Cellular network cell clustering and prediction based on network traffic patterns

Patent metadata

Field	Value
Publication number	US-9538401-B1
Application number	US-201514975116-A
Country	US
Kind code	B1
Filing date	Dec 18, 2015
Priority date	Dec 18, 2015
Publication date	Jan 3, 2017
Grant date	Jan 3, 2017

Abstract

A device may receive an initial set of network parameter values, associated with cells of a cellular network, that are measured or calculated based on communications associated with the cells of the cellular network. The device may determine a set of feature values, associated with the cells of the cellular network, using the initial set of network parameter values. The device may cluster the cells of the cellular network into a first group of clusters using a first clustering technique, and may cluster the cells of the cellular network into a second group of clusters using a second clustering technique. The device may cluster the cells of the cellular network into a final group of clusters based on the first group of clusters and the second group of clusters, and may output information associated with the final group of clusters of the cells of the cellular network.

First claim

What is claimed is:

1. A device, comprising:
one or more processors to:
receive a set of network parameter values associated with multiple cells of a cellular network,
the set of network parameter values being measured or calculated based on communications associated with the multiple cells of the cellular network;

determine a set of feature values, associated with the multiple cells of the cellular network, using the set of network parameter values and based on a set of rules,
a quantity of the set of feature values being less than a quantity of the set of network parameter values;

cluster the multiple cells of the cellular network into a first group of clusters using a first clustering technique that clusters the multiple cells into the first group of clusters based on the set of feature values;
cluster the multiple cells of the cellular network into a second group of clusters using a second clustering technique that clusters the multiple cells into the second group of clusters based on the set of feature values,
the second group of clusters being different from the first group of clusters,
the second clustering technique being different from the first clustering technique;

cluster the multiple cells of the cellular network into a final group of clusters based on the first group of clusters and the second group of clusters; and
output information associated with the final group of clusters of the multiple cells of the cellular network.

2. The device of claim 1 , where the one or more processors, when receiving the set of network parameter values, are to:
receive at least a portion of the set of network parameter values via a base station associated with a cell of the multiple cells of the cellular network.

3. The device of claim 1 , where the set of network parameter values includes at least one of:
a radio frequency performance parameter associated with the cellular network,
a signaling performance parameter associated with the cellular network, or
a network traffic performance parameter associated with the cellular network.

4. The device of claim 1 , where the set of feature values includes a subset of the set of network parameter values.

5. The device of claim 1 , where the set of feature values includes at least one of:
a first value included in the set of network parameter values, or
a second value calculated from one or more values included in the set of network parameter values.

6. The device of claim 1 , where the first group of clusters includes all of the multiple cells of the cellular network; and
where the second group of clusters includes all of the multiple cells of the cellular network.

7. The device of claim 1 , where the set of network parameter values is a first set of network parameter values; and
where the one or more processors are further to:
identify a second set of network parameter values associated with a cluster of cells included in the final group of clusters;
train multiple forecasting models using a third set of network parameter values that is a subset of the second set of network parameter values;
test the multiple forecasting models, based on training the multiple forecasting models, using a fourth set of network parameter values that is a subset of the second set of network parameter values;
generate a combined forecasting model based on testing the multiple forecasting models;
generate one or more forecasted network parameter values for the cluster of cells using the combined forecasting model; and
output the one or more forecasted network parameter values associated with the cluster of cells.

8. A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to:
receive a set of network parameter values associated with multiple cells of a cellular network,
the set of network parameter values being measured or calculated based on communications associated with the multiple cells of the cellular network;

determine a set of feature values, associated with the multiple cells of the cellular network, using the set of network parameter values and based on a set of rules;
cluster the multiple cells of the cellular network into a first group of clusters using a first clustering technique that clusters the multiple cells into the first group of clusters based on the set of feature values;
cluster the multiple cells of the cellular network into a second group of clusters using a second clustering technique that clusters the multiple cells into the second group of clusters based on the set of feature values,
the second clustering technique being different from the first clustering technique;

cluster the multiple cells of the cellular network into a final group of clusters based on the first group of clusters and the second group of clusters; and
output information associated with the final group of clusters of the multiple cells of the cellular network.

9. The non-transitory computer-readable medium of claim 8 , where the one or more instructions, that cause the one or more processors to receive the set of network parameter values, cause the one or more processors to:
receive the set of network parameter values from one or more devices associated with the cellular network.

10. The non-transitory computer-readable medium of claim 8 , where the set of network parameter values includes at least one of:
an accessibility parameter associated with the cellular network,
a retainability parameter associated with the cellular network,
an availability parameter associated with the cellular network,
an integrity parameter associated with the cellular network, or
a mobility parameter associated with the cellular network.

11. The non-transitory computer-readable medium of claim 8 , where the set of feature values includes:
a first value included in the set of network parameter values, and
a second value calculated based on a plurality of values included in the set of network parameter values.

12. The non-transitory computer-readable medium of claim 8 , where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
identify a target set of network parameter values associated with a cluster of cells included in the final group of clusters;
train multiple forecasting models using a training set of network parameter values;
test the multiple forecasting models, based on training the multiple forecasting models, using a test set of network parameter values;
generate a combined forecasting model based on testing the multiple forecasting models;
generate one or more forecasted network parameter values associated with the cluster of cells using the combined forecasting model; and
output the one or more forecasted network parameter values associated with the cluster of cells.

13. The non-transitory computer-readable medium of claim 12 , where the one or more instructions, that cause the one or more processors to generate the combined forecasting model, cause the one or more processors to:
generate the combined forecasting model as a weighted combination of the multiple forecasting models.

14. The non-transitory computer-readable medium of claim 12 , where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
determine an action to be taken to improve operation of the cellular network based on the one or more forecasted network parameter values; and
perform the action.

Assignees

• Verizon Patent & Licensing Inc

Inventors

• Ouyang Ye
• Becht Carol
• Iyer Krishna Pichumani
• Zhu Lily

Classifications

• H04W16/22

  Traffic simulation tools or models · CPC title

• H04W24/02 Primary

  Arrangements for optimising operational condition · CPC title

• H04W16/24

  Cell structures · CPC title