Improved Layered Normalized Min-Sum Algorithm for 5G NR LDPC

Layered Normalised Min-Sum algorithm is a widely used message passing algorithm for decoding Low Density Parity Check codes. The decoding performance heavily depends on the normalisation factor. Firstly, we leverage the bit structure present in 5G transport blocks to develop an improved decoding alg...

Full description

Saved in:
Bibliographic Details
Published in:IEEE wireless communications letters Vol. 11; no. 9; pp. 2015 - 2018
Main Authors: Jayawickrama, Beeshanga Abewardana, He, Ying
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.09.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
5G mobile communication
Algorithms
Artificial neural networks
Decoding
Error correcting codes
Hardware
Iterative decoding
Low density parity check codes
Maximum likelihood decoding
Message passing
neural networks
Performance evaluation
Signal to noise ratio
Training
ISSN:2162-2337, 2162-2345
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Layered Normalised Min-Sum algorithm is a widely used message passing algorithm for decoding Low Density Parity Check codes. The decoding performance heavily depends on the normalisation factor. Firstly, we leverage the bit structure present in 5G transport blocks to develop an improved decoding algorithm for 5G. Secondly, we determine the optimal normalisation factors of the proposed algorithm using a Deep Neural Network. Performance evaluations show an improvement of 0.3-1.9 dB, with no extra cost on multiplier resources on hardware. Hence, the proposed method is highly attractive for practical 5G decoder implementations.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2162-2337
2162-2345
DOI:10.1109/LWC.2022.3192518