Signal power pattern-based location detection and cell placement

• US 10,051,594 B1
• Filed: 08/14/2017
• Issued: 08/14/2018
• Est. Priority Date: 08/14/2017
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Inventors: Ramamurthy, Suryanarayanan
• Primary Examiner(s): Schwartz, Joshua
• Application Number:
  US15/675,860
• Time in Patent Office: 365 Days
• Field of Search: 4554561-4565
• CPC Class Codes: G01S 5/02521 using a radio-map
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04B 17/27 for locating or positioning the transmitter
• CPC Class Codes: H04B 17/318 Received signal strength
• CPC Class Codes: H04W 16/18 Network planning tools
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Abstract

A method is provided for one or more network devices to determine the location of user equipment (UE) in a radio access network (RAN). The method includes collecting UE location indications and corresponding received signal strength measurements for wireless access stations concurrently visible to cooperating UE devices at the indicated locations. Each UE location indication and corresponding received signal strength measurements provide a data point. The method also includes assigning signature areas based on groupings having the same combination of the concurrently visible wireless access stations, identifying multiple clusters of data points within the signature areas, and calculating an estimated location for each cluster based on the UE location indications from the data points. After the designating, the method includes receiving, from a UE device, a listing of concurrently visible wireless access stations and corresponding received signal strength measurements by the other UE device, and generating a location estimate for the other UE device by correlating the concurrently visible wireless access stations and the corresponding received signal strength measurements in the listing to one of the clusters within one of the signature areas.

Claims

1. A method performed by one or more network devices for a radio access network (RAN), the method comprising:

collecting user equipment (UE) location indications and corresponding received signal strength measurements for wireless access stations concurrently visible to cooperating UE devices at the indicated locations, wherein each UE location indication and corresponding received signal strength measurements provide a data point;

assigning signature areas having the same combination of the concurrently visible wireless access stations;

identifying multiple clusters of data points in the signature areas;

calculating an estimated location for each cluster of the multiple clusters based on the UE location indications from the data points;

receiving, from another UE device after the calculating, a listing of concurrently visible wireless access stations and corresponding received signal strength measurements by the other UE device; and

generating a location estimate for the other UE device by correlating the concurrently visible wireless access stations and the corresponding received signal strength measurements in the listing to one cluster of the multiple clusters within one of the signature areas.

2. The method of claim 1, wherein the received signal strength measurements include reference signal received power (RSRP) measurements.

3. The method of claim 1, wherein identifying the clusters of data points includes applying machine-learning algorithms to all data points in the signature area for a certain time window to identify a geographic grouping.

4. The method of claim 1, wherein the signature area indicates a geographic space where a unique group of wireless access stations can be concurrently viewed by the UE devices.

5. The method of claim 1, wherein correlating the concurrently visible wireless access stations and the corresponding received signal strength measurements in the listing includes:

matching the concurrently visible wireless access stations in the listing with the combination of concurrently visible wireless access stations for one of the signature areas, and

identifying a best match for the listing of received signal strength measurements to received signal strength measurements for the one cluster.

6. The method of claim 1, wherein calculating the estimated location for each of the clusters includes:

averaging positions of data points within each of the clusters, or

identifying centers of areas that covers all data points within each of the clusters.

7. The method of claim 1, wherein the UE location indications include data from satellite-based positioning or cellular-based positioning services.

8. The method of claim 1, further comprising:

identifying time intervals with high RAN usage;

extracting, from network data for the time intervals, uplink traffic for each signature area over incremental periods;

extracting, from the network data for the time intervals, a number of concurrent UEs for each signature area over the incremental periods;

ranking the signature areas based on the extracted uplink traffic and the extracted number of concurrent UEs; and

selecting target locations for small cells from the ranked signature areas.

9. The method of claim 8, further comprising:

updating the signature areas to reflect placement of the small cells.

10. The method of claim 8, wherein identifying the time intervals with high RAN usage includes:

identifying time intervals where sustained high traffic is detected at wireless access stations that utilizes uplink and/or downlink radio bearers beyond a configurable threshold, and

identifying time intervals where a number of active concurrent users is sustained above another configurable threshold.

11. The method of claim 8, wherein the network data includes call detail records (CDRs).

12. The method of claim 1, further comprising:

assembling, based on the location estimate for the UE device and other location estimates for other UE devices, a heat map of concurrent users.

13. A network device, comprising:

an interface that communicates with a network;

a memory configured to store instructions; and

a processor, coupled to the interface and the memory, wherein the processor is configured to execute the instructions stored in the memory to;

collect user equipment (UE) location indications and corresponding received signal strength measurements for wireless access stations concurrently visible to cooperating UE devices at the indicated locations, wherein each UE location indication and corresponding received signal strength measurements provide a data point;

assign signature areas having the same combination of the concurrently visible wireless access stations;

identify multiple clusters of data points in the signature areas;

calculate an estimated location for each of the clusters based on the UE location indications from the data points in each respective cluster of the multiple clusters;

receive, from another UE device after the calculating, a listing of concurrently visible wireless access stations and corresponding received signal strength measurements by the other UE device; and

generate a location estimate for the other UE device by correlating the concurrently visible wireless access stations and the corresponding received signal strength measurements in the listing to one cluster of the multiple clusters within one of the signature areas.

14. The network device of claim 13, wherein, when collecting UE location indications and corresponding received signal strength measurements, the processor is further configured to execute the instructions stored in the memory to:

receive, from the cooperating UE devices, batch files with reference signal received power (RSRP) measurements and the location indications.

15. The network device of claim 13, wherein, when identifying the clusters of data points, the processor is further configured to:

apply a k-means clustering algorithm to the UE location indication from each data point in the signature area for a certain time window.

16. The network device of claim 13, wherein, when correlating the concurrently visible wireless access stations and the corresponding received signal strength measurements in the listing, the processor is further configured to:

match the concurrently visible wireless access stations in the listing with the combination of concurrently visible wireless access stations for one of the signature areas, and

identifying a best match for the listing of received signal strength measurements to received signal strength measurements for the one cluster.