Novel Performance Analysis of Network Coded Communications in Single-Relay Networks

TL;DR

This paper presents a new theoretical framework for analyzing single-relay networks using Random Linear Network Coding, including a passive relay mode, demonstrating significant performance improvements over traditional methods.

Contribution

It introduces a novel performance analysis framework for relay networks with passive relay mode and non-binary coding, extending prior models and verifying results through simulations.

Findings

Passive relay mode doubles decoding probability

Theoretical results match simulation for binary and non-binary fields

Passive relay significantly outperforms active-only relay

Abstract

In this paper, we analyze the performance of a single-relay network in which the reliability is provided by means of Random Linear Network Coding (RLNC). We consider a scenario when both source and relay nodes can encode packets. Unlike the traditional approach to relay networks, we introduce a passive relay mode, in which the relay node simply retransmits collected packets in case it cannot decode them. In contrast with the previous studies, we derive a novel theoretical framework for the performance characterization of the considered relay network. We extend our analysis to a more general scenario, in which coding coefficients are generated from non-binary fields. The theoretical results are verified using simulation, for both binary and non-binary fields. It is also shown that the passive relay mode significantly improves the performance compared with the active-only case, offering an up to two-fold gain in terms of the decoding probability. The proposed framework can be used as a building block for the analysis of more complex network topologies.