A wind turbine layout method and related equipment based on high-resolution wind resource data

Abstract

The present invention provides a fan layout method and related equipment based on high-resolution wind resource data, which is applied to the field of data processing technology. This application obtains the information of the area to be installed with fans sent by the client; processes the information of the area to be installed with fans to generate a land type image with identification information; processes the land type image with identification information to generate a number of land type slice images; obtains an initial fan layout calculation model stored in the current server that matches the identification information of the area to be installed with fans; processes the initial fan layout calculation model based on a preset processing rule to generate a target fan layout calculation model; processes the land type slice images based on the target fan layout calculation model to generate the fan power generation potential value of the area to be installed with fans; processes the fan power generation potential value based on the target fan layout calculation model to generate the fan installation information of the area to be installed with fans.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a fan layout method and related equipment based on high-resolution wind resource data. Background Art

[0002] As a renewable and clean energy, wind energy is widely used in the field of wind power generation. In the past decade or so, centralized wind power generation projects or decentralized wind power generation projects have been developed in most regions. With the deepening of the concept of green and low-carbon, the development speed of wind power projects has been further accelerated. In recent years, the wind power generation industry has developed rapidly. With the ebb of relevant subsidy policies, the successful implementation of wind power projects has put forward more stringent requirements for relevant cost control. On the other hand, a large number of areas rich in wind resources are located in hilly and mountainous areas. With the in-depth development of wind power projects in plain areas, more new wind power projects are selected in complex terrain areas, which also brings certain difficulties to the design and development of wind farms.

[0003] During the development and construction of wind power projects, the investigation of restrictive factors in the region and the resource analysis and optimization of fan positions are important bases for measuring the feasibility and value of wind power projects. The traditional design scheme is that designers judge the restrictive factors according to experience and manually arrange the machine positions. As the planning of wind power base projects becomes larger and the number of fans increases, the factors to be considered in the planning increase geometrically. Affected by factors such as the limitations of designers' work experience and design cycles, it is usually difficult to achieve the optimal layout plan and the maximum utilization and development of land resources for fan position selection.

[0004] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present application is to provide a fan layout method and related equipment based on high-resolution wind resource data, which at least overcome the problems existing in the prior art to a certain extent. By obtaining a fan layout calculation model that matches the identification information of the area to be installed, the information of the area to be installed is processed, comprehensively considering factors such as wind speed, wind direction, elevation, etc., and avoiding obstacles such as rivers and buildings, and combining the terrain features of mountain tops and ridge lines across the country, the optimal layout of fan positions is achieved.

[0006] Other features and advantages of the present application will become apparent through the following detailed description, or be learned in part through the practice of the present invention.

[0007] According to one aspect of the present application, there is provided a fan layout method based on high-resolution wind resource data, including: obtaining the information of the area to be installed with fans sent by the client; processing the information of the area to be installed with fans to generate a land type image with identification information, where the identification information includes target mountaintop point information, ridgeline information, and avoidance area information; processing the land type image with identification information to generate a plurality of land type sliced images, where the plurality of land type sliced images are high-resolution images; obtaining the server address storing the fan layout calculation model matching the identification information; if the number of servers storing the fan layout calculation model is multiple, obtaining the business load status of the multiple servers; if the server with the lowest business load status is the current server, obtaining the initial fan layout calculation model matching the identification information of the area to be installed with fans stored in the current server; processing the initial fan layout calculation model based on a preset processing rule to generate a target fan layout calculation model; processing the land type sliced images based on the target fan layout calculation model to generate the fan power generation potential value of the area to be installed with fans; processing the fan power generation potential value based on the target fan layout calculation model to generate the fan installation information of the area to be installed with fans.

[0008] In one embodiment of the present application, the processing the information of the area to be installed with fans to generate a land type image with identification information includes: extracting an image of the surface information of the area to be installed with fans based on a deep learning neural network model to generate a surface information image of the area to be installed with fans; performing grayscale processing on the surface information image of the area to be installed with fans to generate a surface information image with a target brightness; performing image normalization processing on the surface information image with the target brightness to generate a surface information image with a preset size; performing image enhancement processing on the surface information image with the preset size to generate a land type image, where the land type image includes soil organic carbon content information, soil type information, and gravel information.

[0009] In one embodiment of the present application, processing the initial wind turbine layout calculation model based on a preset processing rule to generate a target wind turbine layout calculation model includes: obtaining a training sample set for updating the wind turbine layout calculation model; extracting features from the training sample set to determine an original feature library; dividing the training sample set according to the original feature library to generate a training set and a test set; using a classifier to predict each test set divided by the original feature library to determine a prediction result; using a preset algorithm to train each training set divided by the original feature library to obtain a test set class prediction result; generating a training sample set with target feature data according to the prediction result and the test set class prediction result; and processing the initial wind turbine layout calculation model based on the training sample set with target feature data to generate a target wind turbine layout calculation model.

[0010] In one embodiment of the present application, processing the land type slice image based on the target wind turbine layout calculation model to generate a wind turbine power generation potential value for the area to be installed with wind turbines includes: obtaining elevation information corresponding to a plurality of land type slice images; obtaining mountaintop point information and ridgeline information corresponding to different land type slice images based on the elevation information; generating wind speed values corresponding to different land type slice images based on the mountaintop point information and ridgeline information corresponding to different land type slice images; and processing the wind speed values corresponding to different land type slice images to generate a wind speed value for the area to be installed with wind turbines.

[0011] In one embodiment of the present application, processing the land type slice image based on the target wind turbine layout calculation model to generate a wind turbine power generation potential value for the area to be installed with wind turbines further includes: the target wind turbine layout calculation model includes a calculation formula for obtaining the wind speed value of the area to be installed with wind turbines, where the calculation formula for the wind speed value of the area to be installed with wind turbines is:

[0012] where ρ is the density (kg / m3); i is the ridgeline coordinate; j is the mountaintop point coordinate; u is the wind speed (m / s); μ is the dynamic viscosity coefficient (Pa·s); μ t is the turbulent dynamic viscosity coefficient (Pa·s); ε is the turbulent kinetic energy dissipation rate (m2 / s2); and Sui is the mean strain rate tensor.

[0013] In one embodiment of the present application, processing the land type slice image based on the target wind turbine layout calculation model to generate the wind turbine power generation potential value of the area to be installed with turbines further includes: processing the wind speed value of the area to be installed with turbines based on the avoidance area information to generate a wind energy emission value; processing the wind energy emission value and the wind speed value of the area to be installed with turbines based on the wind turbine layout calculation model to generate the wind turbine power generation potential value of the area to be installed with turbines; the wind turbine layout calculation model includes a calculation formula for obtaining the wind turbine power generation potential value of the area to be installed with turbines, wherein the calculation formula for the wind turbine power generation potential value of the area to be installed with turbines is: where EF is the wind turbine power generation potential value of the area to be installed with turbines, Q req is the wind energy emission value, Q is the total wind energy value of the area to be installed with turbines, δ is the CO concentration, Q co is the CO emission amount of the area to be installed with turbines, P0 is the standard atmospheric pressure, P is the atmospheric pressure of the area to be installed with turbines, T is the summer temperature of the area to be installed with turbines, and T0 is the standard temperature.

[0014] In one embodiment of the present application, processing the wind turbine power generation potential value based on the wind turbine layout calculation model to generate the wind turbine installation information of the area to be installed with turbines includes: obtaining a preset wind turbine installation value; processing the wind turbine power generation potential value of the area to be installed with turbines based on the wind turbine layout calculation model to generate an initial wind turbine installation value; processing the initial wind turbine installation value based on the preset wind turbine installation value to generate a target wind turbine installation value.

[0015] In another aspect of the present application, a wind turbine layout device based on high-resolution wind resource data, characterized in that the device includes: an acquisition module, configured to acquire the information of the area to be installed with turbines sent by the client; acquire the server address storing the wind turbine layout calculation model matching the identification information; a processing module, configured to process the information of the area to be installed with turbines to generate a land type image with identification information, wherein the identification information includes target mountaintop point information, ridge line information and avoidance area information; process the land type image with identification information to generate a plurality of land type slice images, wherein the plurality of land type slice images are high-resolution images; if there are multiple servers storing the wind turbine layout calculation model, acquire the service load status of the multiple servers; if the server with the lowest service load status is the current server, acquire the initial wind turbine layout calculation model matching the identification information of the area to be installed with turbines stored in the current server; process the initial wind turbine layout calculation model based on a preset processing rule to generate a target wind turbine layout calculation model; process the land type slice image based on the target wind turbine layout calculation model to generate the wind turbine power generation potential value of the area to be installed with turbines; process the wind turbine power generation potential value based on the target wind turbine layout calculation model to generate the wind turbine installation information of the area to be installed with turbines.

[0016] According to another aspect of the present application, an electronic device, characterized in that it includes: a first processor; and a memory for storing executable instructions of the first processor; wherein, the first processor is configured to execute the above-mentioned fan layout method based on high-resolution wind resource data by executing the executable instructions.

[0017] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a second processor, the above-mentioned fan layout method based on high-resolution wind resource data is implemented.

[0018] According to another aspect of the present application, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a third processor, the above-mentioned fan layout method based on high-resolution wind resource data is implemented.

[0019] For a fan layout method and related devices based on high-resolution wind resource data provided by the present application, the server obtains the information of the area to be installed with fans sent by the client; processes the information of the area to be installed with fans to generate a land type image with identification information, where the identification information includes target mountaintop point information, ridge line information, and avoidance area information; processes the land type image with identification information to generate a number of land type slice images, where the number of land type slice images are high-resolution images; obtains the server address storing the fan layout calculation model matching the identification information; if the number of servers storing the fan layout calculation model is multiple, obtains the service load status of multiple servers; if the server with the lowest service load status is the current server, obtains the initial fan layout calculation model matching the identification information of the area to be installed with fans stored by the current server; processes the initial fan layout calculation model based on a preset processing rule to generate a target fan layout calculation model; processes the land type slice images based on the target fan layout calculation model to generate the fan power generation potential value of the area to be installed with fans; processes the fan power generation potential value based on the target fan layout calculation model to generate the fan installation information of the area to be installed with fans. By obtaining the fan layout calculation model matching the identification information of the area to be installed with fans to process the information of the area to be installed with fans, comprehensively considering factors such as wind speed, wind direction, elevation, etc., and avoiding obstacles such as rivers and buildings, and combining the terrain features of mountaintops and ridge lines across the country, the optimal layout of fan positions is realized.

[0020] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1The flowchart of a fan layout method provided by an embodiment of the present application is shown;

[0022] Figure 2 The structural schematic diagram of a fan layout device provided by an embodiment of the present application is shown;

[0023] Figure 3 The structural schematic diagram of an electronic device provided by an embodiment of the present application is shown;

[0024] Figure 4 The schematic diagram of a storage medium provided by an embodiment of the present application is shown. Detailed implementation manners

[0025] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0026] Next, in combination with Figure 1 The fan layout method based on high-resolution wind resource data according to an exemplary embodiment of the present application is described. It should be noted that the following application scenarios are only shown for the convenience of understanding the spirit and principle of the present application, and the embodiments of the present application are not limited in this regard. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0027] In one embodiment, the present application also proposes a fan layout method based on high-resolution wind resource data and related devices. Figure 1 The flowchart of a fan layout method based on high-resolution wind resource data according to an embodiment of the present application is schematically shown. As Figure 1 shown, this method is applied to a server and includes:

[0028] S101, obtaining the information of the area to be installed with fans sent by the client.

[0029] In one embodiment, the information of the area to be installed with fans includes the expected range to be installed with fans, which may be a land range in units of townships, villages, towns, or cities. Specifically, the present solution does not limit this, and reasonable data can be selected according to actual needs.

[0030] S102, processing the information of the area to be installed with fans to generate a land type image with identification information.

[0031] In one implementation, the identification information includes target mountaintop point information, ridgeline information, and avoidance area information. Contour lines with intervals of 15m and 75m are generated based on the 100-meter resolution elevation data of the whole country, and a mountain shadow result map is generated. The two constitute a shaded relief map to assist in judging the position of the mountaintop points. Focus statistical analysis is performed on the elevation data, processed with an 11*11 window, and the generated result is reclassified by subtracting the DEM data to obtain mountaintop point data in raster form. After converting the raster data into vectors and combining it with the shaded relief map, unreasonable mountaintop points are deleted, and thus the distribution of the mountaintop points is obtained.

[0032] In ArcGIS, the "Slope" tool in the "Spatial Analyst" toolbox is used to generate a slope map. A moving window (such as 3x3 or 5x5 pixels) slides on the elevation data to find local maximum points, which are the mountaintop points. Filter out local maximum points with lower elevation or smaller slope, and retain significant mountaintop points. Smooth the extracted mountaintop points to reduce noise points. Use median filtering or other smoothing techniques to remove isolated points, thereby identifying and generating the corresponding ridgeline.

[0033] During the process of wind turbine installation, it is necessary to avoid buildings. This solution identifies buildings in the satellite images of Tianditu based on image recognition technology. Through convolutional neural network (CNN) and deep learning technology, building detection and classification are performed on high-resolution satellite images. During the process of wind turbine installation, it is also necessary to avoid rivers and river basin areas and maintain a certain buffer distance from the main trunk of the main road. This solution uses national river data, national river basin data, and national road data.

[0034] In another implementation, based on a deep learning neural network model, image extraction is performed on the information of the area to be installed with wind turbines to generate a surface information image of the area to be installed; the surface information image of the area to be installed is grayscale processed to generate a surface information image with a target brightness; the surface information image with the target brightness is normalized to generate a surface information image of a preset size; the surface information image of the preset size is enhanced to generate a land type image, where the land type image includes soil organic carbon content information, soil type information, and gravel information.

[0035] This application does not limit the specific implementation methods of grayscale processing and image normalization. As long as the relevant functions can be achieved, based on the deep learning neural network model, image extraction is performed on the land type information of the area to be installed with wind turbines, and the tree vegetation coverage area, soil coverage area, and water flow area in the image are obtained as the corresponding surface information images. The corresponding surface information images are grayscale processed and normalized to generate a land type image.

[0036] Then, perform enhancement processing on the processed image. The enhancement processing methods include image radiation enhancement processing and image spectral enhancement processing. Feature extraction is performed on the image based on a deep learning neural network model, and enhancement processing is carried out, so that the image is clearer and the data volume is smaller, facilitating subsequent coincidence and superposition processing.

[0037] S103. Process the land type image with identification information to generate a number of land type slice images.

[0038] In one implementation, slice the land type image that has undergone grayscale processing and image normalization processing to generate multiple local images. Process each of the multiple local images separately to generate scores corresponding to the multiple local images, and add up the scores corresponding to the multiple local images to obtain the final score of the area to be evaluated. This solution does not limit the calculation method for generating the scores corresponding to the local images, and the applicant can select the corresponding calculation method according to actual needs for calculation. In addition, the scores corresponding to the multiple local images will be processed separately to obtain the influencing factor with the largest proportion in generating the scores of the corresponding local images, and several land type slice images will be generated based on the influencing factor. The server will obtain the geographical information with the same scores and determine what the main influencing factors for different geographical information are, and then judge the correlation between different influencing factors. If the main influencing factors for different geographical information are the same, it indicates that the importance of this main influencing factor is relatively high.

[0039] In addition, enhancement processing will also be performed on several land type slice images. The enhancement processing methods include image radiation enhancement processing and image spectral enhancement processing. Feature extraction is performed on the image based on a deep learning neural network model, and enhancement processing is carried out, so that the image is clearer and the data volume is smaller, facilitating subsequent coincidence and superposition processing. The several land type slice images are high-resolution images.

[0040] S104. Obtain the server address storing the fan layout calculation model that matches the identification information.

[0041] In one implementation, the identification information can be represented by a preset specific symbol. This embodiment does not limit the specific symbol, as long as the solution can be implemented. This embodiment does not limit the method for obtaining the server address, as long as the solution can be implemented.

[0042] S105. If there are multiple servers storing the fan layout calculation model, obtain the business load status of the multiple servers.

[0043] In one implementation, by obtaining the service load status of a server with a fan layout calculation model, the problem that the processing progress of related servers is affected because the current load of a certain server (for example, at least one of the service load and the machine operation load) is large is reduced. In this embodiment, the client will be adjusted in real time according to the service load status of multiple servers to send the information of the area to be arranged with fans to the server with a lower load, so as to reduce the service processing pressure on a single or multiple servers and achieve the purpose of load balancing to a great extent.

[0044] S106. If the server with the lowest service load status is the current server, obtain the initial fan layout calculation model that matches the identification information of the area to be arranged with fans stored in the current server.

[0045] S107. Process the initial fan layout calculation model based on a preset processing rule to generate a target fan layout calculation model.

[0046] In one implementation, obtain a training sample set for updating the fan layout calculation model; extract features from the training sample set to determine an original feature library, and use existing technologies to divide the original feature library to generate a training data set and a test data set. In this embodiment, as long as it can be divided, there is no restriction on the method used. Divide the training sample set according to the original feature library to generate a training set and a test set; use a classifier to predict each test set divided from the original feature library to determine the prediction result; use a preset algorithm to train each training set divided from the original feature library to obtain the prediction result of the test set class; generate a training sample set with target feature data according to the prediction result and the prediction result of the test set class; process the initial fan layout calculation model based on the training sample set with target feature data to generate a target fan layout calculation model. Use a preset algorithm to train each training data set divided from the original feature library to obtain the prediction result of the test set class. In the embodiment, as long as the prediction result of the test set class can be obtained, there is no restriction on the algorithm used. Generate target feature data according to the prediction result and the prediction result of the test set class.

[0047] Specifically, obtain the data classification result corresponding to the training data set. Since the classification result of each training data set can be determined in advance and can be directly obtained from the outside. Compare the prediction result with the data classification result to determine the first comparison result; compare the prediction result of the test set class with the data classification result to determine the second comparison result; when judging whether the second comparison result and the first comparison result meet the preset requirements, when they meet the preset requirements, determine the corresponding features as target feature data.

[0048] S108. Process the land type slice images based on the target wind turbine layout calculation model to generate the wind turbine power generation potential values for the areas where turbines are to be installed.

[0049] In one implementation, obtain the elevation information corresponding to a number of land type slice images, obtain the mountaintop point information and ridgeline information corresponding to different land type slice images based on the elevation information, generate the wind speed values corresponding to different land type slice images based on the mountaintop point information and ridgeline information corresponding to different land type slice images. The areas where turbines are to be installed are areas where the wind speed is greater than 6 m / s and the elevation is less than 3000 meters. Specifically, these two parameters can be adjusted according to actual business requirements. According to the requirements of wind speed and elevation parameters, screen the areas where turbines can be installed that meet the requirements. For example, areas where the wind speed does not meet the requirements will not be arranged with turbines during installation.

[0050] Obtain the highest point according to the ridgeline. The point with the maximum wind resource is within the preset range of the highest point. Among them, the point with the maximum wind resource is the position where the wind speed value is higher than the preset threshold. Set the position of the first wind turbine at the highest point; if the point with the maximum wind resource is outside the preset range of the highest point, then set the position of the first wind turbine at the point with the maximum wind resource. Process the wind speed values corresponding to different land type slice images to generate the wind speed values for the areas where turbines are to be installed. Wind speed is a key factor in the power generation efficiency of wind power projects. The higher the wind speed, the greater the utilization rate of wind energy. Therefore, based on different wind speed values, judge how to initially allocate wind turbines at different positions.

[0051] In another implementation, the target wind turbine layout calculation model includes a calculation formula for obtaining the wind speed values of the areas where turbines are to be installed. Among them, the calculation formula for the wind speed values of the areas where turbines are to be installed is:

[0052]

[0053] where ρ is the density (kg / m3); i is the ridgeline coordinate; j is the mountaintop point coordinate; u is the wind speed (m / s); μ is the dynamic viscosity coefficient (Pa·s); μ t is the turbulent dynamic viscosity coefficient (Pa·s); ε is the turbulent kinetic energy dissipation rate (m2 / s2); Sui is the mean strain rate tensor. In practical applications, the formula for calculating the wind speed needs to combine terrain data, meteorological data, and the principles of fluid dynamics. These calculations usually involve numerical simulation and computer simulation technologies to predict the wind speed distribution in specific areas of the wind farm.

[0054] In another implementation, the wind speed value in the area to be installed with wind turbines is processed based on the avoidance area information to generate a wind energy emission value; the wind energy emission value and the wind speed value in the area to be installed with wind turbines are processed based on the wind turbine layout calculation model to generate the wind turbine power generation potential value in the area to be installed with wind turbines; the wind turbine layout calculation model includes a calculation formula for obtaining the wind turbine power generation potential value in the area to be installed with wind turbines. The calculation formula for the wind turbine power generation potential value in the area to be installed with wind turbines is as follows:

[0055] where EF is the wind turbine power generation potential value in the area to be installed with wind turbines, Q req is the wind energy emission value, Q is the total wind energy value in the area to be installed with wind turbines, δ is the CO concentration, Q co is the CO emission in the area to be installed with wind turbines, P0 is the standard atmospheric pressure, P is the atmospheric pressure in the area to be installed with wind turbines, T is the summer temperature in the area to be installed with wind turbines, and T0 is the standard temperature.

[0056] The wind speed value in the area to be installed with wind turbines is processed based on the avoidance area information to obtain the wind energy emission value corresponding to each area. Since there are areas that need to be avoided, it may lead to fewer wind turbine layouts in some areas, resulting in the wind turbine power generation potential value being lower than the preset threshold. By predicting or corresponding to the wind turbine power generation potential value in advance, it can be used as a reference for the subsequent actual wind turbine layout.

[0057] S109. Process the wind turbine power generation potential value based on the target wind turbine layout calculation model to generate the wind turbine layout information in the area to be installed with wind turbines.

[0058] In one implementation, a preset wind turbine layout value is obtained. The layout information of the wind turbines can be set based on the wind turbine model that needs to be installed according to the actual business site selection. The default number of installed wind turbines is 30, 5D parallel to the main direction, and 3D perpendicular to the main wind direction. The parameters can be adjusted according to the actual business requirements.

[0059] The wind turbine power generation potential value in the area to be installed with wind turbines is processed based on the wind turbine layout calculation model to generate an initial wind turbine layout value, and the initial wind turbine layout value is processed based on the preset wind turbine layout value to generate a target wind turbine layout value. That is, the preset wind turbine layout value is set without considering the actual terrain. Therefore, there will be a certain error between the initial wind turbine layout value and the preset wind turbine layout value. The area to be installed with wind turbines is divided into a custom area and a restricted area. According to the custom area and the restricted area, the union and difference set operations are used to calculate the wind turbine layout area. The difference set operation is performed on the custom area and the restricted area to obtain all the point sets in the area to be installed with wind turbines. If the final number of installed wind turbines is greater than the number required by the business, the wind turbine layout screening is performed according to the principles of wind speed priority, elevation priority, or power generation priority according to the actual business requirements.

[0060] In this application, the server obtains the information of the area to be installed with wind turbines sent by the client; processes the information of the area to be installed with wind turbines to generate a land type image with identification information, where the identification information includes target mountaintop point information, ridgeline information, and avoidance area information; processes the land type image with identification information to generate a number of land type sliced images, where the number of land type sliced images are high-resolution images; obtains the server address storing the wind turbine layout calculation model matching the identification information; if there are multiple servers storing the wind turbine layout calculation model, obtains the business load status of multiple servers; if the server with the lowest business load status is the current server, obtains the initial wind turbine layout calculation model matching the identification information of the area to be installed with wind turbines stored in the current server; processes the initial wind turbine layout calculation model based on a preset processing rule to generate a target wind turbine layout calculation model; processes the land type sliced images based on the target wind turbine layout calculation model to generate the wind turbine power generation potential value of the area to be installed with wind turbines; processes the wind turbine power generation potential value based on the target wind turbine layout calculation model to generate the wind turbine installation information of the area to be installed with wind turbines. By obtaining the wind turbine layout calculation model matching the identification information of the area to be installed with wind turbines to process the information of the area to be installed with wind turbines, comprehensively considering factors such as wind speed, wind direction, elevation, etc., and avoiding obstacles such as rivers and buildings, and combining the topographic features of mountaintops and ridgelines across the country, the optimal layout of wind turbine positions is achieved.

[0061] Optionally, in another embodiment based on the above method of this application, the extracting features from the training sample set to determine the original feature library includes:

[0062] Obtain a historical land type image data set, where the historical land type image data set includes land type image information from all over the country within a preset time range;

[0063] Process the historical land type image data set to obtain abnormal land type features and correlation co-occurrence frequencies;

[0064] Process the abnormal land type features and the correlation co-occurrence frequencies to generate correlation matrix information;

[0065] Generate a number of image feature data based on the correlation matrix information;

[0066] Generate the original feature library based on the number of image feature data.

[0067] In one implementation, data mining is used to extract abnormal land types (i.e., information on areas to be avoided) and their correlations from the historical land type image dataset, establish the relationships between land type images, form a prior knowledge map for wind turbine layout, and then domain experts check one by one whether the correlations between land type images and wind turbine layout are valid to complete the calibration of the correlation matrix, thereby completing the screening of image feature data.

[0068] In another implementation, it includes a calculation formula for the co-occurrence frequency of correlations. The specific calculation formula is: where C ij represents the number of times concept i and concept j co-occur at the report level. C j represents the total number of times concept j appears. P ij represents the frequency of concept i when concept j appears. Based on the co-occurrence frequency P, a correlation matrix A can be constructed.

[0069] In addition, it also includes a calculation formula for the correlation matrix. The specific calculation formula is: where τ is the co-occurrence frequency threshold. If P ij is greater than or equal to the threshold τ, it is considered that there is a correlation from concept i to concept j; otherwise, there is no correlation.

[0070] By applying the above technical solutions, the server obtains the information on the area to be laid out sent by the client; based on the deep learning neural network model, it extracts images from the information on the area to be laid out to generate a surface information image of the area to be laid out; grayscales the surface information image of the area to be laid out to generate a surface information image with a target brightness; normalizes the surface information image with the target brightness to generate a surface information image of a preset size; enhances the surface information image of the preset size to generate a land type image, where the land type image includes soil organic carbon content information, soil type information, and gravel information, and the identification information includes target mountaintop point information, ridge line information, and avoidance area information; processes the land type image with the identification information to generate a number of land type slice images, where the number of land type slice images are high-resolution images.

[0071] Obtain the server address storing the fan layout calculation model matching the identification information; if there are multiple servers storing the fan layout calculation model, obtain the business load status of multiple servers; if the server with the lowest business load status is the current server, obtain the initial fan layout calculation model stored in the current server and matching the identification information of the area to be installed with fans; obtain the training sample set for updating the fan layout calculation model; perform feature extraction on the training sample set to determine the original feature library; divide the training sample set according to the original feature library to generate a training set and a test set; use a classifier to predict each test set divided by the original feature library to determine the prediction result; use a preset algorithm to train each training set divided by the original feature library to obtain the test set class prediction result; generate a training sample set with target feature data according to the prediction result and the test set class prediction result; process the initial fan installation calculation model based on the training sample set with target feature data to generate a target fan layout calculation model. Obtain the elevation information corresponding to several land type slice images; obtain the mountaintop point information and ridge line information corresponding to different land type slice images based on the elevation information; generate the wind speed values corresponding to different land type slice images based on the mountaintop point information and ridge line information corresponding to different land type slice images.

[0072] The target fan layout calculation model includes a calculation formula for obtaining the wind speed value of the area to be installed with fans. Among them, the calculation formula for the wind speed value of the area to be installed with fans is:

[0073] Among them, ρ is the density (kg / m3); i is the ridge line coordinate; j is the mountaintop point coordinate; u is the wind speed (m / s); μ is the dynamic viscosity coefficient (Pa·s); μ t is the turbulent dynamic viscosity coefficient (Pa·s); ε is the turbulent kinetic energy dissipation rate (m2 / s2); Sui is the mean strain rate tensor; process the wind speed value of the area to be installed with fans based on the avoidance area information to generate the wind energy emission value; process the wind energy emission value and the wind speed value of the area to be installed with fans based on the fan layout calculation model to generate the fan power generation potential value of the area to be installed with fans; the fan layout calculation model includes a calculation formula for obtaining the fan power generation potential value of the area to be installed with fans. Among them, the calculation formula for the fan power generation potential value of the area to be installed with fans is: Among them, EF is the fan power generation potential value of the area to be installed with fans, Q req is the wind energy emission value, Q is the total wind energy value of the area to be installed with fans, δ is the CO concentration, Q coLet CO emissions in the area to be installed with wind turbines be \(CO\), the standard atmospheric pressure be \(P_0\), the atmospheric pressure in the area to be installed with wind turbines be \(P\), the summer temperature in the area to be installed with wind turbines be \(T\), and the standard temperature be \(T_0\); process the wind speed values corresponding to the sliced images of different land types to generate the wind speed value in the area to be installed with wind turbines; obtain the preset wind turbine installation value; process the wind turbine power generation potential value in the area to be installed with wind turbines based on the wind turbine layout calculation model to generate the initial wind turbine installation value; process the initial wind turbine installation value based on the preset wind turbine installation value to generate the target wind turbine installation value. By obtaining the wind turbine layout calculation model that matches the identification information of the area to be installed with wind turbines to process the information of the area to be installed with wind turbines, comprehensively considering factors such as wind speed, wind direction, elevation, etc., and avoiding obstacles such as rivers and buildings, and combining the topographic features of the national mountain tops and ridge lines, the optimal layout of wind turbine positions is realized.

[0074] In one implementation, as Figure 2 shown, the present application also provides a wind turbine layout device based on high-resolution wind resource data, including:

[0075] An acquisition module 201, configured to acquire the information of the area to be installed with wind turbines sent by the client; acquire the server address storing the wind turbine layout calculation model that matches the identification information;

[0076] A processing module 202, configured to process the information of the area to be installed with wind turbines to generate a land type image with identification information, where the identification information includes target mountaintop point information, ridge line information, and avoidance area information; process the land type image with identification information to generate a number of land type sliced images, where the number of land type sliced images are high-resolution images; if the number of servers storing the wind turbine layout calculation model is multiple, acquire the business load status of multiple servers; if the server with the lowest business load status is the current server, acquire the initial wind turbine layout calculation model that matches the identification information of the area to be installed with wind turbines stored in the current server; process the initial wind turbine layout calculation model based on a preset processing rule to generate a target wind turbine layout calculation model; process the land type sliced images based on the target wind turbine layout calculation model to generate the wind turbine power generation potential value in the area to be installed with wind turbines; process the wind turbine power generation potential value based on the target wind turbine layout calculation model to generate the wind turbine installation information in the area to be installed with wind turbines.

[0077] In another implementation of the present application, the processing module 202 is configured to process the information of the area to be installed with wind turbines to generate a land type image with identification information, including:

[0078] Perform image extraction on the information of the area to be installed with wind turbines based on a deep learning neural network model to generate a surface information image of the area to be installed with wind turbines;

[0079] Gray-scale processing is performed on the surface information image of the area to be machine-placed, and a surface information image with a target brightness is generated;

[0080] Image normalization processing is performed on the surface information image with the target brightness, and a surface information image with a preset size is generated;

[0081] Image enhancement processing is performed on the surface information image with the preset size to generate a land type image, where the land type image includes soil organic carbon content information, soil type information, and gravel information.

[0082] In another implementation manner of the present application, the processing module 202 is configured to process the initial fan layout calculation model based on a preset processing rule to generate a target fan layout calculation model, including:

[0083] Obtain a training sample set for updating the fan layout calculation model;

[0084] Perform feature extraction on the training sample set to determine an original feature library;

[0085] Divide the training sample set according to the original feature library to generate a training set and a test set;

[0086] Use a classifier to predict each test set divided by the original feature library to determine a prediction result;

[0087] Use a preset algorithm to train each training set divided by the original feature library to obtain a test set class prediction result;

[0088] Generate a training sample set with target feature data according to the prediction result and the test set class prediction result;

[0089] Process the initial fan layout calculation model based on the training sample set with the target feature data to generate a target fan layout calculation model.

[0090] In another implementation manner of the present application, the processing module 202 is configured to process the land type slice image based on the target fan layout calculation model to generate a fan power generation potential value of the area to be machine-placed, including:

[0091] Obtain elevation information corresponding to a plurality of land type slice images;

[0092] Based on the elevation information, obtain mountaintop point information and ridgeline information corresponding to different land type slice images;

[0093] Generate wind speed values corresponding to different land type slice images based on the mountaintop point information and ridgeline information corresponding to different land type slice images;

[0094] Process the wind speed values corresponding to the sliced images of the different land types to generate the wind speed value of the area to be installed with wind turbines.

[0095] In another embodiment of the present application, the processing module 202 is configured to process the sliced images of the land types based on the target wind turbine layout calculation model to generate the wind turbine power generation potential value of the area to be installed with wind turbines, and further includes:

[0096] The target wind turbine layout calculation model includes a calculation formula for obtaining the wind speed value of the area to be installed with wind turbines. Among them, the calculation formula for the wind speed value of the area to be installed with wind turbines is:

[0097]

[0098] Where ρ is the density (kg / m3); i is the ridgeline coordinate; j is the mountaintop coordinate; u is the wind speed (m / s); μ is the dynamic viscosity coefficient (Pa·s); μ t is the turbulent dynamic viscosity coefficient (Pa·s); ε is the turbulent kinetic energy dissipation rate (m2 / s2); Sui is the mean strain rate tensor.

[0099] In another embodiment of the present application, the processing module 202 is configured to process the sliced images of the land types based on the target wind turbine layout calculation model to generate the wind turbine power generation potential value of the area to be installed with wind turbines, and further includes:

[0100] Process the wind speed value of the area to be installed with wind turbines based on the avoidance area information to generate the wind energy emission value;

[0101] Process the wind energy emission value and the wind speed value of the area to be installed with wind turbines based on the wind turbine layout calculation model to generate the wind turbine power generation potential value of the area to be installed with wind turbines;

[0102] The wind turbine layout calculation model includes a calculation formula for obtaining the wind turbine power generation potential value of the area to be installed with wind turbines. Among them, the calculation formula for the wind turbine power generation potential value of the area to be installed with wind turbines is:

[0103]

[0104] Where EF is the wind turbine power generation potential value of the area to be installed with wind turbines, Q req is the wind energy emission value, Q is the total wind energy value of the area to be installed with wind turbines, δ is the CO concentration, Q co is the CO emission amount of the area to be installed with wind turbines, P0 is the standard atmospheric pressure, P is the atmospheric pressure of the area to be installed with wind turbines, T is the summer temperature of the area to be installed with wind turbines, and T0 is the standard temperature.

[0105] In another embodiment of the present application, the processing module 202 is configured to process the wind turbine power generation potential value based on the wind turbine layout calculation model to generate wind turbine layout information for the area to be installed, including:

[0106] Obtain a preset wind turbine layout value;

[0107] Process the wind turbine power generation potential value of the area to be installed based on the wind turbine layout calculation model to generate an initial wind turbine layout value;

[0108] Process the initial wind turbine layout value based on the preset wind turbine layout value to generate a target wind turbine layout value.

[0109] An embodiment of the present application provides an electronic device, such as Figure 3 shown, the electronic device 3 includes a first processor 300, a memory 301, a bus 302, and a communication interface 303. The first processor 300, the communication interface 303, and the memory 301 are connected through the bus 302. A computer program that can run on the first processor 300 is stored in the memory 301. When the first processor 300 runs the computer program, it executes the wind turbine layout method based on high-resolution wind resource data provided in any of the foregoing embodiments of the present application.

[0110] Among them, the memory 301 may include a high-speed random access memory (RAM: Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 303 (which can be wired or wireless), a communication connection is established between this system network element and at least one other network element, and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0111] The bus 302 may be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 301 is used to store programs. After receiving an execution instruction, the first processor 300 executes the program. The wind turbine layout method based on high-resolution wind resource data disclosed in any of the foregoing embodiments of the present application can be applied to the first processor 300 or implemented by the first processor 300.

[0112] The first processor 300 may be an integrated circuit chip with the ability to process signals. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the first processor 300 or the instructions in the form of software. The above-mentioned first processor 300 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be embodied as being executed by a hardware decoding processor or by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 301, and the first processor 300 reads the information in the memory 301 and combines its hardware to complete the steps of the above method.

[0113] The electronic device provided in the above embodiment of the present application and the fan layout method based on high-resolution wind resource data provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run, or implemented by the application programs stored therein.

[0114] The embodiment of the present application provides a computer-readable storage medium, such as Figure 4 shown, the computer-readable storage medium stores 401 a computer program, and when the computer program is read and run by the second processor 402, it implements the fan layout method based on high-resolution wind resource data as described above.

[0115] The technical solution of the embodiment of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing an electronic device (which may be an air conditioner, a refrigeration device, a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiment of the present application. The aforementioned storage medium includes: various media such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disc that can store program codes.

[0116] The computer-readable storage medium provided by the above embodiments of the present application and the method for arranging wind turbines based on high-resolution wind resource data provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run, or implemented by the application programs stored therein.

[0117] The embodiments of the present application provide a computer program product, including a computer program, which is executed by a third processor to implement the method as described above. The computer program product provided by the above embodiments of the present application and the method for arranging wind turbines based on high-resolution wind resource data provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run, or implemented by the application programs stored therein.

[0118] Each embodiment in the present application is described in a related manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the method for evaluating the arrangement of wind turbines based on high-resolution wind resource data, electronic devices, electronic equipment, and readable storage media, since they are basically similar to the embodiments of the method for arranging wind turbines based on high-resolution wind resource data described above, the description is relatively simple, and reference can be made to the partial description of the embodiments of the method for arranging wind turbines based on high-resolution wind resource data described above for the relevant parts.

[0119] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application should be subject to the scope defined by the claims.

Claims

1. A wind turbine layout method based on high-resolution wind resource data, characterized in that: include: Get the waiting area information sent by the client; Processing the information of the area to be deployed to generate a land type image with identification information, wherein the identification information includes target mountain top information, ridge line information and avoidance area information; Processing the land type image with identification information to generate a plurality of land type slice images, wherein the plurality of land type slice images are high-resolution images; Obtaining a server address storing a wind turbine layout calculation model matching the identification information; If there are multiple servers storing the wind turbine layout calculation model, then obtaining the service load status of the multiple servers; If the server with the lowest service load status is the current server, then obtaining an initial wind turbine layout calculation model that matches the identification information of the area to be laid out stored in the current server; Processing the initial wind turbine layout calculation model based on preset processing rules to generate a target wind turbine layout calculation model; Processing the land type slice image based on the target wind turbine layout calculation model to generate a wind turbine power generation potential value in the area to be laid out; Processing the wind turbine power generation potential value based on the target wind turbine layout calculation model to generate wind turbine layout information in the area to be laid out; The land type slice image is processed based on the target wind turbine layout calculation model to generate the wind turbine power generation potential value of the area to be arranged, including: obtaining elevation information corresponding to a plurality of land type slice images; obtaining mountain top point information and ridge line information corresponding to different land type slice images based on the elevation information; generating wind speed values ​​corresponding to different land type slice images based on the mountain top point information and ridge line information corresponding to the different land type slice images; processing the wind speed values ​​corresponding to the different land type slice images to generate the wind speed value of the area to be arranged; The target wind turbine layout calculation model includes a calculation formula for obtaining the wind speed value of the area to be arranged, wherein the calculation formula for the wind speed value of the area to be arranged is: Where ρ is the density (kg / m 3 ), i is the ridgeline coordinate, j is the mountain top coordinate, u is the wind speed (m / s), μ is the dynamic viscosity coefficient (Pa·s), μ t is the turbulent dynamic viscosity coefficient (Pa·s); ε is the turbulent kinetic energy dissipation rate (m 2 / a 2 );S ui is the average strain rate tensor; The land type slice image is processed based on the target wind turbine layout calculation model to generate a wind turbine power generation potential value in the area to be arranged, and further includes: processing the wind speed value in the area to be arranged based on the avoidance area information to generate a wind energy emission value; processing the wind energy emission value and the wind speed value in the area to be arranged based on the wind turbine layout calculation model to generate a wind turbine power generation potential value in the area to be arranged; the wind turbine layout calculation model includes a calculation formula for obtaining the wind turbine power generation potential value in the area to be arranged, wherein the calculation formula for the wind turbine power generation potential value in the area to be arranged is: Among them, EF is the wind turbine power generation potential value in the area to be installed, Q req is the wind energy emission value, Q is the total wind energy value of the waiting area, δ is the CO concentration, P0 is the standard atmospheric pressure, P is the atmospheric pressure of the waiting area, T is the summer temperature of the waiting area, and T0 is the standard temperature.

2. The method according to claim 1, characterized in that The processing of the information of the area to be deployed to generate a land type image with identification information includes: Extracting images of the area where the machine is to be laid based on a deep learning neural network model to generate a surface information image of the area where the machine is to be laid; grayscale the surface information image of the area to be deployed to generate a surface information image of target brightness; Performing image normalization processing on the surface information image of the target brightness to generate a surface information image of a preset size; The surface information image of the preset size is subjected to image enhancement processing to generate a land type image, wherein the land type image includes soil organic carbon content information, soil type information and gravel information.

3. The method according to claim 1, characterized in that The processing of the initial wind turbine layout calculation model based on a preset processing rule to generate a target wind turbine layout calculation model includes: Acquiring a training sample set for updating the wind turbine layout calculation model; Extracting features from the training sample set to determine an original feature library; Divide the training sample set according to the original feature library to generate a training set and a test set; Use the classifier to predict each test set divided by the original feature library and determine the prediction result; Use the preset algorithm to train each training set divided by the original feature library to obtain the test set class prediction results; Generate a training sample set with target feature data based on the prediction results and the test set prediction results; The initial wind turbine layout calculation model is processed based on the training sample set with target feature data to generate a target wind turbine layout calculation model.

4. The method according to claim 1, characterized in that The wind turbine power generation potential value is processed based on the wind turbine layout calculation model to generate wind turbine layout information in the area to be laid out, including: Get the preset fan layout value; Processing the wind turbine power generation potential value in the area to be arranged based on the wind turbine layout calculation model to generate an initial wind turbine layout value; The initial fan layout value is processed based on the preset fan layout value to generate a target fan layout value.

5. A wind turbine layout device based on high-resolution wind resource data, characterized in that: The device comprises: An acquisition module is used to acquire the area information to be arranged sent by the client; and acquire the server address storing the wind turbine layout calculation model matching the identification information; A processing module, for processing the information of the area to be arranged, generating a land type image with identification information, wherein the identification information includes target mountain top information, ridge line information and avoidance area information; processing the land type image with identification information to generate a plurality of land type slice images, wherein the plurality of land type slice images are high-resolution images; if there are multiple servers storing the wind turbine layout calculation model, obtaining the business load status of multiple servers; if the server with the lowest business load status is the current server, obtaining an initial wind turbine layout calculation model that matches the identification information of the area to be arranged stored in the current server; processing the initial wind turbine layout calculation model based on preset processing rules to generate a target wind turbine layout calculation model; processing the land type slice image based on the target wind turbine layout calculation model to generate a wind turbine power generation potential value in the area to be arranged; processing the wind turbine power generation potential value based on the target wind layout calculation model to generate wind turbine layout information in the area to be arranged; The land type slice image is processed based on the target wind turbine layout calculation model to generate the wind turbine power generation potential value of the area to be arranged, including: obtaining elevation information corresponding to a plurality of land type slice images; obtaining mountain top point information and ridge line information corresponding to different land type slice images based on the elevation information; generating wind speed values ​​corresponding to different land type slice images based on the mountain top point information and ridge line information corresponding to the different land type slice images; processing the wind speed values ​​corresponding to the different land type slice images to generate the wind speed value of the area to be arranged; The target wind turbine layout calculation model includes a calculation formula for obtaining the wind speed value of the area to be arranged, wherein the calculation formula for the wind speed value of the area to be arranged is: Where ρ is the density (kg / m 3 ), i is the ridgeline coordinate, j is the top coordinate, u is the wind speed (m / s), μ is the dynamic viscosity coefficient (Pa·s), μ t is the turbulent dynamic viscosity coefficient (Pa·s); ε is the turbulent kinetic energy dissipation rate (m 2 / s 2 ); Sui is the average strain rate tensor; The land type slice image is processed based on the target wind turbine layout calculation model to generate a wind turbine power generation potential value in the area to be arranged, and further includes: processing the wind speed value in the area to be arranged based on the avoidance area information to generate a wind energy emission value; processing the wind energy emission value and the wind speed value in the area to be arranged based on the wind turbine layout calculation model to generate a wind turbine power generation potential value in the area to be arranged; the wind turbine layout calculation model includes a calculation formula for obtaining the wind turbine power generation potential value in the area to be arranged, wherein the calculation formula for the wind turbine power generation potential value in the area to be arranged is: Among them, EF is the wind turbine power generation potential value in the area to be installed, Q req is the wind energy emission value, Q is the total wind energy value of the waiting area, δ is the CO concentration, P0 is the standard atmospheric pressure, P is the atmospheric pressure of the waiting area, T is the summer temperature of the waiting area, and T0 is the standard temperature.

6. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; The first processor is configured to execute the wind turbine layout method based on high-resolution wind resource data as described in any one of claims 1 to 4 by executing the executable instructions.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the wind turbine layout method based on high-resolution wind resource data as claimed in any one of claims 1 to 4 is implemented.

Images