Hybrid ARQ for URLLC Using Deep Learning

Narayan Prasad Kusi, Sung Hwan Ahn, Dong Ho Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study proposes early HARQ based on Deep learning techniques to predict the decodability of a received codeword early within few decoding iterations of the initial redundancy version(RV) of the codeword. The transmitter reacts with the transmission of the required RV versions in accordance with the feedback. System level simulation is performed for the performance analysis. The simulation shows the significant improvement of link throughput and reduction of delay in comparison to the traditional HARQ maintaining the BLER performance with traditional HARQ.

Original languageEnglish
Title of host publicationICTC 2024 - 15th International Conference on ICT Convergence
Subtitle of host publicationAI-Empowered Digital Innovation
PublisherIEEE Computer Society
Pages179-181
Number of pages3
ISBN (Electronic)9798350364637
DOIs
StatePublished - 2024
Event15th International Conference on Information and Communication Technology Convergence, ICTC 2024 - Jeju Island, Korea, Republic of
Duration: 16 Oct 202418 Oct 2024

Publication series

NameInternational Conference on ICT Convergence
ISSN (Print)2162-1233
ISSN (Electronic)2162-1241

Conference

Conference15th International Conference on Information and Communication Technology Convergence, ICTC 2024
Country/TerritoryKorea, Republic of
CityJeju Island
Period16/10/2418/10/24

Keywords

  • 5G NR
  • Adaptive HARQ
  • Deep Learning
  • IR-HARQ
  • Latency
  • LSTM
  • Reliability
  • URLLC

Fingerprint

Dive into the research topics of 'Hybrid ARQ for URLLC Using Deep Learning'. Together they form a unique fingerprint.

Cite this