System and method for throughput prediction for cellular networks

Patent metadata

Field	Value
Publication number	US-10693575-B2
Application number	US-201816118796-A
Country	US
Kind code	B2
Filing date	Aug 31, 2018
Priority date	Aug 31, 2018
Publication date	Jun 23, 2020
Grant date	Jun 23, 2020

Abstract

Aspects of the subject disclosure may include, for example, a method in which a processing system identifies a plurality of performance indicators comprising device performance indicators for a plurality of communication devices on a cellular network and network performance indicators for the cellular network. The method also includes obtaining historical data regarding the plurality of performance indicators for each of a series of time points during a past time period; the historical data for each of the plurality of performance indicators form an array of values for that performance indicator. The method further includes generating from each array a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period; the set of inputs comprises quantiles of the array, and the algorithm comprises a machine learning algorithm. Other embodiments are disclosed.

First claim

What is claimed is:

1. A method, comprising:
identifying, by a processing system including a processor, a plurality of performance indicators regarding a cellular network;
obtaining, by the processing system, historical data regarding the plurality of performance indicators for each of a series of time points during a past time period having a predetermined length, the historical data for each of the plurality of performance indicators forming an array of values for that performance indicator;
generating, by the processing system from each array, a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period having a predetermined length, the set of inputs comprising a statistical summarization of the array, the algorithm comprising a machine learning algorithm; and
obtaining, by the processing system, a predicted throughput for the cellular network based on the algorithm.

2. The method of claim 1 , wherein the plurality of performance indicators comprises device performance indicators for a plurality of communication devices on the cellular network, network performance indicators for the cellular network, or a combination thereof.

3. The method of claim 1 , further comprising providing, by the processing system, guidance based on the predicted throughput to a network element of the cellular network, a server connected to the cellular network, a client connected to the cellular network, an application executing on the cellular network, or a combination thereof.

4. The method of claim 1 , further comprising allocating, by the processing system, network resources of the cellular network based on the predicted throughput.

5. The method of claim 1 , wherein the machine learning algorithm comprises a regression algorithm.

6. The method of claim 1 , wherein the statistical summarization comprises quantiles of the array.

7. The method of claim 6 , wherein the quantiles of the array correspond to 25th, 50th, 75th and 90th percentiles of the array.

8. The method of claim 6 , wherein the set of inputs further comprises a mean value of the array.

9. The method of claim 1 , wherein the predicted throughput corresponds to a statistical indicator of the throughput over the future time period.

10. The method of claim 1 , further comprising selecting, by the processing system, the length of the past time period and the length of the future time period.

11. The method of claim 2 , wherein a communication device of the plurality of communication devices is a mobile device, and wherein the device performance indicators include a physical speed of the communication device.

12. The method of claim 2 , wherein the cellular network comprises a plurality of cells, and wherein the network performance indicators include a cell load for each of the plurality of cells.

13. A device comprising:
a processing system including a processor; and
a memory that stores executable instructions, wherein the processing system, responsive to executing the instructions, performs operations comprising:
identifying a plurality of performance indicators regarding a cellular network;
obtaining historical data regarding the plurality of performance indicators for each of a series of time points during a past time period having a predetermined length, the historical data for each of the plurality of performance indicators forming an array of values for that performance indicator; and
generating from each array a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period having a predetermined length, the set of inputs comprising a statistical summarization of the array, the algorithm comprising a machine learning algorithm.

14. The device of claim 13 , wherein the plurality of performance indicators comprises device performance indicators for a plurality of communication devices on the cellular network, network performance indicators for the cellular network, or a combination thereof.

15. The device of claim 13 , wherein the machine learning algorithm comprises a regression algorithm, and wherein the operations further comprise generating a prediction for a statistical indicator of the throughput based on the regression algorithm.

16. The device of claim 13 , wherein the set of inputs comprise quantiles of the array.

17. The device of claim 13 , wherein the operations further comprise selecting the length of the past time period and the length of the future time period.

18. A non-transitory machine-readable medium comprising executable instructions, wherein a processing system including a processor, responsive to executing the instructions, performs operations comprising:
identifying a plurality of performance indicators regarding a cellular network;
obtaining historical data regarding the plurality of performance indicators for each of a series of time points during a past time period, the historical data for each of the plurality of performance indicators forming an array of values for that performance indicator; and
generating from each array a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period, the set of inputs comprising a statistical summarization of the array, the algorithm comprising a machine learning algorithm.

19. The non-transitory machine-readable medium of claim 18 , wherein the plurality of performance indicators comprises device performance indicators for a plurality of communication devices on the cellular network, network performance indicators for the cellular network, or a combination thereof.

20. The non-transitory machine-readable medium of claim 18 , wherein the set of inputs comprise quantiles of the array.

Assignees

• At & T Ip I Lp
• Univ College Cork—National Univ Of Ireland

Inventors

• Jana Rittwik
• Halepovic Emir
• Sinha Rakesh
• Gopalakrishnan Vijay
• Zahran Ahmed
• Raca Darijo
• Sreenan Cormac John
• Bathula Balagangadhar G
• Varvello Matteo

Classifications

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• H04W72/542

  using measured or perceived quality · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title