Saved in:
Bibliographic Details
Main Authors: Pokhrel, Shiva Raj, Satish, Deol, Kua, Jonathan, Walid, Anwar
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.16734
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909764571627520
author Pokhrel, Shiva Raj
Satish, Deol
Kua, Jonathan
Walid, Anwar
author_facet Pokhrel, Shiva Raj
Satish, Deol
Kua, Jonathan
Walid, Anwar
contents The growing complexity of network traffic and demand for ultra-low latency communication require smarter packet traffic management. Existing Deep Learning-based queuing approaches struggle with dynamic network scenarios and demand high engineering effort. We propose AQM-LLM, distilling Large Language Models (LLMs) with few-shot learning, contextual understanding, and pattern recognition to improve Active Queue Management (AQM) [RFC 9330] with minimal manual effort. We consider a specific case where AQM is Low Latency, Low Loss, and Scalable Throughput (L4S) and our design of AQM-LLM builds on speculative decoding and reinforcement-based distilling of LLM by tackling congestion prevention in the L4S architecture using Explicit Congestion Notification (ECN) [RFC 9331] and periodic packet dropping. We develop a new open-source experimental platform by executing L4S-AQM on FreeBSD-14, providing interoperable modules to support LLM integration and facilitate IETF recognition through wider testing. Our extensive evaluations show L4S-LLM enhances queue management, prevents congestion, reduces latency, and boosts network performance, showcasing LLMs' adaptability and efficiency in uplifting AQM systems.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16734
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Distilling Large Language Models for Network Active Queue Management
Pokhrel, Shiva Raj
Satish, Deol
Kua, Jonathan
Walid, Anwar
Networking and Internet Architecture
Artificial Intelligence
The growing complexity of network traffic and demand for ultra-low latency communication require smarter packet traffic management. Existing Deep Learning-based queuing approaches struggle with dynamic network scenarios and demand high engineering effort. We propose AQM-LLM, distilling Large Language Models (LLMs) with few-shot learning, contextual understanding, and pattern recognition to improve Active Queue Management (AQM) [RFC 9330] with minimal manual effort. We consider a specific case where AQM is Low Latency, Low Loss, and Scalable Throughput (L4S) and our design of AQM-LLM builds on speculative decoding and reinforcement-based distilling of LLM by tackling congestion prevention in the L4S architecture using Explicit Congestion Notification (ECN) [RFC 9331] and periodic packet dropping. We develop a new open-source experimental platform by executing L4S-AQM on FreeBSD-14, providing interoperable modules to support LLM integration and facilitate IETF recognition through wider testing. Our extensive evaluations show L4S-LLM enhances queue management, prevents congestion, reduces latency, and boosts network performance, showcasing LLMs' adaptability and efficiency in uplifting AQM systems.
title Distilling Large Language Models for Network Active Queue Management
topic Networking and Internet Architecture
Artificial Intelligence
url https://arxiv.org/abs/2501.16734