US 12,438,772 B2
Self-optimizing networks
Praveen Kumar Reddy Mada, Denver, CO (US); Vinayak Sharma, Denver, CO (US); and Hamza Nasir Khokhar, Denver, CO (US)
Assigned to DISH Wireless L.L.C., Englewood, CO (US)
Filed by DISH Wireless L.L.C., Englewood, CO (US)
Filed on May 7, 2024, as Appl. No. 18/657,634.
Application 18/657,634 is a continuation of application No. 18/144,024, filed on May 5, 2023, granted, now 12,009,974.
Prior Publication US 2024/0372777 A1, Nov. 7, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 41/0816 (2022.01); H04L 41/0895 (2022.01); H04L 41/16 (2022.01); H04L 47/83 (2022.01)
CPC H04L 41/0816 (2013.01) [H04L 41/0895 (2022.05); H04L 41/16 (2013.01); H04L 47/83 (2022.05)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, from a distributed computing system servicing requests from user devices of a wireless network, information indicating performance metrics of a first set of computing resources of the distributed computing system;
generating, based on the information indicating performance metrics of the first set of computing resources, information representing usage of the wireless network at a first point in time;
providing the information representing usage of the wireless network to a machine-learning model to predict, based on usage data, network events at a time subsequent to the first point in time;
generating, based on the information indicating performance metrics of the first set of computing resources, second information representing usage of the wireless network at the time subsequent to the first point in time;
comparing output of the machine-learning model and the second information;
determining, based on the comparison, whether one or more predicted network events are represented in the second information; and
adjusting, responsive to determining whether the one or more predicted network events are represented in the second information, the machine-learning model.