Bridging inter-flow and intra-flow network coding in wireless mesh networks: From theory to implementation

Jonas Hansen, Jeppe Krigslund, Daniel E. Lucani, Peyman Pahlevani*, Frank H.P. Fitzek

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

9 Citations (Scopus)
120 Downloads (Pure)

Abstract

This paper presents and characterizes the performance of CORE, a protocol that brings together the efficiency in spectrum usage of inter–session network coding schemes and the robustness against packet losses of intra–session network coding. We provide in-depth mathematical analysis of the gains of CORE followed by protocol design and implementation details needed for CORE's successful deployment in practice. Finally, we provide extensive measurements with off-the-shelf wireless nodes under various channel and system conditions comparing CORE to other state-of-the-art approaches, namely, forwarding (no coding) and COPE (inter-session network coding). These measurements support our theoretical findings, showing that CORE not only outperforms COPE and forwarding in general, but that order of magnitude gains are possible for cases with high packet losses. Specifically, CORE has a throughput gain of more than 10x over a COPE-like scheme and 7x over forwarding when the error ratio is 50 % on all links. Beyond these gains over other protocols, our measurements show that our CORE implementation can achieve close to optimal performance with a gap of less than 0.43 dB.

Original languageEnglish
JournalComputer Networks
Volume145
Pages (from-to)1-12
Number of pages12
ISSN1389-1286
DOIs
Publication statusPublished - 9 Nov 2018

Keywords

  • Ad-hoc network
  • Implementation on real devices
  • Network coding
  • Performance comparison
  • Real-life measurements
  • Wireless mesh networks

Fingerprint

Dive into the research topics of 'Bridging inter-flow and intra-flow network coding in wireless mesh networks: From theory to implementation'. Together they form a unique fingerprint.

Cite this