AloT Cloud-Edge-Terminal Intelligent Control Method and System for Industrial Internet of Things

Abstract

The present application provides an AloT cloud-edge-end intelligent control method and system for the industrial Internet of Things, which relates to the technical field of cloud-edge-end intelligent control. The method includes: creating a cloud-edge-end collaborative architecture; performing an adaptation analysis of intelligent manufacturing tasks according to device performance and device functions, and establishing a first adaptation constraint; using a dynamic task decomposition channel to decompose the intelligent manufacturing tasks, and creating M subtasks; using the cloud center to perform a task competition game analysis of the M subtasks by the terminal devices, and establishing a second adaptation constraint; performing a balance analysis on the first adaptation constraint and the second adaptation constraint to generate an intelligent execution plan for the terminal devices of the intelligent manufacturing tasks. Through the present application, the technical goal of intelligent task scheduling and optimal allocation under the cloud-edge-end collaborative computing architecture can be achieved, and the technical effects of improving task execution efficiency, reducing computing latency, optimizing computing resource utilization, and enhancing data security can be achieved.

Description

Technical Field

[0001] This application relates to the technical field of cloud-edge-end intelligent control, and particularly to an AloT cloud-edge-end intelligent control method and system for industrial Internet of Things. Background Art

[0002] In the context of the development of intelligent manufacturing and industrial Internet of Things, how to efficiently allocate and execute complex computing tasks has become a key issue. Traditional task scheduling methods usually rely on cloud computing centers for unified management and allocation. However, this mode has certain limitations. Especially in the face of complex and variable computing requirements in the industrial Internet of Things environment, a single cloud processing method often leads to uneven distribution of computing resources, low task execution efficiency, and slow system response speed. Therefore, the cloud-edge-end collaborative computing architecture has gradually become an important technical direction to solve this problem. It can combine the powerful computing power of the cloud, the real-time processing ability of edge computing, and the distributed execution ability of terminal devices, thereby optimizing task scheduling and improving computing efficiency.

[0003] Currently, the existing cloud computing mode mainly relies on a centralized computing architecture, that is, all computing tasks need to be uploaded to a remote cloud for processing, and then the computing results are returned to the terminal device. Although this mode can provide powerful computing power, it also has some obvious defects. First, since cloud computing needs to transmit data through the network, for tasks with high real-time requirements in the industrial Internet of Things scenario, the traditional cloud computing mode often fails to meet the requirements. For example, in an intelligent manufacturing system, some key tasks such as equipment fault detection and production process optimization need to complete computing and decision-making in a very short time, and the high latency of the traditional cloud computing mode may lead to untimely system response, thereby affecting production efficiency. Second, with the continuous increase in the number of industrial Internet of Things devices, the load of data transmission is also increasing continuously. The traditional cloud computing mode is easily limited by network bandwidth, resulting in data transmission congestion, thus affecting the efficiency of task execution. In addition, a single cloud computing mode may also face data security and privacy issues. For example, for some sensitive production data, if all are uploaded to the cloud for processing, it may increase the risk of data leakage.

[0004] In summary, there is a technical problem in the prior art that due to the cloud computing mode relying on a centralized computing architecture, computing tasks need to be remotely transmitted, resulting in high latency, network bandwidth limitation, and data security risks, further affecting the requirements for real-time performance, efficiency, and data privacy in the industrial Internet of Things scenario, and thus reducing production efficiency and system stability. Summary of the Invention

[0005] The objective of this application is to provide an AloT cloud-edge-end intelligent control method and system for industrial Internet of Things, so as to solve the technical problems existing in the prior art. Since the cloud computing mode relies on a centralized computing architecture, the computing tasks need to be remotely transmitted, resulting in high latency, limited network bandwidth, and data security risks, further affecting the requirements for real-time performance, efficiency, and data privacy in the industrial Internet of Things scenario, and thus reducing production efficiency and system stability.

[0006] In view of the above problems, this application provides an AloT cloud-edge-end intelligent control method and system for industrial Internet of Things.

[0007] In the first aspect, this application provides an AloT cloud-edge-end intelligent control method for industrial Internet of Things, which is implemented through an AloT cloud-edge-end intelligent control system for industrial Internet of Things, and includes: creating a cloud-edge-end collaborative architecture, where the cloud-edge-end collaborative architecture includes a cloud center, edge computing nodes, and terminal devices, and obtaining an intelligent manufacturing task from the cloud center; obtaining the device performance and device functions of the terminal devices at the edge computing nodes, performing an adaptation analysis of the intelligent manufacturing task according to the device performance and device functions, and establishing a first adaptation constraint; activating the dynamic task decomposition channel of the cloud center, using the dynamic task decomposition channel to decompose the intelligent manufacturing task, and creating M subtasks; using the cloud center to perform a task competition game analysis of the M subtasks by the terminal devices, and establishing a second adaptation constraint; performing a balance analysis on the first adaptation constraint and the second adaptation constraint to generate an intelligent execution plan for the terminal devices of the intelligent manufacturing task.

[0008] In the second aspect, this application also provides an AloT cloud-edge-end intelligent control system for industrial Internet of Things, which is used to execute the AloT cloud-edge-end intelligent control method for industrial Internet of Things as described in the first aspect, and includes: a collaborative architecture creation module, which is used to create a cloud-edge-end collaborative architecture, where the cloud-edge-end collaborative architecture includes a cloud center, edge computing nodes, and terminal devices, and obtain an intelligent manufacturing task from the cloud center; an adaptation analysis module, which is used to obtain the device performance and device functions of the terminal devices at the edge computing nodes, perform an adaptation analysis of the intelligent manufacturing task according to the device performance and device functions, and establish a first adaptation constraint; a task decomposition module, which is used to activate the dynamic task decomposition channel of the cloud center, use the dynamic task decomposition channel to decompose the intelligent manufacturing task, and create M subtasks; a competition game analysis module, which is used to use the cloud center to perform a task competition game analysis of the M subtasks by the terminal devices, and establish a second adaptation constraint; a plan generation module, which is used to perform a balance analysis on the first adaptation constraint and the second adaptation constraint to generate an intelligent execution plan for the terminal devices of the intelligent manufacturing task.

[0009] The technical solution provided in this application has at least the following technical effects or advantages: By achieving the technical goal of intelligent task scheduling and optimal allocation under the cloud-edge-end collaborative computing architecture, the technical effects of improving task execution efficiency, reducing computing latency, optimizing computing resource utilization, and enhancing data security are achieved.

[0010] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically given below. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of this application, nor is it used to limit the scope of this application. Other features of this application will become easily understood through the following description. Brief Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to the provided drawings.

[0012] Figure 1 It is a schematic flowchart of the AloT cloud-edge-end intelligent control method for this application facing the industrial Internet of Things;

[0013] Figure 2 It is a schematic structural diagram of the AloT cloud-edge-end intelligent control system for this application facing the industrial Internet of Things.

[0014] Description of the reference numerals: Collaborative architecture creation module 11, adaptation analysis module 12, task decomposition module 13, competitive game analysis module 14, solution generation module 15. Detailed Description of the Embodiments

[0015] By providing the AloT cloud-edge-end intelligent control method and system for the industrial Internet of Things, this application solves the technical problem in the prior art that due to the cloud computing mode relying on a centralized computing architecture, computing tasks need to be remotely transmitted, resulting in high latency, limited network bandwidth, and data security risks, further affecting the requirements for real-time performance, efficiency, and data privacy in the industrial Internet of Things scenario, and thus reducing production efficiency and system stability. The technical goal of intelligent task scheduling and optimal allocation under the cloud-edge-end collaborative computing architecture is achieved, and the technical effects of improving task execution efficiency, reducing computing latency, optimizing computing resource utilization, and enhancing data security are achieved.

[0016] Next, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application. Additionally, it should be noted that for the sake of description, only the parts related to the present application are shown in the drawings rather than all of them.

[0017] Example 1. Please refer to the attached Figure 1 drawings. The present application provides an AloT cloud-edge-end intelligent control method for industrial Internet of Things, which is applied to an AloT cloud-edge-end intelligent control system for industrial Internet of Things, and specifically includes the following steps:

[0018] S1: Create a cloud-edge-end collaborative architecture, which includes a cloud center, edge computing nodes, and terminal devices, and obtain intelligent manufacturing tasks from the cloud center.

[0019] Specifically, create a cloud-edge-end collaborative architecture and build a system architecture composed of three parts: the cloud, edge computing, and terminal devices. The cloud center is responsible for processing and storing a large amount of data. Among them, according to the real-time collected environmental data and device data, relevant task instructions are generated, and then the tasks are sent to the edge computing nodes or terminal devices. The edge computing nodes are responsible for processing and analyzing data closer to the terminal devices, while the terminal devices are responsible for interacting with the real environment and executing actual tasks. Through the collaborative work of the cloud, edge, and end, the smooth transmission of data and the efficient execution of intelligent decisions can be achieved.

[0020] S2: Obtain the device performance and device functions of the terminal devices at the edge computing nodes, perform adaptation analysis of the intelligent manufacturing tasks according to the device performance and device functions, and establish the first adaptation constraint.

[0021] Specifically, obtain the device performance and device functions of the terminal devices at the edge computing nodes. The device performance refers to the hardware indicators such as the processing ability, computing speed, and memory of the terminal devices, while the device functions refer to the specific tasks that the terminal devices can complete, such as detection, monitoring, control, etc.

[0022] Next, perform an adaptation analysis of the intelligent manufacturing tasks based on the device performance and device functions to evaluate whether the terminal device is capable of handling the current intelligent manufacturing tasks. The intelligent manufacturing tasks include automation control, data acquisition, process optimization, etc. According to the analysis results, set certain constraint conditions for the matching between the device performance and functions and the intelligent manufacturing tasks, and establish the first adaptation constraint. The first adaptation constraint ensures that the device performance and functions are in line with the task requirements, avoiding waste of resources and task execution failures.

[0023] S3: Activate the dynamic task decomposition channel of the cloud center, and use the dynamic task decomposition channel to perform task decomposition of the intelligent manufacturing tasks, creating M subtasks.

[0024] Specifically, activate the dynamic task decomposition channel of the cloud center. The dynamic task decomposition channel is a mechanism for task splitting and scheduling, which can flexibly adjust the task decomposition strategy according to the real-time computing requirements of the system and the device status. For example, in some cases, tasks may need to be broken down into multiple small tasks for parallel processing, while in the case of less computing resources, the number of task splits may need to be reduced to adapt to the computing power. Therefore, activating the dynamic task decomposition channel of the cloud center can make task decomposition more flexible and intelligent, improving the overall computing efficiency.

[0025] Next, using the dynamic task decomposition channel to perform task decomposition of the intelligent manufacturing tasks means that, with the support of the cloud center, through the dynamic task decomposition channel, the intelligent manufacturing tasks are disassembled into smaller subtasks. The task decomposition process needs to consider multiple factors, such as the computing requirements of the tasks, the computing power of the devices, the stability of network communication, etc. For example, a large machine vision detection task may be decomposed into multiple subtasks, each subtask responsible for different detection areas or different feature extraction operations, so that multiple computing devices can be used for parallel processing to improve the detection efficiency. In addition, the dynamic task decomposition channel can adjust the task decomposition strategy according to the real-time computing load situation. For example, in the case of sufficient computing resources, a more refined task split can be adopted to improve the computing parallelism; while in the case of resource constraints, the task split can be reduced to lower the communication and scheduling costs.

[0026] Finally, after the task decomposition is completed, M executable subtasks are finally generated. The value of M depends on the complexity of the task, the availability of computing resources, and the way the task is executed. For example, if an intelligent manufacturing task involves complex data processing and there are sufficient computing resources, M may be relatively large, such as 50 subtasks, and each subtask is executed on a different computing device; while if the computing resources are limited, M may be relatively small, such as only 10 subtasks, to reduce the competition for computing resources. Through reasonable task decomposition, the computing efficiency can be improved, the waste of computing resources can be reduced, and it can be ensured that the task can be completed within the specified time.

[0027] S4: Use the cloud center to conduct a task competition game analysis of the M subtasks by the terminal device, and establish a second adaptation constraint.

[0028] Specifically, the M subtasks are multiple executable tasks created through a dynamic task decomposition channel, and each task may have different computing requirements and execution priorities. Task competition game analysis is a computational method based on game theory, aiming to solve the problem of multiple tasks competing for limited computing resources. For example, when multiple subtasks need to be assigned to different terminal devices, the computing power, current load, and task adaptability of each device will affect the result of task scheduling. Through task competition game analysis, an optimal task allocation strategy can be found to maximize the task execution efficiency and the utilization rate of device resources at the same time.

[0029] Next, after the task competition game analysis is completed, according to the calculation results, more reasonable task allocation constraints are formulated as the second adaptation constraint to ensure that tasks are reasonably assigned to the most suitable terminal devices. If a certain terminal device has low computing power, it may be avoided to assign the task to this device, thus reducing the possibility of computing failure or execution delay. The second adaptation constraint comprehensively considers the results of the task competition game analysis, making the task allocation more intelligent and efficient. For example, in the first adaptation constraint, a certain task may be considered suitable for execution on multiple devices, while in the second adaptation constraint, considering the task competition situation and the real-time computing load of the device, the optimal device is finally selected to execute the task.

[0030] S5: Conduct a balance analysis of the first adaptation constraint and the second adaptation constraint to generate an intelligent execution plan for the terminal device of the intelligent manufacturing task.

[0031] Specifically, a comprehensive comparison is made between the first adaptation constraint and the second adaptation constraint to ensure the rationality of task allocation. The goal of the balance analysis is to find the optimal trade-off point between the two, so that the task can not only match the appropriate device, but also be dynamically optimized according to the real-time computing state. For example, if the first adaptation constraint believes that a certain device is suitable for executing high-computation tasks, but the second adaptation constraint finds that the current load of this device is too high, it may choose to allocate the task to a device with a lower load but slightly lower computing power to improve the overall execution efficiency. The balance analysis usually involves multiple optimization parameters, such as computing resource utilization, task execution time, communication stability, and task completion rate, etc. Finally, based on the results of the balance analysis, an intelligent execution plan for the terminal device of the intelligent manufacturing task is generated. The intelligent execution plan is an optimized task scheduling plan that can reasonably allocate tasks according to the computing power of the device, task requirements, real-time load conditions, and historical execution performance.

[0032] Furthermore, this application also includes: activating the task competition game analysis function of the cloud center, performing the task competition game analysis of M subtasks, and the game characteristics of the competition game analysis function include device adaptability characteristics, historical performance consistency characteristics, communication stability characteristics, and data fidelity guarantee characteristics. The task competition game analysis function performs game compensation through the inter-task cooperation factor.

[0033] Specifically, the task competition game analysis function is as follows: ; where represents the competition game loss of the subtask on the terminal device resources ; represents the dynamic priority weight of the task ; represents the device adaptability factor, that is, the device adaptability characteristic, which is used to measure the adaptability of the terminal device resources to the subtask ; represents the historical performance consistency of the terminal device resources , that is, the historical performance consistency characteristic; represents the communication stability factor, that is, the communication stability characteristic; represents the data fidelity guarantee factor, that is, the data fidelity guarantee characteristic; represents the inter-task cooperation factor; are respectively the weight factors of device adaptability, historical performance consistency, communication stability, and data fidelity guarantee; It is the loss weight factor for the cooperation factor between tasks. Start the task competition game analysis function of the cloud center. Task competition game analysis is a method based on game theory used to solve the problem of multiple tasks competing for limited resources. The analysis function is used to calculate and evaluate the competition relationship between tasks in order to optimize the task allocation strategy.

[0034] Then, perform the task competition game analysis on M subtasks to determine how these subtasks reasonably use the terminal device resources and avoid excessive resource contention leading to a decline in system performance. M represents the number of tasks to be executed. A subtask refers to a small-scale calculation or operation after a complete task is split, and each subtask requires a certain amount of computing resources to complete.

[0035] Next, Characterize the subtask in the terminal device resources The competition game loss on it is used to measure the efficiency loss brought about when multiple subtasks compete for terminal device resources. When multiple tasks simultaneously compete for the same computing resources, situations such as delays, task failures, or a decrease in the utilization rate of computing resources may occur.

[0036] Characterize the task The dynamic priority weight, which refers to a variable used to measure the priorities of different tasks. Dynamic priority means that the priority of a task will be adjusted over time or according to the environment. For example, the priority of an urgent task may increase, while a task of low importance may be postponed to ensure the reasonable allocation of resources.

[0037] Meanwhile, Characterize the device adaptability factor, which is used to measure the adaptability of terminal device resources to subtasks and represents the ability of the device to adapt to different task requirements. For example, a high-performance computing device may be able to handle multiple complex tasks simultaneously, while a low-power device may only be able to perform simple calculations. The higher this factor, the stronger the device's ability to adapt to different tasks.

[0038] Characterize the terminal device resources The historical performance consistency, which refers to a variable used to measure whether the performance of the terminal device was stable during past operations. If the parameters such as the computing speed and response time of the device fluctuate less during different time periods, it indicates that its historical performance consistency is high, meaning that tasks can be executed more reliably.

[0039] The communication stability factor is used to measure the communication quality between a terminal device and the cloud or other devices. If the communication stability factor is high, it indicates a stable network connection, low data transmission latency, and is less likely to experience data loss or transmission interruption, thus ensuring the normal execution of tasks.

[0040] The data fidelity guarantee factor represents a parameter used to measure whether data can maintain integrity and accuracy during transmission and processing. If the data fidelity guarantee factor is high, it means that the data is less interfered with during transmission, has a lower error rate, and the reliability of the final calculation result is higher.

[0041] The task - to - task cooperation factor is used to measure the degree of cooperation among multiple tasks. When the cooperation factor is high, different tasks can efficiently share resources, reduce resource conflicts, and improve the overall system efficiency. For example, on a manufacturing production line, different tasks can share sensor data to optimize the entire production process.

[0042] The weight factors for device adaptability, historical performance consistency, communication stability, and data fidelity guarantee respectively refer to the weight values used to adjust the influence degree of the above - mentioned parameters on the final calculation. Different application scenarios may require different weights. For example, in a system with high real - time requirements, the weight factor of communication stability may be larger, while in a data analysis task, the weight factor of data fidelity may account for a higher proportion. In addition, the loss weight factor of the task - to - task cooperation factor is used to measure the impact of the cooperation degree among tasks on the overall loss. If the task cooperation ability is insufficient, it will lead to a reduction in resource utilization efficiency. Therefore, corresponding loss weight factors need to be set for optimization.

[0043] The task - to - task cooperation factor is calculated as follows: ; where represents the total number of subtasks scheduled on the terminal device resources , represents the subtask and another subtask 's cooperation similarity, and belongs to the set of subtasks scheduled on the terminal device resources .

[0044] First of all, the task - to - task cooperation factor is a parameter used to measure the cooperation of multiple subtasks when they are executed on terminal device resources, which can reflect the degree of mutual influence among tasks. Calculating the task - to - task cooperation factor is to optimize task scheduling, enabling multiple tasks to efficiently share resources, reduce resource waste, and improve the overall execution efficiency.

[0045] Among them, characterizes the total number of subtasks scheduled on the terminal device resources which refers to the number of subtasks running simultaneously on a specific terminal device. Terminal device resources include limited resources such as computing power, storage space, and network bandwidth. When multiple subtasks run simultaneously, reasonable scheduling is required to ensure maximum resource utilization. For example, if a certain terminal device can handle five subtasks simultaneously, but only three subtasks are actually running, it means that the resources are not fully utilized. On the other hand, if the number of running subtasks exceeds its processing capacity, it may cause computing delays or failures.

[0046] characterizes the subtask and another subtask 's collaborative similarity, which means that this variable is used to measure the closeness of cooperation between two subtasks during execution. If two subtasks can share calculation results or data inputs, their collaborative similarity is high. For example, in an image processing task, if one subtask is responsible for image segmentation and another subtask is responsible for object detection, they can share preprocessed data, thus reducing duplicate calculations and improving execution efficiency. On the contrary, if two subtasks require independent data processing and have a low collaborative similarity, the degree of resource sharing between them is low, which may increase the calculation cost.

[0047] belongs to the set of subtasks scheduled on the terminal device resources which means that the subtasks participating in the collaborative factor of the computing task must be part of the task set currently running on the terminal device. The subtask set refers to all tasks scheduled to run on a certain terminal device, rather than all tasks in the entire system. For example, if a certain terminal device is running four subtasks and the entire system has a total of ten subtasks, then only these four tasks need to be considered when calculating the collaborative factor, rather than all ten tasks. This limitation can ensure the pertinence of the calculation and make the task scheduling more accurate.

[0048] Furthermore, this application also includes: evaluating the computing power of the terminal device according to the device performance of the terminal device, and establishing a weak computing device performance protection identifier; performing load analysis of the terminal device within a preset cycle range, and establishing a high load identifier; using the weak computing device performance protection identifier and the high load identifier to perform equilibrium compensation for task competition game analysis, and establishing a second adaptation constraint according to the equilibrium compensation result.

[0049] Specifically, computing power evaluation refers to evaluating the ability of a terminal device to process tasks based on its performance parameters in order to reasonably allocate computing tasks. For example, if a device has strong computing power, complex tasks can be allocated to it, while devices with weak computing power can only execute simple tasks, thereby improving the operating efficiency of the overall system.

[0050] Next, a performance protection identifier for weak computing devices is established, which means that if some terminal devices have low computing power, a special identifier will be set for them to prevent these devices from undertaking computing tasks with excessive loads. Weak computing devices usually refer to devices with low processor performance, small memory, or limited power consumption, such as small sensor nodes or low-power embedded devices. The role of the protection identifier is to restrict the task allocation of such devices to ensure that their performance does not decline or even crash due to overloading calculations.

[0051] Then, at regular time intervals, the operating load conditions of terminal devices are evaluated periodically. The preset cycle range refers to the time window set by those skilled in the art. For example, load detection is performed every ten minutes or every hour. Load analysis mainly focuses on indicators such as the CPU occupancy rate, memory usage rate, and data throughput of the device to judge the current working state of the device. If a device is in a high-load state for a long time, it may affect the stability of the system, so measures need to be taken for optimized scheduling.

[0052] Immediately afterwards, a high-load identifier is established, which means that if a terminal device is detected to be continuously in a high-load state during the load analysis process, a high-load identifier is assigned to it to remind the task scheduling system to avoid further allocating computing tasks to this device to prevent resource exhaustion or task execution failure. For example, if the CPU usage rate of a device remains at 90% for a long time, then this device may no longer be able to undertake new computing tasks, and it will be marked as a busy state through the high-load identifier, thereby optimizing the task allocation strategy.

[0053] Furthermore, an equilibrium compensation for task competition game analysis is carried out using the performance protection identifier for weak computing devices and the high-load identifier, which means comprehensively considering the computing power and current load conditions of the device to optimize the task allocation plan. Task competition game analysis is a computational method based on game theory, aiming to solve the problem of multiple tasks competing for limited computing resources. Equilibrium compensation means that by reasonably adjusting the task allocation, it is ensured that the computing resources of different devices can be best utilized, neither overloading the devices with weak computing power nor overloading the high-load devices. For example, if a weak computing device originally needs to execute five tasks but due to insufficient computing power, the allocation plan can be adjusted to let a device with stronger computing power take over two of these tasks, thereby achieving equilibrium compensation.

[0054] Finally, a second adaptation constraint is established based on the equilibrium compensation result, which means that after the task competition game analysis is completed, the matching relationship between tasks and devices is further optimized according to the equilibrium compensation result. The role of the second adaptation constraint is to ensure more reasonable task allocation and avoid resource waste or computational bottlenecks. For example, if a device was considered suitable for executing a certain task in the previous adaptation analysis, but its adaptability has changed due to increased subsequent load, then the second adaptation constraint will re-evaluate the task allocation and adjust the resource usage strategy to maintain the stability and efficiency of the system.

[0055] Furthermore, this application also includes: uploading time constraints, computational complexity constraints, computational requirement constraints, and task association constraints for the intelligent manufacturing task; obtaining the maximum computing power and minimum computing power of the terminal device, and establishing a granularity decomposition constraint based on the maximum computing power and the minimum computing power; performing task decomposition on the intelligent manufacturing task according to the granularity decomposition constraint, the time constraint, the computational complexity constraint, the computational requirement constraint, and the task association constraint to create M subtasks.

[0056] Specifically, time constraints, computational complexity constraints, computational requirement constraints, and task association constraints for the intelligent manufacturing task are uploaded for subsequent analysis and processing. An intelligent manufacturing task refers to calculations or operations that need to be performed during the industrial production process, such as production scheduling, equipment control, data analysis, etc. The time constraint means that the task must be completed within a specified time. For example, the processing of a certain part must be completed within 20 minutes, otherwise it will affect the entire production process. The computational complexity constraint is a standard for measuring the computational resources required for a task, which determines how much computing power is needed to complete the task. For example, complex artificial intelligence model inference requires a high computational complexity, while a simple temperature monitoring task has a low computational complexity. The computational requirement constraint refers to the computational resources required for a task, including CPU, memory, storage, etc. For example, a certain task may require high-performance GPU computing, while another task only requires basic numerical operations. The task association constraint refers to the interdependent relationship between different tasks. For example, the output of a certain task may be the input of another task, so they must be executed in a certain order.

[0057] Next, obtaining the maximum computing power and minimum computing power of the terminal device means detecting the computing power of all available terminal devices. The maximum computing power refers to the ability of the device with the strongest computing performance, such as a high-performance computing server or an industrial-grade edge computing node. The minimum computing power refers to the device with the weakest computing power in the system, such as a low-power sensor or an embedded device. The purpose of obtaining these two extreme values is to evaluate the overall computing power range of the system and provide a basis for subsequent task decomposition.

[0058] Then, establish the granularity decomposition constraint based on the highest computing power and the lowest computing power, which means setting the decomposition granularity of the task according to the range of the device computing power. The granularity decomposition constraint determines how many subtasks the task is split into and the computing amount of each subtask. If the computing power range is large, indicating that there are powerful computing devices available, the task can be split into finer granularities, enabling multiple devices to process in parallel and improving the overall efficiency. For example, if a task requires 100 units of computing amount, and the device with the highest computing power can process 50 units per second, while the device with the lowest computing power can only process 5 units per second, then the system may split the task into multiple subtasks of different sizes and allocate them to devices with different computing powers respectively to achieve optimal computing scheduling.

[0059] Finally, perform the task decomposition of the intelligent manufacturing task according to the granularity decomposition constraint, time constraint, computing complexity constraint, computing requirement constraint, and task association constraint to create M subtasks, splitting the intelligent manufacturing task into M subtasks for more reasonable allocation to different terminal devices for execution. Task decomposition is an important means for the intelligent manufacturing system to optimize the utilization rate of computing resources. For example, a large data analysis task may be split into multiple small tasks for parallel computing and executed by different devices respectively, thus accelerating the computing speed. If the time constraint is tight, the task may be preferentially allocated to devices with high computing power; if the computing requirement is high, the task allocation to devices with low computing power may be minimized to ensure the smooth completion of the task. Table 1 is the data record form of the latest intelligent manufacturing task and the computing power of the terminal device.

[0060] Table 1: Data Record Form of the Latest Intelligent Manufacturing Task and the Computing Power of the Terminal Device

[0061]

[0062] Furthermore, this application also includes: monitoring the execution of subtasks on the terminal device to establish the execution monitoring result; performing the execution lag analysis of the subtasks based on the execution monitoring result to establish the execution lag identifier; establishing the optimization constraint according to the execution lag identifier, and performing the optimization of the execution plan with the optimization constraint.

[0063] Specifically, monitor the execution of subtasks on the terminal device. Execution monitoring refers to the real-time tracking and recording of the situation of the terminal device executing subtasks, such as monitoring key indicators such as the execution time of the task, computing resource consumption, and data transmission delay. Organize and store these monitoring data to establish the execution monitoring result for subsequent analysis. For example, if the CPU usage rate of a certain terminal device is always close to 100% when executing a subtask, while the CPU usage rate of another device executing the same task is only 50%, then this difference will be recorded to determine whether the task allocation strategy needs to be adjusted.

[0064] Next, based on the execution monitoring results, perform an analysis of the execution lag of subtasks, establish an execution lag identifier, and use the data from the execution monitoring to analyze the execution efficiency of the tasks. Execution lag refers to the delay situation that occurs during the execution of subtasks. For example, the task execution time exceeds the expectation, or the task execution progress lags behind the scheduling plan. Execution lag may be caused by various factors, such as insufficient computing resources, network communication delays, or unreasonable task scheduling. The execution lag identifier is a label for these task delay situations, which is used to optimize the task scheduling strategy. For example, if a certain terminal device causes task lag due to high load, an execution lag identifier can be assigned to this device to remind the task scheduling system to reduce the task allocation to this device.

[0065] Then, establish an optimization constraint based on the execution lag identifier, and perform optimization of the execution plan with the optimization constraint. The optimization constraint refers to the rule for optimizing task allocation based on the execution lag identifier, to ensure that the tasks can be executed more efficiently. For example, if a certain device is judged to have a high load due to the execution lag identifier, its reception of new tasks can be restricted, or some tasks can be reallocated to devices with lower load. Optimization refers to adjusting the entire task execution plan based on the optimization constraint to improve the task execution efficiency. For example, if it is found that some devices have long-term execution lag, while other devices still have computing margin, the optimized plan may reallocate tasks, so that the overall execution time is shortened and the utilization rate of computing resources is improved.

[0066] Furthermore, this application also includes: performing an analysis of the impact on the synchronous execution of associated tasks according to the lag identifier, generating a lag time constraint according to the impact analysis result; obtaining a task requirement constraint for the lag subtask according to the lag identifier, and performing successor optimization of the terminal device according to the lag time constraint and the task requirement constraint, and performing optimization of the execution plan with the successor optimization result.

[0067] Specifically, perform an analysis of the impact on the synchronous execution of associated tasks according to the lag identifier. The lag identifier is used to identify subtasks whose execution time exceeds the expectation. Associated tasks refer to multiple interdependent tasks. For example, the output of one task may be the input of another task. Therefore, if a certain task has a lag, it may affect the execution of subsequent tasks. The analysis of the impact on synchronous execution refers to evaluating this impact. For example, if a task is expected to be completed within 10 minutes but actually takes 15 minutes, then the downstream tasks that depend on this task will also be affected.

[0068] Generating a lag time constraint according to the impact analysis result means setting a new time constraint. For example, if the execution lag of a certain task affects the overall production process, the time window of other tasks may be adjusted to reduce the overall delay impact.

[0069] Next, obtain the task requirement constraints of the hysteresis sub-tasks based on the hysteresis identifier, and perform replacement optimization of the terminal device according to the hysteresis time constraint and the task requirement constraints. The hysteresis sub-tasks refer to the tasks that affect the overall progress due to execution hysteresis, and the task requirement constraints refer to the computing resources, storage space, network bandwidth, etc. required by these tasks during execution. For example, if a certain sub-task requires high computing power but the computing power of the allocated device is low, resulting in task hysteresis, then its computing resource requirement constraints can be adjusted to better match the appropriate computing resources during the replacement optimization process. Replacement optimization means finding a more suitable terminal device to execute these hysteresis tasks. Possible strategies include transferring the task to a device with stronger computing power, reducing the computing complexity of the task, or adjusting the task scheduling order to reduce the overall delay. For example, if a task is delayed due to insufficient computing power of a certain device and another device has a low current load, the task can be re-allocated to the latter to speed up the execution progress.

[0070] Finally, perform optimization of the execution plan based on the replacement optimization result, which means that after the replacement optimization is completed, the overall execution strategy is optimized according to the new task allocation plan. The goal of the optimization is to ensure that all tasks can be completed in the shortest time while maximizing the utilization rate of computing resources. For example, in an intelligent manufacturing environment, if a task is delayed due to high device load, a device with a lower load can be found through replacement optimization and the task can be re-allocated, so that the overall execution time is shortened, thereby optimizing the production efficiency.

[0071] Furthermore, this application also includes: determining whether the optimization adaptation value of the terminal device that has completed the execution of the sub-task meets a preset threshold; if the optimization adaptation value of the terminal device that has completed the execution of the sub-task meets the preset threshold, then output the terminal device with the highest optimization adaptation value as the replacement optimization result.

[0072] Specifically, the terminal device that has completed the execution of the sub-task refers to the computing node that has completed a certain sub-task, just finishing the current task, and there may or may not be subsequent tasks. Determine whether the optimization adaptation value of the terminal device that has completed the execution of the sub-task meets the preset threshold. The optimization adaptation value is an index used to measure the quality of task execution by the terminal device, and may include a comprehensive score of multiple factors such as task execution time, computing resource utilization rate, and energy consumption efficiency. The preset threshold is the set minimum standard used to determine whether the execution performance of the device meets the requirements. For example, if the full score of the optimization adaptation value is 100% and the set preset threshold is 70%, then only the devices with an optimization adaptation value greater than or equal to 70% will be considered qualified execution devices. The process of determining whether the optimization adaptation value meets the preset threshold can help screen out devices with better performance and avoid allocating tasks to devices with poor execution capabilities.

[0073] Next, if the optimization adaptation value of the terminal device that has completed the subtask execution meets the preset threshold, the terminal device with the highest optimization adaptation value is output as the replacement optimization result. If the optimization adaptation value of a terminal device reaches the minimum requirement set by the system, among all the devices that meet the requirement, the device with the highest optimization adaptation value is selected as the best candidate for the replacement task execution. For example, assume that three terminal devices have completed the subtask and obtained optimization adaptation values of 75%, 85%, and 90% respectively, and the preset threshold is 70%. Then, the terminal device corresponding to the highest optimization adaptation value of 90% will be selected as the final replacement optimization result. The output of the replacement optimization result can be used for subsequent task scheduling. For example, if there is a new subtask to be executed currently, it can be preferentially assigned to this device with a high adaptation value to ensure more efficient execution.

[0074] Furthermore, this application also includes: if the optimization adaptation value of the terminal device that has completed the subtask execution does not meet the preset threshold, calculate the interruption loss of the terminal device for which the subtask has not been completed; after compensating the optimization adaptation value of the terminal device for which the subtask has not been completed according to the interruption loss, reconstruct the replacement optimization result.

[0075] Specifically, if the optimization adaptation value of the terminal device that has completed the subtask execution does not meet the preset threshold, calculate the interruption loss of the terminal device for which the subtask has not been completed. The optimization adaptation value is an indicator to measure the quality of the device's task execution. If this value is lower than the preset threshold set by the system, it indicates that the device's execution performance is not ideal, and there may be problems such as low computing efficiency, long task execution time, or low resource utilization. In this case, calculate the interruption loss of the terminal device for which the subtask has not been completed. The terminal device for which the subtask has not been completed refers to the device that has failed to complete the task, such as the device whose task is interrupted due to insufficient computing power, network delay, or system failure. The interruption loss is an indicator to measure the negative impact brought by the uncompleted task, which may include waste of computing resources, extension of task execution time, and cascading effects on other tasks.

[0076] Next, after compensating the optimization adaptation value of the terminal device for which the subtask has not been completed according to the interruption loss, reconstruct the replacement optimization result. For the device that has not completed the task, adjust the optimization adaptation value according to its interruption loss to make up for the impact brought by the uncompleted task. For example, if a device fails to complete the task due to insufficient computing resources, but its communication stability and energy consumption efficiency are relatively high, a certain optimization adaptation value compensation may be given to more fairly measure its comprehensive ability. The compensated optimization adaptation value can be used to optimize task scheduling to ensure that when the task is reallocated, a more suitable device can be more reasonably matched. Reconstructing the replacement optimization result means that after the compensation adjustment, the best task replacement plan will be recalculated, and the most suitable device will be selected to execute the uncompleted task.

[0077] In summary, the AloT cloud-edge-end intelligent control method for industrial Internet of Things provided by this application has the following technical effects: By achieving the technical goal of intelligent task scheduling and optimal allocation under the cloud-edge-end collaborative computing architecture, the technical effects of improving task execution efficiency, reducing computing latency, optimizing computing resource utilization, and enhancing data security are achieved.

[0078] Embodiment 2. Based on the same inventive concept as the AloT cloud-edge-end intelligent control method for industrial Internet of Things in the foregoing embodiment, this application also provides an AloT cloud-edge-end intelligent control system for industrial Internet of Things. Please refer to the appendix Figure 2 , including: a collaborative architecture creation module 11, configured to create a cloud-edge-end collaborative architecture, where the cloud-edge-end collaborative architecture includes a cloud center, edge computing nodes, and terminal devices, and obtain intelligent manufacturing tasks from the cloud center; an adaptation analysis module 12, configured to obtain the device performance and device functions of the terminal devices at the edge computing nodes, perform adaptation analysis of the intelligent manufacturing tasks according to the device performance and device functions, and establish a first adaptation constraint; a task decomposition module 13, configured to activate the dynamic task decomposition channel of the cloud center, use the dynamic task decomposition channel to perform task decomposition of the intelligent manufacturing tasks, and create M subtasks; a competition game analysis module 14, configured to use the cloud center to perform task competition game analysis of the M subtasks by the terminal devices, and establish a second adaptation constraint; and a solution generation module 15, configured to perform balance analysis on the first adaptation constraint and the second adaptation constraint, and generate an intelligent execution solution for the terminal devices of the intelligent manufacturing tasks.

[0079] Furthermore, the AloT cloud-edge-end intelligent control system for industrial Internet of Things is further configured to: activate the task competition game analysis function of the cloud center, and perform task competition game analysis of the M subtasks. The game characteristics of the competition game analysis function include device adaptability characteristics, historical performance consistency characteristics, communication stability characteristics, and data fidelity guarantee characteristics. The task competition game analysis function performs game compensation through the inter-task collaboration factor.

[0080] Furthermore, the AloT cloud-edge-end intelligent control system for industrial Internet of Things is further configured to: upload the time constraint, computing complexity constraint, computing requirement constraint, and task association constraint of the intelligent manufacturing tasks; obtain the maximum computing power and minimum computing power of the terminal devices, and establish a granularity decomposition constraint according to the maximum computing power and the minimum computing power; and perform task decomposition of the intelligent manufacturing tasks according to the granularity decomposition constraint, the time constraint, computing complexity constraint, computing requirement constraint, and task association constraint to create M subtasks.

[0081] Further, the AloT cloud-edge-end intelligent control system for industrial Internet of Things is also used for: monitoring the execution of subtasks of the terminal device and establishing an execution monitoring result; performing an execution lag analysis of the subtasks based on the execution monitoring result and establishing an execution lag identifier; establishing an optimization constraint according to the execution lag identifier and performing optimization of the execution plan based on the optimization constraint.

[0082] Further, the AloT cloud-edge-end intelligent control system for industrial Internet of Things is also used for: analyzing the impact of synchronous execution of linkage tasks according to the lag identifier, and generating a lag time constraint according to the impact analysis result; obtaining the task requirement constraint of the lag subtask according to the lag identifier, and performing replacement optimization of the terminal device according to the lag time constraint and the task requirement constraint, so as to perform optimization of the execution plan according to the replacement optimization result.

[0083] Further, the AloT cloud-edge-end intelligent control system for industrial Internet of Things is also used for: determining whether the optimization adaptation value of the terminal device that has completed the execution of the subtask meets a preset threshold; if the optimization adaptation value of the terminal device that has completed the execution of the subtask meets the preset threshold, outputting the terminal device with the highest optimization adaptation value as the replacement optimization result.

[0084] Further, the AloT cloud-edge-end intelligent control system for industrial Internet of Things is also used for: if the optimization adaptation value of the terminal device that has completed the execution of the subtask cannot meet the preset threshold, calculating the interruption loss of the terminal device that has not completed the execution of the subtask; reconstructing the replacement optimization result after compensating the optimization adaptation value of the terminal device that has not completed the execution of the subtask according to the interruption loss.

[0085] The various embodiments in this specification are described in a progressive manner, and the key points of each embodiment are the differences from other embodiments. The AloT cloud-edge-end intelligent control method and specific examples in the foregoing Embodiment 1 for industrial Internet of Things are equally applicable to the AloT cloud-edge-end intelligent control system for industrial Internet of Things in this embodiment. Through the foregoing detailed description of the AloT cloud-edge-end intelligent control method for industrial Internet of Things, those skilled in the art can clearly know the AloT cloud-edge-end intelligent control system for industrial Internet of Things in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0086] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0087] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of this application and its equivalent technologies, this application also intends to include these changes and modifications.

Claims

1. An AloT cloud-edge-end intelligent control method for industrial Internet of Things, characterized in that, Including: Create a cloud-edge-end collaborative architecture, which includes a cloud center, edge computing nodes, and terminal devices, and obtain intelligent manufacturing tasks from the cloud center; Obtain the device performance and device functions of the terminal devices at the edge computing nodes, perform adaptation analysis of the intelligent manufacturing tasks based on the device performance and device functions, and establish the first adaptation constraint; Activate the dynamic task decomposition channel of the cloud center, use the dynamic task decomposition channel to decompose the intelligent manufacturing tasks, and create M subtasks; Use the cloud center to perform task competition game analysis of the M subtasks by the terminal devices, and establish the second adaptation constraint; Perform balance analysis on the first adaptation constraint and the second adaptation constraint to generate an intelligent execution plan for the terminal devices of the intelligent manufacturing tasks; After generating the intelligent execution plan for the terminal devices of the intelligent manufacturing tasks, it includes: Monitor the execution of the subtasks by the terminal devices, and establish an execution monitoring result; Perform execution lag analysis of the subtasks based on the execution monitoring result, and establish an execution lag identifier; Establish an optimization constraint according to the execution lag identifier, and perform optimization of the execution plan with the optimization constraint; The use of the cloud center to perform task competition game analysis of the M subtasks by the terminal devices includes: Activate the task competition game analysis function of the cloud center, and perform task competition game analysis of the M subtasks. The game characteristics of the competition game analysis function include device adaptability characteristics, historical performance consistency characteristics, communication stability characteristics, and data fidelity guarantee characteristics. The task competition game analysis function performs game compensation through the inter-task cooperation factor.

2. The AloT cloud-edge-end intelligent control method for industrial Internet of Things according to claim 1, wherein, The use of the cloud center to perform task competition game analysis of the M subtasks by the terminal devices further includes: Evaluate the computing power of the terminal devices according to the device performance of the terminal devices, and establish a weak computing device performance protection identifier; Perform load analysis of the terminal devices within a preset cycle range, and establish a high load identifier; Use the weak computing device performance protection identifier and the high load identifier to perform balanced compensation for the task competition game analysis, and establish the second adaptation constraint according to the balanced compensation result.

3. The AloT cloud-edge-end intelligent control method for industrial Internet of Things according to claim 1, characterized in that, The use of the dynamic task decomposition channel to decompose the intelligent manufacturing tasks and create M subtasks includes: Upload the time constraint, computing complexity constraint, computing requirement constraint, and task association constraint of the intelligent manufacturing tasks; Obtain the maximum computing power and minimum computing power of the terminal devices, and establish a granularity decomposition constraint according to the maximum computing power and the minimum computing power; Decompose the intelligent manufacturing tasks according to the granularity decomposition constraint, the time constraint, the computing complexity constraint, the computing requirement constraint, and the task association constraint to create M subtasks.

4. The AloT cloud-edge-end intelligent control method for industrial Internet of Things according to claim 1, characterized in that, The establishment of the optimization constraint according to the execution lag identifier and the optimization of the execution plan with the optimization constraint includes: Perform synchronous execution impact analysis of the linked tasks according to the lag identifier, and generate a lag time constraint according to the impact analysis result; Obtain the task requirement constraints of the hysteresis subtask according to the hysteresis identifier, and perform replacement optimization of the terminal device according to the hysteresis time constraint and the task requirement constraint, so as to perform optimization of the execution plan based on the replacement optimization result.

5. The AloT cloud-edge-end intelligent control method for industrial Internet of Things according to claim 4, wherein, The replacement optimization of the terminal device according to the hysteresis time constraint and the task requirement constraint further includes: Determine whether the optimization adaptation value of the terminal device that has completed the execution of the subtask meets a preset threshold; If the optimization adaptation value of the terminal device that has completed the execution of the subtask meets the preset threshold, output the terminal device with the highest optimization adaptation value as the replacement optimization result.

6. The AloT cloud-edge-end intelligent control method for industrial Internet of Things according to claim 5, characterized in that, The determination of whether the optimization adaptation value of the terminal device that has completed the execution of the subtask meets the preset threshold further includes: If the optimization adaptation value of the terminal device that has completed the execution of the subtask cannot meet the preset threshold, calculate the interruption loss of the terminal device for which the subtask has not been completed; After compensating the optimization adaptation value of the terminal device for which the subtask has not been completed according to the interruption loss, reconstruct the replacement optimization result.

7. An AloT cloud-edge-end intelligent control system for industrial Internet of Things, characterized in that, Steps for implementing the AloT cloud-edge-end intelligent control method for industrial Internet of Things according to any one of claims 1 to 6 include: A collaborative architecture creation module, configured to create a cloud-edge-end collaborative architecture, where the cloud-edge-end collaborative architecture includes a cloud center, edge computing nodes, and terminal devices, and obtain intelligent manufacturing tasks from the cloud center; An adaptation analysis module, configured to obtain the device performance and device functions of the terminal device at the edge computing node, perform adaptation analysis of the intelligent manufacturing task according to the device performance and device functions, and establish a first adaptation constraint; A task decomposition module, configured to activate the dynamic task decomposition channel of the cloud center, perform task decomposition of the intelligent manufacturing task using the dynamic task decomposition channel, and create M subtasks; A competition game analysis module, configured to perform task competition game analysis of the M subtasks by the terminal device using the cloud center, and establish a second adaptation constraint; A solution generation module, configured to perform balance analysis on the first adaptation constraint and the second adaptation constraint, and generate an intelligent execution solution for the terminal device of the intelligent manufacturing task.

Images