Edge computing-based scheduling algorithm and system for local area network

Abstract

The invention provides an edge computing-based scheduling algorithm and system for a local area network. The method comprises the following steps of: obtaining a computing task amount X and a computing scene number N in an edge computing network, and determining the priority of each computing task; allocating the X computing tasks to queues of different priority levels according to the priority levels to form Y ready queues of different priority levels, Y being a positive integer greater than 1; executing the tasks in the ready queue, and selecting n optimal edge computing nodes when each taskis executed, n being a positive integer; and monitoring a task execution process, enabling the calculation time of each time not to exceed a set calculation period, regarding that an unfinished taskexists if the calculation time is in the set calculation period, suspending the unfinished task, and putting the unfinished task at the end of a ready queue of the priority level. According to the scheduling algorithm, computing tasks in different scenes are in different queues, the tasks cannot be blocked for a long time, and normal execution of all the tasks is ensured.

Description

technical field [0001] The present invention relates to the field of computers, in particular to an edge computing-based scheduling algorithm and system for a local area network. Background technique [0002] Edge computing refers to the use of core capabilities such as network, computing, and storage on the side close to objects, users, and data sources to provide users with a lower-cost, faster, more real-time, and more secure integrated open platform. Its applications are launched on the cloud, its logic is executed on the edge side, and its data is generated on the terminal, so as to meet the needs of the industry in real-time business, application intelligence, security and privacy protection. [0003] Edge computing is a distributed computing architecture. By selecting the most suitable edge nodes, large-scale services, data, and calculations are decomposed and cut into smaller, easier-to-manage parts, distributed to edge nodes for execution, and finally form calculati...

AI Technical Summary

Problems solved by technology

[0005] At present, in terms of how to determine the order of task execution, the commonly used method is the first-come-first-serve scheduling algorithm, which schedules tasks according to the order in which they arrive, that is, the job with the longest waiting time in the system is given priority. The waiting time for short tasks after long tasks is large, and the turnaround time with rights is large, which is not conducive to the execution of short tasks

Images