Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Federated Learning for UAV-Based Spectrum Sensing: Enhancing Accuracy Through SNR-Weighted Model Aggregation

Kürşat Tekbıyık, Güneş Karabulut Kurt, Antoine Lesage-Landry

TL;DR

A federated learning (FL)-based method for spectrum sensing in UAV networks to account for their distributed nature and limited computational capacity is proposed and a federated aggregation method is developed that considers the signal-to-noise ratio observed by UAVs to acquire a global model.

Abstract

The increasing demand for data usage in wireless communications requires using wider bands in the spectrum, especially for backhaul links. Yet, allocations in the spectrum for non-communication systems inhibit merging bands to achieve wider bandwidth. To overcome this issue, spectrum-sharing or opportunistic spectrum utilization by secondary users stands out as a promising solution. However, both approaches must minimize interference to primary users. Therefore, spectrum sensing becomes vital for such opportunistic usage, ensuring the proper operation of the primary users. Although this problem has been investigated for 2D networks, unmanned aerial vehicle (UAV) networks need different points of view concerning 3D space, its challenges, and opportunities. For this purpose, we propose a federated learning (FL)-based method for spectrum sensing in UAV networks to account for their distributed nature and limited computational capacity. FL enables local training without sharing raw data while guaranteeing the privacy of local users,lowering communication overhead, and increasing data diversity. Furthermore, we develop a federated aggregation method, namely FedSNR, that considers the signal-to-noise ratio observed by UAVs to acquire a global model. The numerical results show that the proposed architecture and the aggregation method outperform traditional methods.

Federated Learning for UAV-Based Spectrum Sensing: Enhancing Accuracy Through SNR-Weighted Model Aggregation

TL;DR

A federated learning (FL)-based method for spectrum sensing in UAV networks to account for their distributed nature and limited computational capacity is proposed and a federated aggregation method is developed that considers the signal-to-noise ratio observed by UAVs to acquire a global model.

Abstract

The increasing demand for data usage in wireless communications requires using wider bands in the spectrum, especially for backhaul links. Yet, allocations in the spectrum for non-communication systems inhibit merging bands to achieve wider bandwidth. To overcome this issue, spectrum-sharing or opportunistic spectrum utilization by secondary users stands out as a promising solution. However, both approaches must minimize interference to primary users. Therefore, spectrum sensing becomes vital for such opportunistic usage, ensuring the proper operation of the primary users. Although this problem has been investigated for 2D networks, unmanned aerial vehicle (UAV) networks need different points of view concerning 3D space, its challenges, and opportunities. For this purpose, we propose a federated learning (FL)-based method for spectrum sensing in UAV networks to account for their distributed nature and limited computational capacity. FL enables local training without sharing raw data while guaranteeing the privacy of local users,lowering communication overhead, and increasing data diversity. Furthermore, we develop a federated aggregation method, namely FedSNR, that considers the signal-to-noise ratio observed by UAVs to acquire a global model. The numerical results show that the proposed architecture and the aggregation method outperform traditional methods.

Paper Structure

This paper contains 8 sections, 9 equations, 6 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. Federated Learning for Spectrum Sensing
  4. Federated Aggregation
  5. Edge Model Architecture
  6. Dataset Generation and Training
  7. Results and Discussions
  8. Concluding Remarks

Figures (6)

  • Figure 1: Distributed UAVs network employing FL for spectrum sensing.
  • Figure 2: Illustration of edge model architecture consisting of two convolutional layers and several regularizations.
  • Figure 3: Sensing accuracy under different transmit power. The green plot shows the average accuracy of independently trained and tested edge models. The shadowed regions represent $95\%$ confidence intervals.
  • Figure 4: Spectrum sensing accuracy under varying number of UAVs.
  • Figure 5: Impact of Rician fading parameter $K$ on spectrum sensing accuracy.
  • ...and 1 more figures