Adapting Large Language Models for Improving TCP Fairness over WiFi

2024/12/24 by Shyam Kumar Shrestha, Shiva Raj Pokhrel, Shrestha, Shyam Kumar +3
Computer Science · Engineering · #FOS: Computer and information sciences #IPv6, Mobility, Handover, Networks, Security #Network Traffic and Congestion Control #Networking and Internet Architecture (cs.NI) #Wireless Networks and Protocols

paper · pdf · doi:10.48550/arxiv.2412.18200

openalex publication_date 2024/12/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• Congestion Control System Optimization with Large Language Models
• A Deep Reinforcement Learning-Based TCP Congestion Control Algorithm: Design, Simulation, and Evaluation
• A Reinforcement Learning Framework for Application-Specific TCP Congestion-Control
• Distilling Large Language Models for Network Active Queue Management
• Large Language Model (LLM)-enabled In-context Learning for Wireless Network Optimization: A Case Study of Power Control