IP Library Granted Patent US 12684476
Granted Patent B2
US 12684476 · App. 18/476,296 · Granted Jul 14, 2026

Ubiquitous wireless access network selection

Inventors: Ronak Shah (Issaquah, WA); Jason Sikes (Carnation, WA)
Assignee: AT&T Intellectual Property I, L.P.
H04W48/18H04W76/10
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12684476
App. No.
18/476,296
Granted
Jul 14, 2026
Kind
B2
Abstract

A processing system including at least one processor of an endpoint device may obtain performance information of a plurality of wireless access networks in a vicinity of the endpoint device and receive a service request from a first process in operation on the endpoint device. The processing system may then select in response to the service request, a first wireless access network of the plurality of wireless access networks for the first process based upon the performance information of the plurality of wireless access networks and establish a communication session for the first process via the first wireless access network.

Claims (57)

1 . A method comprising:

obtaining, by a processing system including at least one processor of an endpoint device, performance information of a plurality of wireless access networks in a vicinity of the endpoint device, wherein the performance information includes metrics for a plurality of network performance indicators associated with at least one of the plurality of wireless access networks;

receiving, by the processing system, a service request from a first process in operation on the endpoint device;

selecting, by the processing system in response to the service request, a first wireless access network of the plurality of wireless access networks for the first process based upon the performance information of the plurality of wireless access networks, wherein the selecting is in accordance with a selection function comprising at least one machine learning model, and wherein the selection function comprises a plurality of factors associated with the plurality of network performance indicators; and

establishing, by the processing system, a communication session for the first process via the first wireless access network.

2 . The method of claim 1 , wherein the performance information includes metrics for at least one network performance indicator, wherein the selecting is in accordance with a selection function, wherein the selection function comprises a plurality of factors, wherein the plurality of factors further includes at least one of:

at least one factor associated with the at least one network performance indicator;

a cost factor;

a security factor; or

a mobility factor.

3 . The method of claim 2 , wherein the selection function is associated with the first process, and wherein the processing system stores a plurality of selection functions associated with a plurality of processes in operation on the endpoint device.

4 . The method of claim 2 , wherein the selection function is associated with a first process type, wherein the first process is of the first process type, and wherein the processing system stores a plurality of selection functions associated with a plurality of process types in operation on the endpoint device.

5 . The method of claim 1 , wherein the obtaining comprises:

receiving a plurality of broadcasts from the plurality of wireless access networks, each broadcast of the plurality of broadcasts comprising respective performance information for a respective one of the plurality of wireless access networks.

6 . The method of claim 1 , wherein the performance information comprises at least one metric for at least one network performance indicator of the plurality of network performance indicators, and wherein the at least one network performance indicator comprises at least one of:

a bandwidth;

a throughput;

a latency;

a packet loss;

a jitter; or

a round trip time.

7 . The method of claim 1 , wherein the performance information comprises at least one metric for at least one network performance indicator of the plurality of network performance indicators, and wherein the at least one network performance indicator comprises at least one of:

a video quality metric; or

an audio quality metric.

8 . The method of claim 1 , wherein the performance information comprises uplink performance information and downlink performance information.

9 . The method of claim 1 , wherein the obtaining comprises:

establishing a plurality of connections to the plurality of wireless access networks; and

measuring at least one network performance indicator of the plurality of network performance indicators for each wireless access network of the plurality of wireless access networks in accordance with each connection of the plurality of connections to obtain respective network performance indicator metrics for the at least one network performance indicator.

10 . The method of claim 9 , wherein the obtaining further comprises:

closing each connection after the measuring.

11 . The method of claim 9 , wherein the measuring comprises:

applying at least a first test protocol associated with the first process.

12 . The method of claim 11 , wherein the at least the first test protocol includes a plurality of communications with at least a first server associated with the at least the first service via the plurality of connections to the plurality of wireless access networks.

13 . The method of claim 12 , wherein the respective network performance indicator metric for each wireless access network of the plurality of wireless access networks is in accordance with each communication of the plurality of communications with the at least the first server.

14 . The method of claim 12 , wherein the at least the first server comprises:

a video server;

a conference server;

a content distribution network node;

a server of a cloud computing platform; or

a customer premises-based server.

15 . The method of claim 9 , wherein the measuring comprises:

applying a plurality of test protocols associated with a plurality of processes in operation on the endpoint device including at least the first process.

16 . The method of claim 15 , wherein the plurality of processes includes the first process associated with a first video application and a second process associated with a second video application that is different from the first video application.

17 . The method of claim 16 , wherein the first video application is associated with at least a first video server that is accessible via the plurality of wireless networks, and wherein the second video application is associated with at least a second video server that is accessible via the plurality of wireless networks and that is different from the at least the first video server.

18 . The method of claim 1 , wherein the processing system comprises a mobile chipset of the endpoint device.

19 . A non-transitory computer-readable medium storing instructions which, when executed by a processing system including at least one processor of an endpoint device, cause the processing system to perform operations, the operations comprising:

obtaining performance information of a plurality of wireless access networks in a vicinity of the endpoint device, wherein the performance information includes metrics for a plurality of network performance indicators associated with at least one of the plurality of wireless access networks;

receiving a service request from a first process in operation on the endpoint device;

selecting, in response to the service request, a first wireless access network of the plurality of wireless access networks for the first process based upon the performance information of the plurality of wireless access networks, wherein the selecting is in accordance with a selection function comprising at least one machine learning model, and wherein the selection function comprises a plurality of factors associated with the plurality of network performance indicators; and

establishing a communication session for the first process via the first wireless access network.

20 . An apparatus comprising:

a processing system including at least one processor of an endpoint device; and

a computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising:

obtaining performance information of a plurality of wireless access networks in a vicinity of the endpoint device, wherein the performance information includes metrics for a plurality of network performance indicators associated with at least one of the plurality of wireless access networks;

receiving a service request from a first process in operation on the endpoint device;

selecting, in response to the service request, a first wireless access network of the plurality of wireless access networks for the first process based upon the performance information of the plurality of wireless access networks, wherein the selecting is in accordance with a selection function comprising at least one machine learning model, and wherein the selection function comprises a plurality of factors associated with the plurality of network performance indicators; and

establishing a communication session for the first process via the first wireless access network.