# US 2022/0286388 A1 · Predictive routing-based policy adjustments in software-defined networks

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0286388 A1
- Document ID: US20220286388A1
- Status: Published application
- Kind: A1
- Application number: 17/191,233
- Filed: 2021-03-03
- Published: 2022-09-08
- Earliest claimed: 2021-03-03
- Assignees: Cisco Technology, Inc.
- Applicants: Cisco Technology, Inc.
- Inventors: Grégory Mermoud; Jean-Philippe Vasseur; Pierre-André Savalle; Vinay Kumar Kolar
- Web page: https://patentgrep.com/patent/US20220286388A1

## CPC

- H04L 45/28: using route fault recovery
- H04L 45/36: {Backward learning}
- H04L 45/14: {Routing performance; Theoretical aspects}
- H04L 45/64: using an overlay routing layer
- H04L 45/655: Interaction between route computation entities and forwarding entities, e.g. for route determination or for flow table update
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

In one embodiment, a device obtains routing forecasts for a software defined network. The device splits a particular routing policy for the software defined network into two or more routing policies, based on the routing forecasts. The device makes an evaluation as to whether the two or more routing policies should be reverted back into the particular routing policy. The device sends, to a user interface, data indicative of the particular routing policy that was split into the two or more routing policies and the evaluation as to whether the two or more routing policies should be reverted back into the particular routing policy.

## Claims

### Claim 1

A method comprising:
obtaining, by a device, routing forecasts for a software defined network, at least one of the routing forecasts predicting a link failure or a service level agreement (SLA) violation in the software defined network;
splitting, by the device, a particular routing policy for the software defined network into two or more routing policies, based on the routing forecasts;
making, by the device and based on an assessment of whether the predicted link failure or SLA violation actually occurred in the software defined network, an evaluation as to whether the two or more routing policies should be reverted back into the particular routing policy; and
sending, by the device and to a user interface, data indicative of the particular routing policy that was split into the two or more routing policies and the evaluation as to whether the two or more routing policies should be reverted back into the particular routing policy.

### Claim 2 (depends on 1)

The method as in claim 1, wherein the software defined network comprises a software-defined wide area network (SD-WAN).

### Claim 3 (depends on 1)

The method as in claim 1, wherein the particular routing policy was user-specified.

### Claim 4 (depends on 1)

The method as in claim 1, wherein the routing forecasts are generated by a machine learning-based forecasting engine trained to forecast link failures or SLA violations in the software defined network.

### Claim 5 (depends on 1)

The method as in claim 1, further comprising:
reverting, by the device and based on the evaluation, the two or more routing policies back into the particular routing policy.

### Claim 6 (depends on 5)

The method as in claim 5, wherein the device reverts the two or more routing policies back into the particular routing policy, in response to a request from the user interface to do so.

### Claim 7 (depends on 5)

The method as in claim 5, wherein the device reverts the two or more routing policies back into the particular routing policy, automatically.

### Claim 8 (depends on 1)

The method as in claim 1, wherein splitting the particular routing policy for the software defined network into two or more routing policies comprises:
determining that at least one traffic flow to which the particular routing policy applies should remain on its current routing path in the software defined network.

### Claim 9 (depends on 1)

The method as in claim 1, wherein splitting the particular routing policy for the software defined network into two or more routing policies comprises:
determining, based on the routing forecasts, whether all traffic flows to which the particular routing policy applies should be rerouted or only a subset of the traffic flows to which the particular routing policy applies should be rerouted.

### Claim 10 (depends on 1)

The method as in claim 1, further comprising:
receiving, at the device and via the user interface, an indication that the two or more routing policies should be made permanent; and, in response,
permanently replacing the particular routing policy with the two or more routing policies.

### Claim 11

An apparatus, comprising:
one or more network interfaces;
a processor coupled to the one or more network interfaces and configured to execute one or more processes; and
a memory configured to store a process that is executable by the processor, the process when executed configured to:
obtain routing forecasts for a software defined network, at least one of the routing forecasts predicting a link failure or a service level agreement (SLA) violation in the software defined network;
split a particular routing policy for the software defined network into two or more routing policies, based on the routing forecasts;
make, based on an assessment of whether the predicted link failure or SLA violation actually occurred in the software defined network, an evaluation as to whether the two or more routing policies should be reverted back into the particular routing policy; and
send, to a user interface, data indicative of the particular routing policy that was split into the two or more routing policies and the evaluation as to whether the two or more routing policies should be reverted back into the particular routing policy.

### Claim 12 (depends on 11)

The apparatus as in claim 11, wherein the software defined network comprises a software-defined wide area network (SD-WAN).

### Claim 13 (depends on 11)

The apparatus as in claim 11, wherein the particular routing policy was user-specified.

### Claim 14 (depends on 11)

The apparatus as in claim 11, wherein the routing forecasts are generated by a machine learning-based forecasting engine trained to forecast link failures or SLA violations in the software defined network.

### Claim 15 (depends on 11)

The apparatus as in claim 11, wherein the process when executed is further configured to:
revert, based on the evaluation, the two or more routing policies back into the particular routing policy.

### Claim 16 (depends on 15)

The apparatus as in claim 15, wherein the apparatus reverts the two or more routing policies back into the particular routing policy, in response to a request from the user interface to do so.

### Claim 17 (depends on 11)

The apparatus as in claim 11, wherein the apparatus splits the particular routing policy for the software defined network into two or more routing policies by:
determining that at least one traffic flow to which the particular routing policy applies should remain on its current routing path in the software defined network.

### Claim 18 (depends on 11)

The apparatus as in claim 11, wherein the apparatus splits the particular routing policy for the software defined network into two or more routing policies by:
determining, based on the routing forecasts, whether all traffic flows to which the particular routing policy applies should be rerouted or only a subset of the traffic flows to which the particular routing policy applies should be rerouted.

### Claim 19 (depends on 11)

The apparatus as in claim 11, wherein the process when executed is further configured to:
receiving, via the user interface, an indication that the two or more routing policies should be made permanent; and, in response,
permanently replacing the particular routing policy with the two or more routing policies.

### Claim 20

A tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising:
obtaining, by the device, routing forecasts for a software defined network, at least one of the routing forecasts predicting a link failure or a service level agreement (SLA) violation in the software defined network;
splitting, by the device, a particular routing policy for the software defined network into two or more routing policies, based on the routing forecasts;
making, by the device and based on an assessment of whether the predicted link failure or SLA violation actually occurred in the software defined network, an evaluation as to whether the two or more routing policies should be reverted back into the particular routing policy; and
sending, by the device and to a user interface, data indicative of the particular routing policy that was split into the two or more routing policies and the evaluation as to whether the two or more routing policies should be reverted back into the particular routing policy.
