Connected vehicle network data transfer optimization

Patent metadata

Field	Value
Publication number	US-11601825-B2
Application number	US-201916536258-A
Country	US
Kind code	B2
Filing date	Aug 8, 2019
Priority date	Aug 8, 2018
Publication date	Mar 7, 2023
Grant date	Mar 7, 2023

Abstract

Generally described, one or more aspects of the present application correspond to techniques for dynamic management of the timing of data transfer between a connected vehicle and a remote computing system. For example, during navigation a connected vehicle may switch between connections to a number of different networks, each having different parameters (cost, bandwidth, quality, etc.). The disclosed techniques can use inputs including vehicle location, available networks, and data transfer timing requirements to optimize data transfer with respect to one or more of these parameters.

First claim

What is claimed is:

1. A connected vehicle networking system, comprising:
a vehicle including:
at least one transceiver configured to connect to a plurality of networks, and
a computing system configured to execute an application and a network data optimizer; and

at least one server remote from the vehicle and configured to transfer data with the application;
wherein the network data optimizer is configured by computer-executable instructions to act as an intermediary between the application and the at least one server by at least:
determining a data transfer window for transferring data between the application and the least one server;
receiving a predetermined navigational route of the vehicle to a geographic destination;
determining, based on the predetermined navigational route of the vehicle, an expected location of the vehicle during the data transfer window;
identifying, based on the determined expected location, at least a first network and a second network to which the at least one transceiver can connect during the data transfer window;
determining a first cost of transferring data using the first network and a second cost of transferring data using the second network;
identifying which of the first cost and the second cost is a lowest cost;
determining a start time within the data transfer window for transferring the data; and
instructing the application to transfer data with the at least one server when the at least one transceiver is connected to the one of the first and second networks corresponding to the lowest cost.

2. The connected vehicle networking system of claim 1 , wherein the network data optimizer comprises a deep learning model trained to predict optimal data transfer start and stop timings.

3. The connected vehicle networking system of claim 1 , wherein the data optimizer is configured to determine the data transfer window based at least in part on a predefined data transfer interval associated with the application.

4. The connected vehicle networking system of claim 1 , wherein the data optimizer determines the start time within the data transfer window to correspond to a lower cost relative to at least one other possible start time within the data transfer window.

5. The connected vehicle networking system of claim 1 , wherein the start time is later than a beginning of the data transfer window.

6. A computer-implemented method, comprising:
determining a data transfer window for transferring data between an application executing on a computing system of a vehicle and at least one server remote from the vehicle;
receiving a predetermined navigational route of the vehicle to a geographic destination;
determining, based on the predetermined navigational route of the vehicle, an expected location of the vehicle during the data transfer window;
identifying, based on the determined expected location of the vehicle, at least a first network and a second network to which the vehicle can connect during the data transfer window;
determining a first cost of transferring data using the first network and a second cost of transferring data using the second network;
identifying which of the first cost and the second cost is a lowest cost;
determining a start time within the data transfer window for transferring the data; and
instructing the application to transfer data with the at least one server when the vehicle is connected to the one of the first and second networks corresponding to the lowest cost.

7. The computer-implemented method of claim 6 , further comprising instructing the application to transfer the data based additionally on determining that a priority of transferring the data exceeds the lowest cost.

8. The computer-implemented method of claim 6 , wherein the data transfer window is determined based at least in part on a data transfer deadline associated with the application.

9. The computer-implemented method of claim 8 , wherein the data transfer window is further determined based at least in part on a data transfer tolerance associated with the application.

10. The computer-implemented method of claim 6 , wherein the data transfer window is determined based at least in part on a predefined data transfer interval associated with the application.

11. The computer-implemented method of claim 6 , wherein the start time within the data transfer window is selected to correspond to a lower cost relative to at least one other possible start time within the data transfer window.

12. The computer-implemented method of claim 6 , wherein the start time is later than a beginning of the data transfer window.

13. The connected vehicle networking system of claim 1 , wherein the network data optimizer is configured to determine the data transfer window based at least in part on a data transfer deadline associated with the application.

14. The connected vehicle networking system of claim 13 , wherein the data transfer window is further determined based at least in part on a data transfer tolerance associated with the application.

Assignees

• Faraday&Future Inc

Inventors

• Sundar Shyam

Classifications

• G06N3/09

  Supervised learning · CPC title

• H04W24/02 Primary

  Arrangements for optimising operational condition · CPC title

• H04W48/18

  Selecting a network or a communication service · CPC title

• G06N3/08

  Learning methods · CPC title

• G06N20/00

  Machine learning · CPC title