Dynamic inter-cloud placement of virtual network functions for a slice
Examples can include an optimizer that dynamically determines where to place virtual network functions for a slice in a distributed Telco cloud network. The optimizer can determine a slice path that complies with a service level agreement and balances network load. The virtual network functions of the slice can be provisioned at clouds identified by the optimal slice path. In one example, performance metrics are normalized, and tenant-selected weights can be applied. This can allow the optimizer to prioritize particular SLA attributes in choosing an optimal slice path.
1. A method for dynamic inter-cloud placement of virtual network functions (“VNFs”) in a slice path, comprising:
receiving a graphical user interface (“GUI”) selection that adjusts relative weights of first and second service level agreement (“SLA”) attributes, wherein the first and second SLA attributes differ from one another and correspond to a same slice;
determining candidate slice paths relative to an edge cloud, wherein the candidate slice paths include different combinations of VNFs to clouds;
ranking the candidate slice paths based on performance metrics and a load for each candidate slice path,
wherein the load for the candidate slice path is based on load values of the clouds for that candidate slice path,
wherein the performance metrics for the candidate slice path correspond to the first and second SLA attributes, and
wherein the performance metrics are weighted according to the adjusted relative weights of the first and second SLA attributes; and
instantiating the VNFs at the clouds specified by a top ranked slice path.
2. The method of claim 1 , wherein ranking the candidate slice paths further includes normalizing the performance metrics and eliminating candidate slice paths with normalized performance metrics below a threshold.
3. The method of claim 1 , further comprising dynamically redistributing at least one of the VNFs, the redistributing including:
determining a new ranking of candidate slice paths; and
provisioning at least one of the VNFs at a new cloud specified by a new top ranked slice path.
4. The method of claim 1 , further comprising:
receiving a second GUI selection to modify a slice record to include a VNF attribute for a first VNF, wherein ranking the candidate slice paths includes weighting a candidate slice path favorably when the first VNF is assigned to a cloud that satisfies the VNF attribute.
5. The method of claim 1 , wherein determining candidate slice paths includes omitting slice paths that assign a first VNF to a cloud located outside a geographic location specified in a slice record.
6. The method of claim 1 , wherein the top ranked candidate slice path is chosen based on a lowest composite score of multiple candidate slice paths, and wherein the composite score includes adding a weighted cloud load to the relatively weighted performance metrics.
7. The method of claim 1 , further comprising:
ranking the candidate slice paths based on normalized performance metrics, wherein a transform table maps the performance metrics to normalization functions that are based on the SLA attributes.
8. A non-transitory, computer-readable medium comprising instructions that, when executed by a processor, perform stages for dynamically placing virtual network functions (“VNFs”) in a slice, the stages comprising:
receiving a graphical user interface (“GUI”) selection that adjusts relative weights of first and second service level agreement (“SLA”) attributes, wherein the first and second SLA attributes differ from one another and correspond to a same slice;
determining candidate slice paths relative to an edge cloud, wherein the candidate slice paths include different combinations of VNFs to clouds;
ranking the candidate slice paths based on performance metrics and a load for each candidate slice path,
wherein the load for the candidate slice path is based on load values of the clouds of that candidate slice path,
wherein the performance metrics for the candidate slice path correspond to the first and second SLA attributes, and
wherein the performance metrics are weighted according to the adjusted relative weights of the first and second SLA attributes; and
instantiating the VNFs at the clouds specified by a top ranked slice path.
9. The non-transitory, computer-readable medium of claim 8 , wherein ranking the candidate slice paths further includes normalizing the performance metrics and eliminating candidate slice paths with normalized performance metrics below a threshold.
10. The non-transitory, computer-readable medium of claim 8 , the stages further comprising dynamically redistributing at least one of the VNFs, the redistributing including:
determining a new ranking of candidate slice paths; and
provisioning at least one of the VNFs at a new cloud specified by a new top ranked slice path.
11. The non-transitory, computer-readable medium of claim 8 , the stages further comprising:
receiving a second GUI selection to modify a slice record to include a VNF attribute for a first VNF, wherein ranking the candidate slice paths includes weighting a candidate slice path favorably when the first VNF is assigned to a cloud that satisfies the VNF attribute.
12. The non-transitory, computer-readable medium of claim 8 , wherein determining candidate slice paths includes omitting slice paths that assign a first VNF to a cloud located outside a geographic location specified in a slice record.
13. The non-transitory, computer-readable medium of claim 8 , wherein the top ranked candidate slice path is chosen based on a lowest composite score of multiple candidate slice paths, and wherein the composite score includes adding a weighted cloud load to the relatively weighted performance metrics.
14. The non-transitory, computer-readable medium of claim 8 , the stages further comprising:
ranking the candidate slice paths based on normalized performance metrics, wherein a transform table maps the performance metrics to normalization functions that are based on the SLA attributes.
15. A system for dynamically placing virtual network functions (“VNFs”) in a slice, comprising:
a non-transitory, computer-readable medium containing instructions; and
at least one processor that executes the instructions to perform stages comprising:
receiving a graphical user interface (“GUI”) selection that adjusts relative weights of first and second service level agreement (“SLA”) attributes, wherein the first and second SLA attributes differ from one another and correspond to a same slice;
determining candidate slice paths relative to an edge cloud, wherein the candidate slice paths include different combinations of VNFs to clouds;
ranking the candidate slice paths based on performance metrics and a load for each candidate slice path,
wherein the load for the candidate slice path is based on load values of the clouds of that candidate slice path,
wherein the performance metrics for the candidate slice path correspond to the first and second SLA attributes, and
wherein the performance metrics are weighted according to the adjusted relative weights of the first and second SLA attributes; and
instantiating the VNFs at the clouds specified by a top ranked slice path.
16. The system of claim 15 , wherein ranking the candidate slice paths further includes normalizing the performance metrics and eliminating candidate slice paths with normalized performance metrics below a threshold.
17. The system of claim 15 , the stages further comprising dynamically redistributing at least one of the VNFs, the redistributing including:
determining a new ranking of candidate slice paths; and
provisioning at least one of the VNFs at a new cloud specified by a new top ranked slice path.
18. The system of claim 15 , the stages further comprising:
receiving a second GUI selection to modify a slice record to include a VNF attribute for a first VNF, wherein ranking the candidate slice paths includes weighting a candidate slice path favorably when the first VNF is assigned to a cloud that satisfies the VNF attribute.
19. The system of claim 15 , wherein the top ranked candidate slice path is chosen based on a lowest composite score of multiple candidate slice paths, and wherein the composite score includes adding a weighted cloud load to the relatively weighted performance metrics.
20. The system of claim 15 , the stages further comprising:
ranking the candidate slice paths based on normalized performance metrics, wherein a transform table maps the performance metrics to normalization functions that are based on the SLA attributes.