Talk with the Things: Integrating LLMs into IoT Networks

TL;DR

This paper introduces an edge-centric framework integrating LLMs into IoT networks for natural language control and decision-making, validated through a smart home prototype using LLaMA 3 and Gemma 2B models.

Contribution

It presents a modular, lightweight RAG-based LLM deployment on edge devices for IoT, enabling local processing with reduced latency and privacy benefits.

Findings

Model accuracy varies with size and inference time.

Edge deployment improves response times and privacy.

Smart home control demonstrated successfully.

Abstract

The convergence of Large Language Models (LLMs) and Internet of Things (IoT) networks open new opportunities for building intelligent, responsive, and user-friendly systems. This work presents an edge-centric framework that integrates LLMs into IoT architectures to enable natural language-based control, context-aware decision-making, and enhanced automation. The proposed modular and lightweight Retrieval Augmented Generation (RAG)-based LLMs are deployed on edge computing devices connected to IoT gateways, enabling local processing of user commands and sensor data for reduced latency, improved privacy, and enhanced inference quality. We validate the framework through a smart home prototype using LLaMA 3 and Gemma 2B models for controlling smart devices. Experimental results highlight the trade-offs between model accuracy and inference time with respect to models size. At last, we also discuss the potential applications that can use LLM-based IoT systems, and a few key challenges associated with such systems.