Monitor and predict Wi-Fi utilization patterns for dynamic optimization of the operating parameters of nearby ENBS using the same unlicensed spectrum

1. A method implemented by one or more network devices for determining parameter values for a base station of a cellular network, where the base station operates in a wireless band that is shared with one or more wireless access points, where the parameter values are determined to optimize network performance in a manner that allows for fair coexistence between the base station and the one or more wireless access points, the method comprising:

obtaining proximity information for the one or more wireless access points relative to the base station;

obtaining activity information for the one or more wireless access points;

determining, using a machine learning system, parameter values for the base station based on the proximity information and the activity information; causing the base station to be configured with the parameter values;

obtaining a first network performance indicator, wherein the first network performance indicator indicates a level of network performance before the base station was configured with the parameter values;

obtaining a second network performance indicator, wherein the second network performance indicator indicates a level of network performance after the base station was configured with the parameter values;

determining a measure of how configuring the base station with the parameter values affected network performance based on comparing the first network performance indicator and the second network performance indicator; and

training the machine learning system using the measure of how configuring the base station with the parameter values affected network performance.

2. The method of claim 1 , further comprising:

providing the parameter values to a network management component that manages configuration of the base station, wherein the network management component configures the base station with the parameter values.

3. The method of claim 1 , wherein at least one of the one or more wireless access points is a Wi-Fi access point that employs Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards.

4. The method of claim 1 , wherein the base station is an evolved Node B (eNB) that employs Long Term Evolution Unlicensed (LTE-U) or Long Term Evolution License Assisted Access (LTE-LAA).

5. The method of claim 1 , wherein the parameter values include Carrier-Sensing Adaptive Transmission (CSAT) parameter values.

6. The method of claim 1 , wherein the parameter values include Listen Before Talk (LBT) parameter values.

7. The method of claim 6 , wherein the LBT parameter values include any one of an energy detection threshold value, a minimum contention window size value, and a maximum contention window size value.

8. The method of claim 1 , wherein the proximity information includes an indication of an estimated level of interference between the base station and a given wireless access point from the one or more wireless access points.

9. The method of claim 8 , wherein the proximity information further includes an indication of a confidence level of an accuracy of the estimated level of interference between the base station and the given wireless access point.

10. The method of claim 1 , wherein the activity information includes an indication of a predicted level of activity at a given time of a given wireless access point from the one or more wireless access points.

11. The method of claim 10 , wherein the activity information further includes an indication of a predicted traffic type at the given time of the given wireless access point.

12. The method of claim 10 , wherein the activity information further includes an indication of a confidence level of an accuracy of the predicted level of activity at the given time of the given wireless access point.

13. The method of claim 1 , further comprising:

dynamically determining updated parameter values for the base station in response to obtaining updated proximity information or updated activity information.

14. A network device configured to determine parameter values for a base station of a cellular network, where the base station operates in a wireless band that is shared with one or more wireless access points, where the parameter values are determined to optimize network performance in a manner that allows for fair coexistence between the base station and the one or more wireless access points, the network device comprising:

one or more processors; and

a non-transitory machine-readable storage medium having stored therein computer code, which when executed by the one or more processors, causes the network device to:

obtain proximity information for the one or more wireless access points relative to the base station,

obtain activity information for the one or more wireless access points,

determine, using a machine learning system, parameter values for the base station based on the proximity information and the activity information,

cause the base station to be configured with the parameter values,

obtain a first network performance indicator, wherein the first network performance indicator indicates a level of network performance before the base station was configured with the parameter values,

obtain a second network performance indicator, wherein the second network performance indicator indicates a level of network performance after the base station was configured with the parameter values,

determine a measure of how configuring the base station with the parameter values affected network performance based on comparing the first network performance indicator and the second network performance indicator, and

train the machine learning system using the measure of how configuring the base station with the parameter values affected network performance.

15. The network device of claim 14 , wherein the computer code, when executed by the one or more processors, further causes the network device to:

provide the parameter values to a network management component that manages configuration of the base station, wherein the network management component configures the base station with the parameter values.

16. A non-transitory machine-readable storage medium having computer code stored therein, which when executed by one or more processors of a network device, causes the network device to perform operations for determining parameter values for a base station of a cellular network, where the base station operates in a wireless band that is shared with one or more wireless access points, where the parameter values are determined to optimize network performance in a manner that allows for fair coexistence between the base station and the one or more wireless access points, the operations comprising:

obtaining proximity information for the one or more wireless access points relative to the base station;

obtaining activity information for the one or more wireless access points;

determining, using a machine learning system, parameter values for the base station based on the proximity information and the activity information;

causing the base station to be configured with the parameter values;

obtaining a first network performance indicator, wherein the first network performance indicator indicates a level of network performance before the base station was configured with the parameter values;

obtaining a second network performance indicator, wherein the second network performance indicator indicates a level of network performance after the base station was configured with the parameter values;

determining a measure of how configuring the base station with the parameter values affected network performance based on comparing the first network performance indicator and the second network performance indicator; and

training the machine learning system using the measure of how configuring the base station with the parameter values affected network performance.

17. The non-transitory machine-readable storage medium of claim 16 , wherein the operations further comprise:

providing the parameter values to a network management component that manages configuration of the base station, wherein the network management component configures the base station with the parameter values.

18. The non-transitory machine-readable storage medium of claim 16 , wherein the parameter values include Carrier-Sensing Adaptive Transmission (CSAT) parameter values.

19. The non-transitory machine-readable storage medium of claim 16 , wherein the parameter values include Listen Before Talk (LBT) parameter values.

20. The non-transitory machine-readable storage medium of claim 16 , wherein the operations further comprise:

dynamically determining updated parameter values for the base station in response to obtaining updated proximity information or updated activity information.