Edge computing task scheduling method for criticality and timeliness

Abstract

The invention discloses an edge computing task scheduling method for criticality and timeliness. Method for optimizing network flow is adopted. the criticality and effectiveness of different tasks inedge information processing are comprehensively considered; an edge computing task scheduling method oriented to criticality and timeliness is provided; Task processing resource consumption is calculated through the criticality of an information processing task input by a user and the time limit of task execution, a consumption graph model of the criticality and effectiveness of the task is established, and different tasks are dispatched and distributed by adopting a network flow optimization method. According to the method, the tasks can be fairly distributed, and the tasks with high criticality and high effectiveness can be distributed to more resources for calculation on the premise of ensuring that the resources are fairly distributed, so that the tasks can be completed more quickly. The method is mainly suitable for edge task scheduling.

Description

technical field [0001] The invention belongs to the technical field of task scheduling, and in particular relates to a criticality and timeliness-oriented edge computing task scheduling method. Background technique [0002] In the edge system, there are often a large number of different types of services running on different computing nodes. Different types of services process different types of tasks and have different requirements for computing resources. If each task cannot be scheduled to the appropriate node, Enabling different types of tasks to have relatively reasonable resources for calculation will lead to waste of resources, that is, resources may still be idle when there are a large number of tasks backlogged, causing task response time to be too long. [0003] At present, with the emergence of various distributed task scheduling technologies, in order to improve task scheduling efficiency and reduce system response time, designers of task scheduling systems need ...

AI Technical Summary

Problems solved by technology

[0002] In the edge system, there are often a large number of different types of services running on different computing nodes. Different types of services process different types of tasks and have different requirements for computing resources. If each task cannot be scheduled to the appropriate node, Enabling different types of tasks to have relatively reasonable resources for calculation will lead to waste of resources, that is, resources may still be idle when there are a large number of tasks backlogged, causing task response time to be too long

[0003] At present, with the emergence of various distributed task scheduling technologies, in order to improve task scheduling efficiency and reduce system response time, designers of task scheduling systems need to solve the following problems: 1) The scheduler cannot distinguish between long-running service jobs and batch analysis 2) The scheduler needs to add different types of scheduling strategy functions to process different types of tasks, which increases the complexity of business logic and configuration, making deployment and operation and maintenance prone to errors; 3) the scheduler will have queue delays and waiting Task cannot be rolled back

[0005] 1) The consumption value calculation method of the method does not take into account the mission criticality and timeliness;

[0006] 2) The resource allocation method of the method does not take into account the mission criticality and timeliness;

[0007] 3) The consumption function of the method does not take into account the mission criticality and timeliness

Images