Access network connectivity optimization engine

Patent metadata

Field	Value
Publication number	US-12155502-B1
Application number	US-202217968020-A
Country	US
Kind code	B1
Filing date	Oct 18, 2022
Priority date	May 26, 2020
Publication date	Nov 26, 2024
Grant date	Nov 26, 2024

Abstract

Optimized automated access network connectivity is provided. A network connecting device (NCD) may perform an optimized access network setup process upon boot-up to connect to an access network. The optimized process may be determined by a cloud-based machine-learning system based on learned connecting and network usage behaviors. The optimized process may include a sequence of network connectivity evaluations configured to minimize the setup time associated with discovering and connecting to an access network. The optimized process may further reduce or eliminate the probability of device failure due to an erroneous access network implementation by establishing communications with a test server prior to committing an access operating mode to non-volatile memory. The NCD may be configured to modify the device's master configuration settings to include the optimized process such that when a master reset is performed, the device may utilize the optimized process to discover and connect to the access network.

First claim

We claim:

1. A method comprising:
using a machine learning engine to determine an optimized sequence of network connectivity evaluations to perform to discover a Wide Area Network (WAN) access channel for connecting to an access network by a network connecting device;
providing the optimized sequence of network connectivity evaluations to perform to discover the WAN access channel to the network connecting device;
performing one or more network connectivity evaluations included in the optimized sequence until a successful WAN access channel is determined to provide connectivity to the access network, wherein the one or more network connectivity evaluations are performed upon boot-up of the network connecting device;
implementing the successful WAN access channel;
storing the successful WAN access channel;
providing network connectivity data associated with the network connecting device to the machine learning engine;
receiving an updated optimized sequence determined by the machine learning engine based on the network connectivity data; and
storing the updated optimized sequence with the network connectivity device.

2. The method of claim 1 , wherein storing the updated optimized sequence further comprises overwriting master configuration settings with the updated optimized sequence.

3. The method of claim 2 , wherein the master configuration settings are stored in a hidden partition of a non-volatile storage of the network connecting device.

4. The method of claim 1 , wherein performing one or more network connectivity evaluations included in the optimized sequence further comprises:
a first network connectivity evaluation that includes an evaluation of a first type of link; and
a second network connectivity evaluation that includes an evaluation of a second type of link.

5. The method of claim 4 , wherein the first type of link or the second type of link is associated with at least one of:
a Data Over Cable Service Interface Specification (DOCSIS) WAN access channel;
a Direct Subscriber Line (DSL) WAN access channel;
an Ethernet Wide Area Network (EWAN) WAN access channel;
a fiber optic (Optical Network Terminal (ONT)) WAN access channel;
a cellular WAN access channel;
a MoCA WAN access channel; and
a WI-FI WAN access channel.

6. The method of claim 1 , wherein the network connecting device is configured to communicate with more than one type of communication interface.

7. The method of claim 1 , further comprising storing a WAN access operating mode in non-volatile memory as a last-known-good operating mode according to the successful WAN access channel.

8. The method of claim 7 , further comprising establishing communications with a test server with the successful WAN access channel before storing the WAN access operating mode in non-volatile memory.

9. The method of claim 1 , further comprising automatically launching an application included with platform software of the network connecting device at startup for performing the one or more network connectivity evaluations.

10. The method of claim 1 , further comprising performing the one or more network connectivity evaluations as part of avoiding a subsequent scan or a longer duration scan.

11. The method of claim 1 , wherein the machine learning engine uses a machine learning model to determine the optimized sequence on learned connecting and network usage behavior of a plurality of network connecting devices.

12. A system comprising:
a server that includes a machine learning engine, wherein the server is configured to:
use the machine learning engine to determine an optimized sequence of network connectivity evaluations to perform to discover a Wide Area Network (WAN) access channel for connecting to an access network; and
provide the optimized sequence of network connectivity evaluations to at least one network connecting device; and

a network connecting device that is configured to:
receive the optimized sequence of network connectivity evaluations from the server;
perform the one or more network connectivity evaluations included in the optimized sequence until a successful WAN access channel is determined to provide connectivity to an access network, wherein the one or more network connectivity evaluations are performed upon boot-up of the network connecting device;
implement the successful WAN access channel;
store the successful WAN access channel;
provide network connectivity data to the server;
receive an updated optimized sequence from the server based on the network connectivity data; and
store the updated optimized sequence.

13. The system of claim 12 , wherein the network connecting device is further configured to overwrite master configuration settings with the updated optimized sequence.

14. The system of claim 12 , wherein the one or more network connectivity evaluations included in the optimized sequence further comprise:
a first network connectivity evaluation that includes an evaluation of a first type of link; and
a second network connectivity evaluation that includes an evaluation of a second type of link.

15. The system of claim 14 , wherein the first type of link or the second type of link is associated with at least one of:
a Data Over Cable Service Interface Specification (DOCSIS) WAN access channel;
a Direct Subscriber Line (DSL) WAN access channel;
an Ethernet Wide Area Network (EWAN) WAN access channel;
a fiber optic (Optical Network Terminal (ONT)) WAN access channel;
a cellular WAN access channel;
a MoCA WAN access channel; and
a WI-FI WAN access channel.

16. The system of claim 12 , wherein the network connecting device is further configured to establish communications with a test server with the successful WAN access channel before storing a WAN access operating mode to non-volatile memory.

17. The system of claim 12 , wherein the network connecting device is further configured to perform the one or more network connectivity evaluations as part of avoiding a subsequent scan or a longer duration scan.

18. A network connecting device comprising:
a memory storage; and
a processing unit coupled to the memory storage, wherein the processing unit is configured to:
receive an optimized sequence of network connectivity evaluations to perform to discover a Wide Area Network (WAN) access channel for connecting to an access network, wherein machine learning is utilized to determine the optimized sequence of network connectivity evaluations to perform to discover the WAN access channel for connecting to the access network;
perform one or more network connectivity evaluations included in the optimized sequence until a successful WAN access channel is determined to provide connectivity to the access network, wherein the one or more network connectivity evaluations are performed upon boot-up of the network connecting device;
implement the successful WAN access channel;
store the successful WAN access channel;
provide network connectivity data associated with the network connecting device to the machine learning engine;
receive an updated optimized sequence based on the machine learning and the network connectivity data; and
store the updated optimized sequence on the network connectivity device.

19. The network connecting device of claim 18 , wherein the processing unit being configured to perform the one or more network connectivity evaluations included in the optimized sequence further comprises the processing unit being configured to:
a first network connectivity evaluation that includes an

Assignees

• Cox Communications Inc

Inventors

• Overcash Michael Paul
• Nijim Yousef Wasef
• Strothmann James Alan

Classifications

• H04L67/141

  Setup of application sessions (admission control or resource allocation in data switching networks H04L47/70) · CPC title

• G06N20/00

  Machine learning · CPC title

• H04L43/50

  Testing arrangements · CPC title

• H04L41/12

  Discovery or management of network topologies · CPC title

• H04L41/085

  Retrieval of network configuration; Tracking network configuration history · CPC title