Advanced search
2 files | 5.11 MB Add to list

Design and evaluation of learning algorithms for dynamic resource management in virtual networks

Author
Organization
Abstract
Network virtualisation is considerably gaining attention as a solution to ossification of the Internet. However, the success of network virtualisation will depend in part on how efficiently the virtual networks utilise substrate network resources. In this paper, we propose a machine learning-based approach to virtual network resource management. We propose to model the substrate network as a decentralised system and introduce a learning algorithm in each substrate node and substrate link, providing self-organization capabilities. We propose a multiagent learning algorithm that carries out the substrate network resource management in a coordinated and decentralised way. The task of these agents is to use evaluative feedback to learn an optimal policy so as to dynamically allocate network resources to virtual nodes and links. The agents ensure that while the virtual networks have the resources they need at any given time, only the required resources are reserved for this purpose. Simulations show that our dynamic approach significantly improves the virtual network acceptance ratio and the maximum number of accepted virtual network requests at any time while ensuring that virtual network quality of service requirements such as packet drop rate and virtual link delay are not affected.
Keywords
Network virtualization, IBCN, Dynamic Resource Allocation, Virtual Network Embedding, Artificial Intelligence, Machine Learning, Reinforcement Learning, Multiagent Systems

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 2.50 MB
  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 2.60 MB

Citation

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

MLA
Mijumbi, R., et al. “Design and Evaluation of Learning Algorithms for Dynamic Resource Management in Virtual Networks.” IEEE IFIP Network Operations and Management Symposium, 2014, pp. 1–9.
APA
Mijumbi, R., Serrat, J., Gorricho, J., Claeys, M., De Turck, F., & Latré, S. (2014). Design and evaluation of learning algorithms for dynamic resource management in virtual networks. IEEE IFIP Network Operations and Management Symposium, 1–9.
Chicago author-date
Mijumbi, R, J Serrat, JL Gorricho, Maxim Claeys, Filip De Turck, and Steven Latré. 2014. “Design and Evaluation of Learning Algorithms for Dynamic Resource Management in Virtual Networks.” In IEEE IFIP Network Operations and Management Symposium, 1–9.
Chicago author-date (all authors)
Mijumbi, R, J Serrat, JL Gorricho, Maxim Claeys, Filip De Turck, and Steven Latré. 2014. “Design and Evaluation of Learning Algorithms for Dynamic Resource Management in Virtual Networks.” In IEEE IFIP Network Operations and Management Symposium, 1–9.
Vancouver
1.
Mijumbi R, Serrat J, Gorricho J, Claeys M, De Turck F, Latré S. Design and evaluation of learning algorithms for dynamic resource management in virtual networks. In: IEEE IFIP Network Operations and Management Symposium. 2014. p. 1–9.
IEEE
[1]
R. Mijumbi, J. Serrat, J. Gorricho, M. Claeys, F. De Turck, and S. Latré, “Design and evaluation of learning algorithms for dynamic resource management in virtual networks,” in IEEE IFIP Network Operations and Management Symposium, Krakow, Poland, 2014, pp. 1–9.
@inproceedings{4431119,
  abstract     = {{Network virtualisation is considerably gaining attention as a solution to ossification of the Internet. However, the success of network virtualisation will depend in part on how efficiently the virtual networks utilise substrate network resources. In this paper, we propose a machine learning-based approach to virtual network resource management. We propose to model the substrate network as a decentralised system and introduce a learning algorithm in each substrate node and substrate link, providing self-organization capabilities. We propose a multiagent learning algorithm that carries out the substrate network resource management in a coordinated and decentralised way. The task of these agents is to use evaluative feedback to learn an optimal policy so as to dynamically allocate network resources to virtual nodes and links. The agents ensure that while the virtual networks have the resources they need at any given time, only the required resources are reserved for this purpose. Simulations show that our dynamic approach significantly improves the virtual network acceptance ratio and the maximum number of accepted virtual network requests at any time while ensuring that virtual network quality of service requirements such as packet drop rate and virtual link delay are not affected.}},
  author       = {{Mijumbi, R and Serrat, J and Gorricho, JL and Claeys, Maxim and De Turck, Filip and Latré, Steven}},
  booktitle    = {{IEEE IFIP Network Operations and Management Symposium}},
  isbn         = {{9781479909131}},
  keywords     = {{Network virtualization,IBCN,Dynamic Resource Allocation,Virtual Network Embedding,Artificial Intelligence,Machine Learning,Reinforcement Learning,Multiagent Systems}},
  language     = {{eng}},
  location     = {{Krakow, Poland}},
  pages        = {{1--9}},
  title        = {{Design and evaluation of learning algorithms for dynamic resource management in virtual networks}},
  year         = {{2014}},
}

Web of Science
Times cited: