Self-learning network geofences

1. A method to be performed by a user device, the method comprising:

gathering a plurality of data points associated with one or more Citizens Broadband Radio Service (CBRS) deployers;

determining respective identifiers of the one or more CBRS deployers associated with the plurality of data points;

clustering, based on the respective identifiers of the one or more CBRS deployers, the plurality of data points into one or more clusters, wherein each cluster is associated with one of the one or more CBRS deployers, and wherein each cluster is associated with a geofence of a network of the one or more CBRS deployers;

identifying an opportunity for uploading the one or more clusters to a central server; and

uploading the one or more clusters to the central server during the identified opportunity.

2. The method of claim 1 , wherein the plurality of data points are data points from at least one of baseband, global positioning system (GPS), Wi-Fi, or telephony processes of the user device.

3. The method of claim 1 , further comprising:

calculating a respective signal quality for each of the plurality of data points; and

deleting a subset of data points that have a respective signal quality less than a predetermined threshold.

4. The method of claim 1 , wherein the respective signal quality is calculated based on one or more of Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Received Signal Strength Indicator (RSSI), Signal-to-noise ratio (SNR), and Signal-to-Interference-plus-Noise Ratio (SINR).

5. The method of claim 1 , wherein clustering, based on the respective identifiers of the one or more CBRS deployers, the plurality of data points into one or more clusters comprises:

for each data point:

determining whether a center of a nearest cluster associated with a same CBRS deployer is less than a threshold distance away;

if the center of the nearest cluster is less than or equal to the threshold distance away, adding the data point to the nearest cluster; and

if the center of the nearest cluster is greater than the threshold distance, creating a new cluster with the data point as the center of the new cluster.

6. The method of claim 1 , wherein identifying an opportunity for uploading the one or more clusters to a central server comprises:

identifying the opportunity based on a determination that the user device is plugged into power, that the user device is connected to Wi-Fi, and/or that the user device is idle.

7. The method of claim 1 , wherein uploading the one or more clusters to the central server during the identified opportunity comprises:

uploading a threshold number of strongest data points in each cluster.

8. The method of claim 1 , further comprising:

generating a request for geofence data, wherein the request comprises an approximate location of the user device, a list of requested CBRS deployers, and a requested geofence count;

providing the request to the central server; and

receiving, from the central server, self-learned geofence data associated with the list of requested CBRS deployers.

9. The method of claim 1 , further comprising:

using the self-learned geofence data to connect a CBRS network associated with one of the requested CBRS deployers.

10. A system comprising:

one or more processors configured to perform operations comprising:

gathering a plurality of data points associated with one or more Citizens Broadband Radio Service (CBRS) deployers;

determining respective identifiers of the one or more CBRS deployers associated with the plurality of data points;

clustering, based on the respective identifiers of the one or more CBRS deployers, the plurality of data points into one or more clusters, wherein each cluster is associated with one of the one or more CBRS deployers, and wherein each cluster is associated with a geofence of a network of the one or more CBRS deployers;

identifying an opportunity for uploading the one or more clusters to a central server; and

uploading the one or more clusters to the central server during the identified opportunity.

11. The system of claim 10 , wherein the plurality of data points are data points from at least one of baseband, global positioning system (GPS), Wi-Fi, or telephony processes of a user device.

12. The system of claim 10 , the operations further comprising:

calculating a respective signal quality for each of the plurality of data points; and

deleting a subset of data points that have a respective signal quality less than a predetermined threshold.

13. One or more processors of a user device, the one or more processors configured to perform operations comprising:

gathering a plurality of data points associated with one or more Citizens Broadband Radio Service (CBRS) deployers;

determining respective identifiers of the one or more CBRS deployers associated with the plurality of data points;

clustering, based on the respective identifiers of the one or more CBRS deployers, the plurality of data points into one or more clusters, wherein each cluster is associated with one of the one or more CBRS deployers, and wherein each cluster is associated with a geofence of a network of the one or more CBRS deployers;

identifying an opportunity for uploading the one or more clusters to a central server; and

uploading the one or more clusters to the central server during the identified opportunity.

14. The one or more processors of claim 13 , wherein the plurality of data points are data points from at least one of baseband, global positioning system (GPS), Wi-Fi, or telephony processes of the user device.

15. The one or more processors of claim 13 , the operations further comprising:

calculating a respective signal quality for each of the plurality of data points; and

deleting a subset of data points that have a respective signal quality less than a predetermined threshold.

16. The one or more processors of claim 13 , wherein the respective signal quality is calculated based on one or more of Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Received Signal Strength Indicator (RSSI), Signal-to-noise ratio (SNR), and Signal-to-Interference-plus-Noise Ratio (SINR).

17. The one or more processors of claim 13 , wherein clustering, based on the respective identifiers of the one or more CBRS deployers, the plurality of data points into one or more clusters comprises:

for each data point:

determining whether a center of a nearest cluster associated with a same CBRS deployer is less than a threshold distance away;

if the center of the nearest cluster is less than or equal to the threshold distance away, adding the data point to the nearest cluster; and

if the center of the nearest cluster is greater than the threshold distance, creating a new cluster with the data point as the center of the new cluster.

18. The one or more processors of claim 13 , wherein identifying an opportunity for uploading the one or more clusters to a central server comprises:

identifying the opportunity based on a determination that the user device is plugged into power, that the user device is connected to Wi-Fi, and/or that the user device is idle.

19. The one or more processors of claim 13 , wherein uploading the one or more clusters to the central server during the identified opportunity comprises:

uploading a threshold number of strongest data points in each cluster.

20. The one or more processors of claim 13 , the operations further comprising:

generating a request for geofence data, wherein the request comprises an approximate location of the user device, a list of requested CBRS deployers, and a requested geofence count;

providing the request to the central server; and

receiving, from the central server, self-learned geofence data associated with the list of requested CBRS deployers.