Publication: š¼-OMC: cost-aware deep learning for mobile network resource orchestration
Loading...
Identifiers
Publication date
2019-09-23
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Orchestrating resources in 5G and beyond-5G systems
will be substantially more complex than it used to be
in previous generations of mobile networks. In order to take
full advantage of the unprecedented possibilities for dynamic
reconfiguration offered by network softwarization and virtualization
technologies, operators have to embed intelligence in
network resource orchestrators. We advocate that the automated,
data-driven decisions taken by orchestrators must be guided by
considerations on the cost that such decisions involve for the
operator. We show that such a strategy can be implemented via
a deep learning architecture that forecasts capacity rather than
plain traffic, thanks to a novel loss function named alfa-OMC. We
investigate the convergence properties of alfa-OMC, and provide
preliminary results on the performance of the learning process
in case studies with real-world mobile network traffic.
Description
Proceeding of: The 2nd International Workshop on Network Intelligence (NI 2019): Machine Learning for Networking (part of 2019 IEEE International Conference on Computer Communications (IEEE INFOCOM 2019)), 29 April, 2019, Paris, France
Keywords
5G networks, Deep learning, Mobile networks
Bibliographic citation
IEEE INFOCOM 2019- IEEE Conference on Computer Communications, 29 April-2 May 2019, Paris, France [proceedings], 6 pp.