Next Article in Journal
A Review of Smartphone Applications for Solar Photovoltaic Use: Current Status, Limitations, and Future Perspectives
Next Article in Special Issue
Power Allocation for Secrecy-Capacity-Optimization-Artificial-Noise Secure MIMO Precoding Systems under Perfect and Imperfect Channel State Information
Previous Article in Journal
Efficient Operative Cost Reduction in Distribution Grids Considering the Optimal Placement and Sizing of D-STATCOMs Using a Discrete-Continuous VSA
Previous Article in Special Issue
Foreground Objects Detection by U-Net with Multiple Difference Images
Article

You Only Look Once, But Compute Twice: Service Function Chaining for Low-Latency Object Detection in Softwarized Networks †

by 1,*,‡, 2,‡ and 1,‡
1
Centre for Tactile Internet with Human-in-the-Loop, Technische Universität Dresden, 01187 Dresden, Germany
2
Department of Computer Science, Central Michigan University, Mount Pleasant, MI 48859, USA
*
Author to whom correspondence should be addressed.
Extended version of Xiang, Z.; Zhang, R.; Seeling, P. Machine learning for object detection. In Computing in Communication Networks; Fitzek, F.H., Granelli, F., Seeling, P., Eds.; Elsevier/Academic Press: Cambridge, MA, USA, 2020.
The authors contributed equally to this work.
Academic Editor: Cheonshik Kim
Appl. Sci. 2021, 11(5), 2177; https://doi.org/10.3390/app11052177
Received: 22 December 2020 / Revised: 19 February 2021 / Accepted: 25 February 2021 / Published: 2 March 2021
With increasing numbers of computer vision and object detection application scenarios, those requiring ultra-low service latency times have become increasingly prominent; e.g., those for autonomous and connected vehicles or smart city applications. The incorporation of machine learning through the applications of trained models in these scenarios can pose a computational challenge. The softwarization of networks provides opportunities to incorporate computing into the network, increasing flexibility by distributing workloads through offloading from client and edge nodes over in-network nodes to servers. In this article, we present an example for splitting the inference component of the YOLOv2 trained machine learning model between client, network, and service side processing to reduce the overall service latency. Assuming a client has 20% of the server computational resources, we observe a more than 12-fold reduction of service latency when incorporating our service split compared to on-client processing and and an increase in speed of more than 25% compared to performing everything on the server. Our approach is not only applicable to object detection, but can also be applied in a broad variety of machine learning-based applications and services. View Full-Text
Keywords: object detection; latency optimization; mobile edge cloud; connected autonomous cars; smart city; video surveillance object detection; latency optimization; mobile edge cloud; connected autonomous cars; smart city; video surveillance
Show Figures

Figure 1

MDPI and ACS Style

Xiang, Z.; Seeling, P.; Fitzek, F.H.P. You Only Look Once, But Compute Twice: Service Function Chaining for Low-Latency Object Detection in Softwarized Networks. Appl. Sci. 2021, 11, 2177. https://doi.org/10.3390/app11052177

AMA Style

Xiang Z, Seeling P, Fitzek FHP. You Only Look Once, But Compute Twice: Service Function Chaining for Low-Latency Object Detection in Softwarized Networks. Applied Sciences. 2021; 11(5):2177. https://doi.org/10.3390/app11052177

Chicago/Turabian Style

Xiang, Zuo, Patrick Seeling, and Frank H.P. Fitzek. 2021. "You Only Look Once, But Compute Twice: Service Function Chaining for Low-Latency Object Detection in Softwarized Networks" Applied Sciences 11, no. 5: 2177. https://doi.org/10.3390/app11052177

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop