Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

UAV-Assisted Joint Data Collection and Wireless Power Transfer for Batteryless Sensor Networks

Wen Zhang, Aimin Wang, Geng Sun, Jiahui Li, Jiacheng Wang, Changyuan Zhao, Dusit Niyato

TL;DR

This work addresses the challenge of conductive data collection and wireless power transfer for batteryless sensor networks in remote areas using a UAV-enabled platform. It casts the problem as a dynamic, multi-objective optimization that jointly optimizes UAV transmit power and trajectory, aiming to maximize data volume and fairness while minimizing UAV energy, expressed as $f = \sum_{t=1}^{T} \left(-\alpha E[t] + \beta D[t] + \gamma F[t]\right)$. To solve the non-convex, time-varying problem, the authors develop SAC-PP, a DRL method that enhances Soft Actor-Critic with prioritized experience replay and the Performer attention mechanism to handle long horizons and sample efficiency. Simulation results show SAC-PP outperforms TD3, TQC, PPO, and SAC baselines in cumulative reward, data volume, fairness, and energy efficiency, demonstrating the approach’s practical viability for remote sensing with mobile WPT. This framework enables sustainable, low-maintenance operation of batteryless sensors by leveraging UAV-mounted WPT to support robust data collection in challenging environments, with potential extensions to multi-UAV setups and more realistic channel models.

Abstract

The development of wireless power transfer (WPT) and Internet of Things (IoT) offers significant potential but faces challenges such as limited energy supply, dynamic environmental changes, and unstable transmission links. This paper presents an unmanned aerial vehicle (UAV)-assisted data collection and WPT scheme to support batteryless sensor (BLS) networks in remote areas. In this system, BLSs harvest energy from the UAV and utilize the harvested energy to transmit the collected data back to the UAV. The goal is to maximize the collected data volume and fairness index while minimizing the UAV energy consumption. To achieve these objectives, an optimization problem is formulated to jointly optimize the transmit power and UAV trajectory. Due to the non-convexity and dynamic nature of the problem, a deep reinforcement learning (DRL)-based algorithm is proposed to solve the problem. Specifically, this algorithm integrates prioritized experience replay and the performer module to enhance system stability and accelerate convergence. Simulation results demonstrate that the proposed approach consistently outperforms benchmark schemes in terms of collected data volume, fairness, and UAV energy consumption.

UAV-Assisted Joint Data Collection and Wireless Power Transfer for Batteryless Sensor Networks

TL;DR

This work addresses the challenge of conductive data collection and wireless power transfer for batteryless sensor networks in remote areas using a UAV-enabled platform. It casts the problem as a dynamic, multi-objective optimization that jointly optimizes UAV transmit power and trajectory, aiming to maximize data volume and fairness while minimizing UAV energy, expressed as . To solve the non-convex, time-varying problem, the authors develop SAC-PP, a DRL method that enhances Soft Actor-Critic with prioritized experience replay and the Performer attention mechanism to handle long horizons and sample efficiency. Simulation results show SAC-PP outperforms TD3, TQC, PPO, and SAC baselines in cumulative reward, data volume, fairness, and energy efficiency, demonstrating the approach’s practical viability for remote sensing with mobile WPT. This framework enables sustainable, low-maintenance operation of batteryless sensors by leveraging UAV-mounted WPT to support robust data collection in challenging environments, with potential extensions to multi-UAV setups and more realistic channel models.

Abstract

The development of wireless power transfer (WPT) and Internet of Things (IoT) offers significant potential but faces challenges such as limited energy supply, dynamic environmental changes, and unstable transmission links. This paper presents an unmanned aerial vehicle (UAV)-assisted data collection and WPT scheme to support batteryless sensor (BLS) networks in remote areas. In this system, BLSs harvest energy from the UAV and utilize the harvested energy to transmit the collected data back to the UAV. The goal is to maximize the collected data volume and fairness index while minimizing the UAV energy consumption. To achieve these objectives, an optimization problem is formulated to jointly optimize the transmit power and UAV trajectory. Due to the non-convexity and dynamic nature of the problem, a deep reinforcement learning (DRL)-based algorithm is proposed to solve the problem. Specifically, this algorithm integrates prioritized experience replay and the performer module to enhance system stability and accelerate convergence. Simulation results demonstrate that the proposed approach consistently outperforms benchmark schemes in terms of collected data volume, fairness, and UAV energy consumption.
Paper Structure (15 sections, 13 equations, 3 figures, 1 algorithm)

This paper contains 15 sections, 13 equations, 3 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. Network Model
  4. WPT Model
  5. Wireless Data Collection Model
  6. UAV Mobile and Energy Cost Models
  7. Problem Formulation
  8. DRL-based approach
  9. MDP Formulation
  10. SAC Algorithm
  11. SAC-PP
  12. SImulation Results and Analysis
  13. Simulation Setups
  14. Optimization Results
  15. Conclusion

Figures (3)

  • Figure 1: UAV-assisted joint data collection and WPT system for a BLS network. The UAV first charges BLSs within its distance threshold through WPT. BLSs perform sensing and monitoring tasks, and utilize the harvested energy to transmit the collected data back to the UAV using a multiple access scheme.
  • Figure 2: The framework of the SAC-PP algorithm.
  • Figure 3: (a) Cumulative rewards training curve. (b) Average data collected [bits]. (c) Average energy consumption [J]. (d) Average fairness index.