Intent2QoS: Language Model-Driven Automation of Traffic Shaping Configurations

TL;DR

Intent2QoS automates the translation of high-level traffic management intents into Linux traffic control rules using a language model-driven pipeline, improving accuracy and compliance in network configuration.

Contribution

This paper introduces the first end-to-end framework that converts natural language intents into deployable traffic shaping configurations with a semantic model and rule-based validation.

Findings

LLaMA3 achieves 0.88 semantic similarity and 0.87 coverage.

The framework outperforms other models by over 30%.

AQM-guided prompting reduces variability threefold.

Abstract

Traffic shaping and Quality of Service (QoS) enforcement are critical for managing bandwidth, latency, and fairness in networks. These tasks often rely on low-level traffic control settings, which require manual setup and technical expertise. This paper presents an automated framework that converts high-level traffic shaping intents in natural or declarative language into valid and correct traffic control rules. To the best of our knowledge, we present the first end-to-end pipeline that ties intent translation in a queuing-theoretic semantic model and, with a rule-based critic, yields deployable Linux traffic control configuration sets. The framework has three steps: (1) a queuing simulation with priority scheduling and Active Queue Management (AQM) builds a semantic model; (2) a language model, using this semantic model and a traffic profile, generates sub-intents and configuration rules; and (3) a rule-based critic checks and adjusts the rules for correctness and policy compliance. We evaluate multiple language models by generating traffic control commands from business intents that comply with relevant standards for traffic control protocols. Experimental results on 100 intents show significant gains, with LLaMA3 reaching 0.88 semantic similarity and 0.87 semantic coverage, outperforming other models by over 30\. A thorough sensitivity study demonstrates that AQM-guided prompting reduces variability threefold compared to zero-shot baselines.