- Patent Title: System and method for throughput prediction for cellular networks
-
Application No.: US16118796Application Date: 2018-08-31
-
Publication No.: US10693575B2Publication Date: 2020-06-23
- Inventor: Rittwik Jana , Emir Halepovic , Rakesh Sinha , Vijay Gopalakrishnan , Ahmed Zahran , Darijo Raca , Cormac John Sreenan , Balagangadhar G. Bathula , Matteo Varvello
- Applicant: AT&T Intellectual Property I, L.P.
- Applicant Address: US GA Atlanta IE Cork
- Assignee: AT&T Intellectual Property I, L.P.,University College Cork—National University of Ireland
- Current Assignee: AT&T Intellectual Property I, L.P.,University College Cork—National University of Ireland
- Current Assignee Address: US GA Atlanta IE Cork
- Agency: Guntin & Gust, PLC
- Agent Jay Anderson
- Main IPC: H04J1/16
- 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.
Public/Granted literature
- US20200076520A1 System and Method for Throughput Prediction for Cellular Networks Public/Granted day:2020-03-05
Information query