DiffServ (Differentiated services) uses a 6-bit differentiated services code point (DSCP) in the 8-bit differentiated services field (DS field) in the IP header for packet classification purposes. If we already have that for QoS enforcement, why do we need machine learning for QoS prediction in Software Defined Networks? There are many papers that show machine learning mechanisms for QoS classification. Can't we just use the DSCP for that instead?

  • 4
    What decides which DSCP value to assign to what traffic? Rather than manually configuring rules for marking traffic, why not have a program learn to do it for us?
    – YLearn
    Jan 24, 2020 at 6:12
  • Remember that QoS markings and policies are decided by you for your company, and others will classify and create policies that are very different than yours. QoS is about fairness, as you define it. There is no standard that says this type of traffic gets marked this way, and that this marking gets treated that way. It is up to you to decide that. Everyone has a different idea about QoS, which is why it simply does not work over the Internet.
    – Ron Maupin
    Jan 24, 2020 at 13:35
  • Did any answer help you? If so, you should accept the answer so that the question doesn't keep popping up forever, looking for an answer. Alternatively, you can post and accept your own answer.
    – Ron Maupin
    Dec 17, 2020 at 15:01

1 Answer 1


Something has to set the DSCP values. In a traditional network, that comes from either the end user / application, or intervening network hardware. Unless you have significant control of the device/application -- eg. VoIP phone -- the former can be a very dangerous road. The later is a very complicated, and tedious process. It is this area that machine learning can greatly demystify the voodoo of QoS.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.