OTA-TinyML: Over the Air Deployment of TinyML Models and Execution on IoT Devices

This article presents a novel over-the-air (OTA) technique to remotely deploy tiny ML models over Internet of Things (IoT) devices and perform tasks, such as machine learning (ML) model updates, firmware reflashing, reconfiguration, or repurposing. We discuss relevant challenges for OTA ML deploymen...

Full description

Saved in:
Bibliographic Details
Published inIEEE internet computing Vol. 26; no. 3; pp. 69 - 78
Main Authors Sudharsan, Bharath, Breslin, John G., Tahir, Mehreen, Intizar Ali, Muhammad, Rana, Omer, Dustdar, Schahram, Ranjan, Rajiv
Format Journal Article
LanguageEnglish
Published IEEE 01.05.2022
Subjects
Atmospheric modeling
Internet of Things
Machine learning
Performance evaluation
Task analysis
Visualization
Web servers
Online AccessGet full text

Cover

More Information
Summary:This article presents a novel over-the-air (OTA) technique to remotely deploy tiny ML models over Internet of Things (IoT) devices and perform tasks, such as machine learning (ML) model updates, firmware reflashing, reconfiguration, or repurposing. We discuss relevant challenges for OTA ML deployment over IoT both at the scientific and engineering level. We propose OTA-TinyML to enable resource-constrained IoT devices to perform end-to-end fetching, storage, and execution of many TinyML models. OTA-TinyML loads the C source file of ML models from a web server into the embedded IoT devices via HTTPS. OTA-TinyML is tested by performing remote fetching of six types of ML models, storing them on four types of memory units, then loading and executing on seven popular MCU boards.
ISSN:1089-7801
1941-0131
DOI:10.1109/MIC.2021.3133552