K-Means Based TinyML Anomaly Detection and Distributed Model Reuse via the Distributed Internet of Learning (DIoL)
For developers of TinyML systems on resource-constrained MCUs, this work provides a practical method to avoid per-device retraining, enabling scalable deployment.
This paper presents a lightweight K-Means anomaly detection model for MCUs and a distributed model-sharing workflow (DIoL) that allows a model trained on one device to be reused on others without retraining. Experiments on a mini-fridge show consistent anomaly detection, negligible parsing overhead, and identical inference runtimes.
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.