Support Vector Machine Based Spectrum Sensing in Beyond 5G Wireless Networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The primary concern in 5G and beyond wireless technologies revolve around the exponentially growing number of network users and subsequently increasing demand for frequency spectrum utilization. Traditional static spectrum allocation schemes have proven to be highly inefficient in using the available spectrum. In recent years, Dynamic Spectrum Sharing (DSS) solutions based on Cognitive Radio (CR) and Artificial Intelligence (AI)/Machine Learning (ML) have been proposed. CR involves spectrum sensing, spectrum sharing and decision-making paradigms essential for efficient use of radio frequency spectrum. AI/ML techniques, with their autonomous classification, learning, and decision-making capabilities, offer an improved approach. This paper proposes a Support Vector Machine (SVM) based ML technique for spectrum sensing in beyond 5G networks. A theoretical examination of detection and false alarm probabilities is first conducted. It is shown that the SVM algorithm achieves a high probability of detection at 99.66%, ensuring reliable spectrum sensing. Further, it is verified through simulations that the experimental outcomes align closely with the theoretical results concerning both detection and false alarm probabilities.

Original languageEnglish
Title of host publicationProceedings - 11th International Conference on Wireless Networks and Mobile Communications, WINCOM 2024
EditorsSyed Ali Raza Zaidi, Khalil Ibrahimi, Mohamed El Kamili, Abdellatif Kobbane, Nauman Aslam
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages5
ISBN (Electronic)9798350377866
ISBN (Print)9798350377873
DOIs
Publication statusPublished - 5 Sep 2024
Event11th International Conference on Wireless Networks and Mobile Communications - Leeds, United Kingdom
Duration: 23 Jul 202425 Jul 2024
Conference number: 11

Publication series

NameInternational Conference on Wireless Networks and Mobile Communications, WINCOM 2024
PublisherIEEE
Volume2024
ISSN (Print)2769-9986
ISSN (Electronic)2769-9994

Conference

Conference11th International Conference on Wireless Networks and Mobile Communications
Abbreviated titleWINCOM 2024
Country/TerritoryUnited Kingdom
CityLeeds
Period23/07/2425/07/24

Cite this