Spectrum Sensing with Deep Clustering: Label-Free Radio Access Technology Recognition

TL;DR

This paper introduces a label-free deep clustering approach for spectrum sensing that autonomously recognizes radio access technologies in complex environments, reducing the need for labeled data and outperforming existing supervised methods.

Contribution

It presents a novel unsupervised deep clustering architecture for RAT recognition, enabling spectrum sensing without prior labeled data and demonstrating superior performance on real-world datasets.

Findings

Achieves up to 35 percentage points higher accuracy

Uses 22% fewer trainable parameters

Requires 50% less FLOPS compared to state-of-the-art methods

Abstract

The growth of the number of connected devices and network densification is driving an increasing demand for radio network resources, particularly Radio Frequency (RF) spectrum. Given the dynamic and complex nature of contemporary wireless environments, characterized by a wide variety of devices and multiple RATs, spectrum sensing is envisioned to become a building component of future 6G, including as a component within O-RAN or digital twins. However, the current SotA research for RAT classification predominantly revolves around supervised Convolutional Neural Network (CNN)-based approach that require extensive labeled dataset. Due to this, it is unclear how existing models behave in environments for which training data is unavailable thus leaving open questions regarding their generalization capabilities. In this paper, we propose a new spectrum sensing workflow in which the model training does not require any prior knowledge of the RATs transmitting in that area (i.e. no labelled data) and the class assignment can be easily done through manual mapping. Furthermore, we adapt a SSL deep clustering architecture capable of autonomously extracting spectrum features from raw 1D Fast Fourier Transform (FFT) data. We evaluate the proposed architecture on three real-world datasets from three European cities, in the 868 MHz, 2.4 GHz and 5.9 GHz bands containing over 10 RATs and show that the developed model achieves superior performance by up to 35 percentage points with 22% fewer trainable parameters and 50% less floating-point operations per second (FLOPS) compared to an SotA AE-based reference architecture.