Managing LTE network capacity

Patent metadata

Field	Value
Publication number	US-10834610-B2
Application number	US-201916272868-A
Country	US
Kind code	B2
Filing date	Feb 11, 2019
Priority date	Feb 11, 2019
Publication date	Nov 10, 2020
Grant date	Nov 10, 2020

Abstract

Systems and methods are described for monitoring performance and allocating resources to improve the performance of a wireless telecommunications network. A wireless telecommunications network may be comprised of base stations and other infrastructure equipment, which may be sourced from various suppliers. Users may generate traffic on the wireless network, and performance metrics relating to the user experience may be collected from individual base stations. The set of available metrics for a particular base station may vary according to the supplier. A machine learning model is thus trained using metrics from multiple base stations, and used to estimate values for metrics that a particular base station does not provide. The metrics are then further characterized according to the service classes of the users, and resources for improving the performance of base stations are allocated according to the reported and estimated metrics for various service classes.

First claim

What is claimed is:

1. A computer-implemented method comprising:
obtaining a set of metrics collected by a first base station of a plurality of base stations, wherein the set of metrics includes a first metric and a second metric, wherein the first base station does not collect a third metric that is collected by at least one other base station of the plurality of base stations, and wherein the set of metrics is associated with a time period;
calculating, based at least in part on the first metric, the second metric, and a machine learning model trained with metrics collected by the plurality of base stations, the third metric for the first base station during the time period, wherein the third metric quantifies user experiences of low data throughput;
obtaining application data usage information for a plurality of users;
identifying, based at least in part on the application data usage information, a first subset of the plurality of users, wherein the application data usage information indicates that individual users in the first subset experienced low data throughput at the first base station during the time period, and wherein the individual users in the first subset are associated with a first service class;
determining, based at least in part on a size of the first subset, an estimated value of the third metric for the first service class;
generating for display a user interface, the user interface including information regarding a percentage of users in the first service class who experienced low data throughput at the first base station during the time period; and
displaying the user interface on a client computing device.

2. The computer-implemented method of claim 1 , wherein the third metric comprises a number of user data sessions having a throughput lower than a threshold rate.

3. The computer-implemented method of claim 2 , wherein identifying the first subset of the plurality of users comprises identifying individual users for whom the application data usage information indicates a data session throughput lower than the threshold rate.

4. The computer-implemented method of claim 1 , wherein the first metric comprises a channel quality indicator, and wherein the second metric comprises a network load.

5. A system comprising:
a data store configured to store computer-executable instructions; and
a processor in communication with the data store, wherein the computer-executable instructions, when executed by the processor, configure the processor to:
obtain a set of metrics collected by a first base station, wherein the set of metrics includes a first metric and a second metric, and wherein the set of metrics does not include a third metric that is collected by at least one other base station;
calculate, based at least in part on the set of metrics collected by the first base station and a machine learning model trained with user experience metrics, an estimated value for the third metric;
associate a first subset of a plurality of users with the third metric based at least in part on application data usage information for the plurality of users, wherein individual users in the first subset are associated with a first service class; and
transmit information regarding the first subset of the plurality of users to a client computing device.

6. The system of claim 5 , wherein the first subset of the plurality of users comprises users in the first service class who are associated with the third metric.

7. The system of claim 5 , wherein the processor is further configured to determine a percentage of users in the first service class who are associated with the third metric.

8. The system of claim 5 , wherein the processor is further configured to associate a second subset of the plurality of users with the third metric based at least in part on the application data usage information, wherein individual users in the second subset are associated with a second service class.

9. The system of claim 5 , wherein the set of metrics is a first set of metrics, and wherein the processor is further configured to:
obtain a second set of metrics from a second base station, the second set of metrics from the second base station including the first, second, and third metrics; and
determine a priority for allocating resources to the first base station and the second base station based at least in part on the first set of metrics, the second set of metrics, the third metric calculated for the first base station, and the third metric obtained from the second base station.

10. The system of claim 9 , wherein the priority is determined based at least in part on a size of the first subset of the plurality of users.

11. The system of claim 5 , wherein the application data usage information is associated with an application that executes on mobile computing devices.

12. The system of claim 11 , wherein the application is associated with at least one of streaming audio, streaming video, social media, chat, messaging, email, or gaming.

13. The system of claim 5 , wherein the processor is further configured to:
obtain a second set of metrics from a plurality of base stations; and
train the machine learning model using a first portion of the second set of metrics as input and a second portion of the second set of metrics as target output.

14. The system of claim 13 , wherein the second set of metrics is associated with a service class of a plurality of service classes.

15. The system of claim 5 , wherein the third metric indicates a percentage of users who experienced data session throughputs below a threshold rate, and wherein the processor is further configured to determine, for individual service classes of a plurality of service classes, an estimated number of users in the service class who experienced data session throughputs below the threshold rate.

16. The system of claim 5 , wherein the information transmitted to the client computing device includes instructions for displaying a user interface.

17. The system of claim 16 , wherein the user interface comprises a graph that displays the first and second metrics as axes.

18. The system of claim 17 , wherein the user interface displays individual base stations as points on the graph.

19. The system of claim 18 , wherein the user interface displays the third metric as a color or shade of the points.

20. A non-transient computer-readable storage medium storing computer-executable instructions that, when executed by a processor, configure the processor to:
obtain one or more metrics collected by a first base station;
calculate, based at least in part on the one or more metrics and a machine learning model, an additional metric, wherein the additional metric is not collected by the first base station, and wherein the additional metric is collected by at least one other base station;
associate, based at least in part on application data usage information, at least a portion of the additional metric with a first service class of a plurality of service classes; and
transmit information regarding the portion of the additional metric that is associated with the first service class.

21. The non-transient computer-readable storage medium of claim 20 , wherein the processor is further configured to determine, based at least in part on the at least a portion of the additional metric associated with the first service class, a priority for allocating resources to the first base station.

22. The non-transient computer-readable storage medi

Assignees

• T Mobile Usa Inc

Inventors

• Escudero Otto Fonseca
• Dousson Gary
• Jacinto Marie Grace
• Jat Khrum Kashan
• Sandhu Jatinder Singh

Classifications

• H04L41/5022

  by giving priorities, e.g. assigning classes of service · CPC title

• H04W24/08

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

• H04L43/0876

  Network utilisation, e.g. volume of load or congestion level · CPC title

• H04L43/0888

  Throughput · CPC title

• H04W24/10

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