BROWSE
Detail
Conference Paper
DNN Inference Offloading for Object Detection in 5G Multi-access Edge Computing
Cited 6 time in 
Share 
Share
- Authors
- Geun-Yong Kim, Ryangsoo Kim, Sungchang Kim, Ki-Dong Nam, Sung-Uk Rha, Jung-Hyun Yoon
- Issue Date
- 2021-10
- Citation
- International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.389-392
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- In this paper, we present experimental results of a Deep Neural Network (DNN) inference offloading in a realworld 5G MEC testbed to meet requirements for high detection accuracy and low end-to-end latency for object detection. Central Unit (CU), Distributed Unit (DU), Radio Unit (RU), and MEC servers are located in the 5G MEC testbed such that the performance of latency sensitive MEC applications could be tested. We implemented the DNN offloading by applying task pipeline parallelism and DNN task decoupling scheme from edge to MEC server. We verified the effectiveness of the DNN offloading using YOLOv3 in terms of Frames Per Second (FPS) and power consumption in the 5G MEC testbed.
- KSP Keywords
- Deep neural network(DNN), Detection accuracy, End to End(E2E), Frames per second(FPS), Latency-sensitive, Multi-access, Object detection, Power Consumption, Radio Unit(RU), edge computing, end-to-end latency