Distilling Large Language Models for Network Active Queue Management
This work addresses the need for smarter packet traffic management in dynamic network scenarios, offering a solution for network engineers and researchers, though it appears incremental as it builds on existing LLM and AQM techniques.
The authors tackled the challenge of improving Active Queue Management (AQM) for low-latency networks by distilling Large Language Models (LLMs) into AQM-LLM, which enhanced queue management, prevented congestion, reduced latency, and boosted network performance in evaluations.
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.