Advanced search
2 files | 1.23 MB Add to list
Author
Organization
Abstract
Many media services undergo a varying workload, showing periodic usage patterns or unexpected traffic surges. As cloud and NFV services are increasingly softwarized, they enable a fully dynamic deployment and scaling behaviour. At the same time, there is an increasing need for fast and efficient mechanisms to allocate sufficient resources with the same elasticity, only when they are needed. This requires adequate performance models of the involved services, as well as awareness of those models in the involved orchestration machinery. In this paper we present how a scalable content delivery service can be deployed in a resource- and time-efficient manner, using adaptive machine learning models for performance profiling. We include orchestration mechanisms which are able to act upon the profiled knowledge in a dynamic manner. Using an offline profiled performance model of the service, we are able to optimize the online service orchestration, requiring fewer scaling iterations.
Keywords
VNF, NFV, Machine Learning, Performance Profiling

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 803.92 KB
  • 7732 i.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 430.31 KB

Citation

Please use this url to cite or link to this publication:

MLA
Van Rossem, Steven, et al. “Adaptive & Learning-Aware Orchestration of Content Delivery Services.” 2020 6th IEEE Conference on Network Softwarization (NetSoft), Proceedings : Bridging the Gap between Ai and Network Softwarization, edited by F De Turck et al., IEEE, 2020, pp. 77–84, doi:10.1109/NetSoft48620.2020.9165475.
APA
Van Rossem, S., Soenen, T., Tavernier, W., Colle, D., Pickavet, M., & Demeester, P. (2020). Adaptive & learning-aware orchestration of content delivery services. In F. De Turck, P. Chemouil, T. Wauters, M. Zhani, W. Cerroni, R. Pasquini, & Z. Zhu (Eds.), 2020 6th IEEE Conference on Network Softwarization (NetSoft), Proceedings : Bridging the Gap between Ai and Network Softwarization (pp. 77–84). Ghent, Belgium - online: IEEE. https://doi.org/10.1109/NetSoft48620.2020.9165475
Chicago author-date
Van Rossem, Steven, Thomas Soenen, Wouter Tavernier, Didier Colle, Mario Pickavet, and Piet Demeester. 2020. “Adaptive & Learning-Aware Orchestration of Content Delivery Services.” In 2020 6th IEEE Conference on Network Softwarization (NetSoft), Proceedings : Bridging the Gap between Ai and Network Softwarization, edited by F De Turck, P Chemouil, T Wauters, MF Zhani, W Cerroni, R Pasquini, and Z Zhu, 77–84. IEEE. https://doi.org/10.1109/NetSoft48620.2020.9165475.
Chicago author-date (all authors)
Van Rossem, Steven, Thomas Soenen, Wouter Tavernier, Didier Colle, Mario Pickavet, and Piet Demeester. 2020. “Adaptive & Learning-Aware Orchestration of Content Delivery Services.” In 2020 6th IEEE Conference on Network Softwarization (NetSoft), Proceedings : Bridging the Gap between Ai and Network Softwarization, ed by. F De Turck, P Chemouil, T Wauters, MF Zhani, W Cerroni, R Pasquini, and Z Zhu, 77–84. IEEE. doi:10.1109/NetSoft48620.2020.9165475.
Vancouver
1.
Van Rossem S, Soenen T, Tavernier W, Colle D, Pickavet M, Demeester P. Adaptive & learning-aware orchestration of content delivery services. In: De Turck F, Chemouil P, Wauters T, Zhani M, Cerroni W, Pasquini R, et al., editors. 2020 6th IEEE Conference on Network Softwarization (NetSoft), Proceedings : Bridging the Gap between Ai and Network Softwarization. IEEE; 2020. p. 77–84.
IEEE
[1]
S. Van Rossem, T. Soenen, W. Tavernier, D. Colle, M. Pickavet, and P. Demeester, “Adaptive & learning-aware orchestration of content delivery services,” in 2020 6th IEEE Conference on Network Softwarization (NetSoft), Proceedings : Bridging the Gap between Ai and Network Softwarization, Ghent, Belgium - online, 2020, pp. 77–84.
@inproceedings{8669261,
  abstract     = {{Many media services undergo a varying workload, showing periodic usage patterns or unexpected traffic surges. As cloud and NFV services are increasingly softwarized, they enable a fully dynamic deployment and scaling behaviour. At the same time, there is an increasing need for fast and efficient mechanisms to allocate sufficient resources with the same elasticity, only when they are needed. This requires adequate performance models of the involved services, as well as awareness of those models in the involved orchestration machinery. In this paper we present how a scalable content delivery service can be deployed in a resource- and time-efficient manner, using adaptive machine learning models for performance profiling. We include orchestration mechanisms which are able to act upon the profiled knowledge in a dynamic manner. Using an offline profiled performance model of the service, we are able to optimize the online service orchestration, requiring fewer scaling iterations.}},
  author       = {{Van Rossem, Steven and Soenen, Thomas and Tavernier, Wouter and Colle, Didier and Pickavet, Mario and Demeester, Piet}},
  booktitle    = {{2020 6th IEEE Conference on Network Softwarization (NetSoft), Proceedings : Bridging the Gap between Ai and Network Softwarization}},
  editor       = {{De Turck, F and Chemouil, P and Wauters, T and Zhani, MF and Cerroni, W and Pasquini, R and Zhu, Z}},
  isbn         = {{9781728156842}},
  keywords     = {{VNF,NFV,Machine Learning,Performance Profiling}},
  language     = {{eng}},
  location     = {{Ghent, Belgium - online}},
  pages        = {{77--84}},
  publisher    = {{IEEE}},
  title        = {{Adaptive & learning-aware orchestration of content delivery services}},
  url          = {{http://dx.doi.org/10.1109/NetSoft48620.2020.9165475}},
  year         = {{2020}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: