Congestion Control System Optimization with Large Language Models

TL;DR

This paper presents a novel method using large language models to automatically optimize congestion control algorithms, significantly improving performance across diverse network conditions and reducing evaluation time.

Contribution

It introduces a structured LLM-based framework for algorithm generation and evaluation, demonstrating substantial performance gains over existing algorithms like BBR.

Findings

Achieved up to 27% performance improvement over BBR

Validated effectiveness across four different LLMs

Reduced evaluation time through a statistically guided method

Abstract

Congestion control is a fundamental component of Internet infrastructure, and researchers have dedicated considerable effort to developing improved congestion control algorithms. However, despite extensive study, existing algorithms continue to exhibit suboptimal performance across diverse network environments. In this paper, we introduce a novel approach that automatically optimizes congestion control algorithms using large language models (LLMs). Our framework consists of a structured algorithm generation process, an emulation-based evaluation pipeline covering a broad range of network conditions, and a statistically guided method to substantially reduce evaluation time. Empirical results from four distinct LLMs validate the effectiveness of our approach. We successfully identify algorithms that achieve up to 27% performance improvements over the original BBR algorithm in a production QUIC implementation. Our work demonstrates the potential of LLMs to accelerate the design of high-performance network algorithms and paves the way for broader applications in networking systems.