Method and system for improving location determination for stationary user equipment in a cellular network

1 . A method comprising:

receiving a set of communication events from a user equipment to a base station;

obtaining a set of geocoordinates corresponding to the user equipment;

calculating an angular mean for the set of geocoordinates;

sorting the set of geocoordinates based on distances between the set of geocoordinates and a location of the base station to generate an ordered list of geocoordinates;

calculating a k-th order statistic of the ordered list of geocoordinates;

generating a predicted location based on the angular mean and the k-th order statistic; and

assigning the predicted location as a current location of the user equipment in a cellular core network.

2 . The method of claim 1 , wherein obtaining the set of geocoordinates comprises computing latitude values and longitude values for the set of communication events based on at least one communication parameter associated with the set of communication events.

3 . The method of claim 2 , wherein the at least one communication parameter comprises one or more of an identifier of a base station, a cell or transmitter identifier, a timing advance value, a Reference Signal Received Power value, and a Reference Signal Received Quality value.

4 . The method of claim 2 , wherein calculating an angular mean for the set of geocoordinates comprises the latitude values and longitude values into a set of polar coordinates.

5 . The method of claim 1 , wherein sorting the set of geocoordinates based on the distances between the set of geocoordinates and the location of the base station comprises ordering the set of geocoordinates from closest to furthest from the location of the base station.

6 . The method of claim 1 , wherein calculating the k-th order statistic comprises selecting a k-the value from the ordered list of geocoordinates.

7 . The method of claim 6 , further comprising determining a value of k for the k-th order statistic using a ground truth dataset.

8 . A method comprising:

receiving a set of communication events from a user equipment to a base station, wherein the user equipment is classified as stationary;

obtaining a set of geocoordinates corresponding to the user equipment, wherein each geocoordinate of the set of geocoordinates is a location estimate derived from at least one communication parameter of a respective communication event of the set of communication events, and wherein communication parameters of the set of communication events are unchanging;

computing an average geocoordinate based on the set of geocoordinates;

sorting the set of geocoordinates based on distances between the set of geocoordinates and the average geocoordinate to generate an ordered list of geocoordinates;

selecting a subset of the ordered list of geocoordinates, wherein the subset excludes geocoordinates that exceed a distance threshold from the average geocoordinate;

computing a second average geocoordinate based on the subset of the ordered list of geocoordinates; and

assigning the second average geocoordinate as a current location of the user equipment in a cellular core network.

9 . The method of claim 8 , further comprising weighting the subset of the ordered list of geocoordinates.

10 . The method of claim 9 , wherein weighting the subset of the ordered list of geocoordinates comprises weighting the subset of the ordered list of geocoordinates using a monotonic function.

11 . A device comprising:

a processor configured to:

receive a set of communication events from a user equipment to a base station;

obtain a set of geocoordinates corresponding to the user equipment;

calculate an angular mean for the set of geocoordinates;

sort the set of geocoordinates based on distances between the set of geocoordinates and a location of the base station to generate an ordered list of geocoordinates;

calculate a k-th order statistic of the ordered list of geocoordinates;

generate a predicted location based on the angular mean and the k-th order statistic; and

assign the predicted location as a current location of the user equipment in a cellular core network.

12 . The device of claim 11 , wherein obtaining the set of geocoordinates comprises computing latitude values and longitude values for the set of communication events based on at least one communication parameter associated with the set of communication events.

13 . The device of claim 12 , wherein the at least one communication parameter comprises one or more of an identifier of a base station, a cell or transmitter identifier, a timing advance value, a Reference Signal Received Power value, and a Reference Signal Received Quality value.

14 . The device of claim 12 , wherein calculating an angular mean for the set of geocoordinates comprises the latitude values and longitude values into a set of polar coordinates.

15 . The device of claim 11 , wherein sorting the set of geocoordinates based on the distances between the set of geocoordinates and the location of the base station comprises ordering the set of geocoordinates from closest to furthest from the location of the base station.

16 . The device of claim 11 , wherein calculating the k-th order statistic comprises selecting a k-the value from the ordered list of geocoordinates.

17 . The device of claim 16 , wherein the processor is further configured to determine a value of k for the k-th order statistic using a ground truth dataset.

18 . The device of claim 11 , wherein the processor is further configured to determine if communication parameters of the set of communication events are unchanging and, in response:

compute an average geocoordinate based on the set of geocoordinates;

sort the set of geocoordinates based on distances between the set of geocoordinates and the average geocoordinate to generate an ordered list of geocoordinates;

select a subset of the ordered list of geocoordinates;

compute a second average geocoordinate based on the subset of the ordered list of geocoordinates; and

assign the second average geocoordinate as a current location of the user equipment in a cellular core network.

19 . The device of claim 18 , further comprising weighting the subset of the ordered list of geocoordinates.

20 . The device of claim 19 , wherein weighting the subset of the ordered list of geocoordinates comprises weighting the subset of the ordered list of geocoordinates using a monotonic function.