Systems and methods for maintaining a telecommunications network using real-time SQL analysis

Patent metadata

Field	Value
Publication number	US-9743301-B1
Application number	US-201615058147-A
Country	US
Kind code	B1
Filing date	Mar 1, 2016
Priority date	Mar 1, 2016
Publication date	Aug 22, 2017
Grant date	Aug 22, 2017

Abstract

Systems and methods discussed herein provide for real-time and near-real-time analysis of performance for cell towers in order to determine when a cell tower is underperforming in order to perform corrective action before underperformance becomes an increased maintenance and/or service concern. Data is received at periodic intervals from a plurality of cell towers and a plurality of scripts are executed on the data as it is received in order to analyze key performance indicators associated with each tower. The received data is analyzed using real-time data and in some cases by applying the real-time data to a previously developed model to determine if a cell tower is underperforming based on at least one key performance indicator associated with that cell tower.

First claim

What is claimed is:

1. A method for maintaining a cell tower, comprising:
updating, by an application stored in a non-transitory memory of a server and executable by a processor, a short term table, by storing a plurality of data received from each cell tower of a plurality of cell towers, wherein each of the received pluralities of data is associated with a performance metric and stored as an entry in the short term table, wherein at least some performance metrics are associated with a key performance indicator (KPI) for a cell tower of the plurality of cell towers;
initiating, by the application, in the short term table, a first statistical analysis of at least some of the pluralities of data in the short term table, wherein initiating the first statistical analysis comprises performing a z-test and assigning a state to each entry stored in the short term table;
updating, by the application, the short term table during the first statistical analysis, wherein at least some of the updated data replaces data stored in the short term table after first statistical analysis is initiated;
completing, by the application, the first statistical analysis, during the updating of the short term table;
identifying, by the application, based on the completion of the first statistical analysis, at least some KPIs for a second analysis;
performing, by the application, the second statistical analysis on the at least some KPIs identified, wherein the second statistical analysis comprises a power test;
performing, by the application, based on the second statistical analysis, a third statistical analysis comprising a second z-test on at least one KPI of the at least some KPIs using a model, wherein the model is generated based on a long term table, wherein the long term table comprises data associated with the plurality of cell towers, and wherein the inputs used for the z-test and the power test are input into the model and the second z-test is performed on the results;
determining, by the application, based on the third statistical analysis, when the cell tower associated with the at least one KPI is underperforming; and
executing, in response to a determination that the cell tower is underperforming, at least one control action that includes one or more of:
sending a notification that the underperforming cell tower is underperforming,
changing a flag associated with underperforming cell tower performance,
notifying an on-site team, wherein the on-site team is located in proximity to the underperforming cell tower, or
modifying the performance of the underperforming cell tower remotely.

2. The method of claim 1 , further comprising copying, by the application, from the short term table to the long term table, a plurality of expired data, wherein data in the short term table expires after a predetermined time period.

3. The method of claim 2 , wherein the data in the long term table expires after a predetermined time period that is greater than the predetermined time period for expiration of data in the short term table.

4. The method of claim 1 , wherein the state comprises at least one of unanalyzed, analyzed, modified, or deleted, and wherein the application is configured to reset the state during at least the initial statistical analysis.

5. The method of claim 1 , further comprising updating, by the application, the short term table during the second statistical analysis, wherein at least some of the updated data replaces data stored in the short term table after the second statistical analysis is initiated.

6. A system for maintaining a cell tower, comprising:
a server;
a non-transitory memory of the server;
a processor of the server; and
an analysis application stored in the non-transitory memory and executable by the processor to:
receive pluralities of performance data from each of a plurality of cell towers;
store the received performance data as entries in a short term table, wherein the pluralities of performance data are associated with a plurality of performance metrics of the plurality of cell towers and expire a predetermined amount of time after being stored, and wherein at least some of the plurality of performance metrics are associated with a key performance indicator (KPI) of a cell tower of the plurality of cell towers;
initiate a first statistical analysis on at least some of the pluralities of performance data, wherein the first statistical analysis comprises a z-test;
update, after the z-test is initiated, the short term table during the z-test, at the predetermined intervals as additional performance data is received from the plurality of cell towers, wherein at least some of the updated short term table is analyzed during the z-test, and wherein at least some of the updated data replaces data stored in the short term table when the z-test is initiated;
complete, during the updating of the short term table, the z-test;
determine, based on the z-test, a subset of the plurality of performance metrics;
perform, subsequent to the completion of the first statistical analysis, a second statistical analysis on the subset of the plurality of performance metrics;
perform, based on the second statistical analysis, a third statistical analysis comprising a second z-test on at least one performance metric of the subset of the plurality of performance metrics using a model previously generated for the at least one performance metric, wherein the inputs used for the z-test are input into the model to perform the second z-test;
determine, based on the second z-test, that the cell tower associated with the at least one performance metric is underperforming; and
execute, in response to the determination that the cell tower is underperforming, at least one control action that includes one or more of:
sending a notification that the underperforming cell tower is underperforming,
changing a flag associated with underperforming cell tower performance,
notifying an on-site team, wherein the on-site team is located in proximity to the underperforming cell tower, or
modifying the performance of the underperforming cell tower remotely.

7. The system of claim 6 , wherein the analysis application associates each entry in the short term table with a state upon initiation of the first statistical analysis.

8. The system of claim 6 , wherein the analysis application at least one of detects and modifies at least some states associated with each entry in the short term table.

9. The system of claim 6 , wherein the short term table is updated during the second statistical analysis.

10. The system of claim 6 , wherein the application is configured to assign a state to each entry prior to at least the first statistical analysis, wherein the state comprises at least one of unanalyzed, analyzed, modified, or deleted, and wherein the application is configured to reset the state upon completion of the z-test.

11. A method for maintaining a cell tower, comprising:
performing, by an application stored in a non-transitory of a server and executable by a processor, a first statistical analysis comprising a first z-test on a plurality of data stored in a short term table on the non-transitory memory, wherein the application executes on the short term table, and wherein the plurality of data comprises key performance indicators (KPIs) received from a plurality of cell towers and associated with performance of the plurality of cell towers;
determining, by the application, based on the first z-test, a subset of the KPIs;
performing, by the application, a second statistical analysis on the subset of the KPIs, wherein the short term table receives additional pluralities of data during the second stat

Assignees

• Sprint Communications Co Lp

Inventors

• Earl Bryson
• Shelnutt Seth

Classifications

• H04W88/08

  Access point devices · CPC title

• H04W24/08 Primary

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

• H04L43/0888

  Throughput · CPC title

• H04L41/5016

  based on statistics of service availability, e.g. in percentage or over a given time · CPC title