OFCnetLLM: Large Language Model for Network Monitoring and Alertness

2025-07-30

AI Summary

The exponential growth of network monitoring data has rendered conventional query discovery and pattern analysis costly and inefficient. To address this, we propose OFCnetLLM—a novel network monitoring system leveraging open-source large language models (LLMs) within a multi-agent collaborative framework—designed to overcome fundamental limitations of traditional rule-based and statistical approaches in anomaly interpretation, root-cause localization, and automated response generation. OFCnetLLM integrates generative AI for log parsing, semantic pattern recognition, and natural-language interactive diagnostics. It has been preliminarily deployed and validated on the production network of the Optical Fiber Communication (OFC) Conference. Experimental results demonstrate that OFCnetLLM significantly reduces operational labor costs while improving both anomaly detection accuracy and the timeliness of root-cause analysis. The system establishes a new paradigm for explainable, adaptive, and fully automated intelligent network operations and maintenance.

Technology Category

• Multiagent Systems: Agent Communication
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The rapid evolution of network infrastructure is bringing new challenges and opportunities for efficient network management, optimization, and security. With very large monitoring databases becoming expensive to explore, the use of AI and Generative AI can help reduce costs of managing these datasets. This paper explores the use of Large Language Models (LLMs) to revolutionize network monitoring management by addressing the limitations of query finding and pattern analysis. We leverage LLMs to enhance anomaly detection, automate root-cause analysis, and automate incident analysis to build a well-monitored network management team using AI. Through a real-world example of developing our own OFCNetLLM, based on the open-source LLM model, we demonstrate practical applications of OFCnetLLM in the OFC conference network. Our model is developed as a multi-agent approach and is still evolving, and we present early results here.

Problem

• Enhancing network monitoring with Large Language Models
• Reducing costs of managing large monitoring databases
• Automating anomaly detection and root-cause analysis

Innovation

• Leveraging LLMs for network monitoring management
• Multi-agent approach for anomaly detection
• Automating root-cause and incident analysis