Vehicle Task Offloading Scheduling with ML Partitioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current scheduling systems for computing tasks in vehicles are inefficient in minimizing delays, particularly when offloading tasks to servers, due to poor resource allocation and difficulty in dynamically scheduling tasks in environments with multiple vehicles, leading to system delays and unfair resource usage.
Innovation Solution
A scheduling system that uses context information and machine learning to allocate server resources more efficiently by partitioning computing tasks into subtasks, optimizing resource usage and reducing end-to-end delays, while ensuring fair resource allocation between vehicles and servers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If computing tasks are fully offloaded to server for execution, then system delays are reduced, but wireless transmission bandwidth and system resources are excessively used
Solution Approach 1:
The patent segments computing tasks into multiple parts, with some tasks executed locally on the vehicle and others offloaded to the server. This selective task partitioning reduces the amount of data that needs to be transmitted wirelessly while still benefiting from server computing power for complex tasks, thereby resolving the contradiction between reducing system delays and conserving wireless bandwidth.
2Use of energy by moving object
If computing tasks are processed locally on vehicle, then wireless bandwidth is conserved, but system delays increase due to limited computing power
Solution Approach 1:
The patent implements a dynamic task scheduling system that adaptively decides which tasks to execute locally and which to offload to the server based on real-time conditions such as vehicle computing resource availability, task complexity, and network status. This dynamic approach allows the system to optimize the balance between local processing and cloud offloading, reducing system delays while conserving wireless bandwidth.
3Productivity
If performance-oriented scheduling systems are used, then task processing speed is improved, but server resources are excessively used by individual vehicles
Solution Approach 1:
The patent introduces fairness parameters and resource allocation constraints into the scheduling system that dynamically adjust based on each vehicle's historical resource usage and current needs. This ensures that high-performance task processing is maintained while preventing any single vehicle from monopolizing server resources, thereby resolving the contradiction between task processing speed and fair resource distribution.
4Reliability
If scheduling systems attempt to satisfy quality of service for all vehicles, then service quality is improved, but scheduling delays increase in areas with poor wireless coverage
Solution Approach 1:
The patent implements a backoff mechanism that allows vehicles in areas with poor wireless coverage to temporarily defer non-critical task offloading decisions. This preliminary action prevents immediate scheduling delays by allowing vehicles to accumulate tasks locally and offload them when network conditions improve, thereby maintaining quality of service without causing excessive scheduling delays in challenging wireless environments.
Data Source
AI summary
System, methods, and other embodiments described herein relate to improving scheduling of computing tasks in a mobile environment for a vehicle. In one embodiment, a method includes receiving an offloading request associated with a computing task from the vehicle, wherein the offloading request includes context information and a task descriptor related to the computing task. The method also includes scheduling the computing task to execute on a server if the context information and the task descriptor satisfy criteria for using computing resources associated with the server for the vehicle. The method also includes partitioning the computing task into subtasks if the context information satisfies the criteria. A machine learning module may decide partitions of the computing task according to the context information. The method also includes sending a scheduling signal including a scheduling message to the vehicle and the scheduling message includes scheduling information and task partition information associated with offloading the subtasks.