BAR: Blockwise Adaptive Recoding for Batched Network Coding

TL;DR

This paper introduces BAR, a practical adaptive recoding scheme for batched network coding in multi-hop networks, which improves throughput and adapts to channel fluctuations with minimal computational overhead.

Contribution

We propose BAR, a novel adaptive recoding method that learns channel conditions from short observations, enhancing throughput in batched network coding under uncertain and changing environments.

Findings

BAR achieves significant throughput gains for small batch sizes.

BAR's performance is robust to inaccurate channel knowledge.

The scheme is practical for real-world multi-hop IoT networks.

Abstract

Multi-hop networks become popular network topologies in various emerging Internet of things applications. Batched network coding (BNC) is a solution to reliable communications in such networks with packet loss. By grouping packets into small batches and restricting recoding to the packets belonging to the same batch, BNC has a much smaller computational and storage requirements at the intermediate nodes compared with a direct application of random linear network coding. In this paper, we propose a practical recoding scheme called blockwise adaptive recoding (BAR) which learns the latest channel knowledge from short observations so that BAR can adapt to the fluctuation of channel conditions. We focus on investigating practical concerns such as the design of efficient BAR algorithms. We also design and investigate feedback schemes for BAR under imperfect feedback systems. Our numerical evaluations show that BAR has significant throughput gain for small batch size compared with the existing baseline recoding scheme. More importantly, this gain is insensitive to inaccurate channel knowledge. This encouraging result suggests that BAR is suitable to be realized in practice as the exact channel model and its parameters could be unknown and subject to change from time to time.