Method and device for detecting and dispatching multi-dimensional data of distribution network engineering
Through the detection and scheduling method of multi-dimensional data, graph neural networks and timing networks are used to detect abnormalities in the distribution network, determine abnormal power generation equipment, and dispatch mobile energy storage equipment, solving the problem of inaccurate grid fault detection and scheduling in the existing technology. Improves the stability of the power grid.
Patent Information
- Application Number
- CN202411296943.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-18
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-09-18
AI Technical Summary
The prior art cannot accurately detect the faults of distributed power grid systems and perform effective scheduling, resulting in unstability of the power grid.
Using multi-dimensional data detection and scheduling method, by obtaining network structure information and historical power supply information of the distribution network, using graph neural network and timing network for detection, determining abnormal power generation equipment, and scheduling based on the location and number of abnormal times of mobile energy storage equipment , ensure the stability of the power grid.
Accurate detection and scheduling of distributed grid system faults is realized, and the stability and operational safety of the power grid are improved.
Smart Images

Figure CN118826175B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of electric power technology, and in particular to a method and device for detecting and dispatching multi-dimensional data of a distribution network project. Background Art
[0002] As the scale of distributed power grid systems gradually expands, accurately judging the operating status of distributed power grid systems and timely discovering abnormal conditions are important means to ensure the safe operation of distributed power grid systems. Distributed power grid systems include distributed power generation systems and distribution networks. Existing technologies cannot accurately detect system faults and dispatch according to faults, resulting in instability of the power grid system. Summary of the invention
[0003] The embodiments of the present application provide a method and device for detecting and scheduling multi-dimensional data of a power distribution network project, which can accurately detect system faults and perform scheduling according to the faults, thereby improving the stability of the power grid system.
[0004] In a first aspect, the present application provides a method for detecting and scheduling multidimensional data of a distribution network project, which is applied to a detection and scheduling system for multidimensional data of a distribution network project. The detection and scheduling system for multidimensional data of a distribution network project includes a distributed power generation system and a target distribution network. The distributed power generation system is used to supply power to the target distribution network. The distributed power generation system includes a plurality of distributed power generation devices and a plurality of mobile energy storage devices. The detection and scheduling method for multidimensional data of a distribution network project includes:
[0005] Acquire network structure information of the target distribution network, wherein the network structure information includes network topology, node layout, and line information between nodes;
[0006] Inputting the network structure information into the target graph neural network to obtain a network structure detection result, wherein the network structure detection result is an abnormal network structure or a normal network structure;
[0007] If the network structure detection result is that the network structure is normal, then obtaining multiple historical power supply information of the target distribution network in multiple historical time periods, the historical power supply information including load prediction accuracy, power supply margin, and load distribution information;
[0008] Inputting the plurality of historical power supply information into the target timing network in chronological order, and obtaining a power supply detection result, wherein the power supply detection result is abnormal power supply or normal power supply;
[0009] If the power supply detection result is that the power supply is normal, then obtaining the equipment information of each device in the target distribution network, the equipment information including the equipment material level, equipment performance parameters and the total cost of the equipment;
[0010] If the device information meets the preset conditions, each of the distributed power generation devices is determined as a target power generation device;
[0011] Acquire a real value of the power generation of the target power generation equipment and an estimated value of the power generation of the target power generation equipment;
[0012] If the actual value of the power generation of the target power generation equipment is less than a preset ratio of the estimated value of the power generation of the target power generation equipment, the target power generation equipment is determined as an abnormal power generation equipment;
[0013] Determine at least some of the multiple mobile energy storage devices as multiple target mobile energy storage devices;
[0014] Connecting a plurality of the target mobile energy storage devices to a target distribution network to supply power to the target distribution network;
[0015] Acquire the location information and abnormality times of historical abnormal power generation equipment that have abnormalities within a preset time period according to a preset cycle;
[0016] Each of the mobile energy storage devices is dispatched based on the location information and the number of abnormalities of the historical abnormal power generation equipment.
[0017] Optionally, the detection and scheduling method of multi-dimensional data of the distribution network project includes:
[0018] Determine whether the equipment material level of each device in the target distribution network is higher than the corresponding preset equipment level;
[0019] Determine whether the equipment performance parameter of each equipment in the target distribution network is higher than the corresponding equipment performance parameter;
[0020] Determining whether the total equipment cost of the target distribution network is higher than a preset equipment cost;
[0021] If the equipment material level of each device in the target distribution network is higher than the corresponding preset equipment level, the equipment performance parameters of each device in the target distribution network are higher than the corresponding equipment performance parameters, and the total equipment cost of the target distribution network is not higher than the preset equipment cost, it is determined that the equipment information meets the preset equipment conditions.
[0022] Optionally, the detection and scheduling method of multi-dimensional data of the distribution network project includes:
[0023] Based on multiple reference network structure information of multiple reference distribution networks and corresponding annotation labels, the annotation labels are network structure abnormality or network structure normal;
[0024] Constructing structured graph data based on multiple reference network structure information, wherein the graph data includes node data of each node;
[0025] Taking the node data as the node sample, randomly select K node samples as the initial cluster center, and calculate the distance between each node sample and the initial cluster center;
[0026] Assign each node sample to the cluster with the nearest cluster center, and update the cluster center of each cluster;
[0027] Based on the updated cluster center, perform iterative calculations until the stop condition is met, completing the clustering of all node data;
[0028] Encode the node data after clustering and classification, and generate a final category label for each node data, wherein the category label is abnormal or normal;
[0029] The category label of each node data is added to the node data as the feature of the node and multiple reference network structure information is updated to obtain multiple updated reference network structure information and corresponding annotation labels to obtain a data set;
[0030] A preset graph neural network is trained based on the data set to obtain the target graph neural network.
[0031] Optionally, the scheduling of each of the mobile energy storage devices based on the location information and the number of abnormalities of the historical abnormal power generation equipment includes:
[0032] Clustering the distributed power generation equipment based on the location information and the number of abnormalities of the historical abnormal power generation equipment to obtain a plurality of second equipment clusters;
[0033] Determine an area enclosed by each of the historically abnormal power generation equipment in the second equipment cluster as an abnormal area;
[0034] Obtaining the abnormal equipment ratio of the historically abnormal power generation equipment in the abnormal area;
[0035] Determine the target device movement information based on the abnormal device ratio of the historical abnormal power generation equipment in the abnormal area, the total regional equipment of the distributed power generation equipment, and the regional area size, wherein the target device movement information includes the target movement position of each of the mobile energy storage devices;
[0036] Each of the mobile energy storage devices is moved based on the target device movement information, so as to move each of the mobile energy storage devices from a current position to a corresponding target movement position.
[0037] Optionally, the determining of the target device movement information based on the abnormal device ratio of the historical abnormal power generation devices in the abnormal area, the total regional equipment volume of the distributed power generation devices, and the regional area size includes:
[0038] Based on the abnormal device proportion of the historical abnormal power generation equipment in the abnormal area, the total regional equipment amount of the distributed power generation equipment and the regional area size, the energy storage device allocation quantity and allocation priority of the mobile energy storage device allocated to each abnormal area are determined, wherein the higher the abnormal device proportion, the higher the energy storage device allocation quantity and the allocation priority; the larger the total regional equipment amount, the higher the energy storage device allocation quantity and the allocation priority; the larger the regional area size, the higher the energy storage device allocation quantity and the allocation priority;
[0039] The abnormal area with the highest allocation priority is sequentially determined as the target area, the allocation quantity of the energy storage device in the target area is determined as the target allocation quantity, and the second target distance between each mobile energy storage device and each historical abnormal power generation device in the target area is respectively calculated;
[0040] Determine the minimum value of the second target distance between the mobile energy storage device and each of the historical abnormal power generation devices as the third target distance between the mobile energy storage device and the target area;
[0041] Determine the mobile energy storage devices of the target allocation quantity that are ranked first in descending order of the third target distance as the allocated energy storage devices of the target area, and obtain the allocated energy storage devices of each of the abnormal areas;
[0042] The position of the historically abnormal power generation device having the smallest second target distance from the allocated energy storage device in the target area is determined as the target moving position of the allocated energy storage device, and the target moving position of each mobile energy storage device is obtained.
[0043] Optionally, the moving each of the mobile energy storage devices based on the target device movement information to move each of the mobile energy storage devices from a current position to a corresponding target movement position includes:
[0044] Determine the mobile resource consumption of each mobile energy storage device moving to the target mobile position based on the target device movement information;
[0045] Obtaining the amount of power transmission resource loss when the mobile energy storage device transmits electric energy to the historical abnormal power generation equipment and connects to the target distribution network within the preset time period;
[0046] If the power transmission resource loss is greater than the mobile resource consumption, each of the mobile energy storage devices is moved based on the target device movement information to move each of the mobile energy storage devices from a current position to a corresponding target movement position.
[0047] Optionally, determining at least some of the multiple mobile energy storage devices as multiple target mobile energy storage devices includes:
[0048] Obtaining the number of times each mobile energy storage device has been charged and discharged, the time interval since the last charge and discharge, and the remaining power;
[0049] Determine the candidate priority based on the number of times the mobile energy storage device has been charged and discharged, the time interval since the last charge and discharge, and the remaining power;
[0050] The plurality of mobile energy storage devices ranked higher in order of candidate priority from high to low are determined as the plurality of target mobile energy storage devices.
[0051] In a second aspect, the multidimensional data detection and scheduling device of the distribution network project provided by the present application is applied to the multidimensional data detection and scheduling system of the distribution network project, the multidimensional data detection and scheduling system of the distribution network project includes a distributed power generation system and a target distribution network, the distributed power generation system is used to supply power to the target distribution network, the distributed power generation system includes a plurality of distributed power generation devices and a plurality of mobile energy storage devices, the multidimensional data detection and scheduling device of the distribution network project includes:
[0052] A first acquisition module is used to acquire network structure information of the target distribution network, wherein the network structure information includes network topology, node layout, and line information between nodes;
[0053] A first input module is used to input the network structure information into a target graph neural network to obtain a network structure detection result, wherein the network structure detection result is an abnormal network structure or a normal network structure;
[0054] A second acquisition module is used to acquire a plurality of historical power supply information of the target distribution network in a plurality of historical time periods if the network structure detection result is that the network structure is normal, wherein the historical power supply information includes load prediction accuracy, power supply margin, and load distribution information;
[0055] A second input module is used to input the plurality of historical power supply information into a target timing network in chronological order to obtain a power supply detection result, wherein the power supply detection result is abnormal power supply or normal power supply;
[0056] A third acquisition module is used to acquire device information of each device in the target distribution network if the power supply detection result is that the power supply is normal, wherein the device information includes device material level, device performance parameters and total cost of the device;
[0057] A first determination module, configured to determine each of the distributed power generation devices as a target power generation device if the device information meets a preset condition;
[0058] A fourth acquisition module, used to acquire a real value of the power generation of the target power generation equipment and an estimated value of the power generation of the target power generation equipment;
[0059] A second determination module is used to determine the target power generation equipment as an abnormal power generation equipment if the actual value of the power generation power of the target power generation equipment is less than a preset ratio of the estimated value of the power generation power of the target power generation equipment;
[0060] A third determination module, configured to determine at least some of the multiple mobile energy storage devices as multiple target mobile energy storage devices;
[0061] An access module, used to connect a plurality of the target mobile energy storage devices to a target distribution network to supply power to the target distribution network;
[0062] A fifth acquisition module is used to acquire, according to a preset period, the location information and the number of abnormalities of the historical abnormal power generation equipment that has occurred abnormalities within a preset time period;
[0063] A scheduling module is used to schedule each of the mobile energy storage devices based on the location information and the number of abnormalities of the historical abnormal power generation equipment.
[0064] Optionally, the detection and scheduling method of multi-dimensional data of the distribution network project includes:
[0065] Determine whether the equipment material level of each device in the target distribution network is higher than the corresponding preset equipment level;
[0066] Determine whether the equipment performance parameter of each equipment in the target distribution network is higher than the corresponding equipment performance parameter;
[0067] Determining whether the total equipment cost of the target distribution network is higher than a preset equipment cost;
[0068] If the equipment material level of each device in the target distribution network is higher than the corresponding preset equipment level, the equipment performance parameters of each device in the target distribution network are higher than the corresponding equipment performance parameters, and the total equipment cost of the target distribution network is not higher than the preset equipment cost, it is determined that the equipment information meets the preset equipment conditions.
[0069] Optionally, the detection and scheduling method of multi-dimensional data of the distribution network project includes:
[0070] Based on multiple reference network structure information of multiple reference distribution networks and corresponding annotation labels, the annotation labels are network structure abnormality or network structure normal;
[0071] Constructing structured graph data based on multiple reference network structure information, wherein the graph data includes node data of each node;
[0072] Taking the node data as the node sample, randomly select K node samples as the initial cluster center, and calculate the distance between each node sample and the initial cluster center;
[0073] Assign each node sample to the cluster with the nearest cluster center, and update the cluster center of each cluster;
[0074] Based on the updated cluster center, perform iterative calculations until the stop condition is met, completing the clustering of all node data;
[0075] Encode the node data after clustering and classification, and generate a final category label for each node data, wherein the category label is abnormal or normal;
[0076] The category label of each node data is added to the node data as the feature of the node and multiple reference network structure information is updated to obtain multiple updated reference network structure information and corresponding annotation labels to obtain a data set;
[0077] A preset graph neural network is trained based on the data set to obtain the target graph neural network.
[0078] Optionally, the scheduling of each of the mobile energy storage devices based on the location information and the number of abnormalities of the historical abnormal power generation equipment includes:
[0079] Clustering the distributed power generation equipment based on the location information and the number of abnormalities of the historical abnormal power generation equipment to obtain a plurality of second equipment clusters;
[0080] Determine an area enclosed by each of the historically abnormal power generation equipment in the second equipment cluster as an abnormal area;
[0081] Obtaining the abnormal equipment ratio of the historically abnormal power generation equipment in the abnormal area;
[0082] Determine the target device movement information based on the abnormal device ratio of the historical abnormal power generation equipment in the abnormal area, the total regional equipment of the distributed power generation equipment, and the regional area size, wherein the target device movement information includes the target movement position of each of the mobile energy storage devices;
[0083] Each of the mobile energy storage devices is moved based on the target device movement information, so as to move each of the mobile energy storage devices from a current position to a corresponding target movement position.
[0084] Optionally, the determining of the target device movement information based on the abnormal device ratio of the historical abnormal power generation devices in the abnormal area, the total regional equipment volume of the distributed power generation devices, and the regional area size includes:
[0085] Based on the abnormal device proportion of the historical abnormal power generation equipment in the abnormal area, the total regional equipment amount of the distributed power generation equipment and the regional area size, the energy storage device allocation quantity and allocation priority of the mobile energy storage device allocated to each abnormal area are determined, wherein the higher the abnormal device proportion, the higher the energy storage device allocation quantity and the allocation priority; the larger the total regional equipment amount, the higher the energy storage device allocation quantity and the allocation priority; the larger the regional area size, the higher the energy storage device allocation quantity and the allocation priority;
[0086] The abnormal area with the highest allocation priority is sequentially determined as the target area, the allocation quantity of the energy storage device in the target area is determined as the target allocation quantity, and the second target distance between each mobile energy storage device and each historical abnormal power generation device in the target area is respectively calculated;
[0087] Determine the minimum value of the second target distance between the mobile energy storage device and each of the historical abnormal power generation devices as the third target distance between the mobile energy storage device and the target area;
[0088] Determine the mobile energy storage devices of the target allocation quantity that are ranked first in descending order of the third target distance as the allocated energy storage devices of the target area, and obtain the allocated energy storage devices of each of the abnormal areas;
[0089] The position of the historically abnormal power generation device having the smallest second target distance from the allocated energy storage device in the target area is determined as the target moving position of the allocated energy storage device, and the target moving position of each mobile energy storage device is obtained.
[0090] Optionally, the moving each of the mobile energy storage devices based on the target device movement information to move each of the mobile energy storage devices from a current position to a corresponding target movement position includes:
[0091] Determine the mobile resource consumption of each mobile energy storage device moving to the target mobile position based on the target device movement information;
[0092] Obtaining the amount of power transmission resource loss when the mobile energy storage device transmits electric energy to the historical abnormal power generation equipment and connects to the target distribution network within the preset time period;
[0093] If the power transmission resource loss is greater than the mobile resource consumption, each of the mobile energy storage devices is moved based on the target device movement information to move each of the mobile energy storage devices from a current position to a corresponding target movement position.
[0094] Optionally, determining at least some of the multiple mobile energy storage devices as multiple target mobile energy storage devices includes:
[0095] Obtaining the number of times each mobile energy storage device has been charged and discharged, the time interval since the last charge and discharge, and the remaining power;
[0096] Determine the candidate priority based on the number of times the mobile energy storage device has been charged and discharged, the time interval since the last charge and discharge, and the remaining power;
[0097] The plurality of mobile energy storage devices ranked higher in order of candidate priority from high to low are determined as the plurality of target mobile energy storage devices.
[0098] In a third aspect, the electronic device provided in the present application includes a memory and a processor, the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the detection and scheduling method of multi-dimensional data of the distribution network project provided in the present application.
[0099] In a fourth aspect, the computer-readable storage medium provided in the present application stores a plurality of instructions, which are suitable for loading by a processor to implement the steps in the detection and scheduling method of multi-dimensional data of a distribution network project provided in the present application.
[0100] In a fifth aspect, the computer program product provided in the present application includes a computer program or instructions, which, when executed by a processor, implements the steps in the method for detecting and scheduling multi-dimensional data of a distribution network project provided in the present application.
[0101] In the present application, compared with the related art, the network structure information of the target distribution network is obtained, and the network structure information includes the network topology, node layout, and line information between nodes; the network structure information is input into the target graph neural network to obtain the network structure detection result, and the network structure detection result is that the network structure is abnormal or the network structure is normal; if the network structure detection result is that the network structure is normal, multiple historical power supply information of the target distribution network in multiple historical time periods is obtained, and the historical power supply information includes load prediction accuracy, power supply margin, and load distribution information; multiple historical power supply information is input into the target timing network in chronological order to obtain the power supply detection result, and the power supply detection result is that the power supply is abnormal or the power supply is normal; if the power supply detection result is that the power supply is normal, the equipment information of each equipment in the target distribution network is obtained, and the equipment information package Including equipment material level, equipment performance parameters and total equipment cost; if the equipment information meets the preset conditions, each distributed power generation equipment is determined as a target power generation equipment; the actual value of the power generation of the target power generation equipment and the estimated value of the power generation of the target power generation equipment are obtained; if the actual value of the power generation of the target power generation equipment is less than the preset ratio of the estimated value of the power generation of the target power generation equipment, the target power generation equipment is determined as an abnormal power generation equipment; at least part of the multiple mobile energy storage devices are determined as multiple target mobile energy storage devices; multiple target mobile energy storage devices are connected to the target distribution network to supply power to the target distribution network; the location information and abnormal number of historical abnormal power generation equipment that have abnormalities within a preset time period are obtained according to a preset cycle; and each mobile energy storage device is dispatched based on the location information and abnormal number of historical abnormal power generation equipment. The present application can accurately detect system faults and dispatch according to the faults, thereby improving the stability of the power grid system. BRIEF DESCRIPTION OF THE DRAWINGS
[0102] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0103] Figure 1 This is a schematic diagram of a scenario of a detection and dispatching system for multi-dimensional data of a distribution network project provided in an embodiment of the present application;
[0104] Figure 2 It is a flow chart of an embodiment of a method for detecting and scheduling multi-dimensional data of a distribution network project provided by an embodiment of the present application;
[0105] Figure 3 It is a structural schematic diagram of a detection and scheduling device for multi-dimensional data of a distribution network project provided in an embodiment of the present application;
[0106] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0107] It should be noted that the principles of the present application are illustrated by implementing them in an appropriate computing environment. The following description is based on the illustrated specific embodiments of the present application and should not be considered as limiting other specific embodiments of the present application that are not described in detail herein.
[0108] In the following description of the present application, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.
[0109] In the following description of the present application, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.
[0110] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0111] In order to improve the effect of detection and scheduling of multidimensional data of distribution network engineering, the embodiments of the present application provide a detection and scheduling method of multidimensional data of distribution network engineering, a detection and scheduling device of multidimensional data of distribution network engineering, an electronic device, a computer-readable storage medium and a computer program product. Among them, the detection and scheduling method of multidimensional data of distribution network engineering can be executed by the detection and scheduling device of multidimensional data of distribution network engineering, or by an electronic device integrated with the detection and scheduling device of multidimensional data of distribution network engineering.
[0112] 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, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.
[0113] Please refer to Figure 1 , the present application also provides a multi-dimensional data detection and dispatching system for a distribution network project, such as Figure 1As shown, the multi-dimensional data detection and scheduling system of the distribution network project includes a distributed power generation system 300, a target distribution network 200 and an electronic device 100. The distributed power generation system is used to supply power to the target distribution network. The distributed power generation system includes multiple distributed power generation devices and multiple mobile energy storage devices.
[0114] Among them, the electronic device 100 can be any device equipped with a processor and has processing capabilities, such as mobile electronic devices with processors such as smart phones, tablet computers, PDAs, laptops, smart speakers, or fixed electronic devices with processors such as desktop computers, televisions, servers, industrial equipment, etc.
[0115] In addition, if Figure 1 As shown, the multi-dimensional data detection and scheduling system of the distribution network project may also include a memory for storing original data, intermediate data and result data.
[0116] In the embodiment of the present application, the memory may be a cloud memory. Cloud storage is a new concept extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as the storage system) refers to a storage system that uses cluster applications, grid technology, and distributed storage file systems to bring together a large number of storage devices of various types (storage devices are also called storage nodes) in the network through application software or application interfaces to work together and provide external data storage and business access functions.
[0117] At present, the storage method of the storage system is: create a logical volume, and when creating a logical volume, allocate physical storage space for each logical volume, and the physical storage space may be composed of disks of a storage device or several storage devices. The client stores data on a logical volume, that is, stores the data on the file system. The file system divides the data into many parts, each of which is an object. The object contains not only data but also additional information such as data identification (ID, ID entity). The file system writes each object into the physical storage space of the logical volume, and the file system records the storage location information of each object, so that when the client requests to access the data, the file system can allow the client to access the data according to the storage location information of each object.
[0118] The process of the storage system allocating physical storage space to a logical volume is as follows: based on the estimated capacity of the objects stored in the logical volume (this estimate often has a large margin relative to the actual capacity of the objects to be stored) and the grouping of independent redundant disk arrays (RAID, Redundant Array of Independent Disks), the physical storage space is divided into stripes in advance. A logical volume can be understood as a stripe, thereby allocating physical storage space to the logical volume.
[0119] It should be noted that Figure 1 The scenario diagram of the detection and scheduling system for multi-dimensional data of the distribution network project shown is merely an example. The detection and scheduling system for multi-dimensional data of the distribution network project and the scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of the detection and scheduling system for multi-dimensional data of the distribution network project and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.
[0120] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.
[0121] Please refer to Figure 2 , Figure 2 FIG. 1 is a flow chart of an embodiment of a method for detecting and scheduling multi-dimensional data of a distribution network project provided in an embodiment of the present application. Figure 2 As shown, the process of the detection and scheduling method of multi-dimensional data of the distribution network project provided by this application is as follows:
[0122] 201. Obtain network structure information of a target distribution network, where the network structure information includes network topology, node layout, and line information between nodes.
[0123] 202. Input the network structure information into the target graph neural network to obtain a network structure detection result, where the network structure detection result is that the network structure is abnormal or the network structure is normal.
[0124] In an embodiment of the present application, the target graph neural network is used to determine whether the network structure information is abnormal or normal.
[0125] In an embodiment of the present application, a method for detecting and scheduling multi-dimensional data of a distribution network project includes:
[0126] (1) Based on multiple reference network structure information of multiple reference distribution networks and corresponding annotation labels, the annotation labels are abnormal network structure or normal network structure.
[0127] Reference network structure information can be obtained from other distribution networks.
[0128] (2) Constructing structured graph data based on multiple reference network structure information, where the graph data includes node data of each node.
[0129] Among them, the graph data is an undirected graph consisting of nodes and edges.
[0130] (3) Taking the node data as the node sample, randomly select K node samples as the initial clustering centers, and calculate the distance between each node sample and the initial clustering center.
[0131] (4) Assign each node sample to the cluster with the nearest cluster center and update the cluster center of each cluster.
[0132] (5) Based on the updated cluster center, perform iterative calculations until the stopping condition is met and the clustering of all node data is completed.
[0133] (6) Encode the node data after clustering and classification, and generate the final category label for each node data, which is abnormal or normal.
[0134] (7) The category label of each node data is added to the node data as the feature of the node and multiple reference network structure information is updated to obtain multiple updated reference network structure information and corresponding annotation labels to obtain a data set.
[0135] (8) Train the preset graph neural network based on the data set to obtain the target graph neural network.
[0136] Among them, the preset graph neural network can be a GNN network.
[0137] 203. When the network structure detection result shows that the network structure is normal, multiple historical power supply information of the target distribution network in multiple historical time periods is obtained, and the historical power supply information includes load prediction accuracy, power supply margin, and load distribution information.
[0138] Among them, multiple historical time periods are arranged in chronological order.
[0139] 204. Input multiple historical power supply information into the target timing network in chronological order to obtain a power supply detection result, where the power supply detection result is abnormal power supply or normal power supply.
[0140] The target time series network may be an LSTM model.
[0141] 205. If the power supply detection result is that the power supply is normal, then obtain the equipment information of each device in the target distribution network, the equipment information including the equipment material level, equipment performance parameters and the total cost of the equipment.
[0142] 206. If the device information meets the preset conditions, each distributed power generation device is determined as a target power generation device.
[0143] Specifically, determine whether the equipment material level of each device in the target distribution network is higher than the corresponding preset equipment level; determine whether the equipment performance parameters of each device in the target distribution network are higher than the corresponding equipment performance parameters; determine whether the total equipment cost of the target distribution network is higher than the preset equipment cost; if the equipment material level of each device in the target distribution network is higher than the corresponding preset equipment level, the equipment performance parameters of each device in the target distribution network are higher than the corresponding equipment performance parameters and the total equipment cost of the target distribution network is not higher than the preset equipment cost, then determine that the equipment information meets the preset equipment conditions.
[0144] 207. Obtain the actual value of the power generation and the estimated value of the power generation of the target power generation equipment.
[0145] In the embodiment of the present application, the actual value of the power generation power of the target power generation equipment can be obtained through detection.
[0146] In the embodiment of the present application, obtaining the actual value of the power generation and the estimated value of the power generation of the target power generation equipment includes:
[0147] (1) Clustering each distributed power generation device to obtain a plurality of first device clusters, each of which includes a plurality of distributed power generation devices.
[0148] In the embodiment of the present application, each distributed power generation device can be clustered based on the K-Means clustering algorithm to obtain a plurality of first device clusters.
[0149] Specifically, the location information of each distributed power generation device and the weather information of the area where the distributed power generation device is located are obtained, and multiple distributed power generation devices are clustered based on the location information of each distributed power generation device and the weather information of the area where the distributed power generation device is located to obtain multiple first device clusters. Each first device cluster has similar location information and similar weather information of the area where the distributed power generation device is located. Specifically, the regional weather information includes temperature, humidity, wind speed, etc.
[0150] (2) Obtain the actual power generation value of each distributed power generation device in each first device cluster where the target power generation device is located.
[0151] (3) Determine the estimated power generation value of the target power generation device based on the actual power generation value of each distributed power generation device.
[0152] Specifically, determining the estimated power generation value of the target power generation device based on the actual power generation value of each distributed power generation device includes:
[0153] (1) Obtain the true value of the power generated by each distributed power generation device.
[0154] (2) obtaining a first target distance between each distributed power generation device and a target power generation device;
[0155] (3) determining a target weight corresponding to each distributed power generation device based on a first target distance corresponding to each distributed power generation device, wherein the larger the first target distance, the larger the target weight;
[0156] (4) Based on the target weights corresponding to the distributed power generation devices, the actual power generation values of the distributed power generation devices are weighted and summed to obtain the power generation power estimate of the target power generation device.
[0157] 208. If the actual value of the power generation of the target power generation equipment is less than a preset ratio of the estimated value of the power generation of the target power generation equipment, the target power generation equipment is determined as an abnormal power generation equipment.
[0158] The preset ratio can be set according to specific circumstances. For example, the preset ratio is 80%.
[0159] 209. Determine at least some of the multiple mobile energy storage devices as multiple target mobile energy storage devices.
[0160] In the embodiment of the present application, at least some of the multiple mobile energy storage devices are determined as multiple target mobile energy storage devices, including:
[0161] (1) Obtain the number of times each mobile energy storage device has been charged and discharged, the time interval since the last charge and discharge, and the remaining power.
[0162] (2) Determine the candidate priority based on the number of times the mobile energy storage device has been charged and discharged, the time interval since the last charge and discharge, and the remaining power.
[0163] Among them, the number of times the mobile energy storage device has been charged and discharged, the time interval since the last charge and discharge, and the remaining power are normalized respectively to obtain a normalized value of the number of charges and discharges, a normalized value of the time interval, and a normalized value of the remaining power. The candidate priority a is determined based on the normalized value c of the number of charges and discharges, the normalized value t of the time interval, and the normalized value s of the remaining power.
[0164] Specifically, the calculation formula of candidate priority a is as follows:
[0165]
[0166] (3) Multiple mobile energy storage devices ranked higher in candidate priority from high to low are determined as multiple target mobile energy storage devices.
[0167] 210. Connect multiple target mobile energy storage devices to a target distribution network to supply power to the target distribution network.
[0168] 211. Obtain location information and abnormality counts of historical abnormal power generation equipment that has experienced abnormalities within a preset time period according to a preset cycle.
[0169] The preset period may be one week or one month, which can be set according to the specific situation. Since the environment in which multiple mobile energy storage devices are located may change, resulting in mismatch with the distribution network, it is necessary to dispatch the mobile energy storage devices to match the distribution network.
[0170] 212. Dispatch each mobile energy storage device based on the location information and abnormal number of historical abnormal power generation equipment.
[0171] In the embodiment of the present application, each mobile energy storage device is dispatched based on the location information and abnormal number of historical abnormal power generation equipment, including:
[0172] (1) Based on the location information and abnormal times of historical abnormal power generation equipment, distributed power generation equipment is clustered to obtain a plurality of second equipment clusters.
[0173] (2) The area enclosed by each historically abnormal power generation equipment in the second equipment cluster is determined as the abnormal area.
[0174] Among them, each historical abnormal power generation equipment in the second equipment cluster is located in the abnormal area, and the abnormal area is a polygon, and multiple vertices of the abnormal area are each a historical abnormal power generation equipment.
[0175] (3) Obtain the abnormal equipment ratio of historical abnormal power generation equipment in the abnormal area.
[0176] The abnormal equipment ratio is the ratio of the total number of historically abnormal power generation equipment in the abnormal area to the total number of power generation equipment in the abnormal area.
[0177] (4) Determine the target device movement information based on the abnormal device ratio of historical abnormal power generation equipment in the abnormal area, the total regional equipment volume of distributed power generation equipment, and the size of the regional area, wherein the target device movement information includes the target movement position of each mobile energy storage device.
[0178] (5) Moving each mobile energy storage device based on the target device movement information, so as to move each mobile energy storage device from a current position to a corresponding target movement position.
[0179] In a specific embodiment, the target device movement information is determined based on the abnormal device ratio of historical abnormal power generation devices in the abnormal area, the total regional equipment of distributed power generation devices, and the size of the regional area, including:
[0180] (1) The number of energy storage devices and the allocation priority of mobile energy storage devices allocated to each abnormal area are determined based on the abnormal device ratio of historical abnormal power generation equipment in the abnormal area, the total regional equipment volume of distributed power generation equipment, and the size of the regional area. The higher the abnormal device ratio, the higher the number of energy storage devices allocated and the allocation priority. The larger the total regional equipment volume, the higher the number of energy storage devices allocated and the allocation priority. The larger the regional area, the higher the number of energy storage devices allocated and the allocation priority.
[0181] (2) The abnormal areas with the highest allocation priority are determined as target areas in turn, the number of energy storage devices allocated in the target areas is determined as the target allocation number, and the second target distance between each mobile energy storage device and each historical abnormal power generation device in the target area is calculated respectively.
[0182] (3) The minimum value of the second target distance between the mobile energy storage device and each historical abnormal power generation device is determined as the third target distance between the mobile energy storage device and the target area.
[0183] For a mobile energy storage device, the minimum value of the second target distance between the mobile energy storage device and each historical abnormal power generation device is determined as the third target distance between the mobile energy storage device and the target area. That is, the minimum distance between the mobile energy storage device and each historical abnormal power generation device in the target area is used as the distance between the mobile energy storage device and the target area.
[0184] (4) The mobile energy storage devices with the highest number of target allocations sorted from the smallest to the largest third target distance are determined as the allocated energy storage devices of the target area, and the allocated energy storage devices of each abnormal area are obtained.
[0185] The mobile energy storage devices with the smaller target allocation quantity from the target area are determined as the allocated energy storage devices of the target area, which can reduce the power loss.
[0186] (5) The position of the historical abnormal power generation device with the smallest second target distance to the allocated energy storage device in the target area is determined as the target moving position of the allocated energy storage device, thereby obtaining the target moving position of each mobile energy storage device.
[0187] After determining the mobile energy storage device allocated to the target area, further, the mobile energy storage device is moved to the location of the historical abnormal power generation device with a minimum distance.
[0188] In the embodiment of the present application, each mobile energy storage device is moved based on the target device movement information to move each mobile energy storage device from a current position to a corresponding target movement position, including:
[0189] (1) Determine the mobile resource consumption of each mobile energy storage device when moving to the target mobile position based on the target device movement information.
[0190] The mobile resource consumption refers to the resources consumed by each mobile energy storage device to move to the target mobile position, which may be power consumption or the like.
[0191] (2) Obtain the amount of transmission resource loss when the mobile energy storage device transmits electric energy to the historically abnormal power generation equipment and connects to the target distribution network within a preset time period.
[0192] (3) If the power transmission resource loss is greater than the mobile resource consumption, each mobile energy storage device is moved based on the target device movement information to move each mobile energy storage device from a current position to a corresponding target movement position.
[0193] If the transmission resource loss is greater than the mobile resource consumption, it indicates that moving the mobile energy storage device to the historical abnormal power generation device consumes less resources at this time. Therefore, each mobile energy storage device is moved based on the device movement information to move each mobile energy storage device from the current position to the corresponding target moving position.
[0194] In order to facilitate better implementation of the detection and scheduling method for multidimensional data of a distribution network project provided in the embodiment of the present application, the embodiment of the present application also provides a detection and scheduling device for multidimensional data of a distribution network project based on the detection and scheduling method for multidimensional data of a distribution network project. The meaning of the terms is the same as that in the detection and scheduling method for multidimensional data of a distribution network project. For specific implementation details, please refer to the description in the above method embodiment.
[0195] Please refer to Figure 3 , Figure 3 A schematic diagram of the structure of a detection and scheduling device for multi-dimensional data of a distribution network project provided in an embodiment of the present application, wherein the detection and scheduling device for multi-dimensional data of a distribution network project may include:
[0196] The first acquisition module 701 is used to acquire the network structure information of the target distribution network, wherein the network structure information includes the network topology, node layout, and line information between nodes;
[0197] The first input module 702 is used to input the network structure information into the target graph neural network to obtain a network structure detection result, wherein the network structure detection result is an abnormal network structure or a normal network structure;
[0198] The second acquisition module 703 is used to acquire multiple historical power supply information of the target distribution network in multiple historical time periods if the network structure detection result is that the network structure is normal, and the historical power supply information includes load prediction accuracy, power supply margin, and load distribution information;
[0199] The second input module 704 is used to input the plurality of historical power supply information into the target timing network in chronological order to obtain a power supply detection result, wherein the power supply detection result is abnormal power supply or normal power supply;
[0200] The third acquisition module 705 is used to acquire the equipment information of each equipment in the target distribution network if the power supply detection result is that the power supply is normal, and the equipment information includes equipment material level, equipment performance parameters and total equipment cost;
[0201] A first determination module 706, configured to determine each of the distributed power generation devices as a target power generation device if the device information meets a preset condition;
[0202] A fourth acquisition module 707, configured to acquire a real value of the power generation of the target power generation equipment and an estimated value of the power generation of the target power generation equipment;
[0203] A second determination module 708 is configured to determine the target power generation device as an abnormal power generation device if the actual power generation value of the target power generation device is less than a preset ratio of the estimated power generation value of the target power generation device;
[0204] A third determination module 709, configured to determine at least some of the multiple mobile energy storage devices as multiple target mobile energy storage devices;
[0205] An access module 710, configured to connect a plurality of the target mobile energy storage devices to a target distribution network to supply power to the target distribution network;
[0206] The fifth acquisition module 711 is used to acquire the location information and the number of abnormalities of the historical abnormal power generation equipment that has occurred abnormalities within a preset time period according to a preset cycle;
[0207] The scheduling module 712 is used to schedule each of the mobile energy storage devices based on the location information and the number of abnormalities of the historical abnormal power generation equipment.
[0208] The specific implementation of each of the above modules can be found in the previous embodiments and will not be described in detail here.
[0209] An embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the processor is used to execute the steps in the detection and scheduling method of multi-dimensional data of a distribution network project provided in this embodiment by calling a computer program stored in the memory.
[0210] Please refer to Figure 4 , Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
[0211] The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:
[0212] The processor 101 is the control center of the electronic device, which uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 102, and calling data stored in the memory 102. Optionally, the processor 101 may include one or more processing cores; optionally, the processor 101 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 101.
[0213] The memory 102 can be used to store software programs and modules. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 102. The memory 102 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 102 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 102 may also include a memory controller to provide the processor 101 with access to the memory 102.
[0214] The electronic device also includes a power supply 103 for supplying power to each component. Optionally, the power supply 103 can be logically connected to the processor 101 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 103 can also include any components such as one or more DC or AC power supplies, recharging systems, power anomaly detection circuits, power converters or inverters, and power status indicators.
[0215] The electronic device may further include an input unit 104, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
[0216] Although not shown, the electronic device may also include a display unit, an image acquisition component, etc., which will not be described in detail here. Specifically in this embodiment, the processor 101 in the electronic device will load the executable code corresponding to one or more computer programs into the memory 102 according to the following instructions, and the processor 101 will execute the steps in the detection and scheduling method of multi-dimensional data of the distribution network project provided by the present application, such as:
[0217] The network structure information of the target distribution network is obtained, and the network structure information includes the network topology, node layout, and line information between nodes; the network structure information is input into the target graph neural network to obtain the network structure detection result, and the network structure detection result is that the network structure is abnormal or the network structure is normal; if the network structure detection result is that the network structure is normal, multiple historical power supply information of the target distribution network in multiple historical time periods is obtained, and the historical power supply information includes load prediction accuracy, power supply margin, and load distribution information; multiple historical power supply information is input into the target timing network in chronological order, and the power supply detection result is that the power supply is abnormal or the power supply is normal; if the power supply detection result is that the power supply is normal, the equipment information of each equipment in the target distribution network is obtained, and the equipment information includes the equipment material level , equipment performance parameters and total equipment cost; if the equipment information meets the preset conditions, each distributed power generation equipment is determined as a target power generation equipment; the actual value of the power generation of the target power generation equipment and the estimated value of the power generation of the target power generation equipment are obtained; if the actual value of the power generation of the target power generation equipment is less than the preset proportion of the estimated value of the power generation of the target power generation equipment, the target power generation equipment is determined as an abnormal power generation equipment; at least part of the multiple mobile energy storage devices are determined as multiple target mobile energy storage devices; multiple target mobile energy storage devices are connected to the target distribution network to supply power to the target distribution network; the location information and the number of abnormalities of historical abnormal power generation equipment that have occurred abnormalities within a preset time period are obtained according to a preset cycle; and each mobile energy storage device is dispatched based on the location information and the number of abnormalities of the historical abnormal power generation equipment.
[0218] It should be noted that the electronic device provided in the embodiment of the present application and the detection and scheduling method of multi-dimensional data of the distribution network project in the above embodiment belong to the same concept, and its specific implementation process is detailed in the above related embodiments and will not be repeated here.
[0219] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program stored therein is executed on a processor of an electronic device provided in an embodiment of the present application, the processor of the electronic device executes the steps in the detection and scheduling method of multi-dimensional data of a distribution network project provided in the present application. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.
[0220] The present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes various optional implementations of the detection and scheduling method of multi-dimensional data of the above-mentioned distribution network project.
[0221] The above is a detailed introduction to the detection and scheduling method and device for multi-dimensional data of a distribution network project provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
[0222] It should be noted that when the above embodiments of the present application are applied to specific products or technologies, the relevant data of the user is involved, and the user's permission or consent is required, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.
Claims
1. A detection and scheduling method for multi-dimensional data of a distribution network project, characterized in that: A detection and scheduling system for multidimensional data applied to a distribution network project, the detection and scheduling system for multidimensional data of the distribution network project comprising a distributed power generation system and a target distribution network, the distributed power generation system is used to supply power to the target distribution network, the distributed power generation system comprises a plurality of distributed power generation devices and a plurality of mobile energy storage devices, and the detection and scheduling method for multidimensional data of the distribution network project comprises: Acquire network structure information of the target distribution network, wherein the network structure information includes network topology, node layout, and line information between nodes; Inputting the network structure information into the target graph neural network to obtain a network structure detection result, wherein the network structure detection result is an abnormal network structure or a normal network structure; If the network structure detection result is that the network structure is normal, then obtaining multiple historical power supply information of the target distribution network in multiple historical time periods, the historical power supply information including load prediction accuracy, power supply margin, and load distribution information; Inputting the plurality of historical power supply information into the target timing network in chronological order, and obtaining a power supply detection result, wherein the power supply detection result is abnormal power supply or normal power supply; If the power supply detection result is that the power supply is normal, then obtaining the equipment information of each device in the target distribution network, the equipment information including the equipment material level, equipment performance parameters and the total cost of the equipment; If the device information meets the preset conditions, each of the distributed power generation devices is determined as a target power generation device; Acquire a real value of the power generation of the target power generation equipment and an estimated value of the power generation of the target power generation equipment; If the actual value of the power generation of the target power generation equipment is less than a preset ratio of the estimated value of the power generation of the target power generation equipment, the target power generation equipment is determined as an abnormal power generation equipment; Determine at least some of the multiple mobile energy storage devices as multiple target mobile energy storage devices; Connecting a plurality of the target mobile energy storage devices to a target distribution network to supply power to the target distribution network; Acquire the location information and abnormality times of historical abnormal power generation equipment that have abnormalities within a preset time period according to a preset cycle; Each of the mobile energy storage devices is dispatched based on the location information and the number of abnormalities of the historical abnormal power generation equipment.
2. The detection and scheduling method for multi-dimensional data of a distribution network project according to claim 1 is characterized in that: The detection and scheduling method of multi-dimensional data of the distribution network project comprises: Determine whether the equipment material level of each device in the target distribution network is higher than the corresponding preset equipment level; Determine whether the equipment performance parameter of each equipment in the target distribution network is higher than the corresponding equipment performance parameter; Determining whether the total equipment cost of the target distribution network is higher than a preset equipment cost; If the equipment material level of each device in the target distribution network is higher than the corresponding preset equipment level, the equipment performance parameters of each device in the target distribution network are higher than the corresponding equipment performance parameters, and the total equipment cost of the target distribution network is not higher than the preset equipment cost, it is determined that the equipment information meets the preset equipment conditions.
3. The detection and scheduling method for multi-dimensional data of a distribution network project according to claim 2 is characterized in that: The detection and scheduling method of multi-dimensional data of the distribution network project comprises: Based on multiple reference network structure information of multiple reference distribution networks and corresponding annotation labels, the annotation labels are network structure abnormality or network structure normal; Constructing structured graph data based on multiple reference network structure information, wherein the graph data includes node data of each node; Taking the node data as the node sample, randomly select K node samples as the initial cluster center, and calculate the distance between each node sample and the initial cluster center; Assign each node sample to the cluster with the nearest cluster center, and update the cluster center of each cluster; Based on the updated cluster center, perform iterative calculations until the stop condition is met, completing the clustering of all node data; Encode the node data after clustering and classification, and generate a final category label for each node data, wherein the category label is abnormal or normal; The category label of each node data is added to the node data as the feature of the node and multiple reference network structure information is updated to obtain multiple updated reference network structure information and corresponding annotation labels to obtain a data set; A preset graph neural network is trained based on the data set to obtain the target graph neural network.
4. The detection and scheduling method for multi-dimensional data of a distribution network project according to claim 1, characterized in that: The scheduling of each of the mobile energy storage devices based on the location information and the number of abnormalities of the historical abnormal power generation equipment includes: Clustering the distributed power generation equipment based on the location information and the number of abnormalities of the historical abnormal power generation equipment to obtain a plurality of second equipment clusters; Determine an area enclosed by each of the historically abnormal power generation equipment in the second equipment cluster as an abnormal area; Obtaining the abnormal equipment ratio of the historically abnormal power generation equipment in the abnormal area; Determine the target device movement information based on the abnormal device ratio of the historical abnormal power generation equipment in the abnormal area, the total regional equipment of the distributed power generation equipment, and the regional area size, wherein the target device movement information includes the target movement position of each of the mobile energy storage devices; Each of the mobile energy storage devices is moved based on the target device movement information, so as to move each of the mobile energy storage devices from a current position to a corresponding target movement position.
5. The detection and scheduling method for multi-dimensional data of a distribution network project according to claim 4 is characterized in that: The determining of the target device movement information based on the abnormal device ratio of the historical abnormal power generation devices in the abnormal area, the total regional equipment volume of the distributed power generation equipment, and the regional area size includes: Based on the abnormal device proportion of the historical abnormal power generation equipment in the abnormal area, the total regional equipment amount of the distributed power generation equipment and the regional area size, the energy storage device allocation quantity and allocation priority of the mobile energy storage device allocated to each abnormal area are determined, wherein the higher the abnormal device proportion, the higher the energy storage device allocation quantity and the allocation priority; the larger the total regional equipment amount, the higher the energy storage device allocation quantity and the allocation priority; the larger the regional area size, the higher the energy storage device allocation quantity and the allocation priority; The abnormal area with the highest allocation priority is sequentially determined as the target area, the allocation quantity of the energy storage devices in the target area is determined as the target allocation quantity, and the second target distance between each of the mobile energy storage devices and each of the historically abnormal power generation devices in the target area is respectively calculated; Determine the minimum value of the second target distance between the mobile energy storage device and each of the historical abnormal power generation devices as the third target distance between the mobile energy storage device and the target area; Determine the mobile energy storage devices of the target allocation quantity that are ranked first in descending order of the third target distance as the allocated energy storage devices of the target area, and obtain the allocated energy storage devices of each of the abnormal areas; The position of the historically abnormal power generation device having the smallest second target distance from the allocated energy storage device in the target area is determined as the target moving position of the allocated energy storage device, and the target moving position of each of the mobile energy storage devices is obtained.
6. The detection and scheduling method for multi-dimensional data of a distribution network project according to claim 5, characterized in that: The moving each of the mobile energy storage devices based on the target device movement information to move each of the mobile energy storage devices from a current position to a corresponding target movement position includes: Determine the mobile resource consumption of each mobile energy storage device moving to the target mobile position based on the target device movement information; Obtaining the amount of power transmission resource loss when the mobile energy storage device transmits electric energy to the historical abnormal power generation equipment and connects to the target distribution network within the preset time period; If the power transmission resource loss is greater than the mobile resource consumption, each of the mobile energy storage devices is moved based on the target device movement information to move each of the mobile energy storage devices from a current position to a corresponding target movement position.
7. The detection and scheduling method for multi-dimensional data of a distribution network project according to claim 1, characterized in that: The step of determining at least some of the plurality of mobile energy storage devices as a plurality of target mobile energy storage devices comprises: Obtaining the number of times each mobile energy storage device has been charged and discharged, the time interval since the last charge and discharge, and the remaining power; Determine the candidate priority based on the number of times the mobile energy storage device has been charged and discharged, the time interval since the last charge and discharge, and the remaining power; The plurality of mobile energy storage devices ranked higher in order of candidate priority from high to low are determined as the plurality of target mobile energy storage devices.
8. A detection and dispatching device for multi-dimensional data of a distribution network project, characterized in that: A detection and scheduling system for multidimensional data applied to a distribution network project, the detection and scheduling system for multidimensional data of the distribution network project comprising a distributed power generation system and a target distribution network, the distributed power generation system is used to supply power to the target distribution network, the distributed power generation system comprises a plurality of distributed power generation devices and a plurality of mobile energy storage devices, the detection and scheduling device for multidimensional data of the distribution network project comprises: A first acquisition module is used to acquire network structure information of the target distribution network, wherein the network structure information includes network topology, node layout, and line information between nodes; A first input module is used to input the network structure information into a target graph neural network to obtain a network structure detection result, wherein the network structure detection result is an abnormal network structure or a normal network structure; A second acquisition module is used to acquire a plurality of historical power supply information of the target distribution network in a plurality of historical time periods if the network structure detection result is that the network structure is normal, wherein the historical power supply information includes load prediction accuracy, power supply margin, and load distribution information; A second input module is used to input the plurality of historical power supply information into the target timing network in chronological order to obtain a power supply detection result, wherein the power supply detection result is abnormal power supply or normal power supply; A third acquisition module is used to acquire device information of each device in the target distribution network if the power supply detection result is that the power supply is normal, wherein the device information includes device material level, device performance parameters and total device cost; A first determination module, configured to determine each of the distributed power generation devices as a target power generation device if the device information meets a preset condition; A fourth acquisition module, used to acquire a real value of the power generation of the target power generation equipment and an estimated value of the power generation of the target power generation equipment; A second determination module is used to determine the target power generation equipment as an abnormal power generation equipment if the actual power generation value of the target power generation equipment is less than a preset ratio of the estimated power generation value of the target power generation equipment; A third determination module, configured to determine at least some of the multiple mobile energy storage devices as multiple target mobile energy storage devices; An access module, used to connect a plurality of the target mobile energy storage devices to a target distribution network to supply power to the target distribution network; A fifth acquisition module is used to acquire, according to a preset period, the location information and the number of abnormalities of the historical abnormal power generation equipment that has occurred abnormalities within a preset time period; A scheduling module is used to schedule each of the mobile energy storage devices based on the location information and the number of abnormalities of the historical abnormal power generation equipment.
9. An electronic device, characterized in that: It comprises a memory and a processor, the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the steps in the method for detecting and scheduling multi-dimensional data of a distribution network project as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the method for detecting and scheduling multi-dimensional data of a distribution network project as described in any one of claims 1 to 7.
