Adapting Large Language Models for Improving TCP Fairness over WiFi

2024-12-24

AI Summary

To address inter-flow unfairness, inflexible congestion control, and flow starvation in Wi-Fi networks, this paper proposes TCP-LLM—a novel framework that integrates large language models (e.g., Llama) directly into the TCP protocol layer for the first time. Leveraging instruction tuning and prompt engineering, TCP-LLM incorporates network state embeddings and a TCP action decoding module, enabling lightweight, handcrafted-DNN-free adaptation. Crucially, it supports multiple tasks—including fairness regulation, congestion control, and starvation mitigation—without retraining the base model. Evaluated in NS-3, TCP-LLM improves Jain’s fairness index by 37%, reduces training overhead by 90% compared to state-of-the-art AI-based TCP schemes, and demonstrates strong robustness under dynamic channel conditions. Its core innovation lies in transferring the LLM’s generalization capability to low-level network protocol optimization, thereby substantially lowering modeling costs and enhancing adaptability to dynamic network environments.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Fairness
• TCP Optimization
• Network Congestion Control

Innovation

• TCP-LLM
• Large Language Model
• Network Congestion Control