Federated Learning-based Collaborative Wideband Spectrum Sensing and Scheduling for UAVs in UTM Systems

TL;DR

This work addresses the challenge of dynamic spectrum sensing and sharing for networked UAVs in UTM systems under spectrum scarcity. It proposes a data-driven framework built on federated learning with a novel pwFedAvg aggregation that weights clients by received signal power and integrates wireless data generation into the FL loop, followed by fusion of per-UAV sensing results and DDQN-based dynamic spectrum scheduling. A comprehensive, near-realistic synthetic I/Q dataset is generated using MATLAB LTE toolbox and ray-tracing to enable evaluation across multi-cell, multi-path environments, with extensive results comparing CL, LL, and FL (pwFedAvg) configurations and validating spectrum fusion. The contributions include a convergence analysis for pwFedAvg, a channel-aware FL approach, fusion-based inference improvements, and RL-based spectrum allocation, demonstrating practical viability for scalable UAV spectrum management in UTM contexts.

Abstract

In this paper, we propose a data-driven framework for collaborative wideband spectrum sensing and scheduling for networked unmanned aerial vehicles (UAVs), which act as the secondary users (SUs) to opportunistically utilize detected "spectrum holes". Our overall framework consists of three main stages. Firstly, in the model training stage, we explore dataset generation in a multi-cell environment and training a machine learning (ML) model using the federated learning (FL) architecture. Unlike the existing studies on FL for wireless that presume datasets are readily available for training, we propose a novel architecture that directly integrates wireless dataset generation, which involves capturing I/Q samples from over-the-air signals in a multi-cell environment, into the FL training process. Secondly, in the collaborative spectrum inference stage, we propose a collaborative spectrum fusion strategy that is compatible with the unmanned aircraft system traffic management (UTM) ecosystem. Finally, in the spectrum scheduling stage, we leverage reinforcement learning (RL) solutions to dynamically allocate the detected spectrum holes to the secondary users. To evaluate the proposed methods, we establish a comprehensive simulation framework that generates a near-realistic synthetic dataset using MATLAB LTE toolbox by incorporating base-station~(BS) locations in a chosen area of interest, performing ray-tracing, and emulating the primary users channel usage in terms of I/Q samples. This evaluation methodology provides a flexible framework to generate large spectrum datasets that could be used for developing ML/AI-based spectrum management solutions for aerial devices.

Figures (18)

• Figure 1: Unmanned Aircraft System Traffic Management (UTM) architecture showing the separation between Federal Aviation Administration (FAA) and industry developments; Flight Information Management System (FIMS).
• Figure 2: Envisioned FL system model in a Multi-cell wireless network with multiple UAVs.
• Figure 3: A zoomed in version of dataset generation plane of a Multi-cell wireless network with multiple UAVs.
• Figure 4: Multi-label classification using DNN.
• Figure 5: Joint spectrum inference and spectrum scheduling.