehicles (UAVs) employed with wireless power transfer (WPT) capabilities offer a promising solution, the line-of-sight channels that facilitate efficient energy delivery also expose sensitive operational data to adversaries. This paper proposes a novel low-altitude UAV-carried movable antenna-enhanced transmission system joint WPT and covert communications, which simultaneously performs energy supplements to IoT nodes and establishes transmission links with a covert user by leveraging wireless energy signals as a natural cover. Then, we formulate a multi-objective optimization problem that jointly maximizes the total harvested energy of IoT nodes and sum achievable rate of the covert user, while minimizing the propulsion energy consumption of the low-altitude UAV. To address the non-convex and temporally coupled optimization problem, we propose a mixture-of-experts-augmented soft actor-critic (MoE-SAC) algorithm that employs a sparse Top-K gated mixture-of-shallow-experts architecture to represent multimodal policy distributions arising from the conflicting optimization objectives. We also incorporate an action projection module that explicitly enforces per-time-slot power budget constraints and antenna position constraints. Simulation results demonstrate that the proposed approach significantly outperforms some baseline approaches and other state-of-the-art deep reinforcement learning algorithms.

Paper Structure

This paper contains 34 sections, 2 theorems, 38 equations, 6 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Low-altitude UAVs-enabled WPT and Covert Communication System Architectures
  4. Performance Metrics in WPT and Covert Communications
  5. Optimization Approaches
  6. System Model
  7. Scenario Description
  8. Channel Model
  9. Communication and WPT Models
  10. Low-altitude UAV Propulsion Energy Consumption Model
  11. Binary Hypothesis Testing at Warden
  12. Problem Formulation
  13. Covert Requirement
  14. Problem Formulation
  15. MoE-Augmented DRL-based Algorithm
  16. ...and 19 more sections

Key Result

Proposition 1

The optimal decision threshold for the Warden at time slot $t$ is determined as follows: where $\zeta_{0}(t)= \mathbf{h}_{\mathrm{w}}^{\mathrm{H}}(t) \mathbf{W}_{\mathrm{e}}(t)\mathbf{h}_{\mathrm{w}}(t) + \sigma_{\mathrm{w}}^{2}$. Moreover, $\varrho(t) = \frac{\zeta_{1}(t) - \zeta_{0}(t)}{\zeta_{0}(t)}$ wherein $\zeta_{1}(t)$ is calculated by $\mathbf{h}_{\mathrm{w}}^{\mathrm{H}}(t)(\ma

Figures (6)

  • Figure 1: Illustration of the low-altitude UAV-carried MA-enhanced transmission system for joint WPT and covert communications, where the low-altitude UAV is equipped with an MA and performs WPT to IoT nodes to ensure their operational sustainability, while establishing a covert communication link with a covert user to report upon its status. Beyond powering the IoT nodes, the WPT also serves as an active cover to mask the covert transmission.
  • Figure 2: Framework of the MoE-SAC algorithm for the considered low-altitude UAV-carried MA-enhanced transmission system for joint WPT and covert communications. 1 The MoE-SAC algorithm employs a sparse Top-K router to select the K experts with the highest expert weights. 2 A mixture-of-shallow-experts architecture composed of the selected K experts is adopted to jointly model multimodal policy distributions. 3 The sampled raw actions are projected through an action projection module to explicitly enforce per-time-slot power budget constraints and antenna position constraints.
  • Figure 3: Performance comparison from different approaches: (a) Total harvested energy of all IoT nodes per episode and (b) Sum achievable rate of the covert user per episode.
  • Figure 4: Training performance comparison of the proposed MoE-SAC algorithm against baseline algorithms: (a) Episode reward, (b) Total harvested energy of IoT nodes per episode, (c) Sum achievable rate of the covert user per episode, (d) Total propulsion energy consumption of the low-altitude UAV per episode, (e) Number of covert constraint violations per episode, and (f) Ratio of reaching the destination during the training.
  • Figure 5: Trajectory of the low-altitude UAV under the different algorithms.
  • ...and 1 more figures

Theorems & Definitions (4)

  • Proposition 1
  • proof
  • Proposition 2
  • proof