Method and apparatus for determining localized service quality in a wireless network

Patent metadata

Field	Value
Publication number	US-9294366-B2
Application number	US-201314092851-A
Country	US
Kind code	B2
Filing date	Nov 27, 2013
Priority date	Nov 27, 2013
Publication date	Mar 22, 2016
Grant date	Mar 22, 2016

Abstract

A method, computer-readable storage device, and an apparatus for determining a localized service quality in a wireless network are disclosed. For example, the method constructs a tensor comprising a plurality of dimensions to represent data for the localized service quality, receives data for the wireless network that is gathered at a coarse granularity level, populates the tensor in accordance with the data that is gathered, applies an unfolding mechanism to construct a plurality of two dimensional matrices from the tensor, determines for each respective two dimensional matrix of the plurality of two dimensional matrices an approximation for a pre-determined level of accuracy, and populating all entries of each respective two dimensional matrix that are not populated in accordance with the approximation of the respective two dimensional matrix, and determines the localized service quality by applying a folding mechanism across the plurality of two dimensional matrices.

First claim

What is claimed is:

1. A method for determining a localized service quality in a wireless network, the method comprising:
constructing, via a processor, a tensor comprising a plurality of dimensions to represent data for the localized service quality in the wireless network;
receiving, via the processor, data for the wireless network that is gathered at a coarse granularity level;
populating, via the processor, the tensor in accordance with the data that is gathered at the coarse granularity level;
applying, via the processor, an unfolding mechanism to construct a plurality of two dimensional matrices from the tensor;
determining, via the processor, for each respective two dimensional matrix of the plurality of two dimensional matrices that is constructed an approximation for a pre-determined level of accuracy, and populating all entries of each respective two dimensional matrix that are not populated in accordance with the approximation of the respective two dimensional matrix, wherein the determining of the approximation for the pre-determined level of accuracy for a respective matrix of the plurality of two dimensional matrices comprises:
identifying all Eigen values of the respective matrix using singular value decomposition and determining the approximation by applying a threshold; and
selecting a first number of Eigen vectors in accordance with the pre-determined level of accuracy; and

determining, via the processor, the localized service quality by applying a folding mechanism across the plurality of two dimensional matrices.

2. The method of claim 1 , wherein a dimension of the tensor comprises a dimension for spatial locations of network equipment.

3. The method of claim 1 , wherein a dimension of the tensor comprises a dimension for a sequence of times.

4. The method of claim 3 , wherein the sequence of times is in accordance with a pre-determined granularity.

5. The method of claim 1 , wherein a dimension of the tensor comprises a dimension for key performance indicators of service quality.

6. The method of claim 1 , wherein a dimension of the tensor comprises a dimension for types of user endpoint devices.

7. The method of claim 1 , wherein a dimension of the tensor comprises a dimension for indicating models of user endpoint devices.

8. The method of claim 1 , wherein a first number of Eigen vectors that is selected comprises Eigen vectors with a highest concentration of information.

9. The method of claim 1 , further comprising:
using the localized service quality for a purpose.

10. The method of claim 9 , wherein the purpose comprises at least one of: diagnosing a network trouble, determining an impact of a network trouble, network planning, performing load balancing, and optimizing a usage of a network resource.

11. A computer-readable storage device storing a plurality of instructions which, when executed by a processor, cause the processor to perform operations for determining a localized service quality in a wireless network, the operations comprising:
constructing a tensor comprising a plurality of dimensions to represent data for the localized service quality in the wireless network;
receiving data for the wireless network that is gathered at a coarse granularity level;
populating the tensor in accordance with the data that is gathered at the coarse granularity level;
applying an unfolding mechanism to construct a plurality of two dimensional matrices from the tensor;
determining for each respective two dimensional matrix of the plurality of two dimensional matrices that is constructed an approximation for a pre-determined level of accuracy, and populating all entries of each respective two dimensional matrix that are not populated in accordance with the approximation of the respective two dimensional matrix, wherein the determining of the approximation for the pre-determined level of accuracy for a respective matrix of the plurality of two dimensional matrices comprises:
identifying all Eigen values of the respective matrix using singular value decomposition and determining the approximation by applying a threshold; and
selecting a first number of Eigen vectors in accordance with the pre-determined level of accuracy; and

determining the localized service quality by applying a folding mechanism across the plurality of two dimensional matrices.

12. The computer-readable storage device of claim 11 , wherein a dimension of the tensor comprises a dimension for spatial locations of network equipment.

13. The computer-readable storage device of claim 11 , wherein a dimension of the tensor comprises a dimension for a sequence of times.

14. The computer-readable storage device of claim 13 , wherein the sequence of times is in accordance with a pre-determined granularity.

15. The computer-readable storage device of claim 11 , wherein a dimension of the tensor comprises a dimension for key performance indicators of service quality.

16. The computer-readable storage device of claim 11 , wherein a dimension of the tensor comprises a dimension for types of user endpoint devices.

17. The computer-readable storage device of claim 11 , wherein a dimension of the tensor comprises a dimension for indicating models of user endpoint devices.

18. An apparatus for determining a localized service quality in a wireless network, the apparatus comprising:
a processor; and
a computer-readable storage device storing a plurality of instructions which, when executed by the processor, cause the processor to perform operations, the operations comprising:
constructing a tensor comprising a plurality of dimensions to represent data for the localized service quality in the wireless network;
receiving data for the wireless network that is gathered at a coarse granularity level;
populating the tensor in accordance with the data that is gathered at the coarse granularity level;
applying an unfolding mechanism to construct a plurality of two dimensional matrices from the tensor;
determining for each respective two dimensional matrix of the plurality of two dimensional matrices that is constructed an approximation for a pre-determined level of accuracy, and populating all entries of each respective two dimensional matrix that are not populated in accordance with the approximation of the respective two dimensional matrix, wherein the determining of the approximation for the pre-determined level of accuracy for a respective matrix of the plurality of two dimensional matrices comprises:
identifying all Eigen values of the respective matrix using singular value decomposition and determining the approximation by applying a threshold; and
selecting a first number of Eigen vectors in accordance with the pre-determined level of accuracy; and

determining the localized service quality by applying a folding mechanism across the plurality of two dimensional matrices.

Assignees

• At & T Ip I Lp

Inventors

• Mahimkar Ajay
• Aggarwal Vaneet
• Ma Hongyao
• Willinger Walter

Classifications

• H04W24/08

  Testing, {supervising or monitoring} using real traffic · CPC title

• H04L43/12

  Network monitoring probes · CPC title

• H04L41/5009 Primary

  Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF] · CPC title

• H04W24/10

  Scheduling measurement reports {; Arrangements for measurement reports} · CPC title