Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Semantic-Aware Dynamic and Distributed Power Allocation: a Multi-UAV Area Coverage Use Case

Hamidreza Mazandarani, Masoud Shokrnezhad, Tarik Taleb

TL;DR

This work tackles the problem of semantic-aware power allocation in a multi-UAV uplink network for area coverage. It introduces SAMA-D3QL, a multi-agent deep reinforcement learning framework with centralized training and distributed execution, tuned to maximize semantic data quality rather than raw bitrate. The approach demonstrates superior performance over bit-oriented and heuristic baselines, illustrating robust scalability across channel counts, fleet sizes, and dynamics, and highlighting the importance of reward design (PSNR-based) for task-oriented communication. The findings suggest practical impact for 6G aerial-terrestrial networks by enabling scalable, cooperative power control that enhances observation quality under interference and mobility.

Abstract

The advancement towards 6G technology leverages improvements in aerial-terrestrial networking, where one of the critical challenges is the efficient allocation of transmit power. Although existing studies have shown commendable performance in addressing this challenge, a revolutionary breakthrough is anticipated to meet the demands and dynamism of 6G. Potential solutions include: 1) semantic communication and orchestration, which transitions the focus from mere transmission of bits to the communication of intended meanings of data and their integration into the network orchestration process; and 2) distributed machine learning techniques to develop adaptable and scalable solutions. In this context, this paper introduces a power allocation framework specifically designed for semantic-aware networks. The framework addresses a scenario involving multiple Unmanned Aerial Vehicles (UAVs) that collaboratively transmit observations over a multi-channel uplink medium to a central server, aiming to maximise observation quality. To tackle this problem, we present the Semantic-Aware Multi-Agent Double and Dueling Deep Q-Learning (SAMA-D3QL) algorithm, which utilizes the data quality of observing areas as reward feedback during the training phase, thereby constituting a semantic-aware learning mechanism. Simulation results substantiate the efficacy and scalability of our approach, demonstrating its superior performance compared to traditional bit-oriented learning and heuristic algorithms.

Semantic-Aware Dynamic and Distributed Power Allocation: a Multi-UAV Area Coverage Use Case

TL;DR

This work tackles the problem of semantic-aware power allocation in a multi-UAV uplink network for area coverage. It introduces SAMA-D3QL, a multi-agent deep reinforcement learning framework with centralized training and distributed execution, tuned to maximize semantic data quality rather than raw bitrate. The approach demonstrates superior performance over bit-oriented and heuristic baselines, illustrating robust scalability across channel counts, fleet sizes, and dynamics, and highlighting the importance of reward design (PSNR-based) for task-oriented communication. The findings suggest practical impact for 6G aerial-terrestrial networks by enabling scalable, cooperative power control that enhances observation quality under interference and mobility.

Abstract

The advancement towards 6G technology leverages improvements in aerial-terrestrial networking, where one of the critical challenges is the efficient allocation of transmit power. Although existing studies have shown commendable performance in addressing this challenge, a revolutionary breakthrough is anticipated to meet the demands and dynamism of 6G. Potential solutions include: 1) semantic communication and orchestration, which transitions the focus from mere transmission of bits to the communication of intended meanings of data and their integration into the network orchestration process; and 2) distributed machine learning techniques to develop adaptable and scalable solutions. In this context, this paper introduces a power allocation framework specifically designed for semantic-aware networks. The framework addresses a scenario involving multiple Unmanned Aerial Vehicles (UAVs) that collaboratively transmit observations over a multi-channel uplink medium to a central server, aiming to maximise observation quality. To tackle this problem, we present the Semantic-Aware Multi-Agent Double and Dueling Deep Q-Learning (SAMA-D3QL) algorithm, which utilizes the data quality of observing areas as reward feedback during the training phase, thereby constituting a semantic-aware learning mechanism. Simulation results substantiate the efficacy and scalability of our approach, demonstrating its superior performance compared to traditional bit-oriented learning and heuristic algorithms.

Paper Structure

This paper contains 18 sections, 9 equations, 4 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Problem Statement
  3. System Model
  4. Problem Formulation
  5. Complexity Analysis
  6. Proposed Solution
  7. Action Space
  8. State Space
  9. Reward
  10. Architecture
  11. Evaluation
  12. Setup
  13. results
  14. Number of Channels
  15. Number of UAVs
  16. ...and 3 more sections

Figures (4)

  • Figure 1: A simple scenario featuring a single BS and two UAVs hovering in circular paths, transmitting their observations to the BS.
  • Figure 2: At time $t = 0$, three UAVs—denoted as $i$, $j$, and $k$—create a total of seven observing segments, such as $S_{{i, k}}^{0}$. The dashed red line represents the circular trajectory of UAV $i$, illustrating its path while observing the area.
  • Figure 3: Selected Image from the DOTA dataset xia2018dota, and its quantized versions with different bits.
  • Figure 4: Average PSNR values for observation scenes of UAVs per (A) Number of channels (B) Number of UAVs (C) UAV velocities. Each line is an average of results over 6 plane images. Shaded areas represent the standard deviation of the values.