From Data Center IoT Telemetry to Data Analytics Chatbots -- Virtual Knowledge Graph is All You Need

TL;DR

This paper presents a Virtual Knowledge Graph-based system that enables natural language data analytics for IoT telemetry, significantly improving accuracy and reducing latency in data center environments.

Contribution

It introduces a rule-based VKG construction process combined with LLM inference to facilitate natural language access to heterogeneous IoT data, achieving high accuracy and low latency.

Findings

92.5% accuracy in query translation

85% reduction in latency

VKG sizes under 179 MiB

Abstract

Industry 5.0 demands IoT systems that support seamless human-machine collaboration, yet current IoT data analysis requires deep domain, deployment, and query expertise. We show that combining Large Language Models (LLMs) with Knowledge Graphs (KGs) enables natural language access to heterogeneous IoT data. Focusing on data center IoT telemetry, we introduce a rule-based Virtual Knowledge Graph (VKG) construction process and an on-premise LLM inference service to create an end-to-end Data Analytics (DA) chatbot. Our system dynamically generates VKGs per query and translates user input into SPARQL, achieving 92.5% accuracy (vs. 25% for LLM-to-NoSQL) while reducing latency by 85% (20.36s to 3.03s) and keeping VKG sizes under 179 MiB. This work demonstrates that VKG-powered LLM interfaces deliver accurate, low-latency, and relationship-aware access to large-scale telemetry, bridging the gap between users and complex IoT systems in Industry 5.0.