PACE: Redundancy Engineering in RLNC for Low-Latency Communication

Sreekrishna Pandi, Frank Gabriel, Juan A. Cabrera, Simon Wunderlich, Martin Reisslein, Frank H.P. Fitzek

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Random linear network coding (RLNC) is attractive for data transfer as well as data storage and retrieval in complex and unreliable settings. The existing systematic RLNC approach first sends all source symbols in a generation without encoding followed by the coded redundant packets at the tail of the generation. This systematic tail RLNC achieves low delay when packet drops are rare; however, recovery of any dropped source symbol requires to wait for the coded packets at the end of the generation. We propose and evaluate a novel PACE RLNC approach that paces the transmissions of coded redundant packets throughout the generation of source symbols. The paced coded packets enable the recovery of dropped source symbols without waiting for the tail end of the generation. More specifically, we propose PACE-Uniform, which uniformly intersperses individual coded packets throughout the generation, and PACE-Burst, which intersperses bursts of code packets. Our extensive simulation evaluations indicate that PACE-Uniform significantly reduces the mean source symbol delay compared to tail RLNC, while achieving nearly the same loss probability. We also demonstrate the PACE-Burst generalizes the concept of pacing the redundant packet transmissions and can be flexibly tuned between PACE-Uniform and the conventional tail RLNC by controlling the number of coded packets in a burst.

Original languageEnglish (US)
JournalIEEE Access
DOIs
StateAccepted/In press - Aug 5 2017

Fingerprint

Linear networks
Network coding
Redundancy
Communication
Recovery
Data transfer
Data storage equipment

Keywords

  • Delay
  • Generation based network coding
  • Loss probability
  • Random Linear Network Coding (RLNC)
  • Scheduling

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Pandi, S., Gabriel, F., Cabrera, J. A., Wunderlich, S., Reisslein, M., & Fitzek, F. H. P. (Accepted/In press). PACE: Redundancy Engineering in RLNC for Low-Latency Communication. IEEE Access. https://doi.org/10.1109/ACCESS.2017.2736879

PACE : Redundancy Engineering in RLNC for Low-Latency Communication. / Pandi, Sreekrishna; Gabriel, Frank; Cabrera, Juan A.; Wunderlich, Simon; Reisslein, Martin; Fitzek, Frank H.P.

In: IEEE Access, 05.08.2017.

Research output: Contribution to journalArticle

Pandi, Sreekrishna ; Gabriel, Frank ; Cabrera, Juan A. ; Wunderlich, Simon ; Reisslein, Martin ; Fitzek, Frank H.P. / PACE : Redundancy Engineering in RLNC for Low-Latency Communication. In: IEEE Access. 2017.
@article{ef0bed519bfb47829aa06e4692a18f65,
title = "PACE: Redundancy Engineering in RLNC for Low-Latency Communication",
abstract = "Random linear network coding (RLNC) is attractive for data transfer as well as data storage and retrieval in complex and unreliable settings. The existing systematic RLNC approach first sends all source symbols in a generation without encoding followed by the coded redundant packets at the tail of the generation. This systematic tail RLNC achieves low delay when packet drops are rare; however, recovery of any dropped source symbol requires to wait for the coded packets at the end of the generation. We propose and evaluate a novel PACE RLNC approach that paces the transmissions of coded redundant packets throughout the generation of source symbols. The paced coded packets enable the recovery of dropped source symbols without waiting for the tail end of the generation. More specifically, we propose PACE-Uniform, which uniformly intersperses individual coded packets throughout the generation, and PACE-Burst, which intersperses bursts of code packets. Our extensive simulation evaluations indicate that PACE-Uniform significantly reduces the mean source symbol delay compared to tail RLNC, while achieving nearly the same loss probability. We also demonstrate the PACE-Burst generalizes the concept of pacing the redundant packet transmissions and can be flexibly tuned between PACE-Uniform and the conventional tail RLNC by controlling the number of coded packets in a burst.",
keywords = "Delay, Generation based network coding, Loss probability, Random Linear Network Coding (RLNC), Scheduling",
author = "Sreekrishna Pandi and Frank Gabriel and Cabrera, {Juan A.} and Simon Wunderlich and Martin Reisslein and Fitzek, {Frank H.P.}",
year = "2017",
month = "8",
day = "5",
doi = "10.1109/ACCESS.2017.2736879",
language = "English (US)",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - PACE

T2 - Redundancy Engineering in RLNC for Low-Latency Communication

AU - Pandi, Sreekrishna

AU - Gabriel, Frank

AU - Cabrera, Juan A.

AU - Wunderlich, Simon

AU - Reisslein, Martin

AU - Fitzek, Frank H.P.

PY - 2017/8/5

Y1 - 2017/8/5

N2 - Random linear network coding (RLNC) is attractive for data transfer as well as data storage and retrieval in complex and unreliable settings. The existing systematic RLNC approach first sends all source symbols in a generation without encoding followed by the coded redundant packets at the tail of the generation. This systematic tail RLNC achieves low delay when packet drops are rare; however, recovery of any dropped source symbol requires to wait for the coded packets at the end of the generation. We propose and evaluate a novel PACE RLNC approach that paces the transmissions of coded redundant packets throughout the generation of source symbols. The paced coded packets enable the recovery of dropped source symbols without waiting for the tail end of the generation. More specifically, we propose PACE-Uniform, which uniformly intersperses individual coded packets throughout the generation, and PACE-Burst, which intersperses bursts of code packets. Our extensive simulation evaluations indicate that PACE-Uniform significantly reduces the mean source symbol delay compared to tail RLNC, while achieving nearly the same loss probability. We also demonstrate the PACE-Burst generalizes the concept of pacing the redundant packet transmissions and can be flexibly tuned between PACE-Uniform and the conventional tail RLNC by controlling the number of coded packets in a burst.

AB - Random linear network coding (RLNC) is attractive for data transfer as well as data storage and retrieval in complex and unreliable settings. The existing systematic RLNC approach first sends all source symbols in a generation without encoding followed by the coded redundant packets at the tail of the generation. This systematic tail RLNC achieves low delay when packet drops are rare; however, recovery of any dropped source symbol requires to wait for the coded packets at the end of the generation. We propose and evaluate a novel PACE RLNC approach that paces the transmissions of coded redundant packets throughout the generation of source symbols. The paced coded packets enable the recovery of dropped source symbols without waiting for the tail end of the generation. More specifically, we propose PACE-Uniform, which uniformly intersperses individual coded packets throughout the generation, and PACE-Burst, which intersperses bursts of code packets. Our extensive simulation evaluations indicate that PACE-Uniform significantly reduces the mean source symbol delay compared to tail RLNC, while achieving nearly the same loss probability. We also demonstrate the PACE-Burst generalizes the concept of pacing the redundant packet transmissions and can be flexibly tuned between PACE-Uniform and the conventional tail RLNC by controlling the number of coded packets in a burst.

KW - Delay

KW - Generation based network coding

KW - Loss probability

KW - Random Linear Network Coding (RLNC)

KW - Scheduling

UR - http://www.scopus.com/inward/record.url?scp=85028921761&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028921761&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2017.2736879

DO - 10.1109/ACCESS.2017.2736879

M3 - Article

AN - SCOPUS:85028921761

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -