A method and platform for allocating network resources at the edge of power grid under synchronous mapping

Abstract

The present invention discloses a method and platform for allocating network resources at the edge of a power grid under synchronous mapping, and relates to the technical field of power grid resource allocation. The method comprises: performing digital twin modeling on the power grid, obtaining a twin model of the power grid, and identifying multiple edge nodes; synchronizing the status information of multiple edge nodes, and outputting the status information of each edge node; obtaining a first request task, decomposing it, obtaining storage tasks and computing tasks, and predicting the required predicted storage resources and predicted computing resources; obtaining identification storage edge nodes and identification computing edge nodes according to the status information of each edge node; performing resource allocation on storage tasks and computing tasks, and obtaining resource allocation results. The technical problem that the network resources at the edge of the power grid are difficult to adjust according to the real-time status is solved. Through digital twin modeling and synchronization of real-time status information, the accurate allocation of network resources at the edge of the power grid is realized, and the technical effect of improving the utilization rate of power grid resources is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid resource allocation, and in particular to a method and platform for allocating power grid edge network resources under synchronous mapping. Background Art

[0002] In today's rapidly developing smart grid era, the number and complexity of grid edge nodes (such as microgrids, distributed energy storage systems, smart meters, etc.) have increased dramatically. These edge nodes are not only the key link in grid data collection and monitoring, but also undertake important functions such as data processing, storage and local decision-making, which are crucial to the safe and efficient operation of the grid. However, traditional grid resource allocation methods often rely on static planning and centralized management, which are difficult to adapt to the dynamic characteristics of grid edge resources, resulting in unbalanced resource allocation, inefficiency, and even possible grid operation risks. Therefore, how to achieve intelligent and dynamic allocation of grid edge network resources has become an important issue that needs to be solved in the field of smart grids. Summary of the invention

[0003] The present application provides a method and platform for allocating network resources at the edge of a power grid under synchronous mapping, which solves the technical problem that network resources at the edge of a power grid are difficult to adjust according to real-time status.

[0004] In view of the above problems, the present application provides a method and platform for allocating network resources at the edge of a power grid under synchronous mapping.

[0005] In a first aspect of the present application, a method for allocating network resources at the edge of a power grid under synchronous mapping is provided, the method comprising:

[0006] Perform digital twin modeling on the power grid, obtain the power grid twin model, and identify multiple edge nodes of the power grid twin model; synchronize the status information of the multiple edge nodes, and output the status information of each edge node, wherein the status information includes storage resource information and computing resource information of the edge node; obtain a first request task, decompose the first request task, obtain a storage task and a computing task, and predict the predicted storage resources and predicted computing resources required to execute the storage task and the computing task; obtain an identified storage edge node and an identified computing edge node according to the status information of each edge node, wherein the identified storage edge node is a set of edge nodes that meet the predicted storage resources, and the identified computing edge node is a set of edge nodes that meet the predicted computing resources; the power grid twin model allocates resources to the storage task and the computing task based on the identified storage edge node and the identified computing edge node, and obtains a resource allocation result.

[0007] A second aspect of the present application provides a network resource allocation platform for edge grids under synchronous mapping, the platform comprising:

[0008] A model building module, the model building module is used to perform digital twin modeling of the power grid, obtain a power grid twin model, and identify multiple edge nodes of the power grid twin model; a state information acquisition module, the state information acquisition module is used to synchronize the state information of the multiple edge nodes and output the state information of each edge node, wherein the state information includes storage resource information and computing resource information of the edge node; a decomposition module, the decomposition module is used to obtain a first request task, decompose the first request task, obtain a storage task and a computing task, and predict the predicted storage resources and predicted computing resources required to execute the storage task and the computing task; a node acquisition module, the node acquisition module is used to obtain an identification storage edge node and an identification computing edge node according to the state information of each edge node, wherein the identification storage edge node is a set of edge nodes that meet the predicted storage resources, and the identification computing edge node is a set of edge nodes that meet the predicted computing resources; a resource allocation module, the resource allocation module is used for the power grid twin model to allocate resources to the storage task and the computing task based on the identification storage edge node and the identification computing edge node, and obtain a resource allocation result.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, a digital twin model is built for the power grid, a power grid twin model is obtained, and multiple edge nodes of the power grid twin model are identified. Next, the state information of multiple edge nodes is synchronized, and the state information of each edge node is output, wherein the state information includes the storage resource information and computing resource information of the edge node. At the same time, the first request task is obtained, the first request task is decomposed, the storage task and the computing task are obtained, and the predicted storage resources and predicted computing resources required to execute the storage task and the computing task are predicted. Then, according to the state information of each edge node, the identification storage edge node and the identification computing edge node are obtained, wherein the identification storage edge node is a set of edge nodes that meet the predicted storage resources, and the identification computing edge node is a set of edge nodes that meet the predicted computing resources. Finally, the power grid twin model allocates resources to the storage task and the computing task based on the identification storage edge node and the identification computing edge node, and obtains the resource allocation result. The technical problem that the network resources at the edge of the power grid are difficult to adjust according to the real-time status is solved. Through digital twin modeling and real-time state information synchronization, the accurate allocation of network resources at the edge of the power grid is realized, and the technical effect of improving the utilization rate of power grid resources is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] 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.

[0012] Figure 1 A schematic diagram of a flow chart of a method for allocating network resources at the edge of a power grid under synchronous mapping provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the structure of a power grid edge network resource allocation platform under synchronous mapping provided in an embodiment of the present application.

[0014] Explanation of reference numerals: model building module 11, state information acquisition module 12, decomposition module 13, node acquisition module 14, resource allocation module 15. DETAILED DESCRIPTION

[0015] The present application solves the technical problem that it is difficult to adjust the edge network resources of the power grid according to the real-time status by providing a method and platform for allocating edge network resources of the power grid under synchronous mapping.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides a method for allocating network resources at the edge of a power grid under synchronous mapping, wherein the method comprises:

[0019] Perform digital twin modeling on the power grid, obtain the power grid twin model, and identify multiple edge nodes of the power grid twin model.

[0020] By collecting various types of data from the power grid, including but not limited to the physical structure of the power grid, equipment parameters, operating status (such as voltage, current, power, etc.), environmental factors (such as weather, temperature) and historical fault records, digital twin technology is used to build a virtual image of the power grid based on the collected data, that is, the power grid twin model. The power grid twin model can accurately reflect the actual operating status, dynamic characteristics and potential risks of the power grid, providing a solid foundation for subsequent resource allocation. Based on the power grid digital twin model, multiple edge nodes of the power grid can be identified. Edge nodes usually refer to those devices located at the edge of the power grid that are responsible for data collection, processing or control, such as smart meters, distributed energy systems (such as solar panels, wind turbines), energy storage devices, and smart terminals responsible for monitoring and control; by analyzing the equipment distribution, functional characteristics and connection relationships in the power grid twin model, multiple edge nodes can be automatically identified. These edge nodes are the basic units for power grid resource allocation.

[0021] Furthermore, the method further comprises:

[0022] A fault recovery mechanism is set in the power grid twin model; the storage task and the computing task are monitored respectively based on the resource allocation result, and when any edge node fails, the faulty edge node is identified; the power grid twin model uses the fault recovery mechanism to identify the updated edge node of the faulty edge node, and reallocates tasks and executes tasks according to the updated edge node.

[0023] A fault recovery mechanism is set up in the power grid twin model to ensure rapid response when a fault occurs and reduce the impact of the fault on the operation of the power grid. Based on the resource allocation results, the storage tasks and computing tasks are monitored separately. When any edge node fails, the power grid twin model can quickly identify the faulty edge node. At the same time, it evaluates the impact of the fault on the ongoing storage tasks and computing tasks and determines whether task redistribution is required. Using the fault recovery mechanism, the power grid twin model begins to search for available update edge nodes. These nodes should meet the storage and computing resource requirements and be able to take over the tasks of the faulty nodes. Considering the availability, performance, geographical location and other factors of the nodes, the most suitable update edge node is selected; according to the selected update edge node, the power grid twin model reallocates tasks, that is, transfers the storage tasks and computing tasks originally assigned to the faulty node to the update node. By setting up a fault recovery mechanism in the power grid twin model and monitoring and redistributing tasks based on the resource allocation results, the reliability and resilience of the power grid can be significantly improved.

[0024] The state information of the multiple edge nodes is synchronized, and the state information of each edge node is output, wherein the state information includes storage resource information and computing resource information of the edge node.

[0025] Through sensors, communication protocols or existing data interfaces, status information is collected from each edge node. The status information includes storage resource information and computing resource information of the edge node. Among them, storage resource information includes total storage capacity, used storage capacity, remaining storage capacity, etc.; computing resource information includes CPU usage, memory occupancy, processing capacity (such as the number of tasks processed per second), etc. This information reflects the computing power of the edge node and is an important basis for judging whether it can undertake new tasks, perform task scheduling and load balancing. The collected data is integrated into the power grid twin model to ensure that the status information of each edge node can be accurately reflected in the model. By synchronizing the status information of multiple edge nodes and outputting detailed storage resource information and computing resource information, the distribution and usage of power grid edge resources can be obtained in real time, so as to make reasonable resource allocation decisions.

[0026] A first request task is obtained, the first request task is decomposed, a storage task and a computing task are obtained, and predicted storage resources and predicted computing resources required to execute the storage task and the computing task are predicted.

[0027] After receiving the first request task (such as data processing, energy scheduling, etc.), the first request task is decomposed to obtain storage tasks and computing tasks. According to the storage tasks and computing tasks obtained after decomposition, resource prediction is performed to obtain predicted storage resources and predicted computing resources, wherein the predicted storage resources include total storage space requirements, read and write speed requirements, etc., and the predicted computing resources include CPU time, memory usage, network bandwidth requirements, etc. Specifically, the characteristics of the storage task, such as data volume, data type, storage cycle, etc., are analyzed, and the storage space size, read and write speed, etc. required to complete the storage task are predicted using historical data; the computational complexity, parallelism, dependencies, etc. of the computing task are analyzed, and the execution process of the computing task is simulated using performance evaluation tools or simulation software to predict the required CPU time, memory usage, network bandwidth, etc.

[0028] According to the status information of each edge node, an identification storage edge node and an identification computing edge node are obtained, wherein the identification storage edge node is a set of edge nodes that meet the predicted storage resources, and the identification computing edge node is a set of edge nodes that meet the predicted computing resources.

[0029] After obtaining the predicted resource requirements, the edge node set that can meet these requirements can be screened out according to the status information of each edge node. Specifically, those edge nodes with sufficient storage resources are identified as storage edge nodes, and those edge nodes with sufficient computing resources are identified as computing edge nodes.

[0030] The power grid twin model allocates resources to the storage task and the computing task based on the identified storage edge node and the identified computing edge node, and obtains a resource allocation result.

[0031] The power grid twin model can execute resource allocation decisions based on the screened identified storage edge nodes and identified computing edge nodes, assign storage tasks and computing tasks to appropriate edge node sets respectively, and thus obtain resource allocation results.

[0032] Furthermore, allocating resources to the storage task based on the identified storage edge node includes:

[0033] Based on the power grid twin model, the number of the identification storage edge nodes is obtained ; Initialize the number of edge nodes used for storage resource allocation, where the number of edge nodes used for storage resource allocation is less than the number ; in the amount stated The number of edge nodes used for storage resource allocation is optimized for the quantity constraint condition to obtain a first node quantity optimal solution; and storage resources are allocated to the storage task according to the first node quantity optimal solution.

[0034] Preferably, the number of identification storage edge nodes is obtained from the power grid twin model ; By initializing edge nodes, these edge nodes are used to allocate storage resources, and the number of edge nodes used to allocate storage resources is less than the number After determining the initial number of nodes, optimization algorithms such as greedy algorithms and genetic algorithms can be used to find the best number of nodes to allocate storage resources. The number constraint condition ensures that the optimization process does not exceed the total number of available nodes. After the optimization, the optimal solution for the first number of nodes is obtained. The optimal solution for the first number of nodes is the number of nodes that can maximize storage efficiency or minimize cost under given constraints. Storage resources are allocated according to the optimal solution for the first number of nodes.

[0035] Furthermore, the method for allocating resources to the computing task based on the identified computing edge node includes:

[0036] Based on the power grid twin model, the number of edge nodes identified and calculated is obtained. ; Initialize the number of edge nodes used for computing resource allocation, where the number of edge nodes used for computing resource allocation is less than the number ; in the amount stated The number of edge nodes used for computing resource allocation is optimized for the quantity constraint condition to obtain a second optimal solution for the number of nodes; and computing resources are allocated to the storage task according to the second optimal solution for the number of nodes.

[0037] Preferably, the number of edge nodes identified and calculated is obtained from the power grid twin model ; By initializing edge nodes, these edge nodes are used to allocate computing resources, and the number of edge nodes used for computing resource allocation is less than the number After determining the initial number of nodes, optimization algorithms such as greedy algorithms and genetic algorithms can be used to find the best number of nodes to allocate computing resources. The number constraint condition ensures that the optimization process does not exceed the total number of available nodes. After the optimization, the optimal solution for the second number of nodes is obtained. The optimal solution for the second number of nodes is the number of nodes that can maximize computing efficiency and minimize computing time or cost under given constraints. Storage resources are allocated according to the optimal solution for the first number of nodes.

[0038] Furthermore, the method for obtaining the resource allocation result further includes:

[0039] The task synergy of the storage task and the computing task is calculated respectively, and the storage task synergy and the computing task synergy are output, wherein the task synergy includes communication delay, bandwidth, load and protocol compatibility indicators; when the storage task synergy meets the preset synergy indicator or when the computing task synergy meets the preset synergy indicator, the synergy constraint condition is activated; the resource allocation result is verified according to the synergy constraint condition, the resource allocation result is optimized according to the verification result, and the optimized resource allocation result is output.

[0040] Preferably, task synergy includes communication delay, bandwidth, load and protocol compatibility indicators, wherein communication delay is used to evaluate the delay of data transmission related to storage tasks between edge nodes, bandwidth refers to whether the available bandwidth is sufficient to support the data transmission requirements of storage tasks, load is used to evaluate the current load of storage edge nodes, and protocol compatibility is applicable to confirming that the protocol required by the storage task is compatible with the protocol supported by the edge node; based on communication delay, bandwidth, load and protocol compatibility indicators, storage task synergy and computing task synergy are calculated respectively, and corresponding evaluation results are output; when storage task synergy or computing task synergy meets preset synergy indicators (preset synergy indicators are pre-set according to system requirements, performance requirements and resource availability, etc.), synergy constraints can be activated, and synergy constraints are used to further restrict or optimize resource allocation to ensure efficient and stable operation of the system; according to the activated synergy constraints, the current resource allocation results are verified and the verification results are output; according to the verification results, the resource allocation results are optimized, including reallocating storage and computing tasks to different edge nodes, adjusting resource allocation amounts, introducing new synergy mechanisms, etc., and the optimized resource allocation results are output.

[0041] Furthermore, the resource allocation result is verified according to the coordination constraint condition, and the method includes:

[0042] When the coordination of the storage tasks meets the preset coordination index, identify the first edge node set corresponding to the optimal solution of the first node quantity; perform coordination verification on each edge node in the first edge node set to obtain the verification result; if the verification fails, optimize the first edge node set according to the coordination constraint condition until the preset coordination index is met, and output the optimized first edge node set; use the optimized first edge node set to update the resource allocation result.

[0043] Preferably, when the storage task coordination meets the preset coordination index, the corresponding first edge node set is identified from the power grid twin model according to the optimal solution of the first node quantity calculated previously, and the first edge node set includes the edge nodes selected for storage resource allocation; a coordination check is performed on each edge node in the first edge node set, and the verification process will consider coordination indicators such as communication delay, bandwidth, load, and protocol compatibility to evaluate whether the edge node set can maintain good coordination performance while meeting the storage task requirements; if the verification result shows that the first edge node set does not meet the preset coordination index (that is, the verification fails), it is necessary to check the coordination constraint conditions according to the coordination constraint conditions. The set is optimized, including replacing nodes (replacing some edge nodes with poor coordination in the set with other nodes with better performance), adjusting resource configuration (reallocating storage resources to nodes in the set to balance the load and improve resource utilization), etc. The optimization process may require multiple iterations until the first edge node set meets the preset coordination index; once the first edge node set meets the preset coordination index, it is regarded as the optimized result and the optimized first edge node set is output; the information of the optimized first edge node set is updated to the resource allocation result, including updating the allocation plan of the storage task, the status information of the edge node, and the related coordination parameters, etc.

[0044] Furthermore, the expression of the resource allocation result after output optimization includes: ;in, It is the optimized resource allocation result, which is used for resource allocation of storage tasks and computing tasks. It means finding the value that maximizes the objective function in the node set. , , The weight coefficient is used to adjust the influence of each factor in the comprehensive formula. is the weight coefficient of storage resource matching, is the weight of computing resource matching degree, is the weight of task synergy; is the available storage resource of the ith edge node, To store the resource requirements of the task, is the storage resource utilization, which represents the ratio of the available storage resources of the i-th edge node to the storage task resource requirements; is the available computing resources of the ith edge node, To calculate the resource requirements of the task, is the computing resource utilization, which represents the ratio of the available computing resources of the i-th edge node to the computing task resource requirements; For a node collection The sum of the synergies between the nodes in is the synergy between nodes i and j calculated by communication delay, bandwidth, load and protocol compatibility indicators. Specifically, the expression of the optimized resource allocation result is: ; This expression takes into account the three key factors of storage resource matching, computing resource matching and task coordination, and uses the weight coefficient , , To adjust the relative importance of these factors in the overall optimization; represents the optimized resource allocation result, i.e., a set of edge nodes that are allocated to perform storage and computing tasks to achieve the overall optimal resource utilization and task coordination; It means finding the value that maximizes the objective function in the node set; is the available storage resource of the ith edge node, To store the resource requirements of the task, is the storage resource utilization, which represents the ratio of the available storage resources of the i-th edge node to the storage task resource requirements; is the available computing resources of the ith edge node, To calculate the resource requirements of the task, is the computing resource utilization, which represents the ratio of the available computing resources of the i-th edge node to the computing task resource requirements; For a node collection The sum of the synergies between the nodes in is the synergy between node i and node j calculated by communication delay, bandwidth, load and protocol compatibility index. In summary, the embodiment of the present application has at least the following technical effects:

[0045] First, a digital twin model is built for the power grid, a power grid twin model is obtained, and multiple edge nodes of the power grid twin model are identified. Next, the state information of the multiple edge nodes is synchronized, and the state information of each edge node is output, wherein the state information includes the storage resource information and computing resource information of the edge node. At the same time, a first request task is obtained, the first request task is decomposed, a storage task and a computing task are obtained, and the predicted storage resources and predicted computing resources required to execute the storage task and the computing task are predicted. Then, according to the state information of each edge node, an identification storage edge node and an identification computing edge node are obtained, wherein the identification storage edge node is a set of edge nodes that meet the predicted storage resources, and the identification computing edge node is a set of edge nodes that meet the predicted computing resources. Finally, the power grid twin model allocates resources to the storage task and the computing task based on the identification storage edge node and the identification computing edge node, and obtains the resource allocation result. The technical problem that the network resources at the edge of the power grid are difficult to adjust according to the real-time status is solved. Through digital twin modeling and synchronization of real-time status information, the accurate allocation of network resources at the edge of the power grid is realized, and the technical effect of improving the utilization rate of power grid resources is achieved. Example 2, based on the same inventive concept as a method for allocating network resources at the edge of the power grid under synchronous mapping in the aforementioned embodiment, as Figure 2 As shown, the present application provides a network resource allocation platform for edge grid under synchronous mapping, wherein the platform includes:

[0046] A model building module 11, the model building module 11 is used to perform digital twin modeling of the power grid, obtain a power grid twin model, and identify multiple edge nodes of the power grid twin model; a state information acquisition module 12, the state information acquisition module 12 is used to synchronize the state information of the multiple edge nodes and output the state information of each edge node, wherein the state information includes storage resource information and computing resource information of the edge node; a decomposition module 13, the decomposition module 13 is used to obtain a first request task, decompose the first request task, obtain a storage task and a computing task, and predict the predicted storage resources and predicted computing resources required to execute the storage task and the computing task; a node acquisition module 14, the node acquisition module 14 is used to obtain an identification storage edge node and an identification computing edge node according to the state information of each edge node, wherein the identification storage edge node is a set of edge nodes that meet the predicted storage resources, and the identification computing edge node is a set of edge nodes that meet the predicted computing resources; a resource allocation module 15, the resource allocation module 15 is used for the power grid twin model to allocate resources to the storage task and the computing task based on the identification storage edge node and the identification computing edge node, and obtain a resource allocation result.

[0047] Furthermore, the resource allocation module 15 is used to execute the following method:

[0048] The task synergy of the storage task and the computing task is calculated respectively, and the storage task synergy and the computing task synergy are output, wherein the task synergy includes communication delay, bandwidth, load and protocol compatibility indicators; when the storage task synergy meets the preset synergy indicator or when the computing task synergy meets the preset synergy indicator, the synergy constraint condition is activated; the resource allocation result is verified according to the synergy constraint condition, the resource allocation result is optimized according to the verification result, and the optimized resource allocation result is output.

[0049] Furthermore, the resource allocation module 15 is used to execute the following method:

[0050] Based on the power grid twin model, the number of the identification storage edge nodes is obtained ; Initialize the number of edge nodes used for storage resource allocation, where the number of edge nodes used for storage resource allocation is less than the number ; in the amount stated The number of edge nodes used for storage resource allocation is optimized for the quantity constraint condition to obtain a first node quantity optimal solution; and storage resources are allocated to the storage task according to the first node quantity optimal solution.

[0051] Furthermore, the resource allocation module 15 is used to execute the following method:

[0052] When the coordination of the storage tasks meets the preset coordination index, identify the first edge node set corresponding to the optimal solution of the first node quantity; perform coordination verification on each edge node in the first edge node set to obtain the verification result; if the verification fails, optimize the first edge node set according to the coordination constraint condition until the preset coordination index is met, and output the optimized first edge node set; use the optimized first edge node set to update the resource allocation result.

[0053] Furthermore, the resource allocation module 15 is used to execute the following method:

[0054] Based on the power grid twin model, the number of edge nodes identified and calculated is obtained. ; Initialize the number of edge nodes used for computing resource allocation, where the number of edge nodes used for computing resource allocation is less than the number ; in the amount stated The number of edge nodes used for computing resource allocation is optimized for the quantity constraint condition to obtain a second optimal solution for the number of nodes; and computing resources are allocated to the storage task according to the second optimal solution for the number of nodes.

[0055] Furthermore, the model building module 11 is used to execute the following method:

[0056] A fault recovery mechanism is set in the power grid twin model; the storage task and the computing task are monitored respectively based on the resource allocation result, and when any edge node fails, the faulty edge node is identified; the power grid twin model uses the fault recovery mechanism to identify the updated edge node of the faulty edge node, and reallocates tasks and executes tasks according to the updated edge node.

[0057] Furthermore, the resource allocation module 15 is used to execute the following method: ;in, It is the optimized resource allocation result, which is used for resource allocation of storage tasks and computing tasks. It means finding the value that maximizes the objective function in the node set. , , The weight coefficient is used to adjust the influence of each factor in the comprehensive formula. is the weight coefficient of storage resource matching, is the weight of computing resource matching degree, is the weight of task synergy; is the available storage resource of the ith edge node, To store the resource requirements of the task, is the storage resource utilization, which represents the ratio of the available storage resources of the i-th edge node to the storage task resource requirements; is the available computing resources of the ith edge node, To calculate the resource requirements of the task, is the computing resource utilization, which represents the ratio of the available computing resources of the i-th edge node to the computing task resource requirements; For a node collection The sum of the synergies between the nodes in The synergy of node i and node j is calculated by communication delay, bandwidth, load and protocol compatibility index. It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0058] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0059] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for allocating network resources at the edge of a power grid under synchronous mapping, characterized in that: The method comprises: Performing digital twin modeling on a power grid, obtaining a power grid twin model, and identifying multiple edge nodes of the power grid twin model; Synchronizing state information of the plurality of edge nodes, and outputting state information of each edge node, wherein the state information includes storage resource information and computing resource information of the edge node; Obtain a first request task, decompose the first request task, obtain a storage task and a computing task, and predict the predicted storage resources and the predicted computing resources required to execute the storage task and the computing task; According to the status information of each edge node, an identification storage edge node and an identification computing edge node are obtained, wherein the identification storage edge node is a set of edge nodes that meet the predicted storage resources, and the identification computing edge node is a set of edge nodes that meet the predicted computing resources; The power grid twin model allocates resources to the storage task and the computing task based on the identified storage edge node and the identified computing edge node, and obtains a resource allocation result; When the storage task synergy satisfies a preset synergy index or when the computing task synergy satisfies the preset synergy index, activating a synergy constraint condition; The resource allocation result is verified according to the collaborative constraint condition, the resource allocation result is optimized according to the verification result, and the optimized resource allocation result is output. The expression for outputting the optimized resource allocation result includes: ; in, It is the optimized resource allocation result, which is used for resource allocation of storage tasks and computing tasks. It means finding the value that maximizes the objective function in the node set. , , The weight coefficient is used to adjust the influence of each factor in the comprehensive formula. is the weight coefficient of storage resource matching, is the weight of computing resource matching degree, is the weight of task synergy; is the available storage resource of the ith edge node, To store the resource requirements of the task, is the storage resource utilization, which represents the ratio of the available storage resources of the i-th edge node to the storage task resource requirements; is the available computing resources of the ith edge node, To calculate the resource requirements of the task, is the computing resource utilization, which represents the ratio of the available computing resources of the i-th edge node to the computing task resource requirements; For a node collection The sum of the synergies between the nodes in is the synergy between nodes i and j calculated by communication delay, bandwidth, load and protocol compatibility indicators.

2. The method according to claim 1, characterized in that The method for obtaining resource allocation results further includes: The task synergy of the storage task and the computing task is calculated respectively, and the storage task synergy and the computing task synergy are output, wherein the task synergy includes communication delay, bandwidth, load and protocol compatibility indicators.

3. The method according to claim 2, characterized in that Allocating resources to the storage task based on the identified storage edge node includes: Based on the power grid twin model, the number of the identification storage edge nodes is obtained ; Initialize the number of edge nodes used for storage resource allocation, where the number of edge nodes used for storage resource allocation is less than the number ; In the stated quantity Optimizing the number of edge nodes used for storage resource allocation for the quantity constraint condition to obtain an optimal solution for the number of first nodes; Storage resources are allocated to the storage task according to the optimal solution of the first node quantity.

4. The method according to claim 3, characterized in that Verifying the resource allocation result according to the coordination constraint condition, the method comprising: When the storage task coordination satisfies a preset coordination index, identifying a first edge node set corresponding to the first node quantity optimal solution; Performing a coordination check on each edge node in the first edge node set to obtain a verification result, and if the verification fails, optimizing the first edge node set according to the coordination constraint condition until the preset coordination index is met, and outputting the optimized first edge node set; The resource allocation result is updated using the optimized first edge node set.

5. The method according to claim 1, characterized in that Based on the identification computing edge node, resources are allocated to the computing task, and the method further includes: Based on the power grid twin model, the number of edge nodes identified and calculated is obtained. ; Initialize the number of edge nodes used for computing resource allocation, where the number of edge nodes used for computing resource allocation is less than the number ; In the stated quantity Optimizing the number of edge nodes used for computing resource allocation for the quantity constraint condition to obtain an optimal solution for the number of second nodes; Computing resources are allocated to the storage task according to the optimal solution of the number of the second nodes.

6. The method according to claim 1, characterized in that The method further comprises: Setting a fault recovery mechanism in the power grid twin model; The storage task and the computing task are monitored respectively based on the resource allocation result, and when any edge node fails, the failed edge node is identified; The power grid twin model uses the fault recovery mechanism to identify the updated edge node of the faulty edge node, reallocates tasks according to the updated edge node, and executes tasks.

7. A network resource allocation platform for edge grid under synchronous mapping, characterized in that: For implementing a method for allocating network resources at the edge of a power grid under synchronous mapping according to any one of claims 1 to 6, the platform comprises: A model building module, the model building module is used to perform digital twin modeling on the power grid, obtain the power grid twin model, and identify multiple edge nodes of the power grid twin model; A status information acquisition module, the status information acquisition module is used to synchronize the status information of the multiple edge nodes and output the status information of each edge node, wherein the status information includes storage resource information and computing resource information of the edge node; A decomposition module, the decomposition module is used to obtain a first request task, decompose the first request task, obtain a storage task and a computing task, and predict the predicted storage resources and the predicted computing resources required to execute the storage task and the computing task; A node acquisition module, the node acquisition module is used to acquire an identification storage edge node and an identification computing edge node according to the state information of each edge node, wherein the identification storage edge node is a set of edge nodes that meet the predicted storage resources, and the identification computing edge node is a set of edge nodes that meet the predicted computing resources; A resource allocation module, wherein the resource allocation module is used for the power grid twin model to allocate resources to the storage task and the computing task based on the identified storage edge node and the identified computing edge node, and obtain resource allocation results.

Images