K-Means Based TinyML Anomaly Detection and Distributed Model Reuse via the Distributed Internet of Learning (DIoL)

TL;DR

This paper introduces a lightweight K-Means anomaly detection system for resource-limited microcontrollers, featuring a distributed model-sharing workflow called DIoL that enables model reuse across devices without retraining.

Contribution

The paper proposes a novel distributed model-sharing framework, DIoL, allowing TinyML models to be exported and reused across multiple microcontrollers without retraining.

Findings

Successful on-device anomaly detection with real power measurements.

Model sharing via DIoL incurs negligible overhead.

Identical inference performance on different devices using shared models.

Abstract

This paper presents a lightweight K-Means anomaly detection model and a distributed model-sharing workflow designed for resource-constrained microcontrollers (MCUs). Using real power measurements from a mini-fridge appliance, the system performs on-device feature extraction, clustering, and threshold estimation to identify abnormal appliance behavior. To avoid retraining models on every device, we introduce the Distributed Internet of Learning (DIoL), which enables a model trained on one MCU to be exported as a portable, text-based representation and reused directly on other devices. A two-device prototype demonstrates the feasibility of the "Train Once, Share Everywhere" (TOSE) approach using a real-world appliance case study, where Device A trains the model and Device B performs inference without retraining. Experimental results show consistent anomaly detection behavior, negligible parsing overhead, and identical inference runtimes between standalone and DIoL-based operation. The proposed framework enables scalable, low-cost TinyML deployment across fleets of embedded devices.