Decoder-in-the-Loop: Genetic Optimization-Based LDPC Code Design

LDPC code design tools typically rely on asymptotic code behavior and are affected by an unavoidable performance degradation due to model imperfections in the short length regime. We propose an LDPC code design scheme based on an evolutionary algorithm, the Genetic Algorithm (GenAlg), implementing a...

Full description

Bibliographic Details
Main Authors: Ahmed Elkelesh, Moustafa Ebada, Sebastian Cammerer, Laurent Schmalen, Stephan ten Brink
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8846017/
id doaj-a65b88d6b4d545dfac1d095ed2cdc97b
record_format Article
spelling doaj-a65b88d6b4d545dfac1d095ed2cdc97b2021-03-29T23:55:23ZengIEEEIEEE Access2169-35362019-01-01714116114117010.1109/ACCESS.2019.29429998846017Decoder-in-the-Loop: Genetic Optimization-Based LDPC Code DesignAhmed Elkelesh0https://orcid.org/0000-0003-1711-0233Moustafa Ebada1https://orcid.org/0000-0003-4224-1665Sebastian Cammerer2https://orcid.org/0000-0002-7614-5156Laurent Schmalen3https://orcid.org/0000-0002-1459-9128Stephan ten Brink4https://orcid.org/0000-0003-1502-2571Institute of Telecommunications, University of Stuttgart, Stuttgart, GermanyInstitute of Telecommunications, University of Stuttgart, Stuttgart, GermanyInstitute of Telecommunications, University of Stuttgart, Stuttgart, GermanyCommunications Engineering Lab, Karlsruhe Institute of Technology, Karlsruhe, GermanyInstitute of Telecommunications, University of Stuttgart, Stuttgart, GermanyLDPC code design tools typically rely on asymptotic code behavior and are affected by an unavoidable performance degradation due to model imperfections in the short length regime. We propose an LDPC code design scheme based on an evolutionary algorithm, the Genetic Algorithm (GenAlg), implementing a &#x201C;decoder-in-the-loop&#x201D; concept. It inherently takes into consideration the channel, code length and the number of iterations while optimizing the error-rate of the actual decoder hardware architecture. We construct short length LDPC codes (i.e., the parity-check matrix) with error-rate performance comparable to, or even outperforming that of well-designed standardized short length LDPC codes over both AWGN and Rayleigh fading channels. Our proposed algorithm can be used to design LDPC codes with special graph structures (e.g., accumulator-based codes) to facilitate the encoding step, or to satisfy any other practical requirement. Moreover, GenAlg can be used to design LDPC codes with the aim of reducing decoding latency and complexity, leading to coding gains of up to 0.325 dB and 0.8 dB at BLER of 10<sup>-5</sup> for both AWGN and Rayleigh fading channels, respectively, when compared to state-of-the-art short LDPC codes. Also, we analyze what can be learned from the resulting codes and, as such, the GenAlg particularly highlights design paradigms of short length LDPC codes (e.g., codes with degree-1 variable nodes obtain very good results).https://ieeexplore.ieee.org/document/8846017/LDPC codesbelief propagation decodingshort LDPC code designEXIT chartsgenetic algorithmevolutionary algorithms
collection DOAJ
language English
format Article
sources DOAJ
author Ahmed Elkelesh
Moustafa Ebada
Sebastian Cammerer
Laurent Schmalen
Stephan ten Brink
spellingShingle Ahmed Elkelesh
Moustafa Ebada
Sebastian Cammerer
Laurent Schmalen
Stephan ten Brink
Decoder-in-the-Loop: Genetic Optimization-Based LDPC Code Design
IEEE Access
LDPC codes
belief propagation decoding
short LDPC code design
EXIT charts
genetic algorithm
evolutionary algorithms
author_facet Ahmed Elkelesh
Moustafa Ebada
Sebastian Cammerer
Laurent Schmalen
Stephan ten Brink
author_sort Ahmed Elkelesh
title Decoder-in-the-Loop: Genetic Optimization-Based LDPC Code Design
title_short Decoder-in-the-Loop: Genetic Optimization-Based LDPC Code Design
title_full Decoder-in-the-Loop: Genetic Optimization-Based LDPC Code Design
title_fullStr Decoder-in-the-Loop: Genetic Optimization-Based LDPC Code Design
title_full_unstemmed Decoder-in-the-Loop: Genetic Optimization-Based LDPC Code Design
title_sort decoder-in-the-loop: genetic optimization-based ldpc code design
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2019-01-01
description LDPC code design tools typically rely on asymptotic code behavior and are affected by an unavoidable performance degradation due to model imperfections in the short length regime. We propose an LDPC code design scheme based on an evolutionary algorithm, the Genetic Algorithm (GenAlg), implementing a &#x201C;decoder-in-the-loop&#x201D; concept. It inherently takes into consideration the channel, code length and the number of iterations while optimizing the error-rate of the actual decoder hardware architecture. We construct short length LDPC codes (i.e., the parity-check matrix) with error-rate performance comparable to, or even outperforming that of well-designed standardized short length LDPC codes over both AWGN and Rayleigh fading channels. Our proposed algorithm can be used to design LDPC codes with special graph structures (e.g., accumulator-based codes) to facilitate the encoding step, or to satisfy any other practical requirement. Moreover, GenAlg can be used to design LDPC codes with the aim of reducing decoding latency and complexity, leading to coding gains of up to 0.325 dB and 0.8 dB at BLER of 10<sup>-5</sup> for both AWGN and Rayleigh fading channels, respectively, when compared to state-of-the-art short LDPC codes. Also, we analyze what can be learned from the resulting codes and, as such, the GenAlg particularly highlights design paradigms of short length LDPC codes (e.g., codes with degree-1 variable nodes obtain very good results).
topic LDPC codes
belief propagation decoding
short LDPC code design
EXIT charts
genetic algorithm
evolutionary algorithms
url https://ieeexplore.ieee.org/document/8846017/
work_keys_str_mv AT ahmedelkelesh decoderintheloopgeneticoptimizationbasedldpccodedesign
AT moustafaebada decoderintheloopgeneticoptimizationbasedldpccodedesign
AT sebastiancammerer decoderintheloopgeneticoptimizationbasedldpccodedesign
AT laurentschmalen decoderintheloopgeneticoptimizationbasedldpccodedesign
AT stephantenbrink decoderintheloopgeneticoptimizationbasedldpccodedesign
_version_ 1724188903572766720