Research Article
Energy-Efficient YOLO with Knowledge Distillation and Dynamic Energy Control for Edge Devices
@INPROCEEDINGS{10.1007/978-3-031-93825-2_2, author={Anggi Andriyadi and Chandra Wijaya and Shih-Yen Chen and Ding-Hsiang Huang and Chao-Tung Yang}, title={Energy-Efficient YOLO with Knowledge Distillation and Dynamic Energy Control for Edge Devices}, proceedings={Smart Grid and Internet of Things. 8th EAI International Conference, SGIoT 2024, Taichung, Taiwan, November 23--24, 2024, Proceedings}, proceedings_a={SGIOT}, year={2025}, month={7}, keywords={YOLO Knowledge Distillation Dynamic Energy Control Edge AI}, doi={10.1007/978-3-031-93825-2_2} }- Anggi Andriyadi
Chandra Wijaya
Shih-Yen Chen
Ding-Hsiang Huang
Chao-Tung Yang
Year: 2025
Energy-Efficient YOLO with Knowledge Distillation and Dynamic Energy Control for Edge Devices
SGIOT
Springer
DOI: 10.1007/978-3-031-93825-2_2
Abstract
This paper discusses the ongoing development of an energy-efficient YOLO-based fire detection system optimized for edge devices. Using Knowledge Distillation, we compress the YOLOv8m model into YOLOv8n, making it more suitable for deployment on energy-constrained edge devices while maintaining its accuracy. Additionally, we are designing a real-time dynamic energy control mechanism to manage energy usage during the inference process based on real-time power monitoring. Initial results demonstrate that the proposed method reduces model size and power consumption without compromising performance.
Copyright © 2024–2025 ICST
