On the CPU Usage of Deep Learning Models on an Edge Device

Elarbi Badidi, Dhanya Gopinathan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)


Applications that use the Internet of Things (IoT) capture massive amounts of raw data from sensors and actuators and frequently transmit this data to cloud data centers for processing and analysis. However, due to variable and unpredictable data generation rates and network latency, sending data to a cloud data center can result in a performance bottleneck. Data processing could occur at the network’s edge with the emergence of Fog and Edge computing-hosted microservices. Detecting and tracking objects from images, videos, and live streams are two of the fastest-growing computer vision applications increasingly being deployed at the edge. You Only Look Once (YOLO) models are highly optimized deep learning methods for object detection. This paper analyzes the CPU usage of four YOLO models on an edge device, an Nvidia Jetson Nano, at two different power budgets 5 and 10 W. Results show that the average CPU usage of the four YOLO models is low in 10 W power mode compared to 5 W power mode, except for YOLOv4-tiny. Furthermore, the number of frames per second processed by the four models remains relatively the same when switching from the 10 to 5 W power modes.

Original languageEnglish
Title of host publicationData Science and Algorithms in Systems - Proceedings of 6th Computational Methods in Systems and Software 2022, Vol. 2
EditorsRadek Silhavy, Petr Silhavy, Zdenka Prokopova
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages11
ISBN (Print)9783031214370
Publication statusPublished - 2023
Event6th Computational Methods in Systems and Software, CoMeSySo 2022 - Virtual, Online
Duration: Oct 10 2022Oct 15 2022

Publication series

NameLecture Notes in Networks and Systems
Volume597 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389


Conference6th Computational Methods in Systems and Software, CoMeSySo 2022
CityVirtual, Online


  • Deep learning
  • Edge computing
  • Edge intelligence
  • Intelligent traffic monitoring
  • Object detection

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications


Dive into the research topics of 'On the CPU Usage of Deep Learning Models on an Edge Device'. Together they form a unique fingerprint.

Cite this