Performance Comparison of IBN orchestration using LLM and SLMs

TL;DR

This paper compares the performance of SLMs and LLMs in IBN orchestration for 5G and 6G networks, highlighting that SLMs offer faster completion speeds while maintaining similar accuracy to LLMs.

Contribution

It introduces a hierarchical multi-agent framework for IBN orchestration that integrates both SLMs and LLMs, demonstrating their comparative performance.

Findings

SLMs improve IBN lifecycle speed by 20%

Both models have similar translation accuracy

Framework enables full automation in network management

Abstract

The evolution of both 5G and 6G networks is driving the advancement of fully autonomous network management, placing Intent-Based Networking at the centre of this transformation. This paper introduces a novel framework for 5G and 6G IBN orchestration that leverages a stateful, hierarchical multi-agent architecture to achieve full automation using both SLMs and LLMs. Both models have been evaluated for translation accuracy using metrics such as BLEU, METEOR, and ROUGE-L, as well as computational complexity. Experimental results show that both models exhibit similar accuracy. However, result shows that SLMs can improve the overall completion speed of the IBN lifecycle by 20%.