CSIT: channel state and idle time predictor using a neural network for cognitive LTE-Advanced network

Abstract

Cognitive radio (CR) is a novel methodology that facilitates unlicensed users to share a licensed spectrum without interfering with licensed users. This intriguing approach is exploited in the Long Term Evolution-Advanced (LTE-A) network for performance improvement. Although LTE-A is the foremost mobile communication standard, future underutilization of the spectrum needs to be addressed. Therefore, dynamic spectrum access is explored in this study. The performance of CR in LTE-A can significantly be enhanced by employing predictive modeling. The neural network-based channel state and idle time (CSIT) predictor is proposed in this article as a learning scheme for CR in LTE-A. This predictive-based learning is helpful in two ways: sensing only those channels that are predicted to be idle and selecting the channels for CR transmission that have the largest predicted idle time. The performance gains by exploiting CSIT prediction in CR LTE-A network are evaluated in terms of spectrum utilization, sensing energy, channel switching rate, packet loss ratio, and average instantaneous throughput. The results illustrate that significant performance is achieved by employing CSIT prediction in LTE-A network.

Immuno-neural network for spectrum prediction

“…A reduction in the MGL increases the SU spectrum utilization and user throughput for a fixed MGRP. This paper addresses this problem and extends existing work [5] by designing a scheme that reduces the MGL/ISAT to improve the SU spectrum utilization and throughput in the cognitive LTE-Advanced network. The reduction of the ISAT is beneficial to applications using the window based transmission control protocol (TCP).…”

“…Shahid et al [5] propose the use of a multilayer perceptron neural network for spectrum prediction in the cognitive LTE-A. The presented results in their work show that using the neural network for spectrum prediction reduces the collision rate between SUs and PUs in the LTE-A network, improves throughput, spectrum utilization and reduces the channel switching rate for SUs.…”

“…The presented results in their work show that using the neural network for spectrum prediction reduces the collision rate between SUs and PUs in the LTE-A network, improves throughput, spectrum utilization and reduces the channel switching rate for SUs. However, in [5] the SU is required to learn about new channels using the neural network whenever the SU moves in the network either via spectrum sensing or docitively. This learning requirement necessitate that the secondary user undergo the input sample acquisition time each time it changes its channel.…”

Optimized Energy Harvesting, Cluster-Head Selection and Channel Allocation for IoTs in Smart Cities

“…Therefore, to support such a massive number of devices and to provide them their desired throughput, a highly spectral efficient technique is required to address this issue. A possible way for accomplishing this is to extend the operating frequency using cognitive radio (CR) technology [32,33,34,35]. The CR is an intelligent radio that learns, decides and reconfigures itself according to the available portion of the spectrum [36].…”

Energy Efficient Doppler Assisted Channel Estimation for Highly Mobile OFDM Systems

“…On the other hand, circuit energy also plays an important role in the lifetime of the battery operated nodes. Therefore, many authors [9][10][11][12][13][14][15][16] have considered circuit energy while assessing the energy efficiency of different schemes. The solutions discussed above only consider the transmission energy and do not take into account the circuit energy.…”