Artificial neural network design for improved spectrum sensing in cognitive radio
- PDF / 2,172,242 Bytes
- 20 Pages / 595.276 x 790.866 pts Page_size
- 64 Downloads / 214 Views
(0123456789().,-volV) (0123456789().,-volV)
Artificial neural network design for improved spectrum sensing in cognitive radio Dhaval K. Patel1 • Miguel Lo´pez-Benı´tez2,3 • Brijesh Soni1
•
A´ngel F. Garcı´a-Ferna´ndez2,3
Ó Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Dynamic Spectrum Access/Cognitive Radio systems access the channel in an opportunistic, non-interfering manner with the primary network. These systems utilize spectrum sensing techniques to sense the occupancy of the primary user. In this paper, an artificial neural network based hybrid spectrum sensing technique is proposed, which considers sensing as a binary classification problem to detect whether the primary user is idle or busy. The proposed scheme utilizes energy detection and likelihood ratio test statistic as features to train the neural network. Moreover, we demonstrate the impact of hyperparameter tuning and carry out the detailed study of it, yielding a combination of best-suited hyperparameters. The performance of the proposed sensing scheme is validated on primary signals of various real world radio technologies acquired with an empirical testbed setup. We conclude that the best performing configuration results in an increase of approximately 63% in detection performance compared to classical energy detection and improved energy detection sensing schemes when averaged over all the radio technologies considered in this work. Keywords Artificial neural network Hyperparameter tuning Cognitive radio Spectrum sensing
1 Introduction 1.1 Background With the expeditious advancement of wireless communication technologies and the advent of 5G massive multiple input multiple output (MIMO) systems, spectrum resources are becoming highly scarce [1]. As per the spectrum & Brijesh Soni [email protected] Dhaval K. Patel [email protected] Miguel Lo´pez-Benı´tez [email protected] ´ ngel F. Garcı´a-Ferna´ndez A [email protected] 1
School of Engineering and Applied Science, Ahmedabad University, Ahmedabad, India
2
Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, UK
3
ARIES Research Centre, Antonio de Nebrija University, Madrid, Spain
occupancy campaign in 2016, the overall usage of spectrum ranges from 7 to 34%, which demonstrates significant under-utilization of the spectrum resources [2]. Evidently, the conventional fixed spectrum allocation policy is not optimal. Hence, the spectrum allocation needs to be dynamic for efficient usage and opportunistic access of the spectrum band. Dynamic Spectrum Access/Cognitive Radio (DSA/CR) is envisaged as a promising solution to alleviate this existing conflict between increasing spectrum demand and spectrum under-utilization [3]. DSA/CR systems aims at increasing the efficiency of spectrum usage by allowing unlicensed or secondary users (SUs) to opportunistically access licensed spectrum bands temporarily unused by the licensed or primary users (PUs) in a non-interfering manne
Data Loading...
