Efficient Spectrum Occupancy Prediction Exploiting Multidimensional Correlations through Composite 2D-LSTM Models.

Mehmet Ali Aygül,Hüseyin Arslan,Daniel Benevides Da Costa,Mehmet İzzet Sağlam,Hasan Fehmi Ateş,Mahmoud Nazzal

doi:10.3390/s21010135

Abstract

In cognitive radio systems, identifying spectrum opportunities is fundamental to efficiently use the spectrum. Spectrum occupancy prediction is a convenient way of revealing opportunities based on previous occupancies. Studies have demonstrated that usage of the spectrum has a high correlation over multidimensions, which includes time, frequency, and space. Accordingly, recent literature uses tensor-based methods to exploit the multidimensional spectrum correlation. However, these methods share two main drawbacks. First, they are computationally complex. Second, they need to re-train the overall model when no information is received from any base station for any reason. Different than the existing works, this paper proposes a method for dividing the multidimensional correlation exploitation problem into a set of smaller sub-problems. This division is achieved through composite two-dimensional (2D)-long short-term memory (LSTM) models. Extensive experimental results reveal a high detection performance with more robustness and less complexity attained by the proposed method. The real-world measurements provided by one of the leading mobile network operators in Turkey validate these results.

Highlights

Accommodating exploding data traffic is among one of the biggest challenges for the communication systems in the fifth-generation (5G) and beyond
The quality of a trained machine learning (ML) classifier model is shown in Figure 12 as in the training and testing losses and accuracies versus epochs for the spectrum occupancy prediction when the Taksim dataset is used with the 2D-long short-term memory (LSTM)
This paper has demonstrated the advantage of exploiting occupancy correlation over time, frequency, and space, for spectrum occupancy prediction

Summary

Introduction

Accommodating exploding data traffic is among one of the biggest challenges for the communication systems in the fifth-generation (5G) and beyond. In 5G networks, data rates will be multiplied by ten compared to fourth-generation [1], and latency will go down to one millisecond or less [2]. The ever-increasing demanding nature of higher rate communications causes an inherent gap with the scarcity of the available spectrum [3]. Cognitive radio (CR) is believed to be one of the key solutions to bridge this gap [4]. CR enables secondary users (SUs) to opportunistically use available spectrum bands (referred to as spectrum holes) unused by primary users (PUs) [5]. It is evident that this needs identification of spectrum usage states, in a process referred to as spectrum sensing

Objectives

Methods

Findings

Conclusion