Power station data sharing method and device, electronic equipment and storage medium

Abstract

The invention discloses a power station data sharing method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence. On the basis that shared environment monitoring equipment is reserved, residual power stations are clustered, and virtual environment monitoring equipment is established for power station clusters obtained through clustering; meteorological data requirements of a large number of scattered remaining power stations are integrated to a small number of representative target nodes. The problems that the coverage rate of environment monitoring equipment of a distributed photovoltaic power station system is low and part of power stations in a power station sparse distribution area cannot obtain meteorological data support due to the fact that the part of power stations exceed the effective sharing range of single nearest environment monitoring equipment are solved, and the technical effect of improving the coverage rate of the environment monitoring equipment is achieved. Even if a certain environment monitoring device breaks down, the photovoltaic power station in the original coverage area of the environment monitoring device can be quickly switched into the power station cluster of the virtual environment monitoring device, so that the continuity of meteorological data supply is ensured, and the robustness of the distributed photovoltaic power station system when the distributed photovoltaic power station system deals with a single-point fault is improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a power plant data sharing method, apparatus, electronic device and storage medium. Background Technology

[0002] In the management of distributed photovoltaic power stations, providing accurate meteorological data support is a core requirement. This is especially true for a large number of photovoltaic power stations that have not installed on-site environmental monitoring equipment, as the lack of meteorological data directly affects subsequent power generation efficiency analysis and system evaluation.

[0003] In related technologies, when a photovoltaic power station is not equipped with its own environmental monitoring equipment, it is usually linked to a geographically nearest power station that has installed environmental monitoring equipment, and the measured meteorological data from the environmental monitoring equipment installed there is used directly.

[0004] However, as the scale of photovoltaic power plant clusters expands, the limitations of this solution become increasingly apparent. First, its coverage is limited by the actual layout of environmental monitoring equipment. In areas with sparsely distributed power plants, those far from existing monitoring equipment cannot be effectively covered, creating data blind spots. Second, if this single data source fails, all power plants relying on it will immediately lose meteorological data support, leading to the interruption of core business operations based on this data, exposing the inadequacy of distributed photovoltaic power plant systems in responding to single-point failures. Summary of the Invention

[0005] This application provides a power plant data sharing method, apparatus, electronic device, and storage medium to at least solve the problems of low coverage of environmental monitoring equipment and low robustness in dealing with single-point failures in distributed photovoltaic power plant systems in related technologies.

[0006] This application provides a power plant data sharing method, including: In a distributed photovoltaic power station cluster, select several remaining power stations that currently do not share environmental monitoring equipment; An undirected graph is constructed based on the relative position information between the multiple remaining power stations; wherein, the vertices of the undirected graph represent the remaining power stations, and the edges of the vertices of the undirected graph represent the relative position information between the remaining power stations. The adaptive clustering radius is determined based on the minimum distance between adjacent remaining power stations represented by the undirected graph. Based on the adaptive clustering radius, the multiple remaining power stations are clustered to obtain multiple power station clusters; wherein, the power station cluster includes multiple of the remaining power stations; For any of the aforementioned power plant clusters, the remaining power plant closest to the cluster centroid is selected as the target power plant. A virtual environmental monitoring device is created on the target power station to determine virtual meteorological data within the power station cluster based on the virtual environmental monitoring device; wherein, all remaining power stations within the power station cluster share the virtual meteorological data.

[0007] This application also provides a power plant data sharing device, including: The filtering module is used to filter out multiple remaining power stations in a distributed photovoltaic power station cluster that do not currently share environmental monitoring equipment; A construction module is used to construct an undirected graph based on the relative position information between the multiple remaining power stations; wherein, the vertices of the undirected graph represent the remaining power stations, and the edges of the vertices of the undirected graph represent the relative position information between the remaining power stations; The determination module is used to determine the adaptive clustering radius based on the minimum distance between adjacent remaining power stations represented by the undirected graph; A clustering module is used to cluster the multiple remaining power stations according to the adaptive clustering radius to obtain multiple power station clusters; wherein, the power station cluster includes multiple remaining power stations; The selection module is used to select, for any of the power plant clusters, the remaining power plant closest to the cluster centroid as the target power plant; A sharing module is used to create a virtual environmental monitoring device on the target power station to determine virtual meteorological data within the power station cluster based on the virtual environmental monitoring device; wherein, all remaining power stations within the power station cluster share the virtual meteorological data.

[0008] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of any of the above-described power plant data sharing methods.

[0009] This application also provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of any of the above-described power plant data sharing methods.

[0010] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described power plant data sharing methods.

[0011] This application achieves the goal of consolidating the meteorological data needs of a large number of scattered remaining power stations into a few representative target nodes by clustering the remaining power stations while retaining shared environmental monitoring equipment, and establishing virtual environmental monitoring equipment for the resulting power station clusters. This solves the problems of low environmental monitoring equipment coverage in distributed photovoltaic power station systems and the inability of some power stations in sparsely distributed areas to obtain meteorological data support because they are outside the effective sharing range of a single nearest environmental monitoring equipment. It achieves the technical effect of improving the coverage of environmental monitoring equipment. Even if a certain environmental monitoring equipment fails, photovoltaic power stations within its original coverage area can quickly switch to the power station cluster of the virtual environmental monitoring equipment to ensure the continuity of meteorological data supply, thus improving the robustness of the distributed photovoltaic power station system in the face of single-point failures. Attached Figure Description

[0012] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of the power plant data sharing system on which the embodiments of this application are based; Figure 2 A flowchart illustrating the power plant data sharing method provided in this application embodiment; Figure 3 This is a schematic diagram of the structure of an undirected graph provided in an embodiment of this application; Figure 4 A flowchart illustrating an exemplary power plant data sharing method provided in this application embodiment; Figure 5 A flowchart illustrating another exemplary power plant data sharing method provided in this application embodiment; Figure 6 A flowchart illustrating yet another exemplary power plant data sharing method provided in this application embodiment; Figure 7 This is a schematic diagram of a clustering algorithm provided in an embodiment of this application; Figure 8 This is a schematic diagram of the structure of the power plant data sharing device provided in the embodiments of this application; Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0014] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0015] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0016] Environmental monitoring equipment, or simply environmental monitoring instrument (EMI), is used in situations where EMI is limited. Currently, a common approach is to pair a photovoltaic power station that is geographically closest to an EMI station that has already installed one, and then directly use the latter's measured meteorological data. This approach reduces hardware procurement costs to some extent and enables the initial reuse of data resources. However, as the scale of distributed photovoltaic power station clusters expands, the limitations of this solution become increasingly apparent. First, its coverage is limited by the actual layout of the environmental monitoring equipment (EMB). In areas with sparsely distributed power stations, those far from the existing EMBs cannot be effectively covered, creating data blind spots. Second, this solution heavily relies on the continuous and stable operation of a single EMB. If the EMB, which serves as the data source, fails, all target power stations relying on its data will immediately lose data support, and the entire system faces the risk of interruption, indicating insufficient robustness.

[0017] In areas where power plants are sparsely distributed or environmental monitoring equipment (EME) is unevenly deployed, some power plants may be unable to obtain reliable meteorological data support because they are outside the effective sharing range. Furthermore, when an EME, which serves as the sole data source, malfunctions, all target power plants relying on its data will face the risk of data interruption. Once these situations occur, core operations based on EME data, such as theoretical power generation calculations and photovoltaic system loss decomposition, will be forced to halt, exposing the current system's significant shortcomings in robustness.

[0018] To address the aforementioned technical problems, this application provides a power station data sharing method, apparatus, electronic device, and storage medium. By clustering the remaining power stations while retaining shared environmental monitoring equipment, and establishing virtual environmental monitoring equipment for the resulting power station clusters, the meteorological data needs of a large number of dispersed remaining power stations are integrated onto a few representative target nodes. This solves the problems of low environmental monitoring equipment coverage in distributed photovoltaic power station systems and the inability of some power stations in sparsely distributed areas to obtain meteorological data support because they are outside the effective sharing range of a single nearest environmental monitoring device. It achieves the technical effect of improving the coverage of environmental monitoring equipment. Even if a certain environmental monitoring device fails, photovoltaic power stations within its original coverage area can quickly switch to the power station cluster of the virtual environmental monitoring equipment to ensure the continuity of meteorological data supply, thus improving the robustness of the distributed photovoltaic power station system in the face of single-point failures.

[0019] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0020] The specific application environment architecture or specific hardware architecture on which the power plant data sharing method depends is described here.

[0021] First, the structure of the power plant data sharing system on which this application is based will be described: The power plant data sharing method, apparatus, electronic device, and storage medium provided in this application are applicable to meteorological data sharing among power plants in a distributed photovoltaic power plant cluster. Figure 1 The diagram shown illustrates the structure of the power plant data sharing system based on the embodiments of this application. It mainly includes a distributed photovoltaic power plant cluster and power plant data sharing equipment. Specifically, the power plant data sharing equipment, based on the power plant data sharing method provided in the embodiments of this application, shares meteorological data with the remaining power plants in the distributed photovoltaic power plant cluster.

[0022] This application provides a power plant data sharing method for sharing meteorological data among power plants in a distributed photovoltaic power plant cluster. The execution subject of this application embodiment is an electronic device, such as a server, desktop computer, laptop computer, tablet computer, or other electronic devices that can be used to share meteorological data among power plants in a distributed photovoltaic power plant cluster.

[0023] like Figure 2 The diagram shown is a flowchart illustrating a power plant data sharing method provided in an embodiment of this application. The method includes: Step 201: Select multiple remaining power stations in the distributed photovoltaic power station cluster that do not currently share environmental monitoring equipment.

[0024] It should be noted that a distributed photovoltaic (PV) power station cluster includes multiple PV power stations, some of which are equipped with environmental monitoring equipment. This environmental monitoring equipment can be shared. "Remaining power stations" refers to PV power stations that are not currently located near existing environmental monitoring equipment and cannot obtain meteorological data through shared meteorological data from such equipment.

[0025] Step 202: Construct an undirected graph based on the relative position information between multiple remaining power stations.

[0026] In this graph, the vertices represent the remaining power stations, and the edges between the vertices represent the relative positions of the remaining power stations.

[0027] Specifically, such as Figure 3 The diagram shown is a schematic representation of the structure of an undirected graph provided in an embodiment of this application. The set of location points of the remaining power stations can be assumed to be... , Indicates the remaining power stations latitude and longitude coordinates, where Given the number of remaining power stations, the Haversine formula is used to calculate the number of each power station among the remaining power stations. With power station Distance between And construct a symmetric distance matrix :

[0028] Furthermore, the relative positional information among the remaining power stations is treated as an undirected weighted graph. ,in For the set of vertices, ; Let be the set of edges. The weight of the edge is , According to and Obtained directly from the symmetric distance matrix D.

[0029] Step 203: Determine the adaptive clustering radius based on the minimum distance between adjacent remaining power stations represented by the undirected graph.

[0030] Specifically, the minimum distance between each adjacent remaining power station can be determined by traversing the undirected graph, and then the adaptive clustering radius can be determined through analysis and calculation. The adaptive clustering radius represents a reasonable clustering range for the remaining power stations.

[0031] Step 204: Based on the adaptive clustering radius, cluster the remaining power stations to obtain multiple power station clusters.

[0032] The power station cluster includes several remaining power stations.

[0033] Specifically, based on the adaptive clustering radius and the distance between each remaining power station, the remaining power stations within the adaptive clustering radius can be clustered into a single cluster.

[0034] Step 205: For any power station cluster, select the remaining power station closest to the cluster centroid as the target power station.

[0035] Specifically, the geographic centroid (cluster centroid) of all remaining power stations within the cluster can be calculated based on the average latitude and longitude of all remaining power stations. Then, the remaining power station closest to the cluster centroid can be selected as the target power station.

[0036] Step 206: Create a virtual environmental monitoring device on the target power station to determine virtual meteorological data within the power station cluster based on the virtual environmental monitoring device.

[0037] Among them, all remaining power stations within the power station cluster share virtual meteorological data.

[0038] Specifically, by selecting target power stations in each power station cluster to create virtual environmental monitoring equipment, all remaining power stations within the cluster can share the virtual meteorological data within the power station cluster determined by the virtual environmental monitoring equipment. This reduces the consumption of power station computing resources for creating and running virtual environmental monitoring equipment, and saves data sharing costs while ensuring that each remaining power station can obtain continuous meteorological data.

[0039] The virtual meteorological data and the actual meteorological data collected by the environmental monitoring equipment contain the same content, including key meteorological parameters such as local horizontal irradiance, ambient temperature, and backplane temperature.

[0040] Based on the above embodiments, as an implementable approach, in one embodiment, multiple remaining power stations in a distributed photovoltaic power station cluster that currently do not have shared environmental monitoring equipment are screened, including: Step 2011: Iterate through each tenant in the distributed photovoltaic power station cluster to filter out tenants equipped with environmental monitoring equipment; wherein, the tenants include multiple photovoltaic power stations; Step 2012: For any tenant equipped with environmental monitoring equipment, obtain the first basic information of all photovoltaic power stations under that tenant and the second basic information of all environmental monitoring equipment. Step 2013: Based on the preset sharing radius, the first basic information, and the second basic information, determine the multiple remaining power stations under the tenant that currently do not have shared environmental monitoring equipment.

[0041] Among them, the distance between the remaining power station and all environmental monitoring equipment under the tenant is greater than the preset shared radius.

[0042] For example, such as Figure 4 The diagram illustrates an exemplary power plant data sharing method provided in this application. It iterates through each tenant, first determining whether the currently processed tenant has deployed an environmental monitoring device (EMD). If the tenant has an EMD, the basic information of all photovoltaic power plants under that tenant is collected, including the power plant ID, longitude, and latitude. That is, the first basic information of the photovoltaic power plant includes the power plant ID, longitude, and latitude. The basic information of all EMDs under that tenant is then collected, including their associated power plant ID, longitude, and latitude. That is, the second basic information of the environmental monitoring device includes the power plant ID, longitude, and latitude of its associated power plant. A configurable preset sharing radius is set for each EMD. All power stations located within the neighborhood radius (preset shared radius) of any environmental meteorological instrument are marked as shared environmental meteorological instrument power stations. The meteorological data for these power stations will directly use the measured data from their respective environmental meteorological instruments. The distance between the i-th environmental meteorological instrument and the j-th power station is... It can be calculated using the Haversine formula:

[0043]

[0044]

[0045]

[0046] In the formula, and This indicates the latitude information of the environmental monitoring instrument and the power station. and This indicates the longitude information of the environmental monitoring instrument and the power station. , These represent the latitude of the environmental measuring instrument and the power station in radians, respectively, in rad. , These represent the longitude in radians for the environmental measuring instrument and the power station, respectively, in rad. , These represent the angular difference between latitude and longitude, respectively, in rad. This is an intermediate variable of Haversine, and is dimensionless. The central angle of the sphere, in rad; The average radius of the Earth is usually taken as... , in km.

[0047] In multi-tenant service architectures, existing solutions struggle to effectively isolate tenants. A failure or data anomaly in an environmental monitoring device (EPD) under one tenant can affect other tenants' power plants that rely on that data source, causing the impact to spread across tenants and compromising the independence of each tenant's operations. Therefore, if a tenant lacks an EPD, all power plants under that tenant are considered as remaining power plants.

[0048] Based on the above embodiments, as an implementable approach, in one embodiment, determining the adaptive clustering radius according to the minimum distance between adjacent remaining power stations represented by the undirected graph includes: Step 2031: Traverse the undirected graph to obtain the minimum spanning tree corresponding to the undirected graph; Step 2032: Quantitative threshold calculation is performed based on the minimum distance between adjacent remaining power stations represented by the minimum spanning tree to obtain the quantitative threshold of the minimum spanning tree. Step 2033: Use the quantile threshold of the minimum spanning tree as the adaptive clustering radius.

[0049] For example, such as Figure 5 The diagram shown illustrates another exemplary power plant data sharing method provided in this application. First, a symmetric distance matrix D is constructed based on the distances between the remaining power plants, treating the locations of the remaining power plants as an undirected weighted graph. ,in For the set of vertices, ; Let be the set of edges. , Let represent the edge between the i-th vertex and the j-th vertex, with the edge weight being . Initialize by selecting any vertex. Let the set of currently connected vertices be... The current set of edges in the minimum spanning tree is ={}, meaning the set of edges in the current minimum spanning tree is empty, and the set of candidate edges is... .

[0050] exist Select the edge with the smallest weight Add the edge to the set of edges of the minimum spanning tree. And update and :

[0051]

[0052]

[0053] Repeat the above update process, where the final value determined in each loop is... The point is the next iteration. A point is a point when all vertices are connected. When the minimum spanning tree (MST) is reached, output the minimum spanning tree (MST):

[0054] in, , , This represents the k-th edge of the minimum spanning tree (MST). and Let the two vertices of the k-th edge be represented by the set of edge weights. .

[0055] Furthermore, based on the set of edge weights Calculate quantile threshold :

[0056] In the formula, Represents a set The Quantiles, i.e., those with a minimum value. Make Adaptive clustering radius , in km.

[0057] Based on the above embodiments, as an implementable approach, in one embodiment, multiple remaining power stations are clustered according to an adaptive clustering radius to obtain multiple power station clusters, including: Step 2041: Determine the neighborhood of each remaining power station based on the adaptive clustering radius; Step 2042: For any remaining power station, determine whether the number of remaining power stations in the neighborhood of the remaining power station is less than a preset minimum number threshold. Step 2043: If the number of remaining power stations in the neighborhood of the remaining power stations is not less than the preset minimum number threshold, the remaining power stations are designated as core power stations. Step 2044: Cluster the remaining power stations based on the core power station to obtain multiple power station clusters.

[0058] For example, such as Figure 6 The diagram shown illustrates another exemplary power plant data sharing method provided in this application embodiment. After determining the adaptive clustering radius, the method calculates the data for any remaining stations. of - Neighborhood, that is, determining the neighborhood of each remaining power station:

[0059] Furthermore, to judge If true, mark it. With the core point, This is the minimum neighbor count threshold (preset minimum count threshold), used to define the lower limit of local density. Indicates the remaining power stations The number of remaining power stations in the neighborhood of a power station, which is the number of points (power stations) in the neighborhood of each power station.

[0060] Specifically, in one embodiment, for any core power station, the remaining power stations in the neighborhood of the core power station can be clustered using the core power station as the clustering core to obtain an initial cluster of each core power station; if there is an intersection between any two or more initial clusters, the two or more initial clusters are merged to obtain multiple power station clusters.

[0061] There is no overlap between the multiple power station clusters.

[0062] Specifically, for any core point Create a new cluster That is, determine the initial clusters and perform direct density reachability expansion:

[0063] Wherein, direct density attainability can be interpreted as if point lie in of - within the neighborhood, and If it is the core point, then it is called Direct density can reach If the neighborhoods of two core points intersect Then the corresponding clusters are merged: In the formula Indicates the original core point is The initial clusters. For sites that were not clustered. If it does not belong to any power station cluster If so, it is marked as a noise point (isolated point). Among them, such as Figure 7 The diagram shown is a schematic of the clustering algorithm provided in an embodiment of this application. For example, the final clustering result at this time is:

[0064] In the formula, Represents a cluster of power stations. This indicates the final number of power plant clusters formed; Represents the set of noise points. Indicates the number of noise points.

[0065] In this context, boundary points represent photovoltaic power plants with insufficient density on their own, but belonging to a cluster. The neighborhood of such a power plant contains fewer power plants than MinPts, therefore it cannot be considered a core point. However, it falls within the neighborhood of a core point and is thus clustered into the cluster containing that core point.

[0066] Specifically, in one embodiment, if the number of remaining power stations in the neighborhood of the remaining power station is less than a preset minimum threshold, the remaining power station can be designated as a noise power station; a virtual environmental monitoring device can be created on the noise power station to determine the virtual meteorological data of the noise power station based on the virtual environmental monitoring device.

[0067] Specifically, if If it is not true, then mark it. For noise points (noise power plants), since noise power plants do not belong to any power plant cluster, virtual environmental monitoring equipment is created at the noise points to determine virtual meteorological data of the noise power plants based on the virtual environmental monitoring equipment, so as to ensure that the noise power plants can obtain virtual meteorological data normally.

[0068] Based on the above embodiments, as an implementable approach, in one embodiment, a virtual environmental monitoring device is created on the target power plant to determine virtual meteorological data within the power plant cluster based on the virtual environmental monitoring device, including: Step 2061: Obtain multi-source meteorological data and historical operating data of the target power station; wherein, the historical operating data includes at least the geographical location information and operating status information of the target power station; Step 2062: Based on multi-source meteorological data and historical operating data of the target power station, train the preset machine learning model to obtain the virtual environmental monitoring equipment; Step 2063: Deploy the virtual environment monitoring equipment to the target power plant; Step 2064: Input the current operating data of the target power plant into the virtual environment monitoring device so that the virtual environment monitoring device can determine the virtual meteorological data within the power plant cluster based on the current operating data.

[0069] It should be noted that the multi-source meteorological data includes satellite remote sensing data corresponding to the geographical location of the target power station, used to characterize cloud cover distribution, irradiance variation trends, etc., on a large spatial scale; it also includes numerical weather prediction data corresponding to the geographical location, used to provide temporal evolution information of meteorological elements at future times; and it also includes historical meteorological observation data, used to enhance the model's ability to learn regional climate characteristics. The geographical location information of the target power station includes the latitude and longitude information of the power station, used to establish the mapping relationship between meteorological data and specific spatial locations; the operational status information characterizes the operational status of the power station, such as historical power data or processed power characteristic data. This type of data can indirectly reflect the impact of meteorological conditions such as irradiance, ambient temperature, and component temperature on the operation of the power station. By simultaneously acquiring multi-source meteorological data and historical operational data of the power station, the subsequent training process not only relies on external meteorological information but can also integrate the operational response characteristics of the power station itself, thereby providing data support for building a high-precision virtual meteorological prediction model.

[0070] Specifically, the training process for the pre-defined machine learning model can use the geographical location information of the target power station as spatial feature input, multi-source meteorological data as environmental feature input, and historical operating status data of the power station as response feature input or monitoring signal. Through the training process, the machine learning model acquires the ability to predict key meteorological elements at a corresponding time based on geographical location, historical meteorological characteristics, and power station operating status information. The trained machine learning model constitutes a virtual environmental monitoring device. This virtual environmental monitoring device is functionally equivalent to a physical meteorological monitoring device, but it does not rely on physical sensors; instead, it achieves predictive output of meteorological elements through a data-driven approach.

[0071] Specifically, the virtual environmental monitoring equipment is associated with the identification information of the target power station, and configured to serve the power station cluster to which the target power station belongs, enabling it to provide unified meteorological data prediction results for all power stations within the cluster. The current operating data of the target power station (e.g., current power or processed power characteristics) is input into the virtual environmental monitoring equipment, which, combined with learned historical meteorological characteristics, the response relationship of the current operating state to meteorological conditions, and external meteorological data characteristics corresponding to the latitude and longitude of the target power station, predicts key meteorological parameters of the area where the target power station is located at the current or future time. These parameters include, but are not limited to, horizontal irradiance, ambient temperature, and backplane temperature.

[0072] Furthermore, the predicted virtual meteorological data serves as unified meteorological input data at the power plant cluster level, benefiting all power plants within the cluster. This enables a continuous supply of meteorological data required for power plant operation without relying on physical meteorological monitoring equipment.

[0073] The power plant data sharing method provided in this application, while retaining shared environmental monitoring equipment, clusters the remaining power plants and establishes virtual environmental monitoring equipment for the resulting power plant clusters. This integrates the meteorological data needs of a large number of scattered remaining power plants onto a few representative target nodes. This solves the problems of low environmental monitoring equipment coverage in distributed photovoltaic power plant systems and the inability of some power plants in sparsely distributed areas to obtain meteorological data support because they are outside the effective sharing range of a single nearest environmental monitoring device. It achieves the technical effect of improving the coverage of environmental monitoring equipment. Even if a certain environmental monitoring device fails, photovoltaic power plants within its original coverage area can quickly switch to the power plant cluster of the virtual environmental monitoring equipment to ensure the continuity of meteorological data supply, thus improving the robustness of the distributed photovoltaic power plant system in dealing with single-point failures.

[0074] Furthermore, since virtual weather stations (virtual environmental monitoring equipment) do not rely on a single physical device, their data originates from machine learning models driven by numerical weather prediction, satellite remote sensing data, and power plant operation data. Therefore, even if a certain environmental monitoring instrument fails, power plants within its original coverage area can be quickly transferred to the cluster served by the virtual weather station to ensure the continuity of meteorological data supply. For power plants that cannot be integrated into the original power plant cluster, they can be treated as noise power plants, and a separate virtual weather station (virtual environmental monitoring equipment) can be established for them. In response to the increasing computational pressure of the ever-expanding scale of photovoltaic power plant clusters, the clustering method solves the problem of how to efficiently process the massive meteorological data demand of power plants under limited computing power. For clustering algorithms, the Minimum Spanning Tree (MST) algorithm is combined with the Density-Based Clustering (DBSCAN) algorithm. MST is used to extract the overall topology of the power plant's spatial distribution, and the neighborhood radius, a key parameter of DBSCAN, is automatically derived based on its edge weight distribution. This solves the problem that the neighborhood radius of traditional DBSCAN needs to be set by manual experience or repeated experiments. In addition, a "field monitoring-virtual supplementation" meteorological data sharing framework with tenant as the granularity is proposed. In addition to solving the problems of data coverage and single point of failure, multi-tenant isolation is explicitly taken as one of the core design goals, and the processing independence between tenants is ensured through the algorithm.

[0075] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0076] The embodiments of this application also provide a power plant data sharing device for executing the power plant data sharing method provided in the above embodiments.

[0077] like Figure 8The diagram shown is a structural schematic of a power plant data sharing device provided in an embodiment of this application. The power plant data sharing device 80 includes: a filtering module 801, a construction module 802, a determination module 803, a clustering module 804, a selection module 805, and a sharing module 806.

[0078] The system comprises the following modules: a filtering module for selecting multiple remaining power stations in a distributed photovoltaic power station cluster that currently lack shared environmental monitoring equipment; a construction module for building an undirected graph based on the relative positions of the remaining power stations, where vertices represent remaining power stations and edges represent their relative positions; a determination module for determining an adaptive clustering radius based on the minimum distance between adjacent remaining power stations represented by the undirected graph; a clustering module for clustering the remaining power stations based on the adaptive clustering radius to obtain multiple power station clusters, where each cluster includes multiple remaining power stations; a selection module for selecting the remaining power station closest to the cluster centroid as the target power station for any given cluster; and a sharing module for creating virtual environmental monitoring equipment on the target power station to determine virtual meteorological data within the power station cluster based on this equipment, where all remaining power stations within the cluster share the virtual meteorological data.

[0079] For a description of the features in the embodiment corresponding to the power plant data sharing device, please refer to the relevant description in the embodiment corresponding to the power plant data sharing method, which will not be repeated here.

[0080] Embodiments of this application also provide an electronic device, such as... Figure 9 The diagram shown is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, including a processor 10 and a memory 20. The memory 20 stores a computer program, and the processor 10 is configured to run the computer program to execute the steps in any of the above-described power plant data sharing method embodiments.

[0081] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above-described embodiments of the power plant data sharing method when it is run.

[0082] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0083] Embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above-described power plant data sharing method embodiments.

[0084] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above-described power plant data sharing method embodiments.

[0085] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0086] The foregoing has provided a detailed description of a power plant data sharing method, apparatus, electronic device, and storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only intended to aid in understanding the method and core ideas of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A power plant data sharing method, characterized in that, include: In a distributed photovoltaic power station cluster, select several remaining power stations that currently do not share environmental monitoring equipment; An undirected graph is constructed based on the relative position information between the multiple remaining power stations; wherein, the vertices of the undirected graph represent the remaining power stations, and the edges of the vertices of the undirected graph represent the relative position information between the remaining power stations. The adaptive clustering radius is determined based on the minimum distance between adjacent remaining power stations represented by the undirected graph. Based on the adaptive clustering radius, the multiple remaining power stations are clustered to obtain multiple power station clusters; wherein, the power station cluster includes multiple of the remaining power stations; For any of the aforementioned power plant clusters, the remaining power plant closest to the cluster centroid is selected as the target power plant. A virtual environmental monitoring device is created on the target power station to determine virtual meteorological data within the power station cluster based on the virtual environmental monitoring device; wherein, all remaining power stations within the power station cluster share the virtual meteorological data.

2. The power plant data sharing method according to claim 1, characterized in that, The process of selecting multiple remaining power stations in a distributed photovoltaic power station cluster that currently do not have shared environmental monitoring equipment includes: The process iterates through each tenant in the distributed photovoltaic power station cluster to filter out tenants equipped with environmental monitoring equipment; wherein, the tenants include multiple photovoltaic power stations; For any tenant equipped with environmental monitoring equipment, obtain the first basic information of all photovoltaic power plants under that tenant and the second basic information of all environmental monitoring equipment; Based on the preset sharing radius, the first basic information, and the second basic information, determine the multiple remaining power stations under the tenant that currently do not have shared environmental monitoring equipment; The distance between the remaining power station and all environmental monitoring devices under the tenant is greater than the preset shared radius.

3. The power plant data sharing method according to claim 1, characterized in that, The step of determining the adaptive clustering radius based on the minimum distance between adjacent remaining power stations represented by the undirected graph includes: Traverse the undirected graph to obtain the minimum spanning tree corresponding to the undirected graph; Based on the minimum distance between adjacent remaining power stations represented by the minimum spanning tree, a quantile threshold is calculated to obtain the quantile threshold of the minimum spanning tree. The quantile threshold of the minimum spanning tree is used as the adaptive clustering radius.

4. The power plant data sharing method according to claim 1, characterized in that, The step of clustering the remaining power stations according to the adaptive clustering radius to obtain multiple power station clusters includes: The neighborhood of each of the remaining power stations is determined based on the adaptive clustering radius; For any of the remaining power stations, determine whether the number of remaining power stations in the neighborhood of the remaining power station is less than a preset minimum number threshold. If the number of remaining power stations in the neighborhood of the remaining power station is not less than a preset minimum threshold, the remaining power station shall be regarded as the core power station. Based on the core power station, the remaining power stations are clustered to obtain multiple power station clusters.

5. The power plant data sharing method according to claim 4, characterized in that, The step of clustering the remaining power stations based on the core power station to obtain multiple power station clusters includes: For any of the core power plants, the remaining power plants in the neighborhood of the core power plant are clustered using the core power plant as the clustering core to obtain an initial cluster for each core power plant. If there is an intersection between any two or more initial clusters, the two or more initial clusters are merged to obtain multiple power plant clusters; There is no overlap between the multiple power station clusters.

6. The power plant data sharing method according to claim 4, characterized in that, The method further includes: If the number of remaining power stations in the neighborhood of the remaining power station is less than a preset minimum threshold, the remaining power station will be designated as a noise power station. A virtual environmental monitoring device is created on the noise power station to determine virtual meteorological data of the noise power station based on the virtual environmental monitoring device.

7. The power plant data sharing method according to claim 1, characterized in that, The step of creating a virtual environmental monitoring device on the target power station to determine virtual meteorological data within the power station cluster based on the virtual environmental monitoring device includes: Acquire multi-source meteorological data and historical operating data of the target power station; wherein the historical operating data includes at least the geographical location information and operating status information of the target power station; Based on the multi-source meteorological data and the historical operation data of the target power station, a preset machine learning model is trained to obtain a virtual environment monitoring device; Deploy the virtual environment monitoring equipment to the target power plant; The current operating data of the target power plant is input into the virtual environment monitoring device, so that the virtual environment monitoring device can determine the virtual meteorological data within the power plant cluster based on the current operating data.

8. A power plant data sharing device, characterized in that, include: The filtering module is used to filter out multiple remaining power stations in a distributed photovoltaic power station cluster that do not currently share environmental monitoring equipment; A construction module is used to construct an undirected graph based on the relative position information between the multiple remaining power stations; wherein, the vertices of the undirected graph represent the remaining power stations, and the edges of the vertices of the undirected graph represent the relative position information between the remaining power stations; The determination module is used to determine the adaptive clustering radius based on the minimum distance between adjacent remaining power stations represented by the undirected graph; A clustering module is used to cluster the multiple remaining power stations according to the adaptive clustering radius to obtain multiple power station clusters; wherein, the power station cluster includes multiple remaining power stations; The selection module is used to select, for any of the power plant clusters, the remaining power plant closest to the cluster centroid as the target power plant; A sharing module is used to create a virtual environmental monitoring device on the target power station to determine virtual meteorological data within the power station cluster based on the virtual environmental monitoring device; wherein, all remaining power stations within the power station cluster share the virtual meteorological data.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the power plant data sharing method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of the power plant data sharing method as described in any one of claims 1 to 7.

Images