- Author
- Adnan Sabovic, Michiel Aernouts, Dragan Subotic, Jaron Fontaine (UGent) , Eli De Poorter (UGent) and Jeroen Famaey (UGent)
- Organization
- Project
- Abstract
- With the advent of Tiny Machine Learning (tinyML), it is increasingly feasible to deploy optimized ML models on constrained battery-less Internet of Things (IoT) devices with minimal energy availability. Due to the unpredictable and dynamic harvesting environment, successfully running tinyML on battery-less devices is still challenging. In this paper, we present the energy -aware deployment and management of tinyML algorithms and application tasks on battery-less IoT devices. We study the trade-offs between different inference strategies, analyzing under which circumstances it is better to make the decision locally or send the data to the Cloud where the heavy-weight ML model is deployed, respecting energy, accuracy, and time constraints. To decide which of these two options is more optimal and can satisfy all constraints, we define an energy-aware tinyML optimization algorithm. Our approach is evaluated based on real experiments with a prototype for battery-less person detection, which considers two different environments: (i) a controllable setup with artificial light, and (ii) a dynamic harvesting environment based on natural light. Our results show that the local inference strategy performs best in terms of execution speed when a controllable harvesting environment is considered. It can execute 3 times as frequently as remote inference at a harvesting current of 2 mA and using a capacitor of 1.5 F. In a realistic harvesting scenario with natural light and making use of the energy-aware optimization algorithm, the device will favor remote inference under high light conditions due to the better accuracy of the Cloud-based model. Otherwise, it switches to local inference.
- Keywords
- Sustainable IoT, Battery-less AI, Energy harvesting, TinyML, Energy-aware optimization, Person detection
Downloads
-
8264 acc.pdf
- full text (Accepted manuscript)
- |
- open access
- |
- |
- 1.77 MB
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 2.37 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01HAC4AT1EB85E9T1P0ZHQYZQX
- MLA
- Sabovic, Adnan, et al. “Towards Energy-Aware TinyML on Battery-Less IoT Devices.” INTERNET OF THINGS, vol. 22, 2023, doi:10.1016/j.iot.2023.100736.
- APA
- Sabovic, A., Aernouts, M., Subotic, D., Fontaine, J., De Poorter, E., & Famaey, J. (2023). Towards energy-aware tinyML on battery-less IoT devices. INTERNET OF THINGS, 22. https://doi.org/10.1016/j.iot.2023.100736
- Chicago author-date
- Sabovic, Adnan, Michiel Aernouts, Dragan Subotic, Jaron Fontaine, Eli De Poorter, and Jeroen Famaey. 2023. “Towards Energy-Aware TinyML on Battery-Less IoT Devices.” INTERNET OF THINGS 22. https://doi.org/10.1016/j.iot.2023.100736.
- Chicago author-date (all authors)
- Sabovic, Adnan, Michiel Aernouts, Dragan Subotic, Jaron Fontaine, Eli De Poorter, and Jeroen Famaey. 2023. “Towards Energy-Aware TinyML on Battery-Less IoT Devices.” INTERNET OF THINGS 22. doi:10.1016/j.iot.2023.100736.
- Vancouver
- 1.Sabovic A, Aernouts M, Subotic D, Fontaine J, De Poorter E, Famaey J. Towards energy-aware tinyML on battery-less IoT devices. INTERNET OF THINGS. 2023;22.
- IEEE
- [1]A. Sabovic, M. Aernouts, D. Subotic, J. Fontaine, E. De Poorter, and J. Famaey, “Towards energy-aware tinyML on battery-less IoT devices,” INTERNET OF THINGS, vol. 22, 2023.
@article{01HAC4AT1EB85E9T1P0ZHQYZQX,
abstract = {{With the advent of Tiny Machine Learning (tinyML), it is increasingly feasible to deploy optimized ML models on constrained battery-less Internet of Things (IoT) devices with minimal energy availability. Due to the unpredictable and dynamic harvesting environment, successfully running tinyML on battery-less devices is still challenging. In this paper, we present the energy -aware deployment and management of tinyML algorithms and application tasks on battery-less IoT devices. We study the trade-offs between different inference strategies, analyzing under which circumstances it is better to make the decision locally or send the data to the Cloud where the heavy-weight ML model is deployed, respecting energy, accuracy, and time constraints. To decide which of these two options is more optimal and can satisfy all constraints, we define an energy-aware tinyML optimization algorithm. Our approach is evaluated based on real experiments with a prototype for battery-less person detection, which considers two different environments: (i) a controllable setup with artificial light, and (ii) a dynamic harvesting environment based on natural light. Our results show that the local inference strategy performs best in terms of execution speed when a controllable harvesting environment is considered. It can execute 3 times as frequently as remote inference at a harvesting current of 2 mA and using a capacitor of 1.5 F. In a realistic harvesting scenario with natural light and making use of the energy-aware optimization algorithm, the device will favor remote inference under high light conditions due to the better accuracy of the Cloud-based model. Otherwise, it switches to local inference.}},
articleno = {{100736}},
author = {{Sabovic, Adnan and Aernouts, Michiel and Subotic, Dragan and Fontaine, Jaron and De Poorter, Eli and Famaey, Jeroen}},
issn = {{2543-1536}},
journal = {{INTERNET OF THINGS}},
keywords = {{Sustainable IoT,Battery-less AI,Energy harvesting,TinyML,Energy-aware optimization,Person detection}},
language = {{eng}},
pages = {{20}},
title = {{Towards energy-aware tinyML on battery-less IoT devices}},
url = {{http://doi.org/10.1016/j.iot.2023.100736}},
volume = {{22}},
year = {{2023}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: