Adapting Large Language Models for Improving TCP Fairness over WiFi

TL;DR

This paper introduces TCP-LLM, a framework that leverages large language models to improve TCP performance and fairness in WiFi networks, reducing manual design effort and enhancing adaptability in dynamic environments.

Contribution

The paper presents TCP-LLM, the first framework using LLMs for TCP, enabling better generalization and performance with minimal fine-tuning in diverse network scenarios.

Findings

TCP-LLM reduces flow unfairness effectively.

It adapts congestion control dynamically.

It prevents starvation in WiFi networks.

Abstract

The new transmission control protocol (TCP) relies on Deep Learning (DL) for prediction and optimization, but requires significant manual effort to design deep neural networks (DNNs) and struggles with generalization in dynamic environments. Inspired by the success of large language models (LLMs), this study proposes TCP-LLM, a novel framework leveraging LLMs for TCP applications. TCP-LLM utilizes pre-trained knowledge to reduce engineering effort, enhance generalization, and deliver superior performance across diverse TCP tasks. Applied to reducing flow unfairness, adapting congestion control, and preventing starvation, TCP-LLM demonstrates significant improvements over TCP with minimal fine-tuning.