Neural network approach for component carrier selection in 4G/5G networks

In order to ensure high transmission rate to a wide range of voice, video and data services, carrier aggregation (CA) has been introduced in the Long Term Evolution Advanced (LTE-A). Moreover, CA is one of the principal enabling technologies for the 5G. Indeed, 4G and 5G can aggregate up to five com...

Full description

Saved in:
Bibliographic Details
Published in2018 Fifth International Conference on Software Defined Systems (SDS) pp. 112 - 117
Main Authors Khdhir, Radhia, Cousin, Bernard, Mnif, Kais, Ben Ali, Khitem
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.04.2018
Subjects
4G/5G cellular network
5G mobile communication
Bandwidth
Carrier Aggregation
Component Carrier selection
Interference
Neural networks
Resource management
Signal to noise ratio
Throughput
Online AccessGet full text

Cover

More Information
Summary:In order to ensure high transmission rate to a wide range of voice, video and data services, carrier aggregation (CA) has been introduced in the Long Term Evolution Advanced (LTE-A). Moreover, CA is one of the principal enabling technologies for the 5G. Indeed, 4G and 5G can aggregate up to five component carriers (CC), simultaneously, to support a higher bandwidth. In this context, CC selection method is necessary. In this paper, we propose a new CC selection method in order to maximize the global system throughput. Neural network approach is introduced to select the best couple user-CC via a utility function. Simulation results prove that the proposed method outperforms in terms of system throughput, fairness and packet loss rate.
DOI:10.1109/SDS.2018.8370431