When Large Language Models Meet Optical Networks: Paving the Way for Automation

TL;DR

This study proposes a framework of LLM-empowered optical networks, facilitating intelligent control of the physical layer and efficient interaction with the application layer through an LLM-driven agent (AI-Agent) deployed in the control layer.

Abstract

Since the advent of GPT, large language models (LLMs) have brought about revolutionary advancements in all walks of life. As a superior natural language processing (NLP) technology, LLMs have consistently achieved state-of-the-art performance on numerous areas. However, LLMs are considered to be general-purpose models for NLP tasks, which may encounter challenges when applied to complex tasks in specialized fields such as optical networks. In this study, we propose a framework of LLM-empowered optical networks, facilitating intelligent control of the physical layer and efficient interaction with the application layer through an LLM-driven agent (AI-Agent) deployed in the control layer. The AI-Agent can leverage external tools and extract domain knowledge from a comprehensive resource library specifically established for optical networks. This is achieved through user input and well-crafted prompts, enabling the generation of control instructions and result representations for autonomous operation and maintenance in optical networks. To improve LLM's capability in professional fields and stimulate its potential on complex tasks, the details of performing prompt engineering, establishing domain knowledge library, and implementing complex tasks are illustrated in this study. Moreover, the proposed framework is verified on two typical tasks: network alarm analysis and network performance optimization. The good response accuracies and sematic similarities of 2,400 test situations exhibit the great potential of LLM in optical networks.

Figures (11)

• Figure 1: The framework of LLM-empowered optical networks, which enables intelligent control of the physical layer and efficient interaction with the application layer through an LLM-driven AI-Agent deployed in the control layer.
• Figure 2: Schematic of some typical prompting techniques, including zero-shot ICL, few-shot ICL, CoT, self-consistency with CoT, and ToT.
• Figure 3: Workflow of LLM to invoke tools and extract information from the domain resource library for executing specific tasks in optical networks.
• Figure 4: Schematic of procedural framework for solving the complex tasks in optical networks based on LLM and LangChain, including five operating steps: intentional analysis, task decomposition, resource selection, problem solving, and final answer generating.
• Figure 5: Schematic of LLM-enabled network alarm analysis based on five-step procedural framework, encompassing three tasks: alarm compression, process priority sorting, and alarm solving suggestions.