PERFECT: Personalized Federated Learning for CBRS Radar Detection

TL;DR

PERFECT is a federated learning framework that enables privacy-preserving, personalized radar detection for CBRS band sensors, effectively handling non-IID data and matching centralized detection performance.

Contribution

It introduces a novel personalized federated learning approach for ESC sensors, improving privacy, efficiency, and scalability in radar detection amidst non-IID data.

Findings

Achieves 99% recall in radar detection, matching centralized models.

Effectively handles non-IID data through model personalization.

Enhances privacy and scalability in spectrum sharing applications.

Abstract

The Citizens Broadband Radio Service (CBRS) band is pivotal for expanding next-generation wireless services, but its success hinges on robustly protecting incumbent users, such as naval radar systems, from interference. This task is delegated to a network of Environmental Sensing Capability (ESC) sensors, which must detect faint radar signals amidst heavy co-channel interference from commercial LTE and 5G users. Traditional centralized detection models raise significant data privacy concerns and are ill-suited for the Non-Independent and Identically Distributed (non-IID) nature of data from geographically dispersed sensors. To overcome these limitations, we propose a novel Federated Learning (FL) framework PERFECT that leverages ESC level personalization for robust and efficient radar detection. PERFECT preserves privacy by training models locally on ESC sensors. Furthermore, our framework is the first to effectively handle non-IID scenarios through model personalization where different ESCs observe distinct radar types. We demonstrate through extensive simulations that PERFECT achieves the mandated 99% recall for radar detection, matching centralized performance while significantly enhancing privacy, efficiency, and scalability for dynamic spectrum sharing.