Adina Waxman

Rivka Gitik, Adina Waxman, Shai Ginzach et al.

In this work, we introduce Blank Space Adaptive Causal Random Linear Network Coding (BS-AC-RLNC), a novel coding scheme designed to mitigate the triplet trade-off between throughput-delay-efficiency in multi-hop networks. BS-AC-RLNC leverages the physical limitations of the network, considering the bottleneck from each node to the destination. In particular, this approach introduces a light-computational re-encoding algorithm, called AC-RLNC (NET), implemented independently at intermediate nodes. NET adaptively adjusts the Forward Error Correction (FEC) rates and schedules idle periods. It incorporates two distinct suspension mechanisms: 1) Blank Space Period, accounting for the forward-channels bottleneck, and 2) No-New No-FEC approach, based on data availability. We present theoretical lower and upper bounds on in-order delivery delay, goodput, and throughput; in the case of in-order delay, we further derive a mean bound. These analytical results are extended to the multicast scenario, providing a broader understanding of the algorithm's performance under diverse network conditions. The experimental results achieve significant improvements in resource efficiency, demonstrating a 20% reduction in channel usage compared to baseline RLNC solutions. Notably, these efficiency gains are achieved while maintaining competitive throughput and delay performance, ensuring improved resource utilization does not compromise network performance.

Adina Waxman, Nir Shlezinger, Alejandro Cohen

Adaptive network coding schemes provide a promising approach to bridging the gap between high data rates and low delay in real-time streaming applications. However, their effectiveness often relies on accurate channel prediction, which is typically based on delayed feedback and is especially challenging when the underlying channel model is unknown. To address this, we introduce a novel integration of network coding with a channel-agnostic, Deep learning-based Noise Prediction algorithm (DeepNP). Unlike traditional estimators, DeepNP predicts statistical noise rates rather than instantaneous noise realizations, significantly simplifying the prediction task while enhancing coding performance. DeepNP is designed to operate with both binary (e.g., acknowledgments) and continuous-valued (e.g., Signal-to-Noise Ratio, SNR) feedback. We incorporate DeepNP into the Adaptive and Causal Random Linear Network Coding (AC-RLNC) framework to jointly optimize throughput and in-order delivery delay. Two variants are proposed: (i) Erasure-Rate DeepNP (ER-DeepNP), which serves as a transport-layer noise predictor and achieves in a numerical study up to a 2x reduction in mean and maximum delay with less than 0.1 loss in throughput compared to statistic-based estimators, under Round-Trip Time (RTT) up to 40 time slots and erasure rates up to 60%; and (ii) Cross-Layer DeepNP (CL-DeepNP), which dynamically adjusts the SNR threshold to maintain high physical layer code rates while achieving low transport-layer erasure rates. This yields, in the presented numerical study, a 25% throughput gain over fixed-threshold approaches. Our results demonstrate that DeepNP enables robust, model-free noise prediction, making adaptive network coding more viable in practical, feedback-limited communication scenarios.