CCA Reimagined: An Exploratory Study of Large Language Models for Congestion Control

TL;DR

This study explores the potential of large language models for congestion control, demonstrating significant latency reductions with minimal throughput loss through an LLM-based adaptive policy.

Contribution

It introduces a systematic, two-phase approach to integrating LLMs into congestion control, extending their role across multiple phases for improved network performance.

Findings

LLM-based congestion control reduces latency by up to 50%.

The approach achieves less than 0.3% throughput sacrifice.

LLMs demonstrate potential for adaptive, general congestion control.

Abstract

In this paper, we conduct an emulation-guided study to systematically investigate the feasibility of Large language model (LLM)-driven congestion control. The exploration is structured into two phases. The first phase derisks the whole capability where we isolate the role of LLM on a single yet crucial congestion avoidance phase so that we can safely examine when to invoke the LLM, what information to provide, and how to formulate LLM instructions. Based on the gained insights, we extend LLM's role to multiple congestion control phase and propose a more generic LLM-based congestion control policy. Our evaluation on both static and dynamic network traces demonstrates that the LLM-based solution can reduce latency by up to 50\% with only marginal throughput sacrifice (e.g., less than 0.3\%) compared to traditional CCAs. Overall, our exploration study confirms the potential of LLMs for adaptive and general congestion control, demonstrating that when granted appropriate control freedom and paired with an effective triggering mechanism, LLM-based policies achieve significant performance gains, particularly under highly dynamic network conditions.