[Online]TinyML Hardware Architectures for Sustainable Smart Cities

TinyML Hardware Architectures for Sustainable Smart Cities
ID:70 Submission ID:85 View Protection:ATTENDEE Updated Time:2026-10-04 23:31:53 Hits:149 Online

Start Time:2026-10-13 12:00 (Asia/Ho_Chi_Minh)

Duration:15min

Session:[S2] Track 2: IoT and applications » [S2-3] Track 2: IoT and applications

Video No Permission Presentation File

Tips: The file permissions under this presentation are only for participants. You have not logged in yet and cannot view it temporarily.

Abstract
The emergence of smart cities has resulted in the increasing use of IoT devices for environmental monitoring, intelligent transport, public safety, energy control, and healthcare applications. Nevertheless, the perpetual streaming of sensor data to cloud servers creates high energy costs, latency, communication overhead, and privacy issues. TinyML is a novel paradigm that allows for AI inference in small edge devices that operate with a power budget of only a few milliwatts. In this paper, we present an extensive study of TinyML hardware architectures towards sustainable smart city applications. Our framework combines low-power microcontrollers, edge AI accelerators, efficient communication components, and renewable energy harvesting technologies for enabling on-the-fly inference at the edge of the network. The analysis shows that compared to traditional cloud-based AI systems, the energy consumption and latency can be reduced by up to 70% and 90%, respectively, while reducing network traffic by 80% and increasing the lifetime of sensor nodes by more than 300%.
 
Keywords
TinyML,Smart Cities,Edge AI,Low-Power Computing,Artificial Intelligence,Process Innovation
Speaker
Wai Yie Leong
researcher INTI International University

Submission Author
Wai Yie Leong INTI International University
Comment submit
Verification code Change another
All comments

CONTACT US

Email: asiancomnet2026@usssociety.org

Website & IT Support: hi@aconf.org

Registration Submit Paper