CN119937436B - AloT cloud edge end intelligent control method and system for industrial Internet of things - Google Patents
AloT cloud edge end intelligent control method and system for industrial Internet of thingsInfo
- Publication number
- CN119937436B CN119937436B CN202510431961.6A CN202510431961A CN119937436B CN 119937436 B CN119937436 B CN 119937436B CN 202510431961 A CN202510431961 A CN 202510431961A CN 119937436 B CN119937436 B CN 119937436B
- Authority
- CN
- China
- Prior art keywords
- task
- constraint
- cloud
- terminal equipment
- optimizing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- General Factory Administration (AREA)
Abstract
The application provides a AloT cloud edge intelligent control method and a AloT 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.
Description
Technical Field
The application relates to the technical field of cloud edge intelligent control, in particular to a AloT 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 AloT 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 AloT cloud edge intelligent control method and system for industrial Internet of things.
The application provides a AloT cloud side intelligent control method for an industrial Internet of things, which is realized by a AloT 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 decomposition channel, creating M subtasks, performing task game analysis of the M subtasks by utilizing the cloud center by utilizing the terminal equipment, 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 tasks.
The application further provides a AloT cloud side intelligent control system facing the industrial Internet of things, which is used for executing the AloT cloud side intelligent control method facing the industrial Internet of things according to the first aspect, and comprises a collaborative framework creation module, a competition game analysis module and a scheme generation module, wherein the collaborative framework creation module is used for creating a cloud-side collaborative framework, the cloud-side collaborative framework comprises a cloud center, an edge computing node and terminal equipment, acquiring intelligent manufacturing tasks from the cloud center, the adaptation analysis module is used for acquiring equipment performance and equipment functions of the terminal equipment at the edge computing node, performing adaptation analysis of the intelligent manufacturing tasks according to the equipment performance and the equipment functions, establishing a first adaptation constraint, activating a dynamic task decomposition channel of the cloud center, performing task decomposition of the intelligent manufacturing tasks by using the dynamic task decomposition channel, creating M sub-tasks, the competition game analysis module is used for performing task competition game analysis of the terminal equipment on the M sub-tasks by using the cloud center, establishing a second adaptation constraint, and the scheme generation module is used for performing balance analysis on the first adaptation constraint and the second adaptation constraint to generate an intelligent manufacturing scheme of the intelligent manufacturing tasks of the terminal equipment.
The technical scheme provided by the application has at least the following technical effects or advantages that the technical effects of improving the task execution efficiency, reducing the calculation delay, optimizing the calculation resource utilization rate and enhancing the data security are achieved by realizing the technical targets of intelligent task scheduling and optimal allocation under the cloud-edge-end cooperative calculation architecture.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent. It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the application or to delineate the scope of the application. Other features of the present application will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the application or the technical solutions of the prior art, the following brief description will be given of the drawings used in the description of the embodiments or the prior art, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained from the drawings provided without the inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a AloT cloud edge intelligent control method facing to the industrial Internet of things;
fig. 2 is a schematic structural diagram of the AloT cloud edge intelligent control system facing the industrial internet of things.
Reference numerals illustrate the collaborative architecture creation module 11, the adaptation analysis module 12, the task decomposition module 13, the competition game analysis module 14, and the scheme generation module 15.
Detailed Description
By providing the AloT cloud edge intelligent control method and system for the industrial Internet of things, 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, high delay, limited network bandwidth and data security risks are caused, the requirements on instantaneity, high efficiency and data privacy in the industrial Internet of things scene are further influenced, and the production efficiency and the system stability are further reduced are solved. The technical targets of intelligent task scheduling and optimal allocation under the cloud-side-end collaborative computing architecture are realized, and the technical effects of improving task execution efficiency, reducing computing delay, optimizing computing resource utilization rate and enhancing data security are achieved.
In the following, the technical solutions of the present application will be clearly and completely described with reference to the accompanying drawings, and it should be understood that the described embodiments are only some embodiments of the present application, but not all embodiments of the present application, and that the present application is not limited by the exemplary embodiments described herein. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. It should be further noted that, for convenience of description, only some, but not all of the drawings related to the present application are shown.
Referring to fig. 1, the application provides a AloT cloud edge intelligent control method for an industrial internet of things, which is applied to a AloT cloud edge intelligent control system for the industrial internet of things, and specifically comprises the following steps:
s1, 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.
Specifically, a cloud-side-end cooperative architecture is created, and a system architecture consisting of three parts of cloud, edge computing and terminal equipment is built. The cloud center is responsible for processing and storing large amounts of data. And generating related task instructions according to the environmental data and the equipment data acquired in real time, and then issuing the tasks to the edge computing nodes or the terminal equipment. The edge computing node is responsible for data processing and analysis at a location closer to the terminal device, which is responsible for interacting with the real environment and performing the actual tasks. Through the cooperative work of the cloud, the edge and the end, smooth data transmission and efficient execution of intelligent decision can be realized.
S2, acquiring equipment performance and equipment functions of the terminal equipment at an edge computing node, performing adaptation analysis of the intelligent manufacturing task according to the equipment performance and the equipment functions, and establishing a first adaptation constraint.
Specifically, the edge computing node obtains the device performance and the device function of the terminal device, where the device performance refers to the processing capability, computing speed, memory and other hardware indexes of the terminal device, and the device function refers to specific tasks that the terminal device can complete, such as detection, monitoring, control and the like.
And then, carrying out adaptation analysis of the intelligent manufacturing task according to the equipment performance and the equipment function, and evaluating whether the terminal equipment can be qualified for the current intelligent manufacturing task. The intelligent manufacturing task comprises automatic control, data acquisition, process optimization and the like, certain constraint conditions are set for matching conditions between equipment performance and functions and the intelligent manufacturing task according to analysis results, and the first adaptation constraint is established. The first adaptation constraint ensures that the performance and the function of the device are consistent with the task requirements, and avoids the waste of resources and the failure of task execution.
And S3, activating a dynamic task decomposition channel of the cloud center, and performing task decomposition of the intelligent manufacturing task by using the dynamic task decomposition channel to create M subtasks.
Specifically, a dynamic task decomposition channel of the cloud center is activated. The dynamic task decomposition channel is a mechanism for task splitting and scheduling, and can flexibly adjust a task decomposition strategy according to real-time computing requirements and equipment states of a system. For example, in some cases, a task may need to be subdivided into multiple small tasks for parallel processing, while in cases where computing resources are less, the number of task splits may need to be reduced to accommodate computing power. Therefore, the dynamic task decomposition channel of the cloud center is activated, so that task decomposition is more flexible and intelligent, and the overall calculation efficiency is improved.
Then, the task decomposition of the intelligent manufacturing task is performed by using the dynamic task decomposition channel, which means that the intelligent manufacturing task is decomposed into smaller subtasks through the dynamic task decomposition channel under the support of the cloud center. The process of task decomposition requires consideration of a number of factors, such as the computational requirements of the task, the computational power of the device, the stability of the network communications, etc. For example, a large machine vision inspection task may be broken down into multiple sub-tasks, each of which is responsible for a different inspection area or different feature extraction operations, so that multiple computing devices may be utilized to process in parallel, improving inspection efficiency. In addition, the dynamic task decomposition channel can adjust the task decomposition strategy according to the real-time calculation load condition. For example, finer task splitting can be adopted to improve the computation parallelism under the condition of sufficient computing resources, and the task splitting can be reduced to reduce the communication and scheduling cost under the condition of limited resources.
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 manner in which the task is performed. For example, if one smart manufacturing task involves complex data processing and the computing resources are sufficient, M may be large, e.g., 50 sub-tasks, each executing on a different computing device, while if the computing resources are limited, M may be small, e.g., only 10 sub-tasks, to reduce competition for computing resources. Through reasonable task decomposition, the calculation efficiency can be improved, the waste of calculation resources is reduced, and the task can be completed within a specified time.
And S4, performing task competition game analysis on M subtasks by using the terminal equipment by utilizing the cloud center, and establishing a second adaptation constraint.
In particular, M subtasks are multiple executable tasks created through a dynamic task decomposition channel, each of which may have different computational requirements and execution priorities. Task competition game analysis is a game theory-based calculation method and aims to solve the problem that a plurality of tasks compete on limited calculation resources. For example, when multiple subtasks need to be distributed to different terminal devices, the computing power, current load, and task suitability of each device all affect the results of task scheduling. Through task competition game analysis, an optimal task allocation strategy can be found, so that task execution efficiency is highest, and equipment resource utilization rate is maximized.
And then, after the task competition game analysis is completed, formulating more reasonable task allocation constraint according to the calculation result, and taking the constraint as a second adaptation constraint to ensure that the task is reasonably allocated to the most suitable terminal equipment. The lower computing power of a certain terminal device may avoid assigning the task to the device, thereby reducing the likelihood of computing failure or execution delay. The second adaptation constraint comprehensively considers the results of task competition game analysis, so that the task allocation is more intelligent and efficient. For example, in a first adaptation constraint a certain task may be considered suitable for multiple devices to perform, while in a second adaptation constraint, in combination with the task competition situation and the real-time computational load of the devices, the optimal device is ultimately selected to perform the task.
And S5, carrying out 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.
Specifically, the first fit constraint and the second fit constraint are comprehensively compared to ensure the rationality of task allocation. The balance analysis aims at finding the optimal folding point between the two, so that the task can be matched with proper equipment and can be dynamically optimized according to the real-time calculation state. For example, if a first fit constraint deems a device suitable for performing a high computational task, but a second fit constraint finds that the device is currently under too high a load, it may choose to assign the task to a device that is under a lower load but has slightly lower computational power to increase overall execution efficiency. Balance analysis typically involves a number of optimization parameters such as computing resource utilization, task execution time, communication stability, and task completion rate. Finally, based on the result of the balance analysis, an intelligent execution scheme of the terminal device of the intelligent manufacturing task is generated. The intelligent execution scheme is an optimized task scheduling scheme, and tasks can be reasonably distributed according to the computing capacity, task demands, real-time load conditions and historical execution performance of the equipment.
Further, the method also comprises the steps of 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.
Specifically, the task competition betting analysis function is as follows: Wherein, the method comprises the steps of, Characterization subtasksAt terminal equipment resourcesThe loss of the competition game on the upper part,Characterizing tasksIs used to determine the dynamic priority weights of the (c),Characterizing device adaptability factors, i.e. device adaptability characteristics, for measuring terminal device resourcesSubtasksIs used for the adaptation of the number of the modules,Characterizing terminal equipment resourcesI.e., historical performance consistency characteristics,The communication stability factor, i.e. the communication stability characteristic,Characterizing data fidelity assurance factors, i.e. data fidelity assurance features,The co-factors between the tasks are characterized,Respectively the weight factors of equipment adaptability, historical performance consistency, communication stability and data fidelity guarantee,And a loss weight factor which is an inter-task cofactor. And starting a task competition game analysis function of the cloud center. Task competition game analysis is a game theory-based method for solving the problem of competition of a plurality of tasks on limited resources. The analysis function is then used to calculate and evaluate the competing relationships between tasks in order to optimize the task allocation policy.
And then, executing task competition game analysis of M subtasks, and determining how to reasonably use terminal equipment resources by the subtasks so as to avoid system performance degradation caused by excessive resource contention. M represents the number of tasks that need to be performed. Subtasks refer to small-scale computation or operations after a complete task is split, each of which requires certain computing resources to complete.
Next to this, the process is carried out,Characterization subtasksAt terminal equipment resourcesThe competition game loss is used for measuring efficiency loss caused by competition of a plurality of subtasks on terminal equipment resources. When multiple tasks compete for the same computing resources at the same time, delays, task failures, or reduced computing resource utilization may occur.
Characterizing tasksRefers to a variable that measures the priority of different tasks. Dynamic priority means that the priority of tasks can be adjusted over time or over environmental changes. For example, the priority of urgent tasks may be raised, while tasks of low importance may be deferred to ensure a reasonable allocation of resources.
At the same time, the method comprises the steps of,And the characteristic device adaptability factor is used for measuring the adaptability of terminal device resources to subtasks and representing the capability of the device to adapt to different task demands. 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 computations. The higher this factor, the more capable the device is to accommodate different tasks.
Characterizing terminal equipment resourcesRefers to a variable that measures whether or not the performance of the terminal device has stabilized during past operation. If the fluctuation of parameters such as calculation speed, response time and the like of the device in different time periods is small, the consistency of the historical performance of the device is high, which means that the task can be executed more reliably.
The communication stability factor is characterized and is used for measuring the communication quality between the terminal equipment and the cloud or other equipment. If the communication stability factor is higher, the network connection is stable, the data transmission delay is low, and the data loss or the transmission interruption is not easy to occur, so that the normal execution of the task is ensured.
The characterization data fidelity assurance factor represents a parameter that is used to measure whether the data can maintain integrity and accuracy during transmission and processing. If the data fidelity guarantee factor is higher, the data is less interfered in the transmission process, the error is lower, and the reliability of the final calculation result is higher.
And characterizing the inter-task co-factors to represent the degree of co-operation among a plurality of tasks. Under the condition of higher synergistic factors, resources can be efficiently shared among different tasks, resource conflict is reduced, and the overall efficiency of the system is improved. For example, on a manufacturing line, different tasks may share sensor data, thereby optimizing the overall production flow.
The weight factors respectively for equipment adaptability, historical performance consistency, communication stability and data fidelity guarantee refer to weight values for adjusting the influence degree of the parameters on final calculation. Different application scenarios may require different weights, for example, in a system with higher 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 be higher. Furthermore, the loss weight factor of inter-task cofactorsThe method is used for measuring the influence of the cooperative degree between tasks on the overall loss, and if the cooperative capacity of the tasks is insufficient, the resource utilization efficiency is reduced, so that the corresponding loss weight factors are required to be set for optimization.
The inter-task cofactor is calculated as follows: Wherein, the method comprises the steps of, Characterizing resources at a terminal deviceThe total number of subtasks scheduled up,Characterization subtasksWith another subtaskIs matched with the similarity of (1)Belonging to the resources of terminal equipmentA set of upper scheduled subtasks.
First, the inter-task co-factor is a parameter for measuring the co-operation of a plurality of subtasks when they are executed on the terminal device resource, and it can reflect the degree of interaction between the tasks. The inter-task cofactor is calculated to optimize task scheduling, so that a plurality of tasks can efficiently share resources, resource waste is reduced, and overall execution efficiency is improved.
Wherein, the Characterizing resources at a terminal deviceThe total number of subtasks scheduled up refers to the number of subtasks running simultaneously on a particular terminal device. The terminal equipment resources comprise limited resources such as computing power, storage space, network bandwidth and the like, and when a plurality of subtasks run simultaneously, reasonable scheduling is needed to ensure that the utilization rate of the resources is maximized. For example, if a certain terminal device is capable of processing five sub-tasks simultaneously, and only three sub-tasks actually run, this means that resources are not fully utilized, and if the running sub-tasks exceed their processing capabilities, calculation delays or failures may be caused.
Characterization subtasksWith another subtaskMeaning that the variable is used to measure how tightly two subtasks are co-operating during execution. If two subtasks can share a computation result or data input, their cooperative 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 may share pre-processing data, thereby reducing duplicate computations and improving execution efficiency. Conversely, if two subtasks require independent data processing, and the cooperative similarity is low, the resource sharing degree between them is low, which may increase the calculation cost.
Belonging to the resources of terminal equipmentThe upper scheduled subtask set means that the subtasks involved in calculating the inter-task cofactor must be part of the set of tasks currently running on the terminal device. A subtask set refers to all tasks scheduled to run on a certain terminal device, not all tasks in the whole system. For example, if a certain terminal device is running four sub-tasks and the entire system has ten sub-tasks in total, then only the four tasks need to be considered in computing the co-factor, not all ten tasks. This limitation can guarantee the pertinence of the calculation, so that the task scheduling is more accurate.
The method comprises the steps of carrying out evaluation on computing capacity of the terminal equipment according to equipment performance of the terminal equipment, establishing a weak computing equipment performance protection identifier, carrying out load analysis on the terminal equipment within a preset period range, establishing a high load identifier, carrying out balanced compensation on task competition game analysis by utilizing the weak computing equipment performance protection identifier and the high load identifier, and establishing a second adaptation constraint according to a balanced compensation result.
Specifically, the computing capability evaluation refers to evaluating the capability of the terminal equipment to process tasks according to the performance parameters of the terminal equipment so as to reasonably distribute the computing tasks. For example, if a device has a high computational power, complex tasks may be allocated, while a device with a low computational power may only perform simple tasks, thereby improving the overall system operating efficiency.
The weak computing device performance protection flags are then established, meaning that if some of the terminal devices have low computing power, they are set with a special flag to prevent them from assuming too high a load of computing tasks. A weak computing device generally refers to a device with lower processor performance, less memory, or limited power consumption, such as a small sensor node or a low power embedded device. The role of the protection id is to limit the task allocation of such devices, ensuring that they do not suffer from performance degradation or even downtime due to overload calculations.
Then, the operation load condition of the terminal equipment is periodically evaluated according to the set time interval. The preset cycle range refers to a time window set by a person skilled in the art, for example, load detection is performed every ten minutes or every hour. The load analysis mainly focuses on the indexes such as CPU occupancy rate, memory utilization rate, data throughput and the like of the equipment so as to judge the current working state of the equipment. If a device is in a high load state for a long time, the stability of the system may be affected, and therefore, measures need to be taken to perform optimal scheduling.
Then, a high load identifier is established, namely if the terminal equipment detects continuous high load in the load analysis process, a high load identifier is allocated to the terminal equipment, the task scheduling system is reminded, and further allocation of calculation tasks to the equipment is avoided, so that resource exhaustion or task execution failure is prevented. For example, if the CPU usage of a device remains 90% for a long period of time, the device may no longer be able to take on a new computing task, and may be marked as busy by a high load flag, thereby optimizing the task allocation policy.
Further, the balance compensation of the task competition game analysis is performed by using the weak computing device performance protection identifier and the high load identifier, which means that the computing capacity and the current load condition of the device are comprehensively considered to optimize the task allocation scheme. Task competition game analysis is a game theory-based calculation method and aims to solve the problem that a plurality of tasks compete on limited calculation resources. The balanced compensation is to ensure that the computing resources of different devices can be optimally utilized by reasonably adjusting the allocation of tasks, so that the devices with weaker computing power are not overloaded, and the high-load devices are not overloaded to operate. For example, if a weak computing device needs to perform five tasks, but due to insufficient computing power, the allocation scheme may be adjusted to allow a device with greater computing power to take over two of the tasks, thereby achieving balanced compensation.
Finally, a second adaptation constraint is established according to the balance compensation result, which means that after the task competition game analysis is completed, the matching relationship between the task and the equipment is further optimized according to the balance compensation result. The second adaptation constraint is used for ensuring that task allocation is more reasonable and avoiding resource waste or calculation bottlenecks. For example, if a device is deemed suitable to perform a task in the last adaptation analysis, but the suitability of the device changes due to subsequent load increases, then the second adaptation constraint will re-evaluate the task allocation and adjust the resource usage policy to maintain the stability and efficiency of the system.
The method further comprises the steps of uploading time constraint, calculation complexity constraint, calculation demand constraint and task association constraint of the intelligent manufacturing task, obtaining the highest calculation capacity and the lowest calculation capacity of the terminal equipment, establishing granularity decomposition constraint according to the highest calculation capacity and the lowest calculation capacity, and performing task decomposition of the intelligent manufacturing task according to the granularity decomposition constraint, the time constraint, the calculation complexity constraint, the calculation demand constraint and the task association constraint to create M subtasks.
Specifically, the time constraints, the computational complexity constraints, the computational demand constraints, and the task association constraints of the intelligent manufacturing task are uploaded for subsequent analysis and processing. Intelligent manufacturing tasks refer to calculations or operations that need to be performed in an industrial production process, such as production scheduling, equipment control, data analysis, and the like. Time constraints mean that tasks must be completed within a specified time, e.g., the machining of a part must be completed within 20 minutes, otherwise the entire production flow is affected. The computational complexity constraint is a measure of the computational resources required for a task, and determines how much computational power is required for the task to complete, e.g., complex artificial intelligence model reasoning requires higher computational complexity, while simple temperature monitoring tasks have lower computational complexity. Computational demand constraints refer to the computational resources required for a task, including CPU, memory, storage, etc., e.g., a task may require high performance GPU computing, while another task requires only basic numerical operations. Task association constraints refer to interdependencies between different tasks, e.g. the output of a certain task may be the input of another task, so they have to be performed in a certain order.
The highest and lowest computing power of the terminal device is then obtained, meaning that the computing power detection is performed for all available terminal devices. The highest computing power refers to the power of the most computationally powerful device, such as a high performance computing server or industrial level edge computing node. The lowest computing power refers to the device in the system that has the least computing power, such as a low power sensor or embedded device. The purpose of acquiring the two extreme values is to evaluate the overall computing power range of the system and provide basis for subsequent task decomposition.
Then, the granularity decomposition constraint is established according to the highest computing power and the lowest computing power, which means that the decomposition granularity of the task is set according to the range of the computing power of the device. Granularity decomposition constraints determine how many subtasks a task is split into, and the amount of computation per subtask. If the computing power range is large, which means that strong computing equipment is available, the task can be split into finer granularity, so that a plurality of equipment are processed in parallel, and the overall efficiency is improved. For example, if a task requires 100 units of computation, while the highest computing power device can handle 50 units per second, while the lowest computing power device can only handle 5 units per second, the system may split the task into multiple different sized sub-tasks, each assigned to a different computing power device, to achieve optimal computing scheduling.
And finally, performing task decomposition of the intelligent manufacturing task according to granularity decomposition constraint, time constraint, calculation complexity constraint, calculation demand constraint and task association constraint to create M subtasks, and splitting the intelligent manufacturing task into M subtasks so as to be more reasonably distributed to different terminal devices for execution. Task decomposition is an important means for intelligent manufacturing systems to optimize computing resource utilization. For example, a large data analysis task may be split into multiple parallel computing subtasks, each performed by a different device, thereby increasing the computing speed. If the time constraint is tight, tasks may be preferentially allocated to high-computing-capacity devices, and if the computing demand is high, task allocation of low-computing-capacity devices may be reduced as much as possible to ensure that the tasks are completed successfully. Table 1 is a table of data records of the most recent intelligent manufacturing task and terminal equipment computing capabilities.
TABLE 1 data recording table of last intelligent manufacturing task and terminal device computing power
The method comprises the steps of performing sub-task execution monitoring on the terminal equipment, establishing an execution monitoring result, performing sub-task execution hysteresis analysis based on the execution monitoring result, establishing an execution hysteresis identification, establishing optimizing constraint according to the execution hysteresis identification, and performing optimizing optimization of the execution scheme according to the optimizing constraint.
Specifically, the execution monitoring of the subtasks performed on the terminal device refers to real-time tracking and recording of the execution situation of the subtasks by the terminal device, for example, monitoring key indexes such as execution time of the tasks, consumption of computing resources, delay of data transmission and the like. The sorting and storing of these monitoring data establishes the execution of the monitoring results for subsequent analysis. For example, if a certain terminal device is executing a subtask, the CPU utilization is always close to 100%, and the CPU utilization of another device is executing the same task is only 50%, this difference will be recorded to determine whether the task allocation policy needs to be adjusted.
And then, performing execution hysteresis analysis of the subtasks based on the execution monitoring result, establishing an execution hysteresis identification, and analyzing the execution efficiency of the tasks by utilizing the data of the execution monitoring. Execution delay refers to a delay condition of subtasks in the execution process, such as unexpected task execution time, task execution progress lagging a scheduling plan, and the like. Execution delay may be caused by a variety of factors, such as insufficient computing resources, network communication delays, or unreasonable task scheduling. The execution hysteresis identification is a label of the task delay conditions and is used for optimizing the task scheduling strategy. For example, a task lag caused by too high load of a certain terminal device may allocate an execution lag identifier to the device, so as to remind the task scheduling system to reduce task allocation to the device.
And then, establishing optimizing constraint according to the execution hysteresis identification, and optimizing the execution scheme by using the optimizing constraint. The optimizing constraint refers to a rule set based on the execution delay identification for optimizing task allocation so as to ensure that the task can be executed more efficiently. For example, if a device is determined to be too high in load due to execution of a hysteresis flag, it may be restricted from receiving new tasks or some tasks may be reassigned to devices with lower loads. The optimizing optimization refers to adjusting the whole task execution scheme on the basis of optimizing constraint so as to improve the task execution efficiency. For example, if some devices are found to have execution delay for a long time, and other devices still have a calculation margin, the optimized scheme may redistribute tasks, so that the overall execution time is shortened, and the utilization rate of the calculation resources is improved.
The method further comprises the steps of carrying out synchronous execution influence analysis of the linkage task according to the hysteresis identification, generating hysteresis time constraint according to an influence analysis result, obtaining task demand constraint of a hysteresis subtask according to the hysteresis identification, and carrying out succession optimization of terminal equipment according to the hysteresis time constraint and the task demand constraint so as to take over optimization of an execution scheme of the succession optimization result.
Specifically, the synchronous execution influence analysis of the linkage task is performed according to the hysteresis identification. Hysteresis identification is used to identify subtasks whose execution times are beyond expectations. A linked task refers to a plurality of interdependent tasks, e.g., the output of one task may be the input of another task, and thus, if a certain task is delayed, execution of a subsequent task may be affected. Synchronous performance impact analysis refers to evaluating such impact, for example, if a task is expected to complete within 10 minutes, but is actually performed for 15 minutes, then downstream tasks that rely on the task may also be impacted.
Generating a lag time constraint based on the impact analysis results 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.
And then, acquiring task demand constraint of the hysteresis subtask according to the hysteresis identification, and carrying out succession optimization of the terminal equipment according to the hysteresis time constraint and the task demand constraint. The lag subtasks refer to tasks that affect overall progress due to execution lag, and task demand constraints refer to computing resources, storage space, network bandwidth, etc. that are required by these tasks when executed. For example, if a subtask requires high computational power, but the assigned device computational power is low, resulting in a task lag, its computational resource demand constraints may be adjusted to better match the appropriate computational resources during the succession optimization process. Successor optimization refers to finding terminal devices that are better suited to perform these lag tasks, and possible strategies include transferring the tasks to more computationally powerful devices, reducing the computational complexity of the tasks, or adjusting the task scheduling order to reduce overall latency. For example, if a device is delayed in tasks due to insufficient computing power and another device is currently loaded less, tasks may be reassigned to the latter to speed up execution progress.
Finally, the optimization of the scheme is executed by the successor optimizing result, which means that the whole executing strategy is optimized according to the new task allocation scheme after the successor optimizing is completed. The goal of the optimization is to ensure that all tasks can be completed in the shortest time while maximizing the utilization of computing resources. For example, in an intelligent manufacturing environment, if a certain task is delayed due to too high a load of the device, the device with lower load can be found by taking over the optimization, and the task is redistributed, so that the whole execution time is shortened, and the production efficiency is optimized.
The method comprises the steps of judging whether the optimizing adaptation value of the terminal equipment with the sub-task execution completed meets a preset threshold value or not, and outputting the terminal equipment with the highest optimizing adaptation value as a succession optimizing result if the optimizing adaptation value of the terminal equipment with the sub-task execution completed meets the preset threshold value.
Specifically, the terminal device with the completed execution of the subtasks refers to a computing node which has completed a subtask, and the current task is just completed, and may or may not have a subsequent task. Judging whether the optimizing adaptation value of the terminal equipment with the subtask execution completed meets a preset threshold value or not, wherein the optimizing adaptation value is an index for measuring the quality of the terminal equipment execution task and can comprise comprehensive scores of a plurality of factors including task execution time, calculation resource utilization rate, energy consumption efficiency and the like. The preset threshold is a set minimum standard for judging whether the execution performance of the device meets the requirement. For example, if the full score of the optimizing fit value is 100% and the preset threshold value is 70%, only devices with optimizing fit values greater than or equal to 70% will be considered as acceptable performing devices. The process of judging whether the optimizing adaptation value meets the preset threshold value can help to screen out equipment with better performance, and avoid the task being distributed to equipment with poorer execution capacity.
And then, if the optimizing adaptation value of the terminal equipment with the sub-task execution completed meets a preset threshold value, outputting the terminal equipment with the highest optimizing adaptation value as a succession optimizing result. If the optimizing adaptation value of one terminal device reaches the minimum requirement set by the system, the device with the highest optimizing adaptation value is selected as the best candidate for executing the succession task in all the devices meeting the requirement. For example, if three terminal devices complete the subtask, 75%, 85% and 90% of the optimizing adaptation values are obtained respectively, and the preset threshold value is 70%, then the terminal device corresponding to the 90% of the highest optimizing adaptation value is selected as the final successor optimizing result. The output of the successor optimizing result may be used for subsequent task scheduling, e.g., if there is currently a new subtask to be executed, it may be preferentially allocated to this high-adaptation value device to ensure more efficient execution.
Further, the method comprises the steps of calculating interrupt loss of the terminal equipment with the sub-tasks not completed if the optimizing adaptation value of the terminal equipment with the sub-tasks not completed cannot meet the preset threshold value, and reconstructing succession optimizing results after compensating the optimizing adaptation value of the terminal equipment with the sub-tasks not completed according to the interrupt loss.
Specifically, if the optimizing adaptation value of the terminal equipment with the sub-task being executed is unable to meet the preset threshold, the interrupt loss of the terminal equipment with the sub-task not being executed is calculated. The optimizing adaptation value is an index for measuring the quality of the task executed by the equipment. If the value is lower than the preset threshold set by the system, the execution performance of the equipment is not ideal, and the problems of low calculation efficiency, overlong task execution time or low resource utilization rate may exist. In this case, the interrupt loss of the terminal device for which the subtask is not performed to completion is calculated. A terminal device that does not perform a sub-task to complete refers to a device that fails to complete the task, such as a device that interrupts the task due to insufficient computing power, network delay, or system failure. Interrupt loss is an indicator of the negative impact of task incompletion, and may include the waste of computing resources, the extension of task execution time, and the linkage impact on other tasks.
And then, after compensating the optimizing adaptation value of the terminal equipment with the sub-tasks not completed according to the interrupt loss, reconstructing and replacing the optimizing result. Aiming at equipment which does not complete the task, the optimizing adaptation value is adjusted according to the interrupt loss of the equipment so as to make up the influence caused by the task incompletion. For example, if a device is not tasked due to insufficient computing resources, but its communication stability and energy consumption efficiency are high, a certain optimization adaptation value compensation may be given to measure its comprehensive capacity more fairly. The compensated optimizing adaptation value can be used for optimizing task scheduling, so that proper equipment can be reasonably matched when the tasks are redistributed. The reconstruction succession optimizing result means that after compensation adjustment, the optimal task succession scheme is recalculated, and the most appropriate equipment is selected to execute the unfinished task.
In summary, the AloT cloud edge intelligent control method for the industrial Internet of things has the following technical effects that by achieving the technical targets of intelligent task scheduling and optimal allocation under a cloud-edge-end cooperative computing architecture, the technical effects of improving task execution efficiency, reducing computing delay, optimizing computing resource utilization rate and enhancing data security are achieved.
The second embodiment of the application provides a AloT cloud side intelligent control system for the industrial internet of things, referring to fig. 2, based on the same inventive concept as that of the AloT cloud side intelligent control method for the industrial internet of things in the foregoing embodiment, which further includes a collaborative architecture creation module 11 for creating a cloud-side collaborative architecture, the cloud-side collaborative architecture includes a cloud center, an edge computing node and a terminal device, acquiring an intelligent manufacturing task from the cloud center, an adaptation analysis module 12 for acquiring device performance and device function of the terminal device at the edge computing node, performing adaptation analysis of the intelligent manufacturing task according to the device performance and device function, creating a first adaptation constraint, a task decomposition module 13 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, creating M sub-tasks, a competition game analysis module 14 for performing competition analysis of the M sub-tasks by using the cloud center, creating a second adaptation constraint, and a scheme generation module 15 for performing balance constraint analysis of the intelligent manufacturing scheme on the first adaptation constraint and the second adaptation constraint.
Further, the AloT cloud side intelligent control system facing the industrial Internet of things is further used for activating a task competition game analysis function of a cloud center and executing task competition game analysis of M subtasks, game features of the 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.
Further, the AloT cloud edge intelligent control system facing the industrial Internet of things is further used for uploading time constraint, calculation complexity constraint, calculation demand constraint and task association constraint of the intelligent manufacturing task, acquiring the highest calculation capacity and the lowest calculation capacity of the terminal equipment, establishing granularity decomposition constraint according to the highest calculation capacity and the lowest calculation capacity, and performing task decomposition of the intelligent manufacturing task according to the granularity decomposition constraint, the time constraint, the calculation complexity constraint, the calculation demand constraint and the task association constraint to create M subtasks.
The AloT cloud edge intelligent control system facing the industrial Internet of things is further used for performing sub-task execution monitoring on the terminal equipment, establishing an execution monitoring result, performing sub-task execution hysteresis analysis based on the execution monitoring result, establishing an execution hysteresis identification, establishing optimizing constraint according to the execution hysteresis identification, and performing optimizing optimization of the execution scheme according to the optimizing constraint.
Furthermore, the AloT cloud edge intelligent control system facing the industrial Internet of things is further used for performing synchronous execution influence analysis of linked tasks according to the hysteresis identification, generating hysteresis time constraint according to influence analysis results, 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 take over optimization of an execution scheme of the optimization result.
Further, the AloT cloud edge intelligent control system facing the industrial Internet of things is further used for judging whether the optimizing adaptation value of the terminal equipment with the sub-task being executed meets a preset threshold or not, and outputting the terminal equipment with the highest optimizing adaptation value as a succession optimizing result if the optimizing adaptation value of the terminal equipment with the sub-task being executed meets the preset threshold.
Further, the AloT cloud edge intelligent control system facing the industrial Internet of things is further used for calculating interrupt loss of the terminal equipment with the sub-tasks not completed by execution if the optimizing adaptation value of the terminal equipment with the sub-tasks completed by execution cannot meet the preset threshold value, and reconstructing and taking over the optimizing result after compensating the optimizing adaptation value of the terminal equipment with the sub-tasks not completed by execution according to the interrupt loss.
In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the AloT cloud edge intelligent control method and the specific example facing the industrial internet of things in the first embodiment are also applicable to the AloT cloud edge intelligent control system facing the industrial internet of things in the first embodiment, and by the foregoing detailed description of the AloT cloud edge intelligent control method facing the industrial internet of things, those skilled in the art can clearly know the AloT cloud edge intelligent control system facing the industrial internet of things in the first embodiment, so that the description is omitted herein for brevity.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalent techniques thereof, the present application is also intended to include such modifications and variations.
Claims (7)
1. AloT 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 AloT 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 AloT 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 AloT 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 AloT 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 AloT 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. AloT cloud edge end intelligent control system for industry thing networking is characterized in that the steps for implementing AloT 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.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510431961.6A CN119937436B (en) | 2025-04-08 | 2025-04-08 | AloT cloud edge end intelligent control method and system for industrial Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510431961.6A CN119937436B (en) | 2025-04-08 | 2025-04-08 | AloT cloud edge end intelligent control method and system for industrial Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119937436A CN119937436A (en) | 2025-05-06 |
| CN119937436B true CN119937436B (en) | 2025-07-29 |
Family
ID=95536844
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510431961.6A Active CN119937436B (en) | 2025-04-08 | 2025-04-08 | AloT cloud edge end intelligent control method and system for industrial Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119937436B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120670176B (en) * | 2025-08-21 | 2025-11-14 | 苏州元脑智能科技有限公司 | A memory resource scheduling method and electronic device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107844374A (en) * | 2017-11-02 | 2018-03-27 | 上海携程商务有限公司 | The task executing method of terminal device, device, electronic equipment, storage medium |
| CN110347492A (en) * | 2019-07-15 | 2019-10-18 | 深圳前海乘势科技有限公司 | Distributed task dispatching method and apparatus based on time parameter method |
| CN118585405A (en) * | 2024-08-06 | 2024-09-03 | 中国南方电网有限责任公司超高压输电公司贵阳局 | Computing power allocation method based on cloud-edge-end intelligent collaboration |
| CN119512763A (en) * | 2024-12-02 | 2025-02-25 | 湖南科技学院 | A self-balancing method for load fluctuation of AI server based on recursive game network |
| CN119739504A (en) * | 2024-11-26 | 2025-04-01 | 中国空间技术研究院 | Cloud-edge collaborative processing system based on network computing technology |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8353763B2 (en) * | 2003-03-31 | 2013-01-15 | Cantor Index, Llc | System and method for betting on a participant in a group of events |
| US20140378201A1 (en) * | 2013-06-24 | 2014-12-25 | Volodymyr Kolomiiets | System for lottery games |
| CN117742971B (en) * | 2023-12-29 | 2024-05-03 | 广东全芯半导体有限公司 | Optimization method and system for main control chip acceleration operation |
| CN119450586B (en) * | 2024-11-20 | 2025-07-15 | 上海酷潮科技股份有限公司 | A 5G intelligent networking method and system based on edge computing |
-
2025
- 2025-04-08 CN CN202510431961.6A patent/CN119937436B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107844374A (en) * | 2017-11-02 | 2018-03-27 | 上海携程商务有限公司 | The task executing method of terminal device, device, electronic equipment, storage medium |
| CN110347492A (en) * | 2019-07-15 | 2019-10-18 | 深圳前海乘势科技有限公司 | Distributed task dispatching method and apparatus based on time parameter method |
| CN118585405A (en) * | 2024-08-06 | 2024-09-03 | 中国南方电网有限责任公司超高压输电公司贵阳局 | Computing power allocation method based on cloud-edge-end intelligent collaboration |
| CN119739504A (en) * | 2024-11-26 | 2025-04-01 | 中国空间技术研究院 | Cloud-edge collaborative processing system based on network computing technology |
| CN119512763A (en) * | 2024-12-02 | 2025-02-25 | 湖南科技学院 | A self-balancing method for load fluctuation of AI server based on recursive game network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119937436A (en) | 2025-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118656181A (en) | An efficient high-throughput computing task scheduling method | |
| CN118567867B (en) | Cloud computing resource optimization method and system | |
| CN119537032B (en) | Large model reasoning scheduling method based on off-network computing power server | |
| US20120102503A1 (en) | Green computing via event stream management | |
| CN111752710B (en) | Data center PUE dynamic optimization method, system and equipment and readable storage medium | |
| CN119937436B (en) | AloT cloud edge end intelligent control method and system for industrial Internet of things | |
| CN119621351A (en) | Computer intelligent service management system and method based on network big data | |
| CN120066720A (en) | Intelligent scheduling system and method based on calculation force demand prediction | |
| CN119316292B (en) | Policy selection method for node backup in multi-domain network | |
| CN119960991A (en) | A strongly adaptive distributed data distribution method supporting dynamic expansion | |
| CN111026519A (en) | Distributed task priority scheduling method and system and storage medium | |
| CN116795534A (en) | Performance dynamic adjustment method and system based on negative feedback mechanism of power Internet of Things | |
| CN120123099A (en) | A resource scheduling method, system, device and medium in an edge cloud computing platform | |
| US20160313780A1 (en) | Multivariable control for power-latency management to support optimization of data centers or other systems | |
| CN120560939A (en) | Server power consumption management method, device, electronic device and storage medium | |
| CN120386792A (en) | Real-time database distributed query optimization method based on in-memory computing | |
| CN120088056A (en) | A method for designing assembly lines based on the small business credit factory model | |
| CN120256083A (en) | Workflow parallel computing execution method, system, terminal device and storage medium | |
| CN119647593A (en) | A method, device, terminal device and storage medium for deducing a time series production model | |
| CN120197911B (en) | Intelligent scheduling method, system, equipment and medium based on equipment use frequency | |
| TWI842325B (en) | Cloud smart workstation | |
| CN120653406B (en) | Task scheduling method, system, storage medium and computer program product | |
| CN120634186B (en) | Multi-machine collaborative operation control method and system based on general sense calculation control technology | |
| CN113391928B (en) | Hardware resource allocation method and device, electronic equipment and storage medium | |
| CN118170550B (en) | Node water level line threshold value adjusting method and device and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |