Towards End-to-End Network Intent Management with Large Language Models
This work addresses the challenge of automating network intent management in mobile networks, making it more accessible and cost-effective for network operators, though it is incremental as it applies existing LLMs to a new domain with a custom evaluation metric.
The paper tackled the problem of generating end-to-end network configurations for 5G/6G mobile networks using large language models (LLMs) to translate human intents into low-level settings, and found that open-source models like LLama and Mistral achieved comparable or superior performance to closed-source models like ChatGPT-4 and Gemini 1.5 Pro, as measured by a novel FEACI metric assessing format, explainability, accuracy, cost, and inference time.
Large Language Models (LLMs) are likely to play a key role in Intent-Based Networking (IBN) as they show remarkable performance in interpreting human language as well as code generation, enabling the translation of high-level intents expressed by humans into low-level network configurations. In this paper, we leverage closed-source language models (i.e., Google Gemini 1.5 pro, ChatGPT-4) and open-source models (i.e., LLama, Mistral) to investigate their capacity to generate E2E network configurations for radio access networks (RANs) and core networks in 5G/6G mobile networks. We introduce a novel performance metrics, known as FEACI, to quantitatively assess the format (F), explainability (E), accuracy (A), cost (C), and inference time (I) of the generated answer; existing general metrics are unable to capture these features. The results of our study demonstrate that open-source models can achieve comparable or even superior translation performance compared with the closed-source models requiring costly hardware setup and not accessible to all users.