Congestion detection using machine learning on arbitrary end-to-end paths

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:
• predict a range of bitrates expected to be required by one or more applications associated with traffic conveyed via a particular path in a network;
• obtain telemetry data indicative of observed bitrates associated with the traffic conveyed via the particular path in the network;
• identify a presence of congestion along the particular path in the network, by comparing the observed bitrates to the range of bitrates expected to be required by the one or more applications;
• and
• cause at least a portion of the traffic to be re-routed from the particular path to a second path in the network, when the apparatus identifies the presence of congestion along the particular path.

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

• predicting, by the device, a range of bitrates expected to be required by one or more applications associated with traffic conveyed via a particular path in a network;
• obtaining, by the device, telemetry data indicative of observed bitrates associated with the traffic conveyed via the particular path in the network;
• identifying, by the device, a presence of congestion along the particular path in the network, by comparing the observed bitrates to the range of bitrates expected to be required by the one or more applications;
• and
• causing, by the device, at least a portion of the traffic to be re-routed from the particular path to a second path in the network, when the device identifies the presence of congestion along the particular path.