Geo-location error correction for small cell placement
View Patent ↗To effectively plan small cell placement within a current macro cell network, it is necessary to identify the traffic hotspots. Small cells can be placed in hotspot locations in order to effectively offload traffic from the corresponding macro cell. Hotspots can be identified based on information about traffic from/to mobile users, particularly, the observed User Equipment (UE) locations and amount of data transmitted from/to the UEs. Provided are systems and methods for accounting for geo-location errors in identifying hotspots and determining small cell placement.
1. A computer-implemented method for macro cell hotspot identification, comprising:
a processor reading an input data comprising a plurality of User Equipment (UE) session records in an area of interest, each of the plurality of UE session records including UE location information, wherein the UE location information comprises a first set of coordinates of a coordinate system;
the processor generating a perturbed data comprising the plurality of UE session records with modified UE location information by adjusting the UE location information in each of the plurality of UE session records in the input data based on observed geo-location error data in the area of interest;
wherein the observed geo-location error data comprises an error vector including a direction and a magnitude;
wherein the modified UE location information comprises a second set of coordinates of the coordinate system determined by translating the first set of coordinates by the error vector; and
the processor identifying a hotspot with a high traffic concentration based on the perturbed data comprising the plurality of UE session records with modified UE location information.
2. The method according to claim 1 , wherein the observed geo-location error data in the area of interest comprises a list of error vectors.
3. The method according to claim 2 , further comprising the processor randomly selecting the error vector from the list of error vectors.
4. The method according to claim 3 , wherein the processor generates the perturbed data by adjusting the UE location information in each of the plurality of UE session records in the input data with the randomly selected error vector.
5. The method according to claim 4 , further comprising the processor newly randomly selecting an error vector from the list of error vectors and generating a new perturbed data by adjusting the UE location information in each of the plurality of UE session records in the input data with the newly randomly selected error vector.
6. The method according to claim 5 , further comprising the processor identifying another hotspot with a high traffic concentration based on the new perturbed data comprising the plurality of UE session records with UE location information modified with the newly randomly selected error vector.
7. The method according to claim 6 , wherein the steps of randomly selecting an error vector, generating a new perturbed data and identifying another hotspot with a high traffic concentration based on the new perturbed data are repeated a plurality of times.
8. The method according to claim 7 , further comprising the processor analyzing a cluster of the identified plurality of hotspots with high traffic concentrations and identifying the centroid of the cluster.
9. The method according to claim 8 , wherein each of the identified plurality of hotspots with high traffic concentrations is the best ranked hotspot for its corresponding perturbed data.
10. The method according to claim 1 , wherein the processor identifies the hotspot with a high traffic concentration also based on amount of data transmitted to and from the UE locations and/or a size of a radius of a small cell.
11. A system for macro cell hotspot identification, comprising a processor configured to:
read an input data comprising a plurality of User Equipment (UE) session records in an area of interest, each of the plurality of UE session records including UE location information, wherein the UE location information comprises a first set of coordinates of a coordinate system;
generate a perturbed data comprising the plurality of UE session records with modified UE location information by adjusting the UE location information in each of the plurality of UE session records in the input data based on observed geo-location error data in the area of interest;
wherein the observed geo-location error data comprises an error vector including a direction and a magnitude;
wherein the modified UE location information comprises a second set of coordinates of the coordinate system determined by translating the first set of coordinates by the error vector; and
identify a hotspot with a high traffic concentration based on the perturbed data comprising the plurality of UE session records with modified UE location information.
12. The system according to claim 11 , wherein the observed geo-location error data in the area of interest comprises a list of error vectors stored in a storage device in communication with the processor.
13. The system according to claim 12 , wherein the processor is further configured to randomly select the error vector from the list of error vectors.
14. The system according to claim 13 , wherein the processor is configured to generate the perturbed data by adjusting the UE location information in each of the plurality of UE session records in the input data with the randomly selected error vector.
15. The system according to claim 14 , wherein the processor is further configured to newly randomly select an error vector from the list of error vectors and generate a new perturbed data by adjusting the UE location information in each of the plurality of UE session records in the input data with the newly randomly selected error vector.
16. The system according to claim 15 , wherein the processor is further configured to identify another hotspot with a high traffic concentration based on the new perturbed data comprising the plurality of UE session records with UE location information modified with the newly randomly selected error vector.
17. The system according to claim 16 , wherein the processor is further configured to reiteratively randomly select an error vector, generate a new perturbed data and identify another hotspot with a high traffic concentration based on the new perturbed data for a plurality of times.
18. The system according to claim 17 , wherein the processor is further configured to analyze a cluster of the identified plurality of hotspots with high traffic concentrations and identifying the centroid of the cluster.
19. The system according to claim 18 , wherein each of the identified plurality of hotspots with high traffic concentrations is the best ranked hotspot for its corresponding perturbed data.
20. The system according to claim 11 , wherein the processor is configured to identify the hotspot with a high traffic concentration also based on amount of data transmitted to and from the UE locations and/or a size of a radius of a small cell.