Abstract

Summarizing state-of-the-art machine learning techniques, we review their technical details and their performance in allocating bandwidth resource in support of latency-sensitive H2M applications. An evaluation of different techniques, in terms of problem formulation, time and memory costs, bandwidth prediction performance, is also presented.

© 2019 The Author(s)

PDF Article

References

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription