Knowledge discovery and data mining-assisted multi-radio access technology control

• US 9,730,098 B2
• Filed: 11/25/2013
• Issued: 08/08/2017
• Est. Priority Date: 11/25/2013
• Status: Active Grant

• Current Assignee: AT&T Mobility II LLC (AT&T, Inc.)
• Original Assignee: AT&T Mobility II LLC (AT&T, Inc.)
• Inventors: Noriega, Dimas R.
• Primary Examiner(s): Jaroenchonwanit, Bunjob
• Application Number:
  US14/089,033
• Publication Number:
  US 20150146549A1
• Time in Patent Office: 1,352 Days
• Field of Search: None
• CPC Class Codes: H04W 24/02 Arrangements for optimising operational condition
• CPC Class Codes: H04W 24/10 Scheduling measurement reports ; Arrangements for measurement reports

Abstract

Joint provisioning of cell sector capacity (CSC) and a defined customer service level (CSL) is provided utilizing a knowledge discovery and data mining-assisted multi-radio access technology controller. For example, Strategic Performance Indexes, CSC and CSL, are identified. The relationships between CSC, CSL, ergodic channel capacity (ECC) and an interface load (IL) for a radio network (RN) (or cell sector of an RN) are determined. Extensive information associated with the RN is collected and neural networks analysis is employed to reduce the information to a manageable set including the specific information associated with ECC and IL. The reduced set of information is mapped to ECC and IL using eigenvalue analysis, and the relationships between the ECC, IL, CSC and CSL are employed to determine the CSC and CSL for the RN (or cell sector of the RN). Network assignments and/or parameters can be updated based on the results.

Claims

1. A method, comprising:

accessing, by a device comprising a processor, first counters for a radio network device, wherein the first counters are associated with a joint condition for the radio network device;

employing, by the device, pattern recognition to reduce the first counters to second counters fewer than the first counters, wherein the second counters are associated with the joint condition for the radio network device; and

determining, by the device, a factor associated with the joint condition, wherein the determining is based on the second counters.

2. The method of claim 1, wherein the factor comprises an ergodic channel capacity of the radio network device, and wherein the ergodic channel capacity and an interface load of the radio network device are associated with a defined strategic performance index indicative of the performance of the radio network device.

3. The method of claim 1, further comprising determining the joint condition for the radio network device, wherein the joint condition is associated with a performance requirement for the radio network device.

4. The method of claim 1, further comprising filtering a group of records within a counter of the first group of counters to remove malformed records of the group of records.

5. The method of claim 4, wherein the filtering comprises performing a time series filtering method on the malformed records to recover correct data and generate new records based on the correct data.

6. The method of claim 5, further comprising mapping the new records to the ergodic channel capacity and the interface load based on performing eigenvalue analysis on information indicative of the new records.

7. The method of claim 1, wherein the employing pattern recognition comprises employing a machine learning analysis.

8. An apparatus, comprising:

a memory to store executable instructions; and

a processor, coupled to the memory, that facilitates execution of the executable instructions to perform operations, comprising;

accessing a first group of counters for a radio network device, wherein the first group of counters is associated with a joint condition for the radio network device;

employing pattern recognition to reduce the first group of counters to a second group of counters, wherein the second group of counters is associated with the joint condition for the radio network device; and

determining a factor associated with the joint condition, wherein the determining is based on the second group of counters.

9. The apparatus of claim 8, wherein the joint condition comprises a defined cell sector capacity of the radio network device.

10. The apparatus of claim 8, wherein the factor comprises an interface load of the radio network device.

11. The apparatus of claim 8, wherein the operations further comprise determining the joint condition for the radio network device.

12. The apparatus of claim 11, wherein the joint condition is associated with a performance requirement for the radio network device, and wherein the performance requirement is a defined customer service level for the radio network device.

13. The apparatus of claim 8, wherein the pattern recognition comprises a data mining analysis.

14. The apparatus of claim 13, wherein the data mining analysis comprises a neural network analysis.

15. The apparatus of claim 13, wherein the data mining analysis comprises a machine learning analysis.

16. The apparatus of claim 8, wherein the employing pattern recognition to reduce the first group of counters to the second group of counters comprises employing eigenvalue analysis to map the first group of counters to capacity model counters for channel capacity and interface load.

17. A non-transitory machine-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

accessing first counters for a radio network device, wherein the first counters are associated with a joint condition for the radio network device;

employing pattern recognition to reduce the first counters to second counters, wherein the second counters are associated with the joint condition for the radio network device, and wherein the employing the pattern recognition comprises determining information indicative of a pattern associated with a defined relationship between an ergodic channel capacity of the radio network device, an interface load of the radio network device and a defined strategic performance index associated with the performance of the radio network device; and

determining a factor associated with the joint condition, wherein the determining is based on the second counters.

18. The non-transitory machine-readable storage medium of claim 17, wherein the pattern recognition comprises a data mining analysis.

19. The non-transitory machine-readable storage medium of claim 18, wherein the data mining analysis comprises a neural network analysis.

20. The non-transitory machine-readable storage medium of claim 17, wherein the joint condition comprises a defined cell sector capacity of the radio network device.