Learning-Based vs Human-Derived Congestion Control: An In-Depth Experimental Study

TL;DR

This study systematically compares learning-based congestion control algorithms with traditional methods like TCP Cubic and BBR, revealing their strengths and limitations through large-scale experiments.

Contribution

It provides a reproducible methodology for evaluating learning-based CC, highlighting challenges, and offering insights into their performance and fairness properties.

Findings

Embedding fairness into reward functions improves fairness but does not generalize.

RL approaches can acquire all available bandwidth with low latency.

Existing learning-based CC under-performs with dynamic bandwidth and latency changes.

Abstract

Learning-based congestion control (CC), including Reinforcement-Learning, promises efficient CC in a fast-changing networking landscape, where evolving communication technologies, applications and traffic workloads pose severe challenges to human-derived, static CC algorithms. Learning-based CC is in its early days and substantial research is required to understand existing limitations, identify research challenges and, eventually, yield deployable solutions for real-world networks. In this paper, we extend our prior work and present a reproducible and systematic study of learning-based CC with the aim to highlight strengths and uncover fundamental limitations of the state-of-the-art. We directly contrast said approaches with widely deployed, human-derived CC algorithms, namely TCP Cubic and BBR (version 3). We identify challenges in evaluating learning-based CC, establish a methodology for studying said approaches and perform large-scale experimentation with learning-based CC approaches that are publicly available. We show that embedding fairness directly into reward functions is effective; however, the fairness properties do not generalise into unseen conditions. We then show that RL learning-based approaches existing approaches can acquire all available bandwidth while largely maintaining low latency. Finally, we highlight that existing the latest learning-based CC approaches under-perform when the available bandwidth and end-to-end latency dynamically change while remaining resistant to non-congestive loss. As with our initial study, our experimentation codebase and datasets are publicly available with the aim to galvanise the research community towards transparency and reproducibility, which have been recognised as crucial for researching and evaluating machine-generated policies.