US 12,302,157 B2
Automatic and real-time cell performance examination and prediction in communication networks
Mehdi Malboubi, San Ramon, CA (US); and Baofeng Jiang, Pleasanton, CA (US)
Assigned to AT&T Intellectual Property I, L.P., Atlanta, GA (US)
Filed by AT&T Intellectual Property I, L.P., Atlanta, GA (US)
Filed on Jul. 14, 2022, as Appl. No. 17/864,663.
Prior Publication US 2024/0022938 A1, Jan. 18, 2024
Int. Cl. H04W 24/10 (2009.01); G06F 18/10 (2023.01); G06F 18/21 (2023.01); H04B 17/318 (2015.01); H04L 41/16 (2022.01)
CPC H04W 24/10 (2013.01) [G06F 18/10 (2023.01); G06F 18/217 (2023.01); H04B 17/318 (2015.01); H04L 41/16 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a processing system including a processor, a first plurality of values of key performance indicators (KPIs) relating to performance of a cell on a communication network, wherein the first plurality of values of the KPIs comprises labeled training data for training a machine learning (ML) model for the performance of the cell;
predicting, by the processing system in accordance with the ML model, a future performance of the cell, resulting in a predicted performance;
subsequently determining, by the processing system, a current performance of the cell for comparing with the predicted performance,
iteratively executing, by the processing system using the labeled training data, a training procedure for the ML model in accordance with the comparing, resulting in a trained ML model; and
testing, by the processing system, the trained ML model,
wherein the labeled training data corresponds to ground truth data comprising a training data set and a test data set,
wherein the trained ML model, when deployed on the communication network subsequent to the testing, receives as input near-real time data regarding the performance of the cell and provides as output predictions of the performance of the cell satisfying an accuracy criterion.