Layered computing system and method of collaborative architecture
Through a collaborative architecture hierarchical computing system, the computing power of edge devices is used to reduce the burden on cloud computing platforms, solve the problems of data processing delays and uneven allocation of computing resources in the power Internet of Things, and improve the overall computing efficiency and intelligence level. .
Patent Information
- Application Number
- CN202411127560.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-12-03
AI Technical Summary
Traditional power Internet of Things architectures face problems such as data processing delays, network bandwidth limitations and uneven allocation of computing resources. Cloud computing provides limited computing power, while edge computing power is not enough to meet the needs.
A layered computing system adopts a collaborative architecture, through the collaborative work of data acquisition devices, local decision-making devices, edge execution devices and cloud servers, process and initial analysis of data in real time, reduce data transmission volume and latency, and conduct complex analysis and global analysis in the cloud. Optimize, rationally allocate computing tasks, make full use of the computing power of edge devices, and reduce the burden on cloud computing platforms.
It improves the intelligence of cloud-edge collaborative computing of the Internet of Things in the Internet of Things, improves the overall computing efficiency, reduces the pressure on computing nodes, realizes adaptive task hierarchical allocation, and reduces computing costs.
Smart Images

Figure CN119065841A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and in particular to a hierarchical computing system and method of a collaborative architecture. Background Art
[0002] With the development of intelligent power system, power Internet of Things (IoT) technology has been widely used. However, the traditional power Internet of Things architecture faces problems such as data processing delay, network bandwidth limitation and uneven distribution of computing resources. Cloud computing provides powerful computing power, but there is data transmission delay; edge computing can provide low-latency services, but the computing power is limited. Therefore, how to achieve efficient collaboration between cloud computing and edge computing has become the key to solving the above problems. Summary of the invention
[0003] The present invention provides a hierarchical computing system and method with a collaborative architecture to fully utilize the computing power of edge devices, reduce the burden on the cloud computing platform, improve the overall computing efficiency of the system, and enhance the intelligence level of cloud-edge collaborative computing of the power Internet of Things.
[0004] According to one aspect of the present invention, a hierarchical computing system of a collaborative architecture is provided, the system comprising:
[0005] A data collection device, used to collect power equipment data of the terminal and send the power equipment data to a local decision-making device;
[0006] A local decision-making device is used to receive the power equipment data, perform decision processing on the power equipment data, and distribute the power equipment data after decision to the edge execution device and the cloud server respectively;
[0007] An edge execution device, configured to process the received power equipment data according to the equipment execution command generated by the local decision-making device, and send the equipment processing data obtained after the data processing to the cloud server through the local decision-making device;
[0008] The cloud server is used to make decisions based on the data processed by the device, obtain cloud decision results, and send the cloud decision results to the edge execution device through the local decision device.
[0009] According to another aspect of the present invention, a hierarchical computing method of a collaborative architecture is provided, the method comprising:
[0010] Collecting the power equipment data of the terminal through the data collection device, and sending the power equipment data to the local decision-making device;
[0011] The power equipment data is received through a local decision-making device, and the power equipment data is processed for decision making respectively, and the power equipment data after the decision is distributed to the edge execution device and the cloud server respectively;
[0012] Processing the received power equipment data according to the equipment execution command generated by the local decision-making device through the edge execution device, and sending the equipment processing data obtained after the data processing to the cloud server through the local decision-making device;
[0013] Through the cloud server, decision processing is performed according to the device processing data to obtain cloud decision results, and the cloud decision results are sent to the edge execution device through the local decision device.
[0014] The technical solution of the embodiment of the present invention collects the power equipment data of the terminal through a data acquisition device, and sends the power equipment data to a local decision-making device. The power equipment data is received through the local decision-making device, and the power equipment data is respectively processed for decision-making, and the power equipment data after the decision is respectively distributed to the edge execution device and the cloud server. The edge execution device processes the received power equipment data according to the device execution command generated by the local decision-making device, and sends the device processing data obtained after the data processing to the cloud server through the local decision-making device. Through the cloud server, decision processing is performed according to the device processing data to obtain the cloud decision result, and the cloud decision result is sent to the edge execution device through the local decision-making device. By reasonably allocating the computing tasks of the edge execution device and the cloud server, the computing power of the edge device is fully utilized, the burden of the cloud computing platform is reduced, the overall computing efficiency of the system is improved, and the intelligence level of the cloud-edge collaborative computing of the power Internet of Things is improved.
[0015] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0017] Figure 1 is a structural diagram of a hierarchical computing system of a collaborative architecture provided according to Embodiment 1 of the present invention;
[0018] Figure 2 is an overall architecture diagram of a hierarchical computing system of a collaborative architecture provided according to Embodiment 1 of the present invention;
[0019] Figure 3 is a flowchart of a hierarchical computing method of a collaborative architecture provided in Embodiment 2 of the present invention;
[0020] Figure 4 It is a schematic diagram of the structure of an electronic device for implementing the hierarchical computing method of the collaborative architecture according to an embodiment of the present invention. DETAILED DESCRIPTION
[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0023] Embodiment 1
[0024] Figure 1 The first embodiment of the present invention provides a structure diagram of a hierarchical computing system with a collaborative architecture. This embodiment is applicable to the case where computing tasks are divided into layers and divided into different tasks. Figure 1 As shown, the system includes:
[0025] The data collection device 101 is used to collect the power equipment data of the terminal and send the power equipment data to the local decision-making device;
[0026] The local decision-making device 102 is used to receive the power equipment data, perform decision processing on the power equipment data, and distribute the power equipment data after decision to the edge execution device and the cloud server respectively;
[0027] The edge execution device 103 is used to process the received power equipment data according to the device execution command generated by the local decision-making device, and send the device processing data obtained after the data processing to the cloud server through the local decision-making device;
[0028] The cloud server 104 is used to perform decision processing based on the device processing data, obtain cloud decision results, and send the cloud decision results to the edge execution device through the local decision device.
[0029] The technical solution of the embodiment of the present invention collects the power equipment data of the terminal through a data acquisition device, and sends the power equipment data to a local decision-making device. The power equipment data is received through the local decision-making device, and the power equipment data is respectively processed for decision-making, and the power equipment data after the decision is respectively distributed to the edge execution device and the cloud server. The edge execution device processes the received power equipment data according to the device execution command generated by the local decision-making device, and sends the device processing data obtained after the data processing to the cloud server through the local decision-making device. Through the cloud server, decision processing is performed according to the device processing data to obtain the cloud decision result, and the cloud decision result is sent to the edge execution device through the local decision-making device. By reasonably allocating the computing tasks of the edge execution device and the cloud server, the computing power of the edge device is fully utilized, the burden of the cloud computing platform is reduced, the overall computing efficiency of the system is improved, and the intelligence level of the cloud-edge collaborative computing of the power Internet of Things is improved.
[0030] The present invention innovatively combines the advantages of cloud computing and edge computing to build an efficient hierarchical computing architecture. Real-time data processing and preliminary analysis are performed at the edge layer, reducing data transmission volume and latency; complex data analysis and global optimization are performed in the cloud, improving overall performance and intelligence level; the cloud-based task optimization model and local database are added to enhance the cloud-edge linkage computing capability, realize adaptive hierarchical task allocation, and reduce the pressure on computing nodes.
[0031] Figure 2 The overall architecture diagram of the layered computing system of the collaborative architecture is as follows: Figure 2 As shown:
[0032] The hierarchical computing system of the collaborative architecture can be divided into two parts: cloud collaborative computing architecture and hierarchical optimization model. First, the power equipment data will be sent from the power equipment and sensors at the terminal layer, and the data acquisition equipment at the edge layer will collect real-time data. After preprocessing, it will be uploaded to the local decision-making device for decision-making. After the local decision-making device at the edge layer performs rapid response calculations, the device execution command will be fed back to the edge execution device at the terminal layer in a timely manner, and the processed power equipment data will be transmitted to the cloud server; the cloud server has powerful computing and storage functions, and is mainly responsible for storing, deeply analyzing and processing massive data at the edge. The final cloud decision result will be transmitted back to the local decision-making device at the edge. The analysis result is generally optimization suggestions, decisions and warnings. Finally, the cloud service makes corresponding decisions based on the analysis results and returns them to the edge execution device.
[0033] The system also includes a task optimization model, which is used to receive the task case data sent by the cloud server and perform model training according to the task case data.
[0034] In the layered and graded optimization architecture, the cloud server will input relevant case data into the task optimization model for training, and transmit the optimized data back to the cloud server to assist the cloud server in performing in-depth analysis calculations.
[0035] The trained task optimization model is also used to: receive the power equipment data sent by the local decision-making device; classify the power equipment data in layers, determine the first device data sent to the edge execution device and the second device data sent to the cloud server in the power equipment data, and determine the data labels corresponding to the power equipment data.
[0036] Specifically, after the task optimization model is trained, it can perform adaptive hierarchical classification processing on the power equipment data uploaded by the edge end, and determine from the power equipment data which first equipment data is calculated by the edge execution device and which tasks are processed by the cloud server, so that the system can reach the overall optimal state. The task hierarchical optimization model allocates tasks to the edge layer and the cloud layer, and sends the computing tasks originally belonging to the cloud layer to the edge layer, reducing the computing cost of the cloud.
[0037] Optionally, the system further includes a local database for receiving data tags corresponding to the power equipment data and storing the data tags.
[0038] Specifically, the task optimization model and the local database work together to determine the data tags corresponding to the power equipment data, and transmit the data tags to the local database at the edge, so that most computing tasks can be solved at the edge layer or even the terminal layer, reducing data processing delays, alleviating network bandwidth pressure, and reasonably allocating computing resources to realize the intelligent cloud-edge collaborative computing of the power Internet of Things.
[0039] The edge execution device is also used to: obtain the data tag in the local database; and determine the cloud decision result corresponding to the power equipment data based on the data tag.
[0040] Specifically, since the calculation of the task hierarchical optimization model is performed on the cloud server, in order to further reduce the cloud computing cost, the calculation results are stored in the local database of the edge layer in the form of tags. When the edge execution device recognizes the corresponding tag, it stops uploading to the cloud server and makes a quick response to local decision-making. This not only improves the real-time and security of the calculation, but also realizes adaptive task hierarchical optimization.
[0041] The system also includes a task allocation optimization model, which is used to convert the nonlinear relationship between the tasks executed by each device into a linear relationship; based on the fusion of knowledge migration and linear relationships, the tasks executed by each device are optimized, the migration direction of the calculation tasks of the power equipment data is determined according to the error function, and based on the migration solution algorithm, the non-dominated sorting and congestion are determined to generate a parent population; offspring individuals are generated through genetic algorithm operations such as crossover mutation, and the parent and offspring individuals are merged to select a reinforcement learning environment; when the termination conditions are met, the solution set corresponding to each of the device execution tasks is output.
[0042] The computing tasks of the power Internet of Things are ever-changing. Each computing task has different properties, difficulties and goals, and there may be multiple goals. There are tens of thousands of such tasks, which undoubtedly brings great difficulty to the calculation of the power Internet of Things. The multi-objective optimization model for a single computing task of the power Internet of Things can be expressed as:
[0043] F MIN (x)=[f1(x),f2(x),...,f n (x)] T
[0044]
[0045] In the formula, R n is the target space, For decision-making space.
[0046] For the thousands of tasks in the power Internet of Things, the following models can be established:
[0047]
[0048] It contains C tasks. is the decision space, and the spatial dimension is n i , the number of decision spaces is equal to the number of tasks.
[0049] For the task space of the power Internet of Things, which is composed of multiple goals and multiple tasks, the difficulty of solving is very complicated. Solving only a single task will greatly increase the computing cost, and the tasks are not completely independent. In order to reduce the complexity and computing cost of computing tasks in the power Internet of Things, a task allocation optimization model based on migration mapping is proposed. The nonlinear relationship search in the model is converted into a linear relationship, and the knowledge migration is integrated to achieve parallel optimization between tasks; the direction of migration is determined according to the error function to ensure the effectiveness of optimization; finally, the optimal solution set is solved, and combined with the computing tasks of the power Internet of Things, it is hierarchically mapped to each port for subsequent processing.
[0050] Aiming at the complex multi-task problem existing in the power Internet of Things, the problem is first divided into task layer, relationship layer and solution layer. The task layer N = {1,2,3,…,n}, which contains n tasks; the relationship layer T = {1,2,3,…,n}, which contains n migration solutions; the solution layer S = {a j ,b j ,c j ,…,n j The task layer is grouped, and the evaluation function is used to determine the non-dominated order and crowding degree in the population composed of the task layer. The number of cycles is preset to ensure the appropriateness and stability of the algorithm. In the power Internet of Things, many tasks have similar properties. In order to reduce the computational cost, transfer learning is introduced here. In order to avoid the impact of negative transfer on the effect of transfer learning, the migration solutions are cross-fused, and the parent population is generated after re-evaluation to determine the non-dominated order and crowding degree. The offspring is generated through genetic algorithm operations such as crossover mutation, and the parent and offspring individuals are merged to select the reinforcement learning environment. Finally, after the termination condition is met, the solution set of each task is output.
[0051] Although the tasks in the power Internet of Things are similar, they are still different in nature. To achieve more efficient hierarchical task allocation, knowledge transfer is one-tenth, and the relationship between tasks determines whether the knowledge transfer is positive. The relationship between tasks in the power Internet of Things is generally nonlinear, and the nonlinear factor f is introduced here. NL To describe the relationship between migration solutions.
[0052] Tasks are source tasks and target tasks for each other. Task j and task k are randomly selected in the task layer, and populations J and K are obtained after populationization. The nonlinear factor is calculated by high-dimensional mapping. The efficiency of transfer learning between populations J and K can be evaluated by the loss function:
[0053]
[0054] In the formula, L is the linear relationship between populations J and K, and ψ is the mapping function. In high-dimensional space, linear relationships are related to linear combinations between populations. According to the properties of space, the above formula can be matrixed to obtain:
[0055] L = f NL Ψ(J) T
[0056]
[0057]
[0058] Transform the loss function Loss to obtain the nonlinear factor f NL :
[0059] f NL =KKe(P,P) T (Ke(J,J)Ke(J,J) T ) -1
[0060] The calculation process of the migration solution is as follows: According to the evaluation value, the best group Best in the population J is mapped to a high dimension and combined with the nonlinear factor f NL Multiplying them gives the migration solution:
[0061] t=f NL Ke(J,Best)
[0062] In order to ensure the performance of the migrated solution t in the solution set layer, the migrated solutions will be migrated to each other and cross-fused to ensure the accuracy of the migrated solution. j ,b j ,c j ,…,n j} is the Pareto optimal solution set.
[0063] Embodiment 2
[0064] Figure 3 This is a flowchart of a hierarchical computing method of a collaborative architecture provided in Embodiment 2 of the present invention. Figure 3 As shown, the method includes:
[0065] S201, collecting power equipment data of the terminal through a data collection device, and sending the power equipment data to a local decision-making device;
[0066] S202, receiving the power equipment data through a local decision-making device, performing decision processing on the power equipment data respectively, and distributing the power equipment data after the decision to an edge execution device and a cloud server respectively;
[0067] S203, performing data processing on the received power equipment data according to the equipment execution command generated by the local decision-making device through the edge execution device, and sending the equipment processing data obtained after the data processing to the cloud server through the local decision-making device;
[0068] S204: Decision processing is performed based on the device processing data through the cloud server to obtain a cloud decision result, and the cloud decision result is sent to the edge execution device through the local decision device.
[0069] The technical solution of the embodiment of the present invention collects the power equipment data of the terminal through a data acquisition device, and sends the power equipment data to a local decision-making device. The power equipment data is received through the local decision-making device, and the power equipment data is respectively processed for decision-making, and the power equipment data after the decision is respectively distributed to the edge execution device and the cloud server. The edge execution device processes the received power equipment data according to the device execution command generated by the local decision-making device, and sends the device processing data obtained after the data processing to the cloud server through the local decision-making device. Through the cloud server, decision processing is performed according to the device processing data to obtain the cloud decision result, and the cloud decision result is sent to the edge execution device through the local decision-making device. By reasonably allocating the computing tasks of the edge execution device and the cloud server, the computing power of the edge device is fully utilized, the burden of the cloud computing platform is reduced, the overall computing efficiency of the system is improved, and the intelligence level of the cloud-edge collaborative computing of the power Internet of Things is improved.
[0070] Embodiment 3
[0071] Figure 4A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0072] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0073] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0074] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the hierarchical computing of the method collaborative architecture.
[0075] In some embodiments, the hierarchical computing of the method collaborative architecture can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the hierarchical computing of the method collaborative architecture described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the hierarchical computing of the method collaborative architecture in any other appropriate manner (for example, by means of firmware).
[0076] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0077] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0078] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0079] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0080] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0081] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0082] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0083] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A hierarchical computing system with a collaborative architecture, characterized in that: include: A data collection device, used to collect power equipment data of the terminal and send the power equipment data to a local decision-making device; A local decision-making device is used to receive the power equipment data, perform decision processing on the power equipment data, and distribute the power equipment data after decision to the edge execution device and the cloud server respectively; An edge execution device, configured to process the received power equipment data according to the equipment execution command generated by the local decision-making device, and send the equipment processing data obtained after the data processing to the cloud server through the local decision-making device; The cloud server is used to make decisions based on the data processed by the device, obtain cloud decision results, and send the cloud decision results to the edge execution device through the local decision device.
2. The system according to claim 1, characterized in that The data acquisition device is also used for: The power equipment data is preprocessed, and the preprocessed power equipment data is sent to a local decision-making device for decision processing.
3. The system according to claim 1, characterized in that The system further comprises: The task optimization model is used to receive the task case data sent by the cloud server and perform model training according to the task case data.
4. The system according to claim 3, characterized in that The task optimization model is also used to: Receiving the power equipment data sent by the local decision-making device; The power equipment data is hierarchically classified to determine first device data sent to an edge execution device and second device data sent to a cloud server in the power equipment data, and data tags corresponding to the power equipment data are determined.
5. The system according to claim 1, characterized in that The system further comprises: The local database is used to receive the data tags corresponding to the power equipment data and store the data tags.
6. The system according to claim 5, characterized in that The edge execution device is also used for: Obtaining the data tag in the local database; Based on the data tag, a cloud-based decision result corresponding to the power equipment data is determined.
7. The system according to claim 1, characterized in that The system further comprises: A task allocation optimization model is used to convert the nonlinear relationship between the tasks executed by each device into a linear relationship; Based on the fusion of knowledge migration and linear relationship, the execution tasks of each of the devices are optimized, the migration direction of the computing tasks of the power equipment data is determined according to the error function, and the parent population is generated after the non-dominated sorting and congestion are determined based on the migration solution algorithm; Generate offspring individuals through genetic algorithm operations such as crossover and mutation, merge parent and offspring individuals and select a reinforcement learning environment; When the termination condition is met, the solution set corresponding to the task executed by each device is output.
8. The system according to claim 7, characterized in that The migration solution algorithm is determined based on nonlinear factors, and the nonlinear factors are calculated by high-dimensional mapping.
9. The system according to claim 7, characterized in that The process of obtaining the nonlinear factor includes: Matrixing the error function to obtain a matrix error function; The matrix error function is transformed to obtain the nonlinear factor.
10. A hierarchical computing method of collaborative architecture, characterized in that: include: Collecting the power equipment data of the terminal through the data collection device, and sending the power equipment data to the local decision-making device; The power equipment data is received through a local decision-making device, and the power equipment data is processed for decision making respectively, and the power equipment data after the decision is distributed to the edge execution device and the cloud server respectively; Processing the received power equipment data according to the equipment execution command generated by the local decision-making device through the edge execution device, and sending the equipment processing data obtained after the data processing to the cloud server through the local decision-making device; Through the cloud server, decision processing is performed according to the device processing data to obtain cloud decision results, and the cloud decision results are sent to the edge execution device through the local decision device.
Citation Information
Cited By
Real-time data collaboration strategy control system, method and device based on cloud edge collaboration scene, computer equipment, storage medium and computer program product
CN119946087A
