Method, control unit and network node for configuration in a wireless communication system

1. A control unit for configuration in a wireless communication system, comprising processing circuitry, and a memory, said memory containing instructions executable by said processing circuitry, whereby said control unit is operative to:

map a service category to a virtual network instance based on service requirements of the service category, the virtual network instance having a first virtual network instance configuration for a current time interval, the first virtual network instance configuration defining a first allocation of resources in a plurality of network layers;

predict a network state in a next time interval, wherein to predict the network state comprises to predict a number of requests of the service category in the next time interval;

determine if the predicted network state in the next time interval results in a predicted performance degradation in the next time interval in relation to at least one network layer of the plurality of network layers;

on condition that there is a predicted performance degradation in the next time interval in relation to at least one network layer of the plurality of network layers, determine a second virtual network instance configuration for the next time interval, the second virtual network instance configuration defining an adapted second allocation of resources in the plurality of network layers at least partly compensating for the predicted performance degradation in the next time interval in relation to the at least one network layer of the plurality of network layers; and

configure the virtual network instance based on the first network instance configuration or the second network instance configuration for the next time interval.

2. The control unit of claim 1 , wherein configure the virtual network instance comprises:

on condition that there is a predicted performance degradation in the next time interval in relation to at least one network layer of the plurality of network layers, configure the virtual network instance based on the second network instance configuration for the next time interval.

3. The control unit of claim 2 , wherein configure the virtual network instance comprises:

on condition that there is no predicted performance degradation in the next time interval of in relation to at least one network layer of the plurality of network layers, maintain the first network instance configuration for the virtual network instance for the next time interval.

4. The control unit of claim 1 , wherein predict a network state comprises:

predict a channel condition in the next time interval.

5. The control unit of claim 1 , wherein the virtual network instance, is a network slice instance, NSI.

6. The control unit of claim 1 , wherein the plurality of network layers comprises a radio layer, cloud layers, and transport layers.

7. The control unit of claim 1 , further operative to predict a network state in a next time interval using a machine learning, ML, algorithm.

8. The control unit of claim 1 , wherein the predicted performance degradation is in relation to a performance indicator of the service category.

9. The control unit of claim 1 , wherein the predicted performance degradation is in relation to one of peak data rate, average data rate, peak spectral efficiency, average spectral efficiency, control plane latency, user plane latency, interrupt at handover, reliability, connection density, mobility, maximum number of digital units needed for a request of the service category, transport layer consumed capacity per request of the service category, and energy of a request of the service category.

10. The control unit of claim 1 , further operative to:

determine an actual network state in the next time interval;

compare the determined actual network state in the next time interval and the predicted network state for the next time interval; and

on condition that the actual network state in the next time interval differs from the predicted network state in the next time interval, compensate for prediction errors.

11. The control unit of claim 1 , wherein determine a second virtual network instance configuration comprises:

allocate, based on the predicted performance degradation in relation to the at least one network layer of the plurality of network layers, additional resources in a different network layer of the plurality of network layers than the at least one network layer of the plurality of network layers, at least partly compensating for the predicted performance degradation in the next time interval in the at least one network layer of the plurality of network layers.

12. A network node for configuration in a wireless communication system, comprising a control unit of claim 1 .

13. A method in a control unit for configuration in a wireless communication system, comprising:

mapping a service category to a virtual network instance based on service requirements of the service category, the virtual network instance having a first virtual network instance configuration for a current time interval, the first virtual network instance configuration defining a first allocation of resources in a plurality of network layers;

predicting a network state in a next time interval, wherein predicting the network state comprises predicting a number of requests of the service category in the next time interval;

determining if the predicted network state in the next time interval results in a predicted performance degradation in the next time interval in relation to at least one network layer of the plurality of network layers;

on condition that there is a predicted performance degradation in the next time interval in relation to at least one network layer of the plurality of network layers, determining a second virtual network instance configuration for the next time interval, the second virtual network instance configuration defining an adapted second allocation of resources in the plurality of network layers at least partly compensating for the predicted performance degradation in the next time interval in relation to the at least one network layer of the plurality of network layers; and

configuring the virtual network instance based on the first network instance configuration or the second network instance configuration for the next time interval.

14. The method of claim 13 , wherein configuring comprises:

on condition that there is a predicted performance degradation in the next time interval in relation to at least one network layer of the plurality of network layers, configuring the virtual network instance based on the second network instance configuration for the next time interval.

15. The method of claim 14 , wherein configuring further comprises:

on condition that there is no predicted performance degradation in the next time interval in relation to at least one network layer of the plurality of network layers, maintaining the first network instance configuration for the virtual network instance for the next time interval.

16. The method of claim 13 , wherein predicting a network state comprises predicting a channel condition in the next time interval.

17. The method of claim 13 , wherein the virtual network instance, is a network slice instance, NSI.

18. The method of claim 13 , wherein predicting a network state is performed using a machine learning, ML, algorithm.