System and method for throughput prediction for cellular networks

• US 10,693,575 B2
• Filed: 08/31/2018
• Issued: 06/23/2020
• Est. Priority Date: 08/31/2018
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.), University College Dublin
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Jana, Rittwik, Halepovic, Emir, Sinha, Rakesh, Gopalakrishnan, Vijay, Zahran, Ahmed, Raca, Darijo, Sreenan, Cormac John, Bathula, Balagangadhar G., Varvello, Matteo
• Primary Examiner(s): Yeung, Mang Hang
• Application Number:
  US16/118,796
• Publication Number:
  US 20200076520A1
• Time in Patent Office: 662 Days
• Field of Search: 370252
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 20/20 Ensemble learning
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06N 7/02 using fuzzy logic computing arrangements based on biological models G06N3/00; computing arrangements using knowledge-based models G06N5/00
• CPC Class Codes: H04B 17/327 Received signal code power [RSCP]
• CPC Class Codes: H04B 17/373 Predicting channel quality or other radio frequency [RF] parameters
• CPC Class Codes: H04B 17/382 for resource allocation, admission control or handover
• CPC Class Codes: H04B 17/3913 Predictive models, e.g. based on neural network models
• CPC Class Codes: H04L 43/0888 Throughput
• CPC Class Codes: H04W 24/08 Testing, supervising or monitoring using real traffic
• CPC Class Codes: H04W 72/542 using measured or perceived quality
• CPC Class Codes: H04W 8/22 Processing or transfer of terminal data, e.g. status or physical capabilities

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.

Claims

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.