DNN inference offloading for object detection in 5G multi-access edge computing

Kim, Geun-Yong; Kim, Ryangsoo; Kim, Sungchang; Nam, Ki-Dong; Rha, Sung-Uk; Yoon, Junghyun

doi:10.1109/ictc52510.2021.9620821

Cited by 4 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5G provides ultra-low-latency, high-reliability connections for the end devices. In [7], Kim et al leveraged the low transmission latency of 5G by combining 5G and MEC to bring the computing power closer to the end devices and reduce the applications latency. Thus, the combination of 5G and MEC makes it excellent for various image and video analysis applications.…”

Section: Related Workmentioning

confidence: 99%

QoC-Driven MEC Transfer System Framework in Wireless Networks

Zhao

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In this paper, we propose a Heterogeneous MEC System Framework based on Transfer Learning (HMECSF-TL), which uses convolutional neural network (CNN) to process few training samples. In view of the time-varying network environment and the limited end devices resources, the HMECSF-TL framework uses transfer learning (TL) technology to optimize the CNN model and jointly optimizes the allocation of computing resources and communication resources, which is beneficial to achieve the dual goals of extending the use time of end devices and improving the speed and the accuracy of image classification. We first introduce the Quality of Content (QoC)-driven MEC transfer system architecture of cloud-edge-end. The cloud server uses the existing image dataset to train the general neural network model in advance and transfer the general model to the edge servers, and then the edge servers deploy the local models to the end devices to form the personalized models. Then, considering the time-varying situation of the network environment, in order to get the updated model faster and better, we present the process of collaborative optimization of model between the edge sever and multiple end devices, using an edge server as an example. Considering the limited resources of the end devices, we propose a joint optimization of energy and latency with the goal of minimizing offloading cost, in order to rapidly improve the speed and the accuracy of image classification with few training samples under the premise of rational resource allocation and verify the performance of the framework experimentally. Simulation results show that the proposed HMECSF-TL framework outperforms the benchmark strategy without TL in terms of reducing the model training time and improving the image classification accuracy, as well as reducing the offloading cost.

show abstract

Section: Related Workmentioning

confidence: 99%

QoC-Driven MEC Transfer System Framework in Wireless Networks

Zhao

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Kim et al present experimental results of DNN inference offloading in a real-world 5G MEC testbed to meet requirements for high detection accuracy and low end-to-end latency for object detection [14]. They implement the DNN offloading by applying task pipeline parallelism and a DNN task-decoupling scheme from the edge to the MEC server.…”

Section: Collborative Inferencementioning

confidence: 99%

A Collaborative Inference Algorithm in Low-Earth-Orbit Satellite Network for Unmanned Aerial Vehicle

Xu,

Zhang,

et al. 2023

Drones

View full text Add to dashboard Cite

In recent years, the low-Earth-orbit (LEO) satellite network has achieved considerable development. Moreover, it is necessary to introduce edge computing into LEO networks, which can provide high-quality services, such as worldwide seamless low-delay computation offloading for unmanned aerial vehicles (UAVs) or user terminals and nearby remote-sensing data processing for UAVs or satellites. However, because the computation resource of the satellite is relatively scarce compared to the ground server, it is hard for a single satellite to complete massive deep neural network (DNN) inference tasks in a short time. Consequently, in this paper, we focus on the multi-satellite collaborative inference problem and propose a novel COllaborative INference algorithm for LEO edge computing called COIN-LEO. COIN-LEO manages to split the complete DNN model into several submodels consisting of some consecutive layers and deploy these submodels to several satellites for inference. We innovatively leverage deep reinforcement learning (DRL) to efficiently split the model and use a neural network (NN) to predict the time required for inference tasks of a specific submodel on a specific satellite. By implementing COIN-LEO and evaluating its performance in a highly realistic satellite-network-emulation platform, we find that our COIN-LEO outperforms baseline algorithms in terms of inference throughput, time consumed and network traffic overhead.

show abstract

Real-Time Facial Emotion Detection Through the Use of Machine Learning and On-Edge Computing

Dowd

Tonekaboni

2022

2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

DNN inference offloading for object detection in 5G multi-access edge computing

Cited by 4 publications

References 4 publications

QoC-Driven MEC Transfer System Framework in Wireless Networks

QoC-Driven MEC Transfer System Framework in Wireless Networks

A Collaborative Inference Algorithm in Low-Earth-Orbit Satellite Network for Unmanned Aerial Vehicle

Real-Time Facial Emotion Detection Through the Use of Machine Learning and On-Edge Computing

Contact Info

Product

Resources

About