Intent-driven network analytics for predictive network slice management

1. A method of network configuration, comprising:

receiving, at a network management function, an intent for a network slice constituent;

configuring computing resources for the network slice constituent to satisfy the intent based on expected performance of the computing resources;

receive feedback with respect to actual performance of the network slice constituent;

determining, based on analysis of the feedback by a management data analytics function (MDAF), a predicted deficiency of the network slice constituent not being able to satisfy the intent, wherein the predicted deficiency is with respect to a constraint on a cost or efficiency of the intent; and

modifying the configuration of the computing resources based on the feedback and the predicted deficiency to satisfy the intent, wherein modifying the configuration of the computing resources comprises reducing an allocation of computing resources to satisfy the intent at a lower cost.

2. The method of claim 1 , wherein receiving the intent comprises receiving an intent including a lower threshold and an upper threshold for performance of the network slice constituent.

3. The method of claim 2 , wherein receiving feedback with respect to actual performance of the network slice constituent comprises monitoring the performance of the network within the lower threshold and the upper threshold.

4. The method of claim 1 , wherein determining the deficiency of the network slice constituent not being able to satisfy the intent comprises receiving a prediction that a likelihood of satisfying the intent is less than a threshold.

5. The method of claim 1 , wherein determining the predicted deficiency of the network slice constituent comprises training a machine learning model at the MDAF to predict a demand on the network slice constituent.

6. The method of claim 5 , wherein the demand on the network slice constituent is a network traffic level.

7. The method of claim 1 , wherein modifying the configuration of the computing resources based on the feedback and the predicted deficiency to satisfy the intent comprises allocating additional computing resources to the network slice constituent to increase a capacity of the network slice constituent to satisfy the intent.

8. The method of claim 1 , wherein determining the predicted deficiency of the network slice constituent with respect to the intent comprises receiving a recommended action from the MDAF to satisfy the intent.

9. The method of claim 1 , wherein receiving feedback with respect to actual performance of the network function comprises receiving feedback at two or more levels of: a network function management function (NFMF), a network slice subnet management function (NSSMF), or a network slice management function (NSMF).

10. A system for network configuration, comprising:

one or more memories, individually or in combination, having computer-executable instructions stored thereon; and

one or more processors, individually or in combination, configured to execute the computer-executable instructions to instantiate;

a network management function configured to:

receive an intent for a network slice constituent;

configure computing resources for the network slice constituent to satisfy the intent based on expected performance of the computing resources;

determine, based on analysis of feedback with respect to actual performance of the network slice constituent by a management data analytics function (MDAF), a predicted deficiency of the network slice constituent not being able to satisfy the intent; and

modify the configuration of the computing resources based on the feedback and the predicted deficiency to satisfy the intent; and

the MDAF configured to:

receive feedback with respect to actual performance of the network slice constituent; and

predict a deficiency of the network slice constituent not being able to satisfy the intent based on analysis of the feedback, wherein the predicted deficiency is with respect to a constraint on a cost or efficiency of the intent, and wherein the network management function is configured to reduce an allocation of computing resources to satisfy the intent at a lower cost.

11. The system of claim 10 , wherein the network function is configured to receive an intent including a lower threshold and an upper threshold for performance of the network slice constituent.

12. The system of claim 10 , wherein the feedback with respect to actual performance of the network slice constituent comprises performance metrics within the lower threshold and the upper threshold.

13. The system of claim 10 , wherein the MDAF is configured to predict a likelihood of the configured network slice constituent satisfying, the intent.

14. The system of claim 10 , wherein the MDAF is configured with a trained machine learning model to predict a demand on the network slice constituent.

15. The system of claim 14 , wherein the demand on the network slice constituent is a network traffic level.

16. The system of claim 10 , wherein the network management function is configured to allocate additional computing resources to the network slice constituent to increase a capacity of the network slice constituent to satisfy the intent.

17. The system of claim 10 , wherein the MDAF is configured to provide a recommended action to satisfy the intent.

18. A non-transitory computer-readable medium storing computer executable instructions for intent based network slice management, comprising instructions to:

receive, at a network management function, an intent for a network slice constituent;

configure computing resources for the network slice constituent to satisfy the intent based on expected performance of the computing resources;

receive feedback with respect to actual performance of the network slice constituent;

determine, based on analysis of the feedback by a management data analytics function (MDAF), a predicted deficiency of the network slice constituent not being able to satisfy the intent, wherein the predicted deficiency is with respect to a constraint on a cost or efficiency of the intent; and

modify the configuration of the computing resources based on the feedback and the predicted deficiency to satisfy the intent by reducing an allocation of computing resources to satisfy the intent at a lower cost.