A virtual power plant resource partitioning method based on a multilayer perceptron

Abstract

The application provides a virtual power plant resource partitioning method based on a multilayer perceptron, and the method comprises the following steps: acquiring geographical position information of each resource in a virtual power plant; adjusting a density-based clustering algorithm according to the geographical position information of each resource in the virtual power plant; performing clustering analysis on the geographical position information of each resource by using the adjusted density-based clustering algorithm to obtain a plurality of first clustering results; counting the number of geographical position information contained in each first clustering result, adjusting the first clustering result according to the number, and obtaining a plurality of second clustering results; taking a range formed by each second clustering result as a partition; and inputting the geographical position information of each resource into a pre-trained multilayer perceptron to obtain an importance score of each resource. The method can partition and effectively regulate each energy resource.

Description

Technical Field

[0001] This invention relates to the field of virtual power plant technology, and more specifically, to a virtual power plant resource partitioning method based on a multilayer sensor. Background Technology

[0002] Virtual power plants were first proposed in 1997 and gained attention in Europe and North America in the early 21st century. Today, many mature demonstration projects have been developed, playing a vital role in absorbing distributed energy resources and stabilizing the electricity market. For my country, however, virtual power plants, as an emerging technology, are still in their initial stages.

[0003] A virtual power plant (VFP) is a power coordination and management system that uses advanced communication technologies and software architecture to aggregate and coordinate various geographically dispersed distributed energy sources, enabling them to participate as a special power plant in the electricity market and grid operation. A VFP aggregates controllable generating units, distributed energy sources, energy storage devices, loads, electric vehicles, communication equipment, etc., onto an energy cloud, and achieves its functions through unified coordination using technical means. Among these, VFP zoning plays a crucial role in VFP operation; therefore, effective zoning is essential for the operation and control of the VFP. Summary of the Invention

[0004] The purpose of this invention is to provide a virtual power plant resource partitioning method based on a multilayer sensor to improve the above-mentioned problems.

[0005] To achieve the above objectives, the embodiments of this application provide the following technical solutions:

[0006] A virtual power plant resource partitioning method based on multilayer sensor includes:

[0007] Obtain the geographical location information of each resource in the virtual power plant;

[0008] The density-based clustering algorithm is adjusted based on the geographical location information of each resource in the virtual power plant. The adjusted density-based clustering algorithm is then used to perform cluster analysis on the geographical location information of each resource to obtain multiple first clustering results.

[0009] The number of geographic location information items contained in each first cluster result is counted. The first cluster results are adjusted according to the number of items to obtain multiple second cluster results. Each second cluster result contains the same number of geographic location information items. The range formed by each second cluster result is used as a partition.

[0010] The geographical location information of each resource is input into a pre-trained multilayer perceptron to obtain the importance score of each resource. The total importance score of each partition is then sent to the staff to help them manage each partition.

[0011] Furthermore, the density-based clustering algorithm is adjusted based on the geographical location information of each resource in the virtual power plant, including:

[0012] The geographic location information of each resource in the virtual power plant is collected to obtain a dataset G, and a neighborhood radius list is generated based on the dataset G.

[0013] A list of minimum neighborhood points is generated based on the neighborhood radius list; the density-based clustering algorithm is then adjusted based on the neighborhood radius list and the list of minimum neighborhood points to obtain the adjusted clustering algorithm.

[0014] Furthermore, a list of neighborhood radii is generated based on the dataset G, including:

[0015] Calculate the distance distribution matrix of each geographic location in the dataset;

[0016] Sort the data in each row of the distance distribution matrix from smallest to largest. After sorting, use the quartile method to remove outliers in each column of the distance distribution matrix. Then, calculate the expected value of the remaining data points to obtain the first value. Save all the calculated first values ​​to the neighborhood radius list.

[0017] Furthermore, the distance distribution matrix of each geographic location in the dataset is calculated, including:

[0018] The distance distribution matrix of each geographic location information in the dataset is calculated according to formula (1), which is:

[0019] G n×n ={Point_Dist(i,j)1≤i≤n,1≤j≤n} (1)

[0020] In formula (1), G n×n Let G be an n×n symmetric matrix; n is the length of the dataset G; Point_Dist(i,j) is the distance between the i-th and j-th geographic locations in the dataset G.

[0021] Furthermore, a list of minimum neighborhood points is generated based on the neighborhood radius list; the density-based clustering algorithm is then adjusted based on the neighborhood radius list and the list of minimum neighborhood points to obtain an adjusted clustering algorithm, including:

[0022] For each neighborhood radius in the neighborhood radius list, the expected value of the number of sample points contained in the neighborhood is used as a parameter in the list of minimum neighborhood points to obtain the list of minimum neighborhood points.

[0023] Arbitrarily select one value from the neighborhood radius list and the neighborhood minimum number of points list as a parameter in the density-based clustering algorithm. After selection, perform clustering analysis using the density-based clustering algorithm to obtain multiple third clustering results. Based on the multiple third clustering results, obtain the adjusted clustering algorithm.

[0024] Furthermore, an adjusted clustering algorithm is obtained based on multiple third-level clustering results, including:

[0025] The silhouette coefficient method is used to calculate the silhouette coefficients corresponding to multiple third clustering results. The silhouette coefficients are analyzed. If the silhouette coefficient is greater than a preset threshold, the currently selected neighborhood radius and the minimum number of neighborhood points are used as the final parameters of the density-based clustering algorithm. Otherwise, a value is randomly selected from the neighborhood radius list and the minimum number of neighborhood points list as the parameters in the density-based clustering algorithm, and clustering and silhouette coefficient calculation are performed again until the silhouette coefficient is greater than the preset threshold.

[0026] Furthermore, the number of geographical location information items contained in each first cluster result is counted, and the first cluster results are adjusted based on the count to obtain multiple second cluster results, including:

[0027] Count the number of geographical location information items contained in each first cluster result. If the number is not equal to the preset value, adjust the geographical location information items contained in each first cluster result so that the number of geographical location information items contained in each first cluster result is equal to the preset value.

[0028] Furthermore, the geographic location information contained in each first cluster result is adjusted so that the number of geographic location information items contained in each first cluster result is equal to a preset value, including:

[0029] The first clustering result containing the number of geographic information items equal to the preset value is recorded as the cluster that does not need adjustment; the first clustering result containing the number of geographic information items not equal to the preset value is recorded as the cluster that needs adjustment; calculate the distance from each cluster that needs adjustment to each cluster that does not need adjustment, add the distances corresponding to each cluster that needs adjustment to obtain the first value, start traversing from the cluster that needs adjustment with the largest first value, and make adjustments, so that the number of geographic information items contained in each first clustering result is equal to the preset value.

[0030] Furthermore, starting with the cluster with the largest first value that needs adjustment, the process iterates through the clusters and makes adjustments so that the number of geographic location information items contained in each first cluster result is equal to a preset value, including:

[0031] Starting with the cluster with the largest first value that needs adjustment, the process iterates through the clusters. If the number of geographic information items contained in the cluster with the largest first value is less than a preset value, the geographic information item closest to the centroid of the cluster with the largest first value is added to the cluster with the largest first value, making the number of geographic information items contained in the cluster equal to the preset value. If the number of geographic information items contained in the cluster with the largest first value is greater than the preset value, the process starts from the geographic information item closest to the centroid of all geographic information items in the cluster with the largest first value and removes them sequentially from the cluster with the largest first value until the number of geographic information items contained in the cluster with the largest first value equals the preset value. During the adjustment process, when the number of geographic information items contained in the cluster equals the preset value, the first clustering result is recorded as a cluster that does not need adjustment.

[0032] Furthermore, the range formed by each second clustering result is used as a partition, including:

[0033] The geographic range formed on the map by all the geographic location information contained in each second cluster result is taken as a partition.

[0034] Secondly, embodiments of this application provide a virtual power plant resource partitioning device based on a multilayer sensor, comprising:

[0035] The acquisition module is used to acquire the geographical location information of each resource in the virtual power plant;

[0036] The clustering module is used to adjust the density-based clustering algorithm based on the geographical location information of each resource in the virtual power plant. The adjusted density-based clustering algorithm is used to perform cluster analysis on the geographical location information of each resource to obtain multiple first clustering results.

[0037] The adjustment module is used to count the number of geographical location information contained in each first cluster result, adjust the first cluster result according to the number, and obtain multiple second cluster results. Each second cluster result contains the same number of geographical location information, and the range formed by each second cluster result is used as a partition.

[0038] The management module is used to input the geographic location information of each resource into a pre-trained multilayer perceptron to obtain the importance score of each resource, and send the total importance score of each partition to the staff to help the staff manage each partition.

[0039] Thirdly, embodiments of this application provide a debris flow risk monitoring device, the device including a memory and a processor. The memory is used to store a computer program; the processor is used to execute the computer program to implement the steps of the above-described virtual power plant resource partitioning method based on a multilayer sensor.

[0040] Fourthly, embodiments of this application provide a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described virtual power plant resource partitioning method based on a multilayer sensor.

[0041] The beneficial effects of this invention are as follows:

[0042] In this invention, the geographical locations of various energy resources are first obtained, and cluster analysis is performed from the perspective of geographical location, resulting in multiple clustering results. Furthermore, the traditional density-based clustering algorithm is improved during clustering, leading to superior clustering performance. After clustering, considering the evenness of resources across different zones, the clustering results are dynamically adjusted to ensure resource balance across zones. Finally, the importance of resources in each zone is scored, which helps staff understand the importance of each zone, facilitating better management and control.

[0043] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a schematic diagram of the virtual power plant resource partitioning method based on multilayer sensor described in this embodiment of the invention;

[0046] Figure 2 This is a schematic diagram of the virtual power plant resource partitioning device based on a multilayer sensor as described in this embodiment of the invention;

[0047] Figure 3 This is a schematic diagram of the virtual power plant resource partitioning equipment structure based on a multilayer sensor as described in this embodiment of the invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0049] It should be noted that similar reference numerals or letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0050] Example 1

[0051] like Figure 1 As shown, this embodiment provides a virtual power plant resource partitioning method based on a multilayer sensor, which includes steps S1, S2, S3 and S4.

[0052] Step S1: Obtain the geographical location information of each resource in the virtual power plant;

[0053] In this step, each resource can be understood as an energy resource, that is, an object that supplies energy;

[0054] Step S2: Adjust the density-based clustering algorithm according to the geographical location information of each resource in the virtual power plant, and use the adjusted density-based clustering algorithm to perform cluster analysis on the geographical location information of each resource to obtain multiple first clustering results;

[0055] In this step, the density-based clustering algorithm is the DBSCAN clustering algorithm. The specific implementation steps of this step include steps S21 and S22.

[0056] Step S21: Collect the geographical location information of each resource in the virtual power plant to obtain dataset G, and generate a neighborhood radius list based on the dataset G;

[0057] In this step, the specific implementation steps for generating the neighborhood radius list based on the dataset G include steps S211 and S212;

[0058] Step S211: Calculate the distance distribution matrix of each geographic location information in the dataset;

[0059] The specific implementation steps of this step include step S2111;

[0060] Step S2111: Calculate the distance distribution matrix of each geographic location information in the dataset according to formula (1), where formula (1) is:

[0061] G n×n ={Point_Dist(i,j)1≤i≤n,1≤j≤n} (1)

[0062] In formula (1), G n×n Let G be an n×n symmetric matrix; n is the length of the dataset G; Point_Dist(i,j) is the distance between the i-th and j-th geographic locations in the dataset G.

[0063] Step S212: Sort the data in each row of the distance distribution matrix from smallest to largest. After sorting, use the quartile method to remove outliers in each column of the distance distribution matrix. Then, calculate the expected value of the remaining data points to obtain the first value. Save all the calculated first values ​​to the neighborhood radius list.

[0064] Step S22: Generate a list of minimum neighborhood points based on the neighborhood radius list; adjust the parameters of the density-based clustering algorithm based on the neighborhood radius list and the list of minimum neighborhood points to obtain the adjusted clustering algorithm.

[0065] The specific implementation steps of this step include step S221 and step S222;

[0066] Step S221: For each neighborhood radius in the neighborhood radius list, take the expected value of the number of sample points contained in the neighborhood as a parameter in the neighborhood minimum number of points list to obtain the neighborhood minimum number of points list.

[0067] This step can be understood as:

[0068]

[0069] In formula (2), Pi is the number of samples in the Epsilon neighborhood of the i-th sample point, and n is the total number of sample points in the dataset G.

[0070] Step S222: Randomly select one value from the neighborhood radius list and the neighborhood minimum number of points list as a parameter in the density-based clustering algorithm. After selection, perform clustering analysis using the density-based clustering algorithm to obtain multiple third clustering results. Based on the multiple third clustering results, obtain the adjusted clustering algorithm.

[0071] In this step, the specific implementation steps of obtaining the adjusted clustering algorithm based on multiple third clustering results include step S2221;

[0072] Step S2221: Calculate the silhouette coefficients corresponding to multiple third clustering results using the silhouette coefficient method; analyze the silhouette coefficients, wherein if the silhouette coefficient is greater than a preset threshold, the currently selected neighborhood radius and the minimum number of neighborhood points are used as the final parameters of the density-based clustering algorithm; otherwise, arbitrarily select a value from the neighborhood radius list and the minimum number of neighborhood points list as the parameters in the density-based clustering algorithm, and perform clustering and silhouette coefficient calculation again until the silhouette coefficient is greater than the preset threshold.

[0073] Traditional DBSCAN clustering algorithm suffers from significant human intervention during training, which negatively impacts clustering performance. Based on the above steps, a new DBSCAN algorithm is proposed that adaptively finds the optimal neighborhood radius (Epsilon parameter) and the minimum number of points (MinPts parameter) without human intervention. This algorithm overcomes the shortcomings of traditional DBSCAN clustering algorithm.

[0074] After the above clustering, considering that the resources contained in each partition should be as even as possible to avoid uneven distribution, this embodiment adjusts each clustering result after clustering. The adjustment steps can make the resources in each partition more even.

[0075] Step S3: Count the number of geographical location information contained in each first cluster result, adjust the first cluster result according to the number, and obtain multiple second cluster results. Each second cluster result contains the same number of geographical location information. The range formed by each second cluster result is used as a partition.

[0076] The specific implementation steps of this step include step S31;

[0077] Step S31: Count the number of geographical location information contained in each first cluster result. If the number is not equal to the preset value, adjust the geographical location information contained in each first cluster result so that the number of geographical location information contained in each first cluster result is equal to the preset value.

[0078] The preset values ​​in this step can be customized according to the user's needs. The specific implementation steps include step S311.

[0079] Step S311: Record the first cluster result containing the number of geographic location information items equal to the preset value as the cluster that does not need adjustment; record the first cluster result containing the number of geographic location information items not equal to the preset value as the cluster that needs adjustment; calculate the distance from each cluster that needs adjustment to each cluster that does not need adjustment, add the distances corresponding to each cluster that needs adjustment to obtain the first value, start traversing from the cluster that needs adjustment with the largest first value, and make adjustments so that the number of geographic location information items contained in each first cluster result is equal to the preset value.

[0080] The specific implementation steps of this step include step S3111;

[0081] Step S3111: Start traversing from the cluster with the largest first value that needs adjustment. If the number of geographical location information contained in the cluster with the largest first value that needs adjustment is less than a preset value, add the geographical location information closest to the centroid of the cluster with the largest first value that needs adjustment to the cluster with the largest first value, so that the number of geographical location information contained in the cluster with the largest first value that needs adjustment is equal to the preset value. If the number of geographical location information contained in the cluster with the largest first value that needs adjustment is greater than the preset value, start from the geographical location information closest to the centroid of all geographical location information in the cluster with the largest first value that needs adjustment, and remove it from the cluster with the largest first value that needs adjustment in turn, until the number of geographical location information contained in the cluster with the largest first value that needs adjustment is equal to the preset value. At the same time, during the adjustment process, when the number of geographical location information contained is equal to the preset value, the first clustering result is recorded as a cluster that does not need adjustment.

[0082] In step S3, the range formed by each second clustering result is taken as a partition. The specific implementation steps include step S32.

[0083] Step S32: Take the geographic range formed on the map by all the geographic location information contained in each second cluster result as a partition.

[0084] Step S4: Input the geographical location information of each resource into the pre-trained multilayer perceptron to obtain the importance score of each resource, and send the total importance score of each partition to the staff to help the staff manage each partition.

[0085] In this step, the pre-trained multilayer perceptron represents the one-to-one correspondence between geographic location information and importance scores; the total importance score can help staff understand the importance of each zone, which is more conducive to management decision-making.

[0086] In this embodiment, the geographical locations of each energy resource were first obtained, and cluster analysis was performed from the perspective of geographical location, resulting in multiple clustering results. Simultaneously, the traditional density-based clustering algorithm was improved during clustering, resulting in superior clustering performance. After clustering, considering the evenness of resources across different partitions, the clustering results were dynamically adjusted to ensure resource balance across partitions. Finally, the importance of resources in each partition was scored, which helps staff understand the importance of each partition, facilitating better management and control.

[0087] Example 2

[0088] like Figure 2 As shown, this embodiment provides a virtual power plant resource partitioning device based on a multilayer sensor. The device includes an acquisition module 1, a clustering module 2, an adjustment module 3, and a management module 4.

[0089] Module 1 is used to obtain the geographical location information of each resource in the virtual power plant;

[0090] Clustering module 2 is used to adjust the density-based clustering algorithm according to the geographical location information of each resource in the virtual power plant. The adjusted density-based clustering algorithm is used to perform clustering analysis on the geographical location information of each resource to obtain multiple first clustering results.

[0091] Adjustment module 3 is used to count the number of geographical location information contained in each first cluster result, adjust the first cluster result according to the number, and obtain multiple second cluster results. Each second cluster result contains the same number of geographical location information, and the range formed by each second cluster result is used as a partition.

[0092] The management module 4 is used to input the geographical location information of each resource into the pre-trained multilayer perceptron to obtain the importance score of each resource, and send the total importance score of each partition to the staff to help the staff manage each partition.

[0093] It should be noted that the specific manner in which each module performs its operation in the apparatus described in the above embodiments has been described in detail in the embodiments of the method, and will not be elaborated here.

[0094] Example 3

[0095] Corresponding to the above method embodiments, this disclosure also provides a virtual power plant resource partitioning device based on a multilayer sensor. The virtual power plant resource partitioning device based on a multilayer sensor described below can be referred to in correspondence with the virtual power plant resource partitioning method based on a multilayer sensor described above.

[0096] Figure 3 This is a block diagram illustrating a virtual power plant resource partitioning device 300 based on a multilayer sensor, according to an exemplary embodiment. Figure 3 As shown, the virtual power plant resource partitioning device 300 based on a multilayer sensor may include a processor 301 and a memory 302. The virtual power plant resource partitioning device 300 based on a multilayer sensor may also include one or more of a multimedia component 303, an I / O interface 304, and a communication component 305.

[0097] The processor 301 controls the overall operation of the multilayer sensor-based virtual power plant resource partitioning device 300 to complete all or part of the steps in the multilayer sensor-based virtual power plant resource partitioning method described above. The memory 302 stores various types of data to support the operation of the multilayer sensor-based virtual power plant resource partitioning device 300. This data may include, for example, instructions for any application or method operating on the multilayer sensor-based virtual power plant resource partitioning device 300, as well as application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 302 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 302 or transmitted via the communication component 305. The audio component also includes at least one speaker for outputting audio signals. I / O interface 304 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 305 is used for wired or wireless communication between the multilayer sensor-based virtual power plant resource partitioning device 300 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 305 may include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0098] In an exemplary embodiment, the virtual power plant resource partitioning device 300 based on a multilayer sensor may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the virtual power plant resource partitioning method based on a multilayer sensor described above.

[0099] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the multilayer sensor-based virtual power plant resource partitioning method described above. For example, the computer-readable storage medium may be the memory 302 including program instructions described above, which may be executed by the processor 301 of the multilayer sensor-based virtual power plant resource partitioning device 300 to complete the multilayer sensor-based virtual power plant resource partitioning method described above.

[0100] Example 4

[0101] Corresponding to the above method embodiments, this disclosure also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the virtual power plant resource partitioning method based on multilayer sensor described above.

[0102] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the virtual power plant resource partitioning method based on a multilayer sensor as described in the above method embodiments.

[0103] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0104] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A virtual power plant resource partitioning method based on a multilayer sensor, characterized in that, include: Obtain the geographical location information of each resource in the virtual power plant; The density-based clustering algorithm is adjusted based on the geographical location information of each resource in the virtual power plant. The adjusted density-based clustering algorithm is then used to perform cluster analysis on the geographical location information of each resource to obtain multiple first clustering results. The number of geographic location information items contained in each first cluster result is counted. The first cluster results are adjusted according to the number of items to obtain multiple second cluster results. Each second cluster result contains the same number of geographic location information items. The range formed by each second cluster result is used as a partition. The geographical location information of each resource is input into a pre-trained multilayer perceptron to obtain the importance score of each resource. The total importance score corresponding to each partition is sent to the staff to help them manage each partition. The adjustment of the density-based clustering algorithm based on the geographical location information of each resource in the virtual power plant includes: The geographic location information of each resource in the virtual power plant is collected to obtain a dataset G, and a neighborhood radius list is generated based on the dataset G. A list of minimum neighborhood points is generated based on the neighborhood radius list; the density-based clustering algorithm is adjusted according to the neighborhood radius list and the list of minimum neighborhood points to obtain the adjusted clustering algorithm; The step of generating a neighborhood radius list based on the dataset G includes: Calculate the distance distribution matrix of each geographic location in the dataset; Sort the data in each row of the distance distribution matrix from smallest to largest. After sorting, use the quartile method to remove outliers in each column of the distance distribution matrix. Then, calculate the expected value of the remaining data points to obtain the first value. Save all the calculated first values ​​to the neighborhood radius list. The distance distribution matrix of each geographic location information in the calculation dataset includes: The distance distribution matrix of each geographic location information in the dataset is calculated according to formula (1), which is: G n×n ={Point D ist(i,j)|1≤i≤n,1≤j≤n} (1) In formula (1), G n×n G is an n×n symmetric matrix; n is the length of the dataset G; Point D ist(i,j) is the distance between the i-th and j-th geographic location information in dataset G; The process includes generating a list of minimum neighborhood points based on the neighborhood radius list; and adjusting the parameters of the density-based clustering algorithm based on the neighborhood radius list and the list of minimum neighborhood points to obtain an adjusted clustering algorithm, including: For each neighborhood radius in the neighborhood radius list, the expected value of all sample points in the neighborhood is used as a parameter in the list of minimum neighborhood points to obtain the list of minimum neighborhood points. Arbitrarily select one value from the neighborhood radius list and the neighborhood minimum number of points list as a parameter in the density-based clustering algorithm. After selection, perform clustering analysis using the density-based clustering algorithm to obtain multiple third clustering results. Based on the multiple third clustering results, obtain the adjusted clustering algorithm.

2. The virtual power plant resource partitioning method based on a multilayer sensor according to claim 1, characterized in that, The adjusted clustering algorithm is derived based on multiple third-order clustering results, including: The silhouette coefficient method is used to calculate the silhouette coefficients corresponding to multiple third clustering results. The silhouette coefficients are analyzed. If the silhouette coefficient is greater than a preset threshold, the currently selected neighborhood radius and the minimum number of neighborhood points are used as the final parameters of the density-based clustering algorithm. Otherwise, a value is randomly selected from the neighborhood radius list and the minimum number of neighborhood points list as the parameters in the density-based clustering algorithm, and clustering and silhouette coefficient calculation are performed again until the silhouette coefficient is greater than the preset threshold.

3. The virtual power plant resource partitioning method based on a multilayer sensor according to claim 1, characterized in that, The number of geographic location information items contained in each first cluster result is counted. The first cluster results are then adjusted based on this count to obtain multiple second cluster results, including: Count the number of geographical location information items contained in each first cluster result. If the number is not equal to the preset value, adjust the geographical location information items contained in each first cluster result so that the number of geographical location information items contained in each first cluster result is equal to the preset value.

4. The virtual power plant resource partitioning method based on a multilayer sensor according to claim 3, characterized in that, The geographic location information contained in each first cluster result is adjusted so that the number of geographic location information items in each first cluster result is equal to a preset value, including: The first clustering result containing the number of geographic information items equal to the preset value is recorded as the cluster that does not need adjustment; the first clustering result containing the number of geographic information items not equal to the preset value is recorded as the cluster that needs adjustment; calculate the distance from each cluster that needs adjustment to each cluster that does not need adjustment, add the distances corresponding to each cluster that needs adjustment to obtain the first value, start traversing from the cluster that needs adjustment with the largest first value, and make adjustments, so that the number of geographic information items contained in each first clustering result is equal to the preset value.

5. The virtual power plant resource partitioning method based on a multilayer sensor according to claim 4, characterized in that, Starting with the cluster with the largest first value that needs adjustment, iterate through the clusters and make adjustments so that the number of geographic location information items contained in each first cluster result is equal to a preset value, including: Starting with the cluster with the largest first value that needs adjustment, the process iterates through the clusters. If the number of geographic information items contained in the cluster with the largest first value is less than a preset value, the geographic information item closest to the centroid of the cluster with the largest first value is added to the cluster with the largest first value, making the number of geographic information items contained in the cluster equal to the preset value. If the number of geographic information items contained in the cluster with the largest first value is greater than the preset value, the process starts from the geographic information item closest to the centroid of all geographic information items in the cluster with the largest first value and removes them sequentially from the cluster with the largest first value until the number of geographic information items contained in the cluster with the largest first value equals the preset value. During the adjustment process, when the number of geographic information items contained in the cluster equals the preset value, the first clustering result is recorded as a cluster that does not need adjustment.

6. The virtual power plant resource partitioning method based on a multilayer sensor according to claim 1, characterized in that, Each range formed by the second clustering result is used as a partition, including: The geographic range formed on the map by all the geographic location information contained in each second cluster result is taken as a partition.

Images