Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Performance Comparison of IBN orchestration using LLM and SLMs

Wai Lwin Phone, Brahim El Boudani, Tasos Dagiuklas, Saptarshi Ghosh

TL;DR

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 is introduced.

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%.

Performance Comparison of IBN orchestration using LLM and SLMs

TL;DR

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 is introduced.

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%.
Paper Structure (14 sections, 5 equations, 2 figures, 7 tables)

This paper contains 14 sections, 5 equations, 2 figures, 7 tables.

Table of Contents

  1. Introduction
  2. State-of-the-Art in Agentic-AI for Network Automation
  3. Proposed Agentic-AI Network Architecture
  4. Multi-Agent Architecture
  5. Message Sequence
  6. Performance Evaluation
  7. Experimentation Setup
  8. Fine-Tuning of Models
  9. Performance Evaluaion Methologies
  10. Bilingual Evaluation Understudy (BLEU)
  11. Metric for Evaluation of Translation with Explicit ORdering (METEOR)
  12. Recall-Oriented Understudy for Gisting Evaluation(ROUGE)
  13. Time Distribution
  14. Conclusion

Figures (2)

  • Figure 1: Proposed IBN Orchestration Architecture.
  • Figure 2: Deployment Diagram