Method for provisioning a wireless network

• US 8,861,353 B2
• Filed: 12/09/2010
• Issued: 10/14/2014
• Est. Priority Date: 12/09/2010
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Duan, Rong, Au, Siu-Tong, Kim, Heeyoung, Ma, Guang-Qin
• Primary Examiner(s): Nguyen, Hanh N
• Application Number:
  US12/964,472
• Publication Number:
  US 20120147760A1
• Time in Patent Office: 1,405 Days
• Field of Search: 370/240, 370/328, 370252-256, 370/352, 370/241, 370/242, 370/245, 370/247, 370/251, 370/341, 455/450, 455/451, 455/452, 455/456, 455/457, 455/524, 455/525, 455/424, 455/423, 455/446, 455/453, 455/425, 455/418
• US Class Current: 370/230.1
• CPC Class Codes: H04L 41/0816 the condition being an adaptation, e.g. in response to network events
• CPC Class Codes: H04L 43/067 using time frame reporting
• CPC Class Codes: H04L 43/16 Threshold monitoring
• CPC Class Codes: H04W 16/24 Cell structures
• CPC Class Codes: H04W 24/02 Arrangements for optimising operational condition
• CPC Class Codes: H04W 24/08 Testing, supervising or monitoring using real traffic

Abstract

A method that collects data and subjects it to statistical analysis to detect localized events, which assists in network provisioning. Illustratively, the data employed is hourly network traffic count that is collected at cell sites. By taking the advantage of additive property of Poisson process, the method integrates spatial neighbor information by aggregating temporal data in various areas, and iteratively estimating the event location and the radius of event impact by examining the posterior probability base on the aggregated data.

Claims

1. A method, executed on a processing platform, for enabling a wireless network to be provisioned, comprising:

collecting, from access points of said network, traffic volume data in successive time intervals;

identifying as event seeds, those of said access points having, during one or more time spans of a preselected number of said successive time intervals, traffic volume that exceeds a threshold;

processing each of the event seeds to determine information including an estimated even center and associated event impact territory, the processing being iterative, each iteration of the processing including statistical analysis, and using the estimated event center and a minimum number, greater than zero, of neighboring access points, each of said iterations enlarging said event impact territory and augmenting said event impact territory, until a preselected condition is met that terminates the processing; and

providing the information to a provisioning system of said wireless network.

2. The method of claim 1 where said event impact territory is expressed by a radius of a circle centered about said associated estimated event center.

3. The method of claim 1 where said event impact territory is defined by a radius of a circle about said estimated event center, and each iteration of the processing enlarges said radius only so much as to encompass a minimum number of access points that were not already encompassed in the immediately previous iteration.

4. The method of claim 1 further comprising:

creating a schedule for delivering portable cell sites to geographical areas based on the information.

5. The method of claim 1 wherein identifying the estimated event center uses a weighted calculation based on geographical locations of the access points in a corresponding event seed of the event seeds and associated traffic levels.

6. A method, executed on a processing platform, for enabling a wireless network to be provisioned, comprising:

collecting, from access points of said network, traffic volume data in successive time intervals;

identifying as event seeds, those of said access points having, during one or more time spans of a preselected number of said successive time intervals, traffic volume that exceeds a threshold;

processing each of the event seeds to determine information including an estimated event center and associated event impact territory; and

providing the information to a provisioning system of said wireless network,

wherein identifying the estimated event center is based on an average of coordinates for all access points in a corresponding event seed of the event seeds.

7. The method of claim 6 where the processing is iterative and each iteration of the processing includes statistical analysis.

8. The method of claim 7 where said statistical analysis is a Markov Modulated Nonhomogenous Poisson Process that is employed to estimate probability with which said traffic volume data is indicative of an event.

9. The method of claim 6 where the processing is iterative and each iteration of the processing includes statistical analysis, and using the estimated event center and a minimum number, greater than zero, of neighboring access points, each of said iterations enlarges said event impact territory and augments said event impact territory, until a preselected condition is met that terminates said processing.

10. The method of claim 9 where said condition is met with traffic attributed to said event is not increased with the enlarged territory.

11. The method of claim 9 wherein the preselected condition includes the event impact territory including an access point that is not impacted by an event associated with a corresponding event seed of the event seeds.

12. An apparatus comprising:

a processing platform configured to collect traffic volume data in successive time intervals from access points, identify as event seeds, those of said access points having, during one or more time spans of a preselected number of said successive time intervals, traffic volume that exceeds a threshold, and process each access point of the event seeds to identify an estimated event center and associated event impact territory, where the processing platform is configured to iteratively process each access point and each iteration of the processing includes statistical analysis, and using the estimated event center and a minimum number, greater than zero, of neighboring access points, each of said iterations enlarges said event impact territory and augments said event impact territory, until a preselected condition is met that terminates the processing; and

a provisioning system configured to provision a wireless network based on the information about the event seeds.

13. The apparatus of claim 12 where said event impact territory is defined by a radius of a circle about said estimated event center, and the processing is iterative and each iteration of the processing enlarges said radius only so much as to encompass a minimum number of access points that were not already encompassed in the immediately previous iteration.

14. The apparatus of claim 12 wherein identifying the estimated event center is based on an average of coordinates for all access points in a corresponding event seed of the event seeds.