公开(公告)号：US10693575B2

公开(公告)日：2020-06-23

申请号：US16118796

申请日：2018-08-31

Applicant: AT&T Intellectual Property I, L.P.

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

IPC: H04J1/16 ,  H04B17/373 ,  H04B17/391 ,  H04L12/26 ,  H04W72/08 ,  H04W8/22 ,  H04B17/382 ,  G06N20/00

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.

公开(公告)号：US20230024501A1

公开(公告)日：2023-01-26

申请号：US17942619

申请日：2022-09-12

Applicant: AT&T Intellectual Property I, L.P. ,  University College Cork - National University of Ireland

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

IPC: H04B17/373 ,  H04B17/391 ,  H04L43/0888 ,  H04W72/08 ,  H04W8/22 ,  H04B17/382 ,  G06N20/00

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.

公开(公告)号：US11476959B2

公开(公告)日：2022-10-18

申请号：US16855479

申请日：2020-04-22

Applicant: AT&T Intellectual Property I, L.P. ,  University College Cork-National University of Ireland

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

IPC: G06F11/00 ,  H04B17/373 ,  H04B17/391 ,  H04L43/0888 ,  H04W72/08 ,  H04W8/22 ,  H04B17/382 ,  G06N20/00

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.

公开(公告)号：US20200252147A1

公开(公告)日：2020-08-06

申请号：US16855479

申请日：2020-04-22

Applicant: AT&T Intellectual Property I, L.P. ,  University College Cork - National University of Ireland

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

IPC: H04B17/373 ,  H04B17/382 ,  H04W8/22 ,  H04W72/08 ,  H04L12/26 ,  H04B17/391 ,  G06N20/00

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.

公开(公告)号：US20200076520A1

公开(公告)日：2020-03-05

申请号：US16118796

申请日：2018-08-31

Applicant: AT&T Intellectual Property I, L.P.

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

IPC: H04B17/373 ,  H04B17/391 ,  H04L12/26 ,  H04B17/382 ,  H04W72/08 ,  H04W8/22 ,  G06F15/18

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.