CN-119937436-B9 - AIoT cloud edge end intelligent control method and system for industrial Internet of things

CN119937436B9CN 119937436 B9CN119937436 B9CN 119937436B9CN-119937436-B9

Abstract

The application provides a AIoT cloud edge intelligent control method and a AIoT cloud edge intelligent control system for industrial Internet of things, which relate to the technical field of cloud edge intelligent control and comprise the steps of creating a cloud-edge-end cooperative framework; the method comprises the steps of performing adaptive analysis of an intelligent manufacturing task according to equipment performance and equipment functions, establishing a first adaptive constraint, performing task decomposition of the intelligent manufacturing task by utilizing a dynamic task decomposition channel, creating M subtasks, performing task competition game analysis of terminal equipment on the M subtasks by utilizing a cloud center, establishing a second adaptive constraint, performing balance analysis on the first adaptive constraint and the second adaptive constraint, and generating an intelligent execution scheme of the terminal equipment of the intelligent manufacturing task. The intelligent task scheduling and optimizing distribution method and the intelligent task scheduling and optimizing distribution device can achieve the technical targets of intelligent task scheduling and optimizing distribution under the cloud-side-end cooperative computing architecture, and achieve the technical effects of improving task execution efficiency, reducing computing delay, optimizing computing resource utilization rate and enhancing data security.

Inventors

CHEN QIUHUANG
TANG ENKE
YU PENGCHENG

Assignees

杭州速利科技有限公司

Dates

Publication Date: 20260512
Application Date: 20250408

Claims (7)

1. AIoT cloud edge end intelligent control method for industrial Internet of things is characterized by comprising the following steps: Creating a cloud-side-end cooperative framework, wherein the cloud-side-end cooperative framework comprises a cloud center, edge computing nodes and terminal equipment, and intelligent manufacturing tasks are acquired from the cloud center; Acquiring equipment performance and equipment function of terminal equipment at an edge computing node, performing adaptation analysis of the intelligent manufacturing task according to the equipment performance and the equipment function, and establishing a first adaptation constraint; Activating a dynamic task decomposition channel of a cloud center, performing task decomposition of the intelligent manufacturing task by using the dynamic task decomposition channel, and creating M subtasks; performing task competition game analysis of the terminal equipment on M subtasks by using the cloud center, and establishing a second adaptation constraint; Performing balance analysis on the first adaptation constraint and the second adaptation constraint to generate an intelligent execution scheme of the terminal equipment of the intelligent manufacturing task; After the intelligent execution scheme of the terminal equipment for generating the intelligent manufacturing task is generated, the method comprises the following steps: Performing sub-task execution monitoring on the terminal equipment, and establishing an execution monitoring result; performing execution hysteresis analysis of the subtasks based on the execution monitoring result, and establishing an execution hysteresis identification; establishing optimizing constraint according to the execution hysteresis identification, and optimizing the execution scheme by using the optimizing constraint; the task competition game analysis of the terminal equipment to the M subtasks is carried out by utilizing the cloud center, and the task competition game analysis comprises the following steps: and activating a task competition game analysis function of the cloud center, and executing task competition game analysis of M subtasks, wherein game features of the task competition game analysis function comprise equipment adaptability features, historical performance consistency features, communication stability features and data fidelity guarantee features, and the task competition game analysis function performs game compensation through inter-task collaborative factors.
2. The intelligent control method for the AIoT cloud edge end of the industrial internet of things according to claim 1, wherein the task competition game analysis of the terminal equipment on the M subtasks is performed by using the cloud center, and the method further comprises: evaluating the computing capacity of the terminal equipment according to the equipment performance of the terminal equipment, and establishing a weak computing equipment performance protection identifier; Carrying out load analysis of the terminal equipment within a preset period range, and establishing a high load identifier; and performing balanced compensation of task competition game analysis by using the weak computing equipment performance protection identifier and the high load identifier, and establishing a second adaptation constraint according to a balanced compensation result.
3. The intelligent control method for the AIoT cloud edge end of the industrial internet of things according to claim 1, wherein the task decomposition of the intelligent manufacturing task by using the dynamic task decomposition channel, creating M subtasks, includes: Uploading time constraint, calculation complexity constraint, calculation demand constraint and task association constraint of the intelligent manufacturing task; acquiring the highest computing capacity and the lowest computing capacity of terminal equipment, and establishing granularity decomposition constraint according to the highest computing capacity and the lowest computing capacity; And performing task decomposition of the intelligent manufacturing task according to the granularity decomposition constraint, the time constraint, the computational complexity constraint, the computational demand constraint and the task association constraint to create M subtasks.
4. The intelligent control method of AIoT cloud edge end for industrial internet of things according to claim 1, wherein the establishing optimizing constraint according to the execution hysteresis identifier, and performing optimizing optimization of the execution scheme according to the optimizing constraint, comprises: performing synchronous execution influence analysis of the linkage task according to the hysteresis identification, and generating hysteresis time constraint according to an influence analysis result; Acquiring task demand constraint of a hysteresis subtask according to the hysteresis identification, and performing succession optimization of terminal equipment according to the hysteresis time constraint and the task demand constraint so as to succession optimization result execution scheme optimizing.
5. The intelligent control method for the AIoT cloud edge end of the industrial internet of things according to claim 4, wherein the performing the succession optimization of the terminal equipment according to the lag time constraint and the task demand constraint further comprises: judging whether the optimizing adaptation value of the terminal equipment with the subtask execution completed meets a preset threshold value or not; if the optimizing adaptation value of the terminal equipment with the sub-task execution completed meets the preset threshold, the terminal equipment with the highest optimizing adaptation value is used as a successor optimizing result to be output.
6. The intelligent control method for the cloud edge end of AIoT oriented to the industrial internet of things according to claim 5, wherein the determining whether the optimizing adaptation value of the terminal device with the subtask performed is satisfied with a preset threshold value further includes: If the optimizing adaptation value of the terminal equipment with the sub-task being executed can not meet the preset threshold value, calculating the interrupt loss of the terminal equipment with the sub-task not being executed; and reconstructing a succession optimizing result after compensating the optimizing adaptation value of the terminal equipment with sub-tasks not completed according to the interrupt loss.
7. AIoT cloud edge end intelligent control system for industry thing networking is characterized in that the steps for implementing AIoT cloud edge end intelligent control method for industry thing networking in any one of claims 1 to 6 include: The collaborative architecture creation module is used for creating a cloud-side-end collaborative architecture, wherein the cloud-side-end collaborative architecture comprises a cloud center, edge computing nodes and terminal equipment, and intelligent manufacturing tasks are acquired from the cloud center; the adaptation analysis module is used for acquiring the equipment performance and the equipment function of the terminal equipment at the edge computing node, carrying out adaptation analysis of the intelligent manufacturing task according to the equipment performance and the equipment function, and establishing a first adaptation constraint; the task decomposition module is used for activating a dynamic task decomposition channel of the cloud center, performing task decomposition of the intelligent manufacturing task by using the dynamic task decomposition channel, and creating M subtasks; The competition game analysis module is used for carrying out task competition game analysis on the M subtasks by the terminal equipment by utilizing the cloud center, and establishing a second adaptation constraint; And the scheme generating module is used for carrying out balance analysis on the first adaptation constraint and the second adaptation constraint and generating an intelligent execution scheme of the terminal equipment of the intelligent manufacturing task.

Description

AIoT cloud edge end intelligent control method and system for industrial Internet of things Technical Field The application relates to the technical field of cloud edge intelligent control, in particular to a AIoT cloud edge intelligent control method and system for industrial Internet of things. Background In the context of the development of intelligent manufacturing and industrial internet of things, how to efficiently distribute and execute complex computing tasks becomes a critical issue. The conventional task scheduling method generally relies on a cloud computing center to perform unified management and allocation, however, the mode has certain limitations, and particularly when facing complex and changeable computing demands in an industrial internet of things environment, a single cloud processing mode often causes uneven computing resource allocation, low task execution efficiency and slow system response speed. Therefore, the cloud-side-end collaborative computing architecture gradually becomes an important technical direction for solving the problem, and can combine the powerful computing capacity of the cloud, the real-time processing capacity of edge computing and the distributed execution capacity of terminal equipment, so that task scheduling is optimized, and computing efficiency is improved. Currently, the existing cloud computing mode mainly depends on a centralized computing architecture, that is, all computing tasks need to be uploaded to a remote cloud for processing, and then a computing result is returned to a terminal device. While this mode may provide a powerful computing power, it also has some significant drawbacks. Firstly, because cloud computing needs to transmit data through a network, for tasks with high real-time requirements in an industrial Internet of things scene, the traditional cloud computing mode is often difficult to meet. For example, in intelligent manufacturing systems, certain critical tasks such as equipment failure detection, production process optimization, etc., require computation and decision making to be completed in a very short time, and the high latency of conventional cloud computing modes may lead to untimely system responses, thereby affecting production efficiency. Secondly, along with the continuous increase of the number of industrial Internet of things devices, the load of data transmission is also continuously improved, and the traditional cloud computing mode is easily limited by network bandwidth, so that the data transmission is congested, and the task execution efficiency is affected. In addition, a single cloud computing mode may also face data security and privacy issues, such as risk of data leakage if all of the sensitive production data is uploaded to the cloud for processing. In summary, in the prior art, because the cloud computing mode depends on the centralized computing architecture, the computing task needs to be remotely transmitted, so that high delay, limited network bandwidth and data security risk are caused, the requirements on instantaneity, high efficiency and data privacy in the industrial internet of things scene are further affected, and the technical problems of production efficiency and system stability are further reduced. Disclosure of Invention The application aims to provide a AIoT cloud edge intelligent control method and system for an industrial Internet of things, which are used for solving the technical problems that in the prior art, because a cloud computing mode depends on a centralized computing architecture, a computing task needs to be transmitted remotely, thereby causing high delay, limited network bandwidth and data security risk, further influencing the requirements on instantaneity, high efficiency and data privacy in the scene of the industrial Internet of things, and further reducing the production efficiency and the system stability. In view of the problems, the application provides a AIoT cloud edge intelligent control method and system for industrial Internet of things. The application provides a AIoT cloud side intelligent control method for an industrial Internet of things, which is realized by a AIoT cloud side intelligent control system for the industrial Internet of things and comprises the steps of creating a cloud-side collaborative architecture, wherein the cloud-side collaborative architecture comprises a cloud center, edge computing nodes and terminal equipment, acquiring intelligent manufacturing tasks from the cloud center, acquiring equipment performance and equipment functions of the terminal equipment at the edge computing nodes, performing adaptive analysis of the intelligent manufacturing tasks according to the equipment performance and the equipment functions, establishing a first adaptive constraint, activating a dynamic task decomposition channel of the cloud center, performing task decomposition of the intelligent manufacturing tasks by utilizing the dynamic task decompo