TRANSFORMING NOC OPERATIONS THROUGH AI-AUGMENTED ALERT TRIAGE AND ESCALATION AUTOMATION
Keywords:
Alert Management, Large Language Models (LLMs), Ollama, Escalation Automation, Prompt Engineering, APScheduler, RabbitMQ, PostgreSQL, WebhookAbstract
Modern Network Operations Centers (NOCs) face significant challenges in managing the large volume of alerts generated by diverse monitoring systems. Manual triage processes, delayed escalation, and the absence of contextual intelligence often lead to prolonged incident resolution times and service degradation. This research proposes an AI-powered NOC Alert Triage and Escalation System that integrates microservice architecture, automated escalation mechanisms, and Large Language Model (LLM)-based analysis to improve alert handling efficiency. The proposed system leverages a FastAPI-based webhook service for real-time alert ingestion, PostgreSQL for persistent storage, RabbitMQ for asynchronous communication, and an Ollama-based LLM service for incident summarization and contextual knowledge enrichment.
Automated escalation is managed through a persistent scheduling mechanism to ensure reliability, even during system restarts. The Experimental evaluation demonstrates a reduction in the Mean Time to Acknowledge (MTTA), improved alert reduplication accuracy, and enhanced incident understanding through AI-generated summaries. The system is scalable, fault-tolerant, and customizable, making it suitable for enterprise-level NOC environments.
