Method and system for managing components of a fifth generation (5G) network slice
The disclosure relates to a method and system, for managing components of a fifth generation (5G) network slice. The method comprises retrieving current locations of a plurality of user equipments (UEs) connected to radio base stations (RBSs) in communication with the 5G network slice; predicting future traffic at the RBSs based on past and current locations of the plurality of UEs; and managing the components of the 5G network slice based on the predicted future traffic patterns.
1. A method for managing components of a fifth generation (5G) network slice, comprising:
retrieving current locations of a plurality of user equipments (UEs) connected to radio base stations (RBSs) in communication with the 5G network slice;
predicting future traffic at the RBSs based on past and current locations of the plurality of UEs, wherein predicting the future traffic comprises feeding a reinforcement learning algorithm with a graphic or a non-graphic distribution, the graphic or non-graphic distribution representing past and current traffic and the past and current locations of the plurality of UEs, and predicting resources needed within the 5G network slice for handling the predicted future traffic at the RBSs; and
managing the components of the 5G network slice based on the predicted future traffic patterns.
2. The method of claim 1 , wherein the past and current locations of the plurality of UEs are collected through a mobility management (MM) node.
3. The method of claim 1 , wherein the reinforcement learning algorithm is based on a convolution neural network (CNN).
4. The method of claim 1 , wherein the resources needed within the 5G network slice comprise packet delivery service instances (PDSIs).
5. The method of claim 1 , wherein managing components of the 5G network slice comprises generating a policy based on the predicted future traffic and sending the policy to a 5G software-defined mobile network orchestrator for enforcing the policy.
6. The method of claim 1 , wherein managing components of the 5G network slice comprises deploying a new PDSI within the 5G network slice.
7. The method of claim 6 , further comprising configuring a packet data convergence protocol (PDCP) for routing future traffic towards the new PDSI.
8. The method of claim 1 , wherein managing components of the 5G network slice comprise tearing down an extra PDSI within the 5G network slice.
9. The method of claim 1 , wherein the 5G network slice uses physical resources of physical delivery nodes located in data centers, each delivery node having a computational capacity, storage and network connectivity dedicated to the 5G network slice and wherein managing components of the 5G network slice comprises coordinating and orchestrating the use of the physical delivery nodes while respecting network slicing constraints defined for different service providers.
10. The method of claim 1 , wherein the steps of the method are executed at predefined time intervals.
11. A system for managing components of a fifth generation (5G) network slice comprising processing circuits and a memory, the memory containing instructions executable by the processing circuits whereby the system is operative to:
retrieve current locations of a plurality of user equipments (UEs) connected to radio base stations (RBSs) in communication with the 5G network slice;
predict future traffic at the RBSs based on past and current locations of the plurality of UEs;
feed a reinforcement learning algorithm with a graphic or a non-graphic distribution, the graphic or non-graphic distribution representing the past and current traffic and the past and current locations of the plurality of UEs, and to predict resources needed within the 5G network slice for handling the future traffic at the RBSs; and
manage the components of the 5G network slice based on the predicted future traffic patterns.
12. The system of claim 11 , wherein the past and current locations of the plurality of UEs are collected through a mobility management (MM) node.
13. The system of claim 11 , wherein the reinforcement learning algorithm is based on a convolution neural network (CNN).
14. The system of claim 11 , wherein the resources needed within the 5G network slice comprise packet delivery service instances (PDSIs).
15. The system of claim 11 , further operative to generate a policy based on the predicted future traffic and to send the policy to a 5G software-defined mobile network orchestrator for enforcing the policy.
16. The system of claim 11 , further operative to deploy a new PDSI within the 5G network slice.
17. The system of claim 16 , further operative to configure a packet data convergence protocol (PDCP) for routing future traffic towards the new PDSI.
18. The system of claim 11 , further operative to tear down an extra PDSI within the 5G network slice.
19. The system of claim 11 , wherein the 5G network slice uses physical resources of physical delivery nodes located in data centers, each delivery node having a computational capacity, storage and network connectivity dedicated to the 5G network slice and further operative to coordinate and orchestrate the use of the physical delivery nodes while respecting network slicing constraints defined for different service providers.
20. The system of claim 11 , further operative to execute operations at predefined time intervals.
21. A non-transitory computer readable media having stored thereon instructions for managing components of a fifth generation (5G) network slice-the instructions comprising:
retrieving current locations of a plurality of user equipments (UEs) connected to radio base stations (RBSs) in communication with the 5G network slice;
predicting future traffic at the RBSs based on past and current locations of the plurality of UEs, wherein predicting the future traffic comprises feeding a reinforcement learning algorithm with a graphic or a non-graphic distribution, the graphic or non-graphic distribution representing past and current traffic and the past and current locations of the plurality of UEs, and predicting resources needed within the 5G network slice for handling the predicted future traffic at the RBSs; and
managing the components of the 5G network slice based on the predicted future traffic patterns.