Adaptive oscillation control for network paths using machine learning

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:
• generate a model of oscillations between a particular path in a network satisfying a service level agreement template of traffic conveyed via the particular path and the particular path in the network not satisfying the service level agreement template;
• cause the traffic to be rerouted onto the particular path, based on a prediction by the model that the particular path will not oscillate for a period of time;
• determine, using the model, an adjustment to the service level agreement template that would reduce the oscillations;
• and
• provide, to a user interface, an indication of the adjustment to the service level agreement template.

A tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising:

• generating, by the device, a model of oscillations between a particular path in a network satisfying a service level agreement template of traffic conveyed via the particular path and the particular path in the network not satisfying the service level agreement template;
• causing, by the device, the traffic to be rerouted onto the particular path, based on a prediction by the model that the particular path will not oscillate for a period of time;
• determining, by the device and using the model, an adjustment to the service level agreement template that would reduce the oscillations;
• and
• providing, by the device and to a user interface, an indication of the adjustment to the service level agreement template.