ETRI-Knowledge Sharing Plaform



논문 검색
구분 SCI
연도 ~ 키워드


학술대회 Kubernetes-based DL Offloading Framework for Optimizing GPU Utilization in Edge Computing
Cited 2 time in scopus Download 3 time Share share facebook twitter linkedin kakaostory
김철원, 김량수, 김근용, 김성창
International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.143-146
21ZK1100, 호남권 지역산업 기반 ICT 융합기술 고도화 지원사업, 이길행
Recent advances in artificial intelligence, especially deep learning techniques, are attracting attention as promising solutions due to their high accuracy in a variety of applications. The deep learning technique requires high computational resources in the training and inference phases, and therefore, it is important to efficiently operate a deep learning application in edge servers equipped with limited computing resources. For efficiently operating deep learning 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.
KSP 제안 키워드
Computing resources, Container orchestration, Deep learning application, GPU utilization, High accuracy, Object detection, Open source, Orchestration system, Real-world, Service orchestration, artificial intelligence