IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

KubEVC-Agent : Kubernetes Edge Vision Cluster Agent for Optimal DNN Inference and Operation

KubEVC-Agent : 머신러닝 추론 엣지 컴퓨팅 클러스터 관리 자동화 시스템

  • Received : 2023.09.27
  • Accepted : 2023.11.06
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

With the advancement of artificial intelligence and its various use cases, accessing it through edge computing environments is gaining traction. However, due to the nature of edge computing environments, efficient management and optimization of clusters distributed in different geographical locations is considered a major challenge. To address these issues, this paper proposes a centralization and automation tool called KubEVC-Agent based on Kubernetes. KubEVC-Agent centralizes the deployment, operation, and management of edge clusters and presents a use case of the data transformation for optimizing intra-cluster communication. This paper describes the components of KubEVC-Agent, its working principle, and experimental results to verify its effectiveness.

Keywords

Acknowledgement

이 논문은 2023년도 정부 (과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임 (No. 2021-0-00907, 능동적 즉시 대응 및 빠른 학습이 가능한 적응형 경량 엣지 연동분석 기술개발).

References

  1. H. Hua, Y. Li, T. Wang, N. Dong, W. Li, J. Cao, "Edge Computing with Artificial Intelligence: A Machine Learning Perspective," ACM Comput. Surv. Vol. 55, No. 9, pp. 1-35 2023. https://doi.org/10.1145/3555802
  2. J. Chen, X. Ran, "Deep Learning With Edge Computing: A Review," IEEE, Vol. 107, No. 8, pp. 1655-1674, 2019. https://doi.org/10.1109/JPROC.2019.2921977
  3. A. Marchisio, M. A. Hanif, F. Khalid, G. Plastiras, C. Kyrkou, T. Theocharides, M. Shafique, "Deep Learning for Edge Computing: Current Trends, Cross-Layer Optimizations, and Open Research Challenges," IEEE, pp. 553-559, 2019.
  4. https://kubernetes.io/
  5. https://www.ansible.com/
  6. M. Artac, T. Borovssak, E. D. Nitto, M. Guerriero, D. A. Tamburri, "DevOps: Introducing Infrastructure-as-Code," IEEE, pp. 497-498, 2017.
  7. https://k3s.io/
  8. https://grpc.io/
  9. S. Popic, D. Pezer, B. Mrazovac, N. Teslic, "Performance Evaluation of Using Protocol Buffers in the Internet of Things Communication," IEEE, pp. 261-265, 2016.
  10. https://prometheus.io/
  11. https://grafana.com/
  12. http://kubevc.ddps.cloud/
  13. https://www.tensorflow.org/
  14. A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam, "Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications," arXiv Preprint arXiv:1704.04861, pp. 1-9, 2017.
  15. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, "Rethinking the Inception Architecture for Computer Vision," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818-2826, 2016.
  16. J. Redmon, S. Divvala, R. Girshick, A. Farhadi. "You Only Look Once: Unified, Real-time Object Detection," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, 2016.
  17. J. Devlin, M. W. Chang, K. Lee, K. Toutanova, "Bert: Pre-training of Deep Bidirectional Transformers for Language Understanding" arXiv Preprint arXiv:1810.04805, pp. 1-16, 2018.