Abstract
Described herein are techniques for activating the appropriate set of mechanisms in a 5G network and for determining the appropriate set of parameters for those mechanisms. This may help create a network slice in the network with specific constraints (e.g., reliability, latency, throughput etc.). These techniques may also enable adjusting mechanisms and/or associated parameters as the situation changes in the network. Currently, it is difficult to select (and dynamically update if needed) the appropriate set of mechanisms and associated parameters. The methods described herein may be located at a digital network center for private 5G networks or at a Network Data Analytics Function (NWDAF) (i.e., in a 5G core network) for private enterprises or Service Provider (SP) scenarios. Alternatively, these techniques may be distributed across multiple entities (e.g., Multi-access Edge Computing (MEC), NWDAF, digital network center, etc.).
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Taneja, Mukesh and Jain, Sudhir, "SELECTION OF SUITABLE MECHANISMS AND ASSOCIATED PARAMETERS FOR A NETWORK SLICE IN A 5G NETWORK USING MACHINE LEARNING APPROACHES", Technical Disclosure Commons, (July 01, 2019)
https://www.tdcommons.org/dpubs_series/2318