Journal
IEEE ACCESS
Volume 10, Issue -, Pages 100867-100877Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2022.3207200
Keywords
Internet of Things; Logic gates; Cloud computing; Performance evaluation; Computational modeling; Memory management; Machine learning; Edge computing; Internet of Things; Deep learning; Transfer learning; Collaborative work; Energy efficiency; Tiny machine learning; IoT; edge computing; 5G; LoRa; gesture recognition; deep learning; transfer learning; federated learning; implementation; MLOps; energy efficiency
Categories
Funding
- Engineering and Physical Sciences Research Council (EPSRC) [EP/S016813/1, EP/N010523/1]
- Royal Academy of Engineering, Transforming Systems [TSP1040, UK 122040]
- Royal Academy through the Distinguished International Associates [DIA-2021-18]
Ask authors/readers for more resources
Machine Learning (ML) on the edge is crucial for new IoT and autonomous system applications. The TinyML framework allows the execution of ML models on low-power embedded devices, offering better power efficiency and reduced latency. The TMLaaS architecture presents design trade-offs in terms of energy consumption, security, privacy, and latency.
Machine Learning (ML) on the edge is key to enabling a new breed of IoT and autonomous system applications. The departure from the traditional cloud-centric architecture means that new deployments can be more power-efficient, provide better privacy and reduce latency for inference. At the core of this paradigm is TinyML, a framework allowing the execution of ML models on low-power embedded devices. TinyML allows importing pre-trained ML models on the edge for providing ML-as-a-Service (MLaaS) to IoT devices. This article presents a TinyMLaaS (TMLaaS) architecture for future IoT deployments. The TMLaaS architecture inherently presents several design trade-offs in terms of energy consumption, security, privacy, and latency. We also present how TMLaaS architecture can be implemented, deployed, and maintained for large-scale IoT deployment. The feasibility of implementation for the TMLaaS architecture has been demonstrated with the help of a case study.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available