In the last decade, deep neural network (DNN)-based object detection technologies have received significant attention as a promising solution to implement a variety of image understanding and video analysis applicatio...
详细信息
In the last decade, deep neural network (DNN)-based object detection technologies have received significant attention as a promising solution to implement a variety of image understanding and video analysis applications on mobile edge devices. However, the execution of computationally intensive DNN-based object detection workloads in mobile edge devices is insufficient in fulfilling the object detection requirements with high accuracy and low latency, owing to the limited computation capacity. In this paper, we implement and evaluate a DNN-based object detection offloading framework to improve the object detection performance of mobile edge devices by offloading computation-intensive workloads to a remote edge server. However, preliminary experimental results have shown that offloading all object detection workloads of mobile edge devices may lead to worse performance than executing the workloads locally. This degradation is obtained from the inefficient resource utilization in the edge computing architectures, both for the edge server and mobile edge devices. To resolve the aforementioned problem with degradation, we devise a device-aware DNN offloading decision algorithm that is aimed to maximize resource utilization in the edge computing architecture. The proposed algorithm decides whether or not to offload the object detection workloads of edge devices by considering their computing power and network bandwidth, and therefore maximizing their average object detection processing frames per second. Through various experiments conducted in a real-life wireless local area network (WLAN) environment, we verified the effectiveness of the proposed DNN-based object detection offloading framework.
Recent advances in artificial intelligence, especially deeplearning techniques, are attracting attention as promising solutions due to their high accuracy in a variety of applications. The deeplearning technique req...
详细信息
ISBN:
(纸本)9781665423830
Recent advances in artificial intelligence, especially deeplearning techniques, are attracting attention as promising solutions due to their high accuracy in a variety of applications. The deeplearning technique requires high computational resources in the training and inference phases, and therefore, it is important to efficiently operate a deeplearning application in edge servers equipped with limited computing resources. For efficiently operating deeplearning applications in edge computing, the offloading method becomes one of the most promising solutions. In this paper, we introduce a deep learning offloading framework for optimizing GPU resource utilization in edge computing architecture. The proposed framework operates on an open-source container orchestration system, Kubernetes, which is used for managing multiple number of object detection offloading microservices running on an edge server. Through the real-world experimental results, we verify that the proposed framework enhances the performance of object detection offloading service by leveraging GPU utilization of edge server throughout applying Kubernetes-based container service orchestration.
暂无评论