Wireless carrier network performance analysis and troubleshooting

• US 10,397,043 B2
• Filed: 07/15/2016
• Issued: 08/27/2019
• Est. Priority Date: 07/15/2015
• Status: Active Grant

• Current Assignee: Tupl, Inc.
• Original Assignee: Tupl, Inc.
• Inventors: Tapia, Pablo, Sanchez-Mejias, Rafael
• Primary Examiner(s): Lin, Kenny S
• Application Number:
  US15/212,110
• Publication Number:
  US 20170019291A1
• Time in Patent Office: 1,138 Days
• Field of Search: None
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04L 41/0631 using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 41/5067 Customer-centric QoS measurements
• CPC Class Codes: H04L 41/5074 Handling of user complaints or trouble tickets
• CPC Class Codes: H04W 24/08 Testing, supervising or monitoring using real traffic
• CPC Class Codes: H04W 24/10 Scheduling measurement reports ; Arrangements for measurement reports

Abstract

An analytic application may provide analysis of performance data for a wireless carrier network to determine root causes of issues. Performance data for network components of the wireless carrier network and device components of user devices that use the network may be obtained. The performance data is processed by aggregating multiple datasets of the performance data into aggregated performance data according to one or more grouping parameters or converge a plurality of datasets of the performance data into converged performance data according to a unitary storage schema. Analysis may be performed on the aggregated performance data or the converged performance data to detect an issue affecting the wireless carrier network or to generate a solution to the issue. The aggregate performance data and the converged performance data may include non-real time data or real time data. Accordingly, the issue or the solution to the issue may be provided for presentation.

Claims

1. One or more non-transitory computer-readable media storing computer-executable instructions that upon execution cause one or more processors to perform acts comprising:

obtaining network component performance data for one or more network components of a wireless carrier network;

obtaining user device performance data for one or more device components of user devices that use the wireless carrier network, the user devices being of subscribers to the wireless carrier network;

processing the network component performance data and the user device performance data by at least one of aggregating multiple datasets of the network component performance data and the user device performance data into aggregated performance data according to one or more grouping parameters or converging a plurality of datasets of the network component performance data and the user device performance data into converged performance data according to a unitary storage schema;

performing analysis on at least one of the aggregated performance data or the converged performance data to detect an issue affecting one or more users of the wireless carrier network or to generate a solution to the issue, the aggregate performance data and the converged performance data including non-real time data or real time data; and

providing at least one of the issue or the solution to the issue for presentation.

2. The one or more non-transitory computer-readable media of claim 1, wherein the acts further comprise providing at least a portion of the aggregated performance data or the converged performance data for presentation.

3. The one or more non-transitory computer-readable media of claim 1, wherein aggregating the multiple datasets includes aggregating additional performance data, wherein converging the plurality of datasets includes converging the additional performance data, and wherein the additional performance data includes one or more of social media data, alarm data, trouble ticket data, or key performance indicator data generated by a network monitoring tool.

4. The one or more non-transitory computer-readable media of claim 1, wherein the one or more grouping parameters include a specific time period, a specific entity component, a specific user device vendor, a specific user device model, or different levels of an entity hierarchy that includes a subscriber level, a device level, a service area level, and a geographical market level, wherein the geographical market level further includes a zip code sublevel, a municipality sublevel, or an additional location-based level.

5. The one or more non-transitory computer-readable media of claim 1, wherein the performing includes performing the analysis using a trained machine learning model that employs multiple types of machine learning algorithms to analyze the aggregated performance data or the converged performance data.

6. The one or more non-transitory computer-readable media of claim 1, wherein the issue is reported for analysis via a subscriber or a network monitoring application generated trouble ticket.

7. The one or more non-transitory computer-readable media of claim 1, wherein the obtaining includes obtaining real time Voice over LTE (VoLTE) service performance data and real time Voice over WiFi (VoWiFi) service performance data for the wireless carrier network, each of the VoLTE service performance data and the VoWiFi service performance data including corresponding key performance indicators (KPIs), wherein the processing includes converging the VoLTE service performance data and the VoWiFi service performance data into converged real time data, and wherein the performing includes analyzing the converged real time data to detect one or more issues affecting one or more user devices that use the wireless carrier network.

8. The one or more non-transitory computer-readable media of claim 1, wherein the performing the analysis includes:

identifying data usage patterns of one or more users whose data usage on the wireless carrier network exceed a predetermined excess data usage threshold during a time interval;

retrieving network cell condition information for one or more geolocations at which a user device of each user of the one or more users used data during the time interval;

comparing the network cell condition information with the data usage patterns of the one or more users at the one or more geolocations;

determining whether a number of users whose data usage negatively affected performance of a congested network cell at a geolocation exceeds a threshold;

providing a recommendation of no deployment of small network cells at the geolocation for presentation in response to a determination that the number of users exceeded the threshold; and

providing a recommendation to deploy one or more small network cells at the geolocation for presentation, the one or more small network cells including a microcell, a femtocell, or a picocell.

9. The one or more non-transitory computer-readable media of claim 8, further comprising identifying at least one user whose data usage did not negatively affect the wireless carrier network even when the data usage of the user exceeded the predetermined excessive data usage threshold.

10. The one or more non-transitory computer-readable media of claim 1, wherein the performing the analysis includes:

receiving recommendations indicating geolocations for deployment of small network cells to alleviate performance issues of the wireless carrier network, the small network cells including a microcell, a femtocell, or a picocell;

obtaining social media data indicating at least one geolocation at which deployment of one or more small network cells is desired; and

cross referencing the recommendations and the social media data to generate one or more deployment geolocations for at least one small network cell.

11. The one or more non-transitory computer-readable media of claim 1, wherein the performing the analysis includes:

retrieving receiving quality of service metrics for the user devices as the user devices access the wireless carrier network via one or more small network cells in a geographical area, the one or more small network cells including a microcell, a femtocell, or a picocell;

comparing performance of the one or more small network cells in the geographical area with respect to the quality of services for the user devices;

generating one or more adjustments for at least one small network cell based comparison of the performance of the one or more small network cells and quality of service for the user devices; and

providing the one or more adjustments for the at least one small network cell for implementation, the one or more adjustments including moving a small network cell to a different location, reorient an antenna of the small network cell in a different direction to reshape a cell coverage area, modifying a data throughput of communication between the small network cell and a macrocell, or updating device software of the small network cell.

12. The one or more non-transitory computer-readable media of claim 11, wherein the performing the analysis further includes providing a unified view that shows the performance of the one or more small network cells in conjunction with performance one at least one network backhaul and one or more macrocells in the geographical area.

13. The one or more non-transitory computer-readable media of claim 1, wherein the performing the analysis includes:

identifying a specific set of network components and device components of a user device that supported an instance of network usage of the wireless carrier network by the user device;

analyzing, using the network component performance data and the user device performance data, performance of the specific set of device components and network components to pinpoint one or more components that negatively impacted a quality of service experienced by a user of the user device during the instance; and

providing data on the one or more components that negatively affected quality of service for presentation.

14. A computer-implemented method, comprising:

obtaining, via a data management platform executing on one or more computing nodes, performance data including network component performance data for one or more network components of a wireless carrier network, user device performance data for one or more device components of user devices that use the wireless carrier network, and one or more of social media data, alarm data, trouble ticket data, and key performance indicator data generated by a network monitoring tool;

processing, via the data management platform executing on one or more computing nodes, the performance data by at least one of aggregating multiple datasets of the performance data into aggregated performance data according to one or more grouping parameters or converging a plurality of datasets of the performance data into converged performance data according to a unitary storage schema, wherein aggregating the multiple datasets of the performance data includes aggregating at least a dataset of the network component performance data and a dataset of the user device performance data, and wherein converging the plurality of datasets of the performance data includes converging at least a dataset of the network component performance data and a dataset of the user device performance data;

performing, via an analytic application executing on the one or more computing nodes, analysis on at least one of the aggregated performance data or the converged performance data to detect an issue affecting one or more users of the wireless carrier network or to generate a solution to the issue, the aggregate performance data and the converged performance data including non-real time data or real time data; and

providing, via the analytic application executing on the one or more computing nodes, at least one of the issue or the solution to the issue for presentation.

15. The computer-implemented method of claim 14, wherein the obtaining includes obtaining real time Voice over LTE (VoLTE) service performance data and real time Voice over WiFi (VoWiFi) service performance data for the wireless carrier network, each of the VoLTE service performance data and the VoWiFi service performance data including corresponding key performance indicators (KPIs), wherein the processing includes converging the VoLTE service performance data and the VoWiFi service performance data into converged real time data, and wherein the performing includes analyzing the converged real time data to detect one or more issues affecting one or more user devices that use the wireless carrier network.

16. The computer-implemented method of claim 14, wherein the performing the analysis includes:

identifying data usage patterns of one or more users whose data usage on the wireless carrier network exceed a predetermined data usage threshold during a time interval;

retrieving network cell condition information for one or more geolocations at which a user device of each user of the one or more users used data during the time interval;

comparing the network cell condition information with the data usage patterns of the one or more users at the one or more geolocations;

determining whether a number of users whose data usage negatively affected performance of a congested network cell at a geolocation exceeds a threshold;

providing a recommendation of no deployment of small network cells at the geolocation for presentation in response to a determination that the number of users exceeded the threshold; and

providing a recommendation to deploy one or more small network cells at the geolocation for presentation, the one or more small network cells including a microcell, a femtocell, or a picocell.

17. The computer-implemented method of claim 14, wherein the performing the analysis includes:

receiving recommendations indicating geolocations for deployment of small network cells to alleviate performance issues of the wireless carrier network, the small network cells including a microcell, a femtocell, or a picocell;

obtaining social media data indicating at least one geolocation at which deployment of one or more small network cells is desired; and

cross referencing the recommendations and the social media data to generate one or more deployment geolocations for at least one small network cell.

18. The computer-implemented method of claim 14, wherein the performing the analysis includes:

retrieving receiving quality of service metrics for user devices as the user devices access the wireless carrier network via one or more small network cells in a geographical area, the one or more small network cells including a microcell, a femtocell, or a picocell;

comparing performance of the one or more small network cells in the geographical area with respect to the quality of services for the user devices;

generating one or more adjustments for at least one small network cell based comparison of the performance of the one or more small network cells and quality of service for the user devices;

providing the one or more adjustments for the at least one small network cell for implementation, the one or more adjustments including moving a small network cell to a different location, reorient an antenna of the small network cell in a different direction to reshape a cell coverage area, modifying a data throughput of communication between the small network cell and a macrocell, or updating device software of the small network cell; and

providing a unified view that shows the performance of the one or more small network cells in conjunction with performance one at least one network backhaul and one or more macrocells in the geographical area.

19. The computer-implemented method of claim 14, wherein the performing the analysis includes:

retrieving the performance data for one or more network components of a wireless carrier network or one or more device components of user devices that use the wireless carrier network;

identifying a specific set of network components and device components of a user device that supported an instance of network usage of the wireless carrier network by the user device;

analyzing performance of the specific set of device components and network components to pinpoint one or more components that negatively impacted a quality of service experienced by a user of the user device during the instance; and

providing data on the one or more components that negatively affected quality of service for presentation.

20. A system, comprising:

one or more processors; and

memory including a plurality of computer-executable components that are executable by the one or more processors to perform a plurality of actions, the plurality of actions comprising;

obtaining performance data for one or more network components of a wireless carrier network and one or more device components of user devices that use the wireless carrier network, the performance data including network component performance data for the one or more network components, user device performance data for the one or more device components of user devices, and one or more of social media data, alarm data, trouble ticket data, and key performance indicator data generated by a network monitoring tool;

processing the performance data by at least one of aggregating multiple datasets of the performance data into aggregated performance data according to one or more grouping parameters or converge a plurality of datasets of the performance data into converged performance data according to a unitary storage schema, wherein aggregating the multiple datasets of the performance data includes aggregating at least a dataset of the network component performance data and a dataset of the user device performance data, and wherein converging the plurality of datasets of the performance data includes converging at least a dataset of the network component performance data and a dataset of the user device performance data;

performing analysis on at least one of the aggregated performance data or the converged performance data using a trained machine learning model to detect an issue affecting one or more users of the wireless carrier network or to generate a solution to the issue, the aggregate performance data and the converged performance data including non-real time data or real time data; and

providing at least one of the issue or the solution to the issue for presentation.