A Novel Machine Learning Approach for Link Adaptation in 5G Wireless Networks

This study addresses a Machine Learning (ML) based Link Adaptation (LA) scheme for 5G New Radio (NR) wireless networks, which aims to improve the system throughput by selecting the best possible choice of the Modulation Coding Scheme (MCS). This work proposes a Deep Neural Network(DNN) based regress...

Full description

Saved in:

Bibliographic Details
Published in:	2020 2nd PhD Colloquium on Ethically Driven Innovation and Technology for Society (PhD EDITS) pp. 1 - 2
Main Authors:	Pati, Preeti Samhita, Sahoo, Shubham Somnath, Krishnaswamy, Dilip, Datta, Raja
Format:	Conference Proceeding
Language:	English
Published:	IEEE 08.11.2020
Subjects:	Adaptation models Deep Neural Network (DNN) Interference Link Adaptation (LA) Mathematical model Modulation Modulation Coding Scheme (MCS) Signal to noise ratio Training data Wireless networks
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	This study addresses a Machine Learning (ML) based Link Adaptation (LA) scheme for 5G New Radio (NR) wireless networks, which aims to improve the system throughput by selecting the best possible choice of the Modulation Coding Scheme (MCS). This work proposes a Deep Neural Network(DNN) based regression model to maximize the Spectral Efficiency (SE) of the system under the 10% Block Error Rate (BLER) and thus finding the best MCS. We consider a 5G NR Frequency Range-1(FR-1), i.e., the Sub-6GHz operating band for the study. Our simulation results show the mapping of Signal to Interference and Noise Ratio (SINR) to the Channel Quality Indicator (CQI) and thus the best possible selection of modulation and coding scheme in case of perfect channel estimation based system which is found to improve the system throughput.
DOI:	10.1109/PhDEDITS51180.2020.9315299