Adaptive location-based SD-WAN policies
An example method includes receiving, by an SD-WAN system, WAN link characterization data for a plurality of WAN links of the SD-WAN system over a time period; and for each site of a plurality of sites of the SD-WAN system, generating, by the SD-WAN system, a local policy for the site, wherein generating the local policy is based on a machine learning model trained with the WAN link characterization data for the plurality of WAN links, and providing the local policy to an SD-WAN edge device of the site.
1. A method comprising:
obtaining, by a network system, characterization data for one or more wide area network (WAN) links;
generating, by the network system and based on a global policy and a machine learning model, a policy for a site of the network system, wherein the global policy comprises one or more rules applicable to a plurality of sites of the network, and wherein the machine learning model is trained with the characterization data for the one or more WAN links; and
providing, by the network system and to a device associated with the site, the policy for the site.
2. The method of claim 1 , wherein the device associated with the site comprises a software-defined wide area network (SD-WAN) edge device.
3. The method of claim 1 , wherein generating the policy includes generating the policy based on a location of the device associated with the site.
4. The method of claim 1 , wherein the machine learning model is trained with policy parameters being applied at a time the characterization data was collected.
5. The method of claim 1 , wherein the WAN link characterization data includes one or more of jitter, latency, time to first packet, packet loss, and maximum transmission unit (MTU) for each of the one or more WAN links.
6. The method of claim 5 , further comprising determining, by the network system, the packet loss based on determining a number of packets transmitted by the device associated with the site that did not reach destination devices specified in the packets.
7. The method of claim 1 , wherein the policy includes a rule to determine whether to reassign the device from a first WAN link associated with the device to a second WAN link associated with the device, wherein the rule includes a quality parameter or a cost factor associated with each of the first WAN link and the second WAN link.
8. The method of claim 1 , wherein generating the policy comprises generating a service policy for each service of one or more services.
9. A network system comprising processing circuitry in communication with memory and configured to:
obtain characterization data for one or more wide area network (WAN) links;
generate, based on a global policy and a machine learning model, a policy for a site of the network system, wherein the global policy comprises one or more rules applicable to a plurality of sites of the network, and wherein the machine learning model is trained with the characterization data for the one or more WAN links; and
provide, to a device associated with the site, the policy for the site.
10. The network system of claim 9 , wherein the device associated with the site comprises a software-defined wide area network (SD-WAN) edge device.
11. The network system of claim 9 , wherein the processing circuitry is configured to generate the policy based on a location of the device associated with the site.
12. The network system of claim 9 , wherein the machine learning model is trained with policy parameters being applied at a time the characterization data was collected.
13. The network system of claim 9 , wherein the characterization data includes one or more of jitter, latency, time to first packet, packet loss, and maximum transmission unit (MTU) for each of the one or more WAN links.
14. The network system of claim 13 , wherein the processing circuitry is further configured to determine the packet loss based on a number of packets transmitted by the device associated with the site that did not reach destination devices specified in the packets.
15. The network system of claim 9 , wherein the policy includes a rule to determine whether to reassign the device from a first WAN link associated with the device to a second WAN link associated with the device, wherein the rule includes a quality parameter or a cost factor associated with each of the first WAN link and the second WAN link.
16. The network system of claim 9 , wherein the policy comprises a service policy associated with a service, and wherein the processing circuitry is configured to generate a corresponding service policy for each service of one or more services.
17. Non-transitory computer-readable storage media comprising instructions that, when executed, configure processing circuitry of a computing system to:
obtain characterization data for one or more wide area network (WAN) links;
generate, based on a global policy and a machine learning model, a policy for a site of a network system, wherein the global policy comprises one or more rules applicable to a plurality of sites of the network system, and wherein the machine learning model is trained with the characterization data for the one or more WAN links; and
provide, to a device associated with the site, the policy for the site.
18. The non-transitory computer-readable storage media of claim 17 , wherein the instructions to generate comprise instructions to generate the policy based on a location of the device associated with the site.
19. The non-transitory computer-readable storage media of claim 17 , wherein the policy includes a rule to determine whether to reassign the device from a first WAN link associated with the device to a second WAN link associated with the device, wherein the rule includes a quality parameter or a cost factor associated with each of the first WAN link and the second WAN link.
20. The non-transitory computer-readable storage media of claim 17 , wherein the instructions to obtain the characterization data comprise instructions to obtain characterization data for a plurality of WAN links of the network system over a time period.