Computing task unloading balance method and system between network nodes, medium and equipment

Abstract

The invention discloses a computing task unloading balancing method and system between network nodes, a medium and equipment. The method comprises the following steps: acquiring own processing performance data from Ntotal fog nodes around a terminal node; the terminal node calculating scheduling priority information of all Ntotal alternative fog nodes by using a preset logic according to the processing performance data of the fog nodes; the terminal node selecting N fog nodes from the Ntotal fog nodes as unloading target nodes of the terminal node calculation task according to the fog node priority information; the terminal node calculating logic calculation task allocation information according to a preset task amount, dividing a calculation task into N + 1 sub-tasks according to the taskallocation information, and sending the N + 1 sub-tasks to the selected N fog nodes and the terminal node for calculation; and the fog node updating own processing performance data according to the real-time performance information in the calculation process and transmitting the updated processing performance data to the terminal node. The technical problems that fog node calculation unloading isuneven, and delay of calculation tasks and fairness of energy consumption between fog nodes cannot be considered at the same time are solved.

Description

technical field [0001] The present invention relates to a calculation task unloading method, in particular to a calculation task unloading balance method, system, medium and equipment among network nodes. Background technique [0002] With the continuous development of network technology, cloud computing is gradually widely used in production and work processes. The cloud-based network architecture can provide powerful computing support for terminal nodes, so that terminal nodes do not need to perform large amounts of data calculation locally. Moving network functions such as computing and storage to cloud servers also enables network operators to manage the entire network more efficiently and centrally. However, with the explosive growth of terminal nodes in recent years, such as smartphones, self-driving cars, smart home devices, etc., massive amounts of data to be processed are generated in the network every moment. These massive amounts of data have brought a heavy burd...

AI Technical Summary

Problems solved by technology

[0004] In view of the above shortcomings of the prior art, the purpose of the present invention is to provide a method, system, medium and equipment for unloading and balancing computing tasks between network nodes, which are applied to the startup process of motor vehicles, and in order to solve the problems existing in the prior art that cannot be balanced The delay of computing tasks and the fairness of energy consumption among fog nodes, unbalanced computing task unloading of fog nodes, high energy consumption of fog nodes in close range, abnormal offline of passive fog nodes, and damage to the battery life of fog nodes are technical problems. Provides a method, system, medium, and device for unloading and balancing computing tasks between network nodes, a method for unloading and balancing computing tasks between network nodes, including: N around terminal nodes total Each fog node obtains its own processing performance data; the terminal node calculates all N total Scheduling priority information of candidate fog nodes; terminal nodes start from N according to the priority information of fog nodes total Each fog node selects N fog nodes as the unloading target nodes of the computing tasks of the terminal nodes; the terminal node calculates the logical computing task allocation information according to the preset task amount, divides the computing tasks into N+1 subtasks according to the task allocation information, and sends them to N fog nodes and terminal nodes are selected for calculation; the fog node updates its own processing performance data according to the real-time performance information during the calculation process and sends it to the terminal node

Images