Systems and methods for managing an automotive edge computing environment

Patent metadata

Field	Value
Publication number	US-11297161-B1
Application number	US-202017065903-A
Country	US
Kind code	B1
Filing date	Oct 8, 2020
Priority date	Oct 8, 2020
Publication date	Apr 5, 2022
Grant date	Apr 5, 2022

Abstract

Systems and methods described herein relate to managing an automotive edge computing environment. One embodiment receives current status information from one or more edge servers; receives and queues requested computing tasks from one or more connected vehicles; selects, as an optimization trigger number N, a largest number of requested computing tasks for which an optimization process can be completed within a time, per requested computing task, that is less than an average time gap between the requested computing tasks; performs the optimization process when a number of queued requested computing tasks exceeds the optimization trigger number N, wherein the optimization process produces an updated data transfer schedule and an updated data process schedule for N queued requested computing tasks; and transmits the updated data transfer schedule and the updated data process schedule to the one or more edge servers and the one or more connected vehicles.

First claim

What is claimed is:

1. A system for managing an automotive edge computing environment, the system comprising:
one or more processors; and
a memory communicably coupled to the one or more processors and storing:
an input module including instructions that when executed by the one or more processors cause the one or more processors to receive current status information from one or more edge servers;
an optimization trigger module including instructions that when executed by the one or more processors cause the one or more processors to:
receive and queue requested computing tasks from one or more connected vehicles; and
select, as an optimization trigger number N, a largest number of requested computing tasks for which an optimization process can be completed within a time, per requested computing task, that is less than an average time gap between the requested computing tasks;

an optimization module including instructions that when executed by the one or more processors cause the one or more processors to perform the optimization process when a number of queued requested computing tasks exceeds the optimization trigger number N, wherein the optimization process produces an updated data transfer schedule and an updated data process schedule for N queued requested computing tasks; and
a communication module including instructions that when executed by the one or more processors cause the one or more processors to transmit the updated data transfer schedule and the updated data process schedule to the one or more edge servers and the one or more connected vehicles.

2. The system of claim 1 , wherein the current status information includes one or more of available memory, process capacity, data transfer capacity, a current data transfer schedule, and a current data process schedule.

3. The system of claim 1 , wherein the requested computing tasks pertain to at least one of downloading data from the one or more edge servers and uploading vehicular sensor data from the one or more connected vehicles to the one or more edge servers.

4. The system of claim 1 , wherein the optimization module includes instructions that when executed by the one or more processors cause the one or more processors to:
formulate a discrete state transition model that represents dynamics of different types of data being transferred among different network nodes and data being processed from one type to another as a function of a current data transfer schedule and a current data process schedule;
formulate constraints representing resource limitations and task requirements using information including one or more of bandwidth limitations, available processor power, available memory, distances among the one or more edge servers and the one or more connected vehicles, future trajectory data pertaining to the one or more connected vehicles, and data destination information; and
evaluate a cost function that accounts for the discrete state transition model and the constraints to produce the updated data transfer schedule and the updated data process schedule for the N queued requested computing tasks.

5. The system of claim 1 , wherein the updated data transfer schedule includes a first set of tuples, each tuple in the first set of tuples including a rate of data transfer from a first network node to a second network node, and the updated data process schedule includes a second set of tuples, each tuple in the second set of tuples including a rate of data processing from a first type of data to a second type of data.

6. The system of claim 1 , wherein the optimization trigger module includes further instructions to reduce the optimization trigger number N based, at least in part, on an urgency level associated with one or more of the queued requested computing tasks.

7. The system of claim 1 , wherein each of the one or more edge servers is deployed in one of a roadside unit (RSU), an office environment, and a residential environment.

8. A non-transitory computer-readable medium for managing an automotive edge computing environment and storing instructions that when executed by one or more processors cause the one or more processors to:
receive current status information from one or more edge servers;
receive and queue requested computing tasks from one or more connected vehicles;
select, as an optimization trigger number N, a largest number of requested computing tasks for which an optimization process can be completed within a time, per requested computing task, that is less than an average time gap between the requested computing tasks;
perform the optimization process when a number of queued requested computing tasks exceeds the optimization trigger number N, wherein the optimization process produces an updated data transfer schedule and an updated data process schedule for N queued requested computing tasks; and
transmit the updated data transfer schedule and the updated data process schedule to the one or more edge servers and the one or more connected vehicles.

9. The non-transitory computer-readable medium of claim 8 , wherein the current status information includes one or more of available memory, process capacity, data transfer capacity, a current data transfer schedule, and a current data process schedule.

10. The non-transitory computer-readable medium of claim 8 , wherein the requested computing tasks pertain to at least one of downloading data from the one or more edge servers and uploading vehicular sensor data from the one or more connected vehicles to the one or more edge servers.

11. The non-transitory computer-readable medium of claim 8 , wherein the instructions to perform the optimization process include instructions that when executed by the one or more processors cause the one or more processors to:
formulate a discrete state transition model that represents dynamics of different types of data being transferred among different network nodes and data being processed from one type to another as a function of a current data transfer schedule and a current data process schedule;
formulate constraints representing resource limitations and task requirements using information including one or more of bandwidth limitations, available processor power, available memory, distances among the one or more edge servers and the one or more connected vehicles, future trajectory data pertaining to the one or more connected vehicles, and data destination information; and
evaluate a cost function that accounts for the discrete state transition model and the constraints to produce the updated data transfer schedule and the updated data process schedule for the N queued requested computing tasks.

12. The non-transitory computer-readable medium of claim 8 , wherein the updated data transfer schedule includes a first set of tuples, each tuple in the first set of tuples including a rate of data transfer from a first network node to a second network node, and the updated data process schedule includes a second set of tuples, each tuple in the second set of tuples including a rate of data processing from a first type of data to a second type of data.

13. The non-transitory computer-readable medium of claim 8 , further including instructions that when executed by the one or more processors cause the one or more processors to reduce the optimization trigger number N based, at least in part, on an urgency level associated with one or more of the queued requested computing tasks.

14. A method of managing an automotive edge computing environment, the method comprising:
receiving current status information from one or more edge servers;
receiving and queueing requested

Assignees

• Toyota Eng & Mfg North America

Inventors

• Liu Yin-Chen
• Kim Baekgyu

Classifications

• G06F2209/5022

  Workload threshold · CPC title

• G06F2209/501

  Performance criteria · CPC title

• G06F2209/483

  Multiproc · CPC title

• G06F9/4881

  Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues · CPC title

• G06F9/5038

  considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration (scheduling strategies G06F9/4881 and subgroups) · CPC title