Reducing FEC-Complexity in Cross-Layer Predictable Data Communication

TL;DR

This paper proposes a code partitioning method to reduce the complexity of MDS codes in HARQ, enabling their use in resource-constrained embedded systems for predictable data communication.

Contribution

It introduces a novel code partitioning technique that lowers the computational complexity of MDS codes in HARQ protocols for embedded applications.

Findings

Reduced computational complexity of MDS codes

Enabling deployment on embedded devices

Maintained predictability in data communication

Abstract

The PRRT protocol enables applications with strict performance requirements such as Cyber-Physical Systems, as it provides predictably low, end-to-end delay via cross-layer pacing and timely error correction via Hybrid ARQ (HARQ). However, the implemented HARQ uses computationally complex Maximum Distance Separable (MDS) codes to generate redundancy. In this paper we propose code partitioning for the complexity reduction of MDS codes, thereby enabling their deployment on constrained embedded devices.