Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AUV Trajectory Learning for Underwater Acoustic Energy Transfer and Age Minimization

Mohamed Afouene Melki, Mohammad Shehab, Mohamed-Slim Alouini

TL;DR

The paper tackles sustainable IoUT by enabling simultaneous acoustic energy transfer and information uplink through an AUV, while explicitly minimizing data freshness via AoI and promoting fairness with Jain's index. It introduces two DRL-based trajectory/scheduling schemes: a high-performance frequency-division duplexing (FDD) approach with two antennas and a lower‑complexity time-division duplexing (TDD) approach with a single antenna, both optimized through Proximal Policy Optimization. The methods demonstrate substantial improvements in average AoI, harvested energy, and data-collection fairness compared with baseline policies, with the FDD variant outperforming in energy and fairness and the TDD variant offering a favorable complexity-energy trade-off; the study also analyzes training energy and CO₂ emissions. The work lays a foundation for scalable, energy-efficient underwater IoUT networks and suggests future directions including multi-AUV systems and RIS-assisted energy/communication enhancements for dynamic environments.

Abstract

Internet of underwater things (IoUT) is increasingly gathering attention with the aim of monitoring sea life and deep ocean environment, underwater surveillance as well as maintenance of underwater installments. However, conventional IoUT devices, reliant on battery power, face limitations in lifespan and pose environmental hazards upon disposal. This paper introduces a sustainable approach for simultaneous information uplink from the IoUT devices and acoustic energy transfer (AET) to the devices via an autonomous underwater vehicle (AUV), potentially enabling them to operate indefinitely. To tackle the time-sensitivity, we adopt age of information (AoI), and Jain's fairness index. We develop two deep-reinforcement learning (DRL) algorithms, offering a high-complexity, high-performance frequency division duplex (FDD) solution and a low-complexity, medium-performance time division duplex (TDD) approach. The results elucidate that the proposed FDD and TDD solutions significantly reduce the average AoI and boost the harvested energy as well as data collection fairness compared to baseline approaches.

AUV Trajectory Learning for Underwater Acoustic Energy Transfer and Age Minimization

TL;DR

The paper tackles sustainable IoUT by enabling simultaneous acoustic energy transfer and information uplink through an AUV, while explicitly minimizing data freshness via AoI and promoting fairness with Jain's index. It introduces two DRL-based trajectory/scheduling schemes: a high-performance frequency-division duplexing (FDD) approach with two antennas and a lower‑complexity time-division duplexing (TDD) approach with a single antenna, both optimized through Proximal Policy Optimization. The methods demonstrate substantial improvements in average AoI, harvested energy, and data-collection fairness compared with baseline policies, with the FDD variant outperforming in energy and fairness and the TDD variant offering a favorable complexity-energy trade-off; the study also analyzes training energy and CO₂ emissions. The work lays a foundation for scalable, energy-efficient underwater IoUT networks and suggests future directions including multi-AUV systems and RIS-assisted energy/communication enhancements for dynamic environments.

Abstract

Internet of underwater things (IoUT) is increasingly gathering attention with the aim of monitoring sea life and deep ocean environment, underwater surveillance as well as maintenance of underwater installments. However, conventional IoUT devices, reliant on battery power, face limitations in lifespan and pose environmental hazards upon disposal. This paper introduces a sustainable approach for simultaneous information uplink from the IoUT devices and acoustic energy transfer (AET) to the devices via an autonomous underwater vehicle (AUV), potentially enabling them to operate indefinitely. To tackle the time-sensitivity, we adopt age of information (AoI), and Jain's fairness index. We develop two deep-reinforcement learning (DRL) algorithms, offering a high-complexity, high-performance frequency division duplex (FDD) solution and a low-complexity, medium-performance time division duplex (TDD) approach. The results elucidate that the proposed FDD and TDD solutions significantly reduce the average AoI and boost the harvested energy as well as data collection fairness compared to baseline approaches.
Paper Structure (35 sections, 54 equations, 8 figures, 4 tables, 1 algorithm)

This paper contains 35 sections, 54 equations, 8 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Contributions
  3. Outline
  4. System Model
  5. Network Model
  6. Channel Model
  7. Problem formulation
  8. Acoustic Energy Transfer and Information Uplink
  9. Acoustic Energy Transfer
  10. Information Uplink
  11. Age Of Information
  12. Duplexing Techniques
  13. Frequency-Division Duplexing
  14. Time-Division Duplexing
  15. Problem Formulation
  16. ...and 20 more sections

Figures (8)

  • Figure 1: AUV and IoUT network in the underwater grid world
  • Figure 2: AET and information uplink using FDD vs TDD
  • Figure 3: The interaction between the agent and the environment
  • Figure 4: Energy harvested and information uplink for different Values of $\beta$ and for frequency $f=40$ KHz.
  • Figure 5: Plot of $\beta^*$ as a function of $d^*$ for different frequencies
  • ...and 3 more figures

Theorems & Definitions (2)

  • Remark 1
  • Remark 2