Abstract

The demand for technologies relying on the radio spectrum, such as mobile communications and IoT, has been growing exponentially. As a consequence, providing access to the radio spectrum is becoming increasingly more important. The ever-growing wireless traffic and the increasing scarcity of available spectrum warrants efficient management of the radio spectrum. At the same time, machine learning (ML) is becoming ubiquitous and has found applications in many fields for its ability to identify patterns and assist with decision-making processes. Recently, machine learning algorithms have been used to address challenges in the wireless communications domain, such as radio spectrum sensing, and have shown better performance than traditional sensing methods, such as energy detection. Spectrum sensing, a method for detecting and identifying different wireless signals being transmitted in the same band of the radio spectrum, is crucial for improving dynamic spectrum sharing, which has the potential to enhance sharing and coexistence of different wireless technologies in the same frequency band and ultimately improve spectrum efficiency. To this end, this research evaluates different types of autoencoders, such as deep, variational and Long Short-Term Memory (LSTM) autoencoders, to identify and differentiate between LTE and Wi-Fi transmissions. The goal is to investigate the performance of the different types of autoencoders on an I/Q dataset consisting of LTE and a combination of Wi-Fi signals (IEEE 802.11ax and IEEE 802.11ac) for the classification task in terms of complexity, precision, and recall to identify the best algorithm. Our models have achieved up to 99.9% precision and 88.1% recall for this classification task. Additionally, with a shortest training time of approximately 47 seconds, the models are suitable for online learning and deployment in a dynamic RF environment.

Highlights

  • T HE number of wireless devices has grown exponentially over the last decade

  • The goal was to identify WiFi transmissions in a spectrum shared by Long Term Evolution (LTE) and Wi-Fi to enable efficient spectrum sharing between the two technologies

  • Wi-Fi datasets with two protocols, IEEE 802.11ax and IEEE 802.11ac, and various Modulation and Coding Scheme (MCS) indices were tested against LTE signals captured using a Universal Software Radio Peripheral (USRP) B210

Read more

Summary

INTRODUCTION

T HE number of wireless devices has grown exponentially over the last decade. More than 30 billion wireless devices were connected to the internet in 2018 and the number is expected to have risen to more than 50 billion in 2020 [1]. Coexistence in the radio spectrum is a crucial aspect and its efficient management is necessary for enabling large numbers of wireless devices and different wireless technologies to coexist. For this reason, researchers have been working on new paradigms to improve the efficiency of radio spectrum management. Most research so far focuses on classifying the signals based on its modulation type, with radio access technology (RAT) classification becoming more common in recent publications. Research has shown that autoencoders are a highly adaptable method for identifying anomalous signals [10] but can be used to pre-train neural networks [11] to further improve classification results in supervised models

RELATED WORK
MACHINE LEARNING
DEEP AUTOENCODER
MODEL IMPLEMENTATION DETAILS
RESULTS
Results
CONCLUSION AND FUTURE WORK

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.