Method and device for constructing model for predicting influence of wind power plant on surface temperature

Abstract

The invention provides a construction method and device of a model for predicting the influence of a wind power plant on surface temperature, and relates to the technical field of data processing. The method comprises the following steps: determining space ranges of a wind power plant area and a contrast area based on satellite remote sensing data, and acquiring wind power plant surface temperature data and contrast surface temperature data by using the space ranges; simulating meteorological variable data of a wind power plant area by using a meteorological numerical model, and screening a wind power plant operation time period by using a wind speed variable in meteorological variables; determining a difference value between the surface temperature data of the wind power plant and the contrast surface temperature data to obtain influence data of the wind power plant on the surface temperature; and taking meteorological variable data corresponding to the wind power plant operation time period as input, taking influence data as output, and constructing a prediction model of the influence of the wind power plant on the surface temperature based on a machine learning algorithm. According to the technical scheme, the influence of the wind power plant on the surface temperature can be accurately predicted through a machine learning algorithm, and the prediction precision and applicability are improved.

Description

Background Art

[0002] Against the backdrop of global climate change, wind power generation, as an important component of renewable energy, has developed rapidly around the world. Wind power generation installed capacity continues to grow, especially in arid and semi-arid areas. However, the ecological environment in these areas is relatively fragile, and the operation of wind power generation facilities may have complex impacts on the local atmosphere and surface environment. Therefore, while promoting the development of the wind power industry, it is urgent to pay attention to its potential impact on the local climate to ensure the coordination and unity of energy development and ecological protection.

[0003] However, for the impact of wind power facilities on local surface temperature, existing technologies mainly rely on ground observations, remote sensing monitoring or numerical simulation methods. Although ground observation data can provide high-precision information, it is difficult to fully describe the temperature change characteristics of a large area due to the limited distribution of measurement points. Remote sensing monitoring methods can obtain large-scale spatial data, but are limited by cloud cover, sensor resolution and imaging frequency, and have deficiencies in data continuity and accuracy. Numerical simulation methods calculate the impact of wind power facilities on local climate through physical models. Although they can provide results with high temporal and spatial resolution, the calculation cost is high, and the simulation accuracy is greatly affected by the quality of input data, model parameter settings and the ability to describe physical processes, resulting in high uncertainty in the prediction results. Therefore, the existing technology lacks accuracy and adaptability when analyzing the impact of wind farms on surface temperature.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute relevant technology known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the embodiments of the present disclosure is to provide a method for constructing a prediction model of the impact of a wind farm on the surface temperature, a method for predicting the impact of a wind farm on the surface temperature, a device for constructing a prediction model of the impact of a wind farm on the surface temperature, a device for predicting the impact of a wind farm on the surface temperature, an electronic device and a computer-readable storage medium, so as to accurately predict the impact of a wind farm on the surface temperature through a machine learning algorithm, thereby improving the prediction accuracy and applicability.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to a first aspect of an embodiment of the present disclosure, there is provided a method for constructing a prediction model of the impact of a wind farm on the ground surface temperature, the method comprising: determining the spatial range of a wind farm area and a control area based on satellite remote sensing data, and using the spatial range to obtain the wind farm surface temperature data and the control surface temperature data; using a meteorological numerical model to simulate the meteorological variable data of the wind farm area, and using the wind speed variable in the meteorological variables to screen the wind farm operation period; determining the difference between the wind farm surface temperature data and the control surface temperature data during the wind farm operation period to obtain the impact data of the wind farm on the ground surface temperature; using the meteorological variable data corresponding to the wind farm operation period as input and the impact data as output, and constructing a prediction model of the impact of the wind farm on the ground surface temperature based on a machine learning algorithm.

[0008] In some example embodiments of the present disclosure, based on the aforementioned scheme, the method for constructing a prediction model for the impact of a wind farm on the surface temperature also includes: calculating a prediction residual based on the prediction results of the prediction model and the impact data; constructing a residual prediction model based on the prediction residual and the meteorological variable data; and post-processing the prediction results of the prediction model for the impact of the wind farm on the surface temperature using the residual prediction model to obtain a final prediction result of the impact of the wind farm on the surface temperature.

[0009] In some example embodiments of the present disclosure, based on the aforementioned scheme, the method of determining the spatial range of a wind farm area and a control area based on satellite remote sensing data, and obtaining wind farm surface temperature data and control surface temperature data using the spatial range, includes: determining the spatial distribution positions of wind turbines in the wind farm area using satellite remote sensing data, and generating the spatial range of the wind farm area based on the spatial distribution of the wind turbines; generating an initial spatial range of the control area in the external space of the wind farm area, and obtaining geographic feature data of the control area using satellite remote sensing data; screening the spatial range of the control area based on the geographic feature data to determine the spatial range of the control area that is consistent with the geographic background of the wind farm area; and obtaining the wind farm surface temperature data and the control surface temperature data from satellite remote sensing data, respectively, based on the spatial ranges of the wind farm area and the control area.

[0010] In some example embodiments of the present disclosure, based on the aforementioned scheme, the meteorological variable data of the wind farm area is simulated using a meteorological numerical model, and the wind speed variables in the meteorological variables are used to screen the wind farm operation time period, including: based on meteorological reanalysis data, obtaining hourly meteorological variable data of the wind farm area using a meteorological numerical model simulation; according to the wind speed variables in the meteorological variable data, determining the time period when the wind speed meets the preset wind turbine operating conditions, so as to screen out the wind farm operation time period.

[0011] In some example embodiments of the present disclosure, based on the aforementioned scheme, during the operation period of the wind farm, determining the difference between the surface temperature data of the wind farm and the control surface temperature data to obtain the impact data of the wind farm on the surface temperature, includes: determining the average surface temperature of the wind farm area and the control area at the same time; calculating the difference between the average surface temperature of the wind farm area and the average surface temperature of the control area at each moment to obtain the impact data of the wind farm on the surface temperature.

[0012] In some example embodiments of the present disclosure, based on the aforementioned scheme, the meteorological variable data corresponding to the operating period of the wind farm is used as input, and the impact data is used as output, and a prediction model for the impact of the wind farm on the surface temperature is constructed based on a machine learning algorithm, including: using a machine learning algorithm to construct multiple prediction models, using the meteorological variable data corresponding to the operating period of the wind farm as input, and the impact data as output to train the multiple prediction models separately; using the validation set data to evaluate the prediction accuracy of the multiple prediction models, and selecting the machine learning model with the highest prediction accuracy as the prediction model for the impact of the wind farm on the surface temperature.

[0013] In some example embodiments of the present disclosure, based on the aforementioned scheme, constructing a residual prediction model based on the prediction residual and the meteorological variable data includes: taking the meteorological variable data corresponding to the wind farm operating period as input, taking the prediction residual as output, and constructing a residual prediction model using a linear regression calibration algorithm.

[0014] In some example embodiments of the present disclosure, based on the aforementioned scheme, the meteorological variable data corresponding to the wind farm operation period is used as input, and the impact data is used as output, and a prediction model of the impact of the wind farm on the surface temperature is constructed based on a machine learning algorithm, including: constructing an input matrix based on the meteorological variable data corresponding to the wind farm operation period, and constructing a target vector based on the wind farm impact data on the surface temperature; extracting a training sample set from the input matrix and the target vector using a self-service sampling method, and constructing a random forest model based on the training sample set, The decision tree ensemble is composed of independently trained decision trees: in, represents the ensemble of decision trees for the random forest model, Indicates A decision tree; Determine the optimal feature partitioning node based on information gain and recursively construct a binary decision tree: in, Indicates A decision tree on the feature The optimal partitioning of As the classification criteria, Indicates the selection The index of the feature that reaches the maximum value, Represents feature index The value range is 1 to n , n Represents the total number of features, and the information gain calculation formula is: ,in, represents data entropy, By feature Performing conditional entropy after partitioning, and constructing a decision tree structure based on the optimal partitioning; The predicted value of the wind farm for the surface temperature is calculated based on the trained random forest model, and the prediction results of all decision trees are used for weighted calculation: in, Represents the time step The final predicted value of Indicates A decision tree for input samples The prediction output is used to obtain a prediction model of the impact of the wind farm on the surface temperature.

[0015] According to a second aspect of an embodiment of the present disclosure, a method for predicting the impact of a wind farm on the ground surface temperature is provided, the method comprising: obtaining meteorological variable data corresponding to the operating period of the wind farm within a target wind farm area; inputting the meteorological variable data into a prediction model for the impact of the wind farm on the ground surface temperature, and obtaining data on the impact of the wind farm on the ground surface temperature within the target wind farm area; wherein the prediction model for the impact of the wind farm on the ground surface temperature is trained according to the method for constructing a prediction model for the impact of the wind farm on the ground surface temperature as described in the above-mentioned embodiment.

[0016] According to a third aspect of an embodiment of the present disclosure, there is provided a device for constructing a prediction model of the impact of a wind farm on the ground surface temperature, the device comprising: a temperature data acquisition module, for determining the spatial range of a wind farm area and a control area based on satellite remote sensing data, and using the spatial range to acquire the surface temperature data of the wind farm and the control surface temperature data; a meteorological data acquisition module, for simulating the meteorological variable data of the wind farm area using a meteorological numerical model, and using the wind speed variable in the meteorological variable to screen the wind farm operation period; an impact data acquisition module, for determining the difference between the surface temperature data of the wind farm and the control surface temperature data during the wind farm operation period, so as to obtain the impact data of the wind farm on the ground surface temperature; a prediction model construction module, for taking the meteorological variable data corresponding to the wind farm operation period as input and the impact data as output, and constructing a prediction model of the impact of the wind farm on the ground surface temperature based on a machine learning algorithm.

[0017] According to a fourth aspect of an embodiment of the present disclosure, a device for predicting the impact of a wind farm on the ground surface temperature is provided, the device comprising: a target data acquisition module, for acquiring meteorological variable data corresponding to the operating period of the wind farm in a target wind farm area; an impact prediction module, for inputting the meteorological variable data into a prediction model for the impact of the wind farm on the ground surface temperature, and obtaining the impact data of the wind farm on the ground surface temperature in the target wind farm area; wherein the prediction model for the impact of the wind farm on the ground surface temperature is trained according to the method for constructing a prediction model for the impact of the wind farm on the ground surface temperature as described in the above-mentioned embodiments.

[0018] According to a fifth aspect of an embodiment of the present disclosure, there is provided an electronic device, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method for constructing a prediction model of the impact of wind farms on the ground surface temperature or the method for predicting the impact of wind farms on the ground surface temperature is implemented.

[0019] According to a sixth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the method for constructing a prediction model of the impact of wind farms on the ground surface temperature or the method for predicting the impact of wind farms on the ground surface temperature according to the above-mentioned method.

[0020] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects: The method for constructing a prediction model of the impact of wind farms on surface temperature in the exemplary embodiment of the present disclosure, on the one hand, determines the spatial range of the wind farm area and the control area based on satellite remote sensing data, and uses the spatial range to obtain the surface temperature data of the wind farm and the control surface temperature data, thereby improving the accuracy of the surface temperature change characteristics of the wind farm. On the other hand, by using the meteorological numerical model to simulate the meteorological variable data of the wind farm area, and combining the wind speed variable in the meteorological variable to screen the wind farm operation period, the data input not only includes the comprehensive impact of the atmospheric environment during the operation of the wind farm, but also can eliminate the data of the non-operating state, improve the representativeness of the data sample, make the model training more targeted, and thus enhance the prediction ability. On the other hand, by taking the meteorological variable data corresponding to the wind farm operation period as input, and the impact data of the wind farm on the surface temperature as output, and using the machine learning algorithm to construct a prediction model of the impact of the wind farm on the surface temperature, the modeling process can combine multi-source data, and extract the complex nonlinear relationship between the data based on the adaptive learning ability, compared with the traditional physical model calculation method, it can effectively improve the prediction accuracy and enhance the adaptability of the model to the impact of the wind farm under different environmental conditions.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0023] Figure 1 A flow chart of a method for constructing a prediction model of the impact of a wind farm on ground surface temperature according to some embodiments of the present disclosure is schematically shown.

[0024] Figure 2 A schematic diagram schematically shows a comparison between the impact of a wind farm on the ground surface temperature predicted by a random forest model according to some embodiments of the present disclosure and the observed value.

[0025] Figure 3 A schematic diagram schematically shows a comparison between the impact of a post-processed wind farm on the ground surface temperature according to some embodiments of the present disclosure and the observed value.

[0026] Figure 4 The figure schematically shows the influence of a wind farm on the ground surface temperature and the change of the observed value with the hour according to the post-processing of some embodiments of the present disclosure.

[0027] Figure 5 A schematic diagram schematically shows a comparison between the hourly variation of the impact of a wind farm on the ground surface temperature and the observed value after post-processing according to some embodiments of the present disclosure.

[0028] Figure 6 A flowchart of a method for predicting the impact of a wind farm on ground surface temperature according to some embodiments of the present disclosure is schematically shown.

[0029] Figure 7 A block diagram of a device for constructing a prediction model of the impact of a wind farm on ground surface temperature according to some embodiments of the present disclosure is schematically shown.

[0030] Figure 8 A block diagram of a device for predicting the impact of a wind farm on ground surface temperature according to some embodiments of the present disclosure is schematically shown.

[0031] Fig. 9 A schematic diagram of the structure of a computer system of an electronic device according to some embodiments of the present disclosure is schematically shown.

[0032] Fig.10 A schematic diagram of a computer-readable storage medium according to some embodiments of the present disclosure is schematically shown.

[0033] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0034] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this specification. Instead, they are merely examples of devices and methods consistent with some aspects of this specification as detailed in the appended claims.

[0035] The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this specification. The singular forms "a", "the" and "the" used in this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0036] It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this specification, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0037] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more comprehensive and complete and will fully convey the concept of the example embodiments to those skilled in the art.

[0038] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0039] Furthermore, the drawings are only schematic illustrations and are not necessarily drawn to scale. The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0040] The impact of wind farms on the surface temperature mainly comes from the downwind turbulence caused by the rotation of wind turbine blades in the atmospheric boundary layer. This turbulence mixes the surface and upper air layers, causing the redistribution of heat and other factors. For example, due to changes in solar radiation, the temperature difference between the upper and surface air layers (the vertical temperature gradient) will change dramatically within a day. During the day, due to strong solar radiation, the vertical temperature gradient is high. At this time, the wind farm will cause the surface air to cool down. At night, the vertical temperature gradient is low, and the wind farm will cause the surface air to warm up. This process will also be transmitted to the surface, causing changes in surface temperature, which can be observed by satellite remote sensing.

[0041] Related technologies mainly rely on ground observations, remote sensing monitoring or numerical simulation methods to analyze the impact of wind power facilities on surface temperature. Although ground observations are highly accurate, their coverage is limited and it is difficult to reflect large-scale changes. Although remote sensing monitoring can obtain data over a large range, it is limited by cloud layers, resolution and imaging frequency, and the data continuity and accuracy are insufficient. Although numerical simulation methods can provide high temporal and spatial resolution results, they have high computational costs and are affected by the quality of input data, model parameters and physical process descriptions. The prediction results are unstable, resulting in limited accuracy and adaptability.

[0042] In order to solve all or part of the technical problems in the above-mentioned related technologies, in an exemplary embodiment of the present disclosure, a method for constructing a prediction model of the impact of a wind farm on the ground surface temperature is firstly proposed. Figure 1 The following is a schematic diagram of a method for constructing a prediction model of the impact of a wind farm on ground surface temperature according to some embodiments of the present disclosure. Figure 1 As shown, the method for constructing the prediction model of the impact of wind farms on ground surface temperature may include the following steps: Step S110: determining the spatial range of the wind farm area and the reference area based on the satellite remote sensing data, and obtaining the wind farm surface temperature data and the reference surface temperature data using the spatial range.

[0043] Step S120, using a meteorological numerical model to simulate meteorological variable data in the wind farm area, and using wind speed variables in the meteorological variables to select the wind farm operation period.

[0044] Step S130, during the operation period of the wind farm, determining the difference between the surface temperature data of the wind farm and the reference surface temperature data to obtain the impact data of the wind farm on the surface temperature.

[0045] Step S140, using the meteorological variable data corresponding to the operating period of the wind farm as input and the impact data as output, constructing a prediction model of the impact of the wind farm on the surface temperature based on a machine learning algorithm.

[0046] This method first extracts the spatial range of the wind farm area and the control area based on satellite remote sensing data, and determines the data set that meets the research requirements through coordinate matching and spatial consistency screening. The surface temperature data of the wind farm and the control surface temperature data are extracted from the screened data set, and the data quality is controlled to eliminate abnormal data and ensure the integrity and reliability of the input data. After the spatial range is determined, the meteorological numerical model is further used to simulate the meteorological variable data of the wind farm area. By inputting the initial meteorological field data and setting the simulation parameters, the meteorological variables of the wind farm area are calculated, the wind speed variables are extracted from them, and the threshold conditions are set to screen the wind farm operation period. By screening the time period that meets the operation requirements of the wind farm, the data input is more targeted, avoiding the influence of the non-operating period, and improving the representativeness of the data.

[0047] During the operation period of the wind farm, the surface temperature data of the wind farm is matched with the control surface temperature data, and the alignment calculation is performed on the time series. The impact data of the wind farm on the surface temperature is determined by difference operation. Outliers are removed for the calculated impact data to ensure the stability of the data. After the data calculation is completed, the meteorological variable data corresponding to the operation period of the wind farm is used as input, and the impact data of the wind farm on the surface temperature is used as output. A prediction model is built based on the machine learning algorithm. The parameter combination is optimized through model training, and the model accuracy is evaluated using the validation set data. The prediction error is analyzed, and the model structure is optimized in combination with the error correction method to improve the accuracy and generalization ability of the prediction results, so that it can be applied to different wind farm areas and environmental conditions.

[0048] Next, the method for constructing the prediction model of the impact of a wind farm on the ground surface temperature in the above exemplary embodiment will be further described.

[0049] Step S110: determining the spatial range of the wind farm area and the reference area based on the satellite remote sensing data, and obtaining the wind farm surface temperature data and the reference surface temperature data using the spatial range.

[0050] Among them, the wind farm area can represent the geographical range where the wind power generation facilities are located based on satellite remote sensing data, and the range is used to extract the surface temperature data of the wind farm. The control area can represent the geographical range used to compare the wind farm area, which has similar geographical features to the wind farm area, but does not contain wind power generation facilities, and is used to extract the control surface temperature data. The wind farm surface temperature data can represent the surface temperature data extracted within the wind farm area, and the data is used to analyze the impact of the operation of wind power generation facilities on the surface temperature. The control surface temperature data can represent the surface temperature data extracted within the control area, and the data is used to compare with the wind farm surface temperature data to determine the impact of the wind farm operation on the surface temperature.

[0051] In some embodiments, the spatial range of the wind farm area and the reference area is determined based on satellite remote sensing data, and the wind farm surface temperature data and the reference surface temperature data are obtained using the spatial range, specifically including the following technical steps: First, the spatial distribution position of wind turbines in the wind farm area is determined using satellite remote sensing data, and the spatial scope of the wind farm area is generated based on the spatial distribution of wind turbines. For example, satellite remote sensing data can be used to extract the spatial distribution position information of wind turbines in a certain plateau area through map tools such as Google Earth. On this basis, the most concentrated wind farms are screened out, totaling 1,721 wind turbines, and the wind turbines are spatially annotated on the map tool, and finally the .shp file is exported for spatial analysis. Based on the spatial distribution of wind turbines, a buffer zone with a fixed radius is constructed with each wind turbine as the center using geographic information system tools, and all buffer zones are merged to generate the spatial scope of the wind farm area to ensure that the wind farm covers all wind turbines and accurately characterizes the overall impact area of ​​the wind farm.

[0052] Then, the initial spatial range of the control area is generated in the external space of the wind farm area, and the geographic feature data of the control area is obtained using satellite remote sensing data. Exemplarily, based on the principle of spatial consistency, a strip buffer zone is set outside the wind farm area to ensure that the control area is outside the influence range of the wind farm while maintaining sufficient spatial distribution uniformity. The initial spatial range of the control area is obtained by establishing a strip buffer zone within 3-8km outside the wind farm area, and extracting the geographic feature data of the control area in combination with satellite remote sensing data, including terrain, altitude, land cover type, etc., to ensure that the spatial distribution of the control area is reasonable and provide basic data support for subsequent screening.

[0053] Next, based on the geographic feature data, the spatial scope of the control area is screened to determine the spatial scope of the control area that is consistent with the geographical background of the wind farm area. Specifically, satellite remote sensing data is used to analyze the geographical features of the wind farm area and the control area, and areas with large differences in topography and landforms in the control area are eliminated, including parts with large altitude changes and significantly different surface cover types, to ensure that the control area and the wind farm area have a high degree of consistency in terms of geographical background. The spatial scope of the screened control area is optimized through spatial analysis methods so that it can accurately reflect the surface temperature characteristics under the condition of no wind turbine operation, thereby improving the comparability of subsequent analysis.

[0054] Finally, based on the spatial range of the wind farm area and the control area, the surface temperature data of the wind farm and the control surface temperature data are obtained from the satellite remote sensing data. For example, the surface temperature inversion data of the Fengyun-4 satellite can be selected, and hourly data with a spatial resolution of 4km and a time resolution of 15-60 minutes can be obtained based on the Fengyun satellite remote sensing data, and the data time range is set to ensure that the data covers the wind farm operation impact period. The downloaded data format is .nc format, and the actual longitude and latitude coordinates are matched by programming table lookup, and converted into geotiff format containing spatial coordinate information to ensure the accuracy of data geographic matching. In the process of data processing, the data quality mark is used for screening, and the data with greater cloud coverage is eliminated to ensure that the acquired wind farm surface temperature data and the control surface temperature data are high-quality data, and can accurately reflect the temperature change characteristics of the study area.

[0055] Step S120: using a meteorological numerical model to simulate meteorological variable data in the wind farm area, and using wind speed variables in the meteorological variables to select the wind farm operation period.

[0056] Among them, the meteorological numerical model can represent a mathematical model for calculating atmospheric physical and dynamic processes, which simulates the time evolution of the atmospheric state through numerical calculation methods based on the input initial and boundary conditions. Meteorological variable data can represent atmospheric state parameters calculated by the meteorological numerical model, including but not limited to wind speed, temperature, humidity, air pressure, etc., which are used to describe the meteorological characteristics in the wind farm area. The wind speed variable can represent the wind speed parameter in the meteorological variable data, which is used to characterize the rate of air flow in the wind farm area and can be used to judge the operating status of the wind farm. The wind farm operating period can represent the time interval when the wind speed variable meets the normal operating conditions of the wind power generation facilities. The data of this period is used for subsequent analysis of the impact of the wind farm operation on the surface temperature.

[0057] In some embodiments, a meteorological numerical model is used to simulate the meteorological variable data of the wind farm area, and the wind speed variable in the meteorological variable is used to screen the wind farm operation time period, which specifically includes the following technical steps: based on the meteorological reanalysis data, the meteorological numerical model is used to simulate and obtain the hourly meteorological variable data of the wind farm area; according to the wind speed variable in the meteorological variable data, the time period when the wind speed meets the preset wind turbine operating conditions is determined to screen out the wind farm operation time period.

[0058] Specifically, based on meteorological reanalysis data, meteorological numerical model simulation is used to obtain hourly meteorological variable data in the wind farm area. First, meteorological reanalysis data is obtained from the target website. For example, the meteorological reanalysis data can be ERA5 (Fifth Generation ECMWF Atmospheric Reanalysis, the fifth generation of European Center for Medium-Term Weather Forecasts Meteorological Reanalysis) data, which is stored in GRIB format and needs to be preprocessed before it can be used for numerical model calculation. ERA5 data is converted through the Weather Research and Forecasting Preprocessing System (WPS) module of the WRF model, which specifically includes three steps. First, run geogrid.exe, set the operating area and nested area of ​​the model, and load static geographic data to ensure that the numerical simulation range meets the research requirements. Then, run ungrib.exe to extract meteorological variables from ERA5 data to ensure that the required atmospheric elements can be used for subsequent simulations. Finally, run metgrid.exe to grid the data processed in the first two steps to generate a standardized data set that can be read by the WRF model. After completing the WPS preprocessing, link the result file generated by metgrid.exe to the WRF directory, and further configure the physical schemes used by the WRF model, including the radiation scheme, boundary layer scheme, cumulus scheme, etc., to ensure that the model can accurately simulate the meteorological characteristics of the wind farm area. Subsequently, run real.exe to initialize the data into a format recognizable by WRF, and run wrf.exe for the final numerical simulation to obtain hourly meteorological variable data in the wind farm area. Since the WRF model usually has better calculation accuracy for meteorological variables than its driving data, the simulation results can provide more detailed meteorological variable information and provide high-quality data for subsequent analysis.

[0059] According to the wind speed variable in the meteorological variable data, the time period when the wind speed meets the preset wind turbine operating conditions is determined to screen out the wind farm operation time period. The operating status of a wind farm can usually be judged by its real-time capacity coefficient, but this data is usually internal data of the operator and is difficult to obtain. Therefore, this embodiment uses the wind speed variable as the criterion for the operation of the wind farm. Generally speaking, the operation of a wind turbine depends on whether the wind speed is within its designed operating range, that is, when the wind speed exceeds the cut-in wind speed but does not reach the cut-out wind speed, the wind turbine is in normal operation. According to the general design parameters of existing wind turbines, a wind speed range of 3m / s to 20m / s is selected as the operation judgment condition of the wind farm. The wind speed variable is extracted from the hourly meteorological variable data, and the time period that meets the wind speed condition is screened out to obtain a wind farm operation time period data set. This method uses a wide range of available wind speed data to replace traditional capacity coefficient data, making the screening of wind farm operation status more feasible and applicable.

[0060] Step S130: during the operation period of the wind farm, determining the difference between the wind farm surface temperature data and the reference surface temperature data to obtain the impact data of the wind farm on the surface temperature.

[0061] The data on the impact of wind farms on the ground surface temperature can be expressed as the result calculated based on the difference between the wind farm surface temperature data and the reference surface temperature data during the wind farm operation period. This data is used to describe the degree of impact of wind farm operation on the ground surface temperature and its temporal and spatial variation characteristics.

[0062] In some embodiments, during the operation period of the wind farm, the difference between the surface temperature data of the wind farm and the control surface temperature data is determined to obtain the impact data of the wind farm on the surface temperature, which specifically includes the following technical steps: determining the average surface temperature of the wind farm area and the control area at the same time; calculating the difference between the average surface temperature of the wind farm area and the average surface temperature of the control area at each moment to obtain the impact data of the wind farm on the surface temperature.

[0063] Exemplarily, when determining the average surface temperature of the wind farm area and the control area at the same time, the average surface temperature of the wind farm area and the control area at the same time can be determined based on the surface temperature data of the Fengyun-4 satellite to construct a temperature comparison data set. To ensure the accuracy of the calculation, it is necessary to perform pixel-level temperature extraction on the wind farm area and the control area respectively. Based on the spatial range of the wind farm area, the surface temperature pixels in the Fengyun-4 satellite remote sensing data are screened, and the average surface temperature of the wind farm area is calculated at the same time step. The surface temperature calculation process of the control area adopts the same method. Based on the selected control area range, the remote sensing temperature data at the corresponding time is extracted, and the average value of the pixel is calculated. Since the surface temperature of the wind farm and the control area is jointly affected by the regional climate background, selecting a control area with a consistent geographical background can effectively reduce the interference of climate element changes on temperature calculation, and ensure that the calculation results can accurately reflect the independent impact of wind farm operation on surface temperature.

[0064] After the surface temperature calculations of the wind farm area and the control area are completed, the difference between the average surface temperature of the wind farm area and the average surface temperature of the control area is calculated moment by moment to obtain the impact data of the wind farm on the surface temperature. The time alignment method is used to ensure that the calculations at each moment are based on the matching data of the wind farm area and the control area to reduce the errors caused by time differences. The specific calculation method is: in, represents the impact of the surface temperature caused by the wind farm at a certain moment, It represents the average value of all surface temperature pixels in the wind farm area at a certain moment. It represents the average value of all surface temperature pixels in the control area at a certain moment.

[0065] Step S140, using the meteorological variable data corresponding to the wind farm operation period as input and the impact data as output, a prediction model of the impact of the wind farm on the surface temperature is constructed based on the machine learning algorithm. In the embodiment of the present disclosure, when constructing the prediction model of the impact of the wind farm on the surface temperature, first, the variables that meet the actual needs of the project are screened from the meteorological variable data output by the WRF mode to construct an efficient and robust data input set. In the data input preparation stage, based on the WRF mode output data in the wind farm operation period, wind speed, temperature, humidity, air pressure and their derivative variables are extracted to ensure that the input data can reflect the main meteorological characteristics of the wind farm area. Although the WRF mode can provide a wealth of meteorological variables, in order to ensure the engineering applicability of the model, only the variables that can be actually measured in the planning and design stage of the wind farm are selected, and the characteristic contribution of each variable is evaluated based on the data analysis method to ensure that the selected variables have a high explanatory power for the impact of the wind farm on the surface temperature. For time series data, the sliding window method is used to reconstruct the meteorological variables to capture the short-term change trend, and the data is normalized to ensure that the numerical range of different variables is consistent to improve the convergence speed and stability of the model. During the model building phase, the data on the impact of wind farms on surface temperature is used as output, and machine learning algorithms based on different principles are selected for modeling to ensure the model's adaptability to data characteristics.

[0066] Exemplarily, the machine learning algorithm may include, but is not limited to, a support vector machine model, a K nearest neighbor model, a random forest model, and a gradient boosting model. Among them, the support vector machine model is a binary classification model, and its basic idea is to find an optimal decision boundary (also called a hyperplane) so that it can separate the two categories to the greatest extent and minimize the classification error of unknown data. The K nearest neighbor model is an instance-based learning method. For a new instance of an unknown category, the category or value of the new instance is predicted based on the category or value of these nearest neighbors by finding the K known instances most similar to the instance in the training set. The random forest model is a tree-based ensemble learning algorithm that improves accuracy and stability by building multiple decision trees and voting or averaging, and introduces randomness to reduce the risk of overfitting. The gradient boosting model is an optimization algorithm based on a gradient boosting decision tree, which forms an integrated model by iteratively building and combining multiple weak learners (usually decision trees). In this embodiment, machine learning modeling is implemented by calling the Scikit-learn function library through Python programming.

[0067] In some embodiments, the meteorological variable data corresponding to the operating period of the wind farm is used as input, and the impact data is used as output, and a prediction model for the impact of the wind farm on the surface temperature is constructed based on a machine learning algorithm, which specifically includes the following technical steps: using a machine learning algorithm to construct multiple prediction models, using the meteorological variable data corresponding to the operating period of the wind farm as input, and the impact data as output to train multiple prediction models separately; using the validation set data to evaluate the prediction accuracy of multiple prediction models, and selecting the machine learning model with the highest prediction accuracy as the prediction model for the impact of the wind farm on the surface temperature.

[0068] Specifically, we first use machine learning algorithms to build multiple prediction models, take the meteorological variable data corresponding to the wind farm operation period as input, and the data on the impact of the wind farm on the surface temperature as output, and train multiple prediction models separately. In the data input stage, we screen wind speed, temperature, air pressure, humidity and their derivative variables from the meteorological variable data output by the WRF model to ensure that the model input characteristics are closely related to the meteorological characteristics of the wind farm area. The time series data is normalized to eliminate the scale differences between different variables and improve the stability of the training process. Subsequently, prediction models are constructed based on machine learning algorithms based on different principles, including vector machine models, K nearest neighbor models, random forest models, and gradient boosting models, and the training data sets are used to optimize and fit the parameters of each model to obtain preliminary prediction results.

[0069] Next, the prediction accuracy of multiple prediction models was evaluated using the validation set data, and the machine learning model with the highest prediction accuracy was selected as the final prediction model for the impact of wind farms on surface temperature. To quantify the prediction accuracy of the model, the data on the impact of wind farms on surface temperature observed by the Fengyun-4 satellite were compared with the prediction results of each model, and the coefficient of determination (R 2 ), root mean square error (RMSE) and mean square error (MSE) for performance evaluation. Among them, the coefficient of determination can measure the degree of fit between the predicted data and the observed data, indicating the model's ability to explain the impact of wind farms on surface temperature. The value range is 0-1. The closer the value is to 1, the stronger the explanatory ability of the model. The mean square error can measure the error between the predicted data and the observed data, indicating the accuracy of the model. The lower the value, the smaller the prediction error of the model. The calculation of these evaluation indicators is realized by calling the statsmodels function library through Python programming, and comparisons are made between multiple models. After the model evaluation is completed, the model with the highest prediction accuracy is selected as the prediction model for the impact of wind farms on surface temperature based on the evaluation results.

[0070] In some embodiments, a random forest algorithm may also be used to construct a prediction model of the impact of wind farms on surface temperature. The specific construction process may include the following technical steps: The first step is to construct an input matrix based on the meteorological variable data corresponding to the wind farm operation period, and construct a target vector based on the data of the wind farm's impact on the surface temperature. The input matrix can be expressed as: The meteorological variable data matrix representing the wind farm operation period, represents the total number of time steps, represents the number of meteorological variables, Represents the time step The next The target vector can be expressed as: represents the impact vector of wind farm on surface temperature, Represents the time step Data on the impact of wind farms on ground surface temperature.

[0071] In the second step, the training sample set is extracted from the input matrix and the target vector using the bootstrap sampling method, and a random forest model is constructed based on the training sample set. The decision tree ensemble is composed of independently trained decision trees: in, represents the ensemble of decision trees for the random forest model, Indicates A decision tree.

[0072] The third step is to determine the optimal feature partitioning node based on information gain and recursively construct a binary decision tree: in, Indicates A decision tree on the feature The optimal partitioning of As the classification criteria, Indicates the selection The index of the feature that reaches the maximum value, Represents feature index The value range is 1 to n , n Represents the total number of features, and the information gain calculation formula is: ,in, represents data entropy, By feature The conditional entropy after partitioning is performed, and a decision tree structure is constructed based on the optimal partitioning.

[0073] The fourth step is to calculate the predicted value of the wind farm for the surface temperature based on the trained random forest model, and use the prediction results of all decision trees for weighted calculation: in, Represents the time step The final predicted value of Indicates A decision tree for input samples The prediction output of wind farms is used to obtain a prediction model for the impact of wind farms on surface temperature.

[0074] In some embodiments, the method for constructing a prediction model for the impact of wind farms on surface temperature includes the following steps: calculating prediction residuals based on the prediction results of the prediction model and the impact data; constructing a residual prediction model based on the prediction residuals and meteorological variable data; and post-processing the prediction results of the prediction model for the impact of wind farms on surface temperature using the residual prediction model to obtain the final prediction results of the impact of wind farms on surface temperature.

[0075] Specifically, in the process of constructing the prediction model of the impact of wind farms on the ground surface temperature, if the accuracy of the initial prediction results is not ideal, the prediction accuracy can be improved by post-processing methods. This embodiment adopts residual modeling for post-processing to correct the system error of the original prediction results, so as to obtain more accurate prediction results of the impact of wind farms on the ground surface temperature. The residual modeling process includes calculating the prediction residual, constructing the residual prediction model, and post-processing the original prediction results using the residual prediction model to optimize the final prediction results.

[0076] First, the prediction residual is calculated based on the prediction results of the prediction model and the impact data to quantify the prediction error. For each wind farm operation period, the difference between the predicted value and the wind farm's impact on the surface temperature observed by the Fengyun-4 satellite is calculated, that is: in, represents the prediction residual, represents the predicted value of the wind farm’s impact on the surface temperature prediction model, Represents the observed wind farm impact data on the surface temperature. Next, a residual prediction model is constructed based on the prediction residuals and meteorological variable data to identify the relationship between the error and the input features. The same data processing method as the initial modeling is used to train the residual prediction model with meteorological variable data as input and prediction residuals as output. This process is consistent with the original machine learning modeling steps, except that the target variable of the model is replaced by the prediction residual value instead of the surface temperature impact value. A variety of machine learning methods, including random forests, support vector machines, and neural networks, are used to train the model, and the fitting ability of different models is evaluated by cross-validation method to select the optimal residual prediction model.

[0077] Finally, the residual prediction model is used to post-process the prediction results of the prediction model of the wind farm's impact on the surface temperature to obtain the final prediction results. The residual prediction model is used to obtain the prediction residual value at each moment, and the value is used to correct the initial prediction result, and the post-processed wind farm's impact on the surface temperature prediction value is calculated. The specific calculation formula is as follows: in, represents the final prediction result after post-processing, It represents the correction value of the residual prediction model to the prediction residual. This correction process effectively reduces the system error, improves the prediction accuracy of the model, and enhances its adaptability to the impact of wind farms under different environmental conditions.

[0078] In some embodiments, a residual prediction model is constructed based on prediction residuals and meteorological variable data, specifically comprising the following steps: using meteorological variable data corresponding to the wind farm operation period as input, using prediction residuals as output, and using a linear regression calibration algorithm to construct a residual prediction model.

[0079] Specifically, first obtain the input data and output data for residual modeling to ensure that the data format is consistent with the model training requirements. Suppose the meteorological variable data corresponding to the wind farm operation period is the input matrix: in, Represents the meteorological variable data matrix corresponding to the wind farm operation period, represents the total number of wind farm operation periods, represents the number of meteorological variables, Represents the time step The next The value of a meteorological variable.

[0080] Correspondingly, the prediction residual is used as the output data to construct the target vector: in, represents the predicted residual vector of the impact of wind farms on surface temperature, Represents the time step Prediction residuals of the impact of wind farms on land surface temperature.

[0081] In the model construction stage, a linear regression calibration algorithm is used to establish a residual prediction model to optimally fit the relationship between meteorological variable data and prediction residuals. The expression of the linear regression model is: in, represents the prediction output of the residual prediction model, represents the regression coefficient vector to be optimized, Represents the intercept term. Regression coefficient and the intercept It can be obtained by minimizing the mean square error, so that the square error of the prediction residual is minimized: in, Represents the residual prediction model at time step The predicted value of Represents the time step The prediction residual is actually calculated under the condition of gradient descent optimization algorithm or analytical solution. and , and finally the residual prediction model is obtained to correct the initial prediction results.

[0082] In some embodiments, the wind farm in the above embodiment is used to construct the model for predicting the impact of the surface temperature on the ground. First, the .shp file of a certain plateau wind farm area and a control area is used to calculate the average value of the Fengyun-4 surface temperature product and the meteorological elements that will be measured in engineering practice, such as wind speed, temperature, humidity, and air pressure, output by WRF. The calculation results of the two are aligned in time and uniformly converted to Beijing time. The Fengyun-4 surface temperature product is quality controlled. After removing the time data of poor quality, 5076 hours of data remain in the 8760 hours of data throughout the year. Then, the WRF wind speed data is used to screen the operation time of the wind farm, and the screening range is 3-20 m / s. The screened data has 3462 hours left. These 3462 groups of data are used for modeling, and these data are divided into training set and verification set according to the ratio of 80% and 20% using Python's train_test_split function library.

[0083] In the training set, a variety of machine learning models and parameter combinations are used to flexibly select and combine meteorological elements output by the WRF model as model input data, and the impact of wind farms on surface temperature observed by the Fengyun-4 satellite is used as model output data. The optimal settings are selected based on the prediction accuracy of the validation set. The optimal model is the random forest model, and its parameter settings are the number of decision trees n_estimators=50, the maximum depth of the decision tree max_depth=10, the minimum number of samples required for node splitting min_samples_split=10, and the minimum number of samples required for leaf nodes min_samples_leaf=15. The selected WRF meteorological elements include vertical temperature lapse rate, wind speed, air pressure, etc. The validation set prediction R based on this model 2 is 0.49, MSE is 0.12°C, Figure 2 The impact of wind farms on surface temperature predicted by the random forest model ( ) and the observed value ( ), each black dot represents a set of observed values ​​and their corresponding predicted values, and the diagonal dotted line represents the ideal prediction result, that is, the model predicted value is completely consistent with the observed value. The black solid line represents the best linear fit relationship between the model predicted value and the observed value, which is used to evaluate the trend error of the model.

[0084] Figure 3 This is a schematic diagram comparing the impact of post-processed wind farms on surface temperature with the observed values. By comparing the adjusted predicted values ​​( ) and the observed value ( ), to evaluate the effect of post-processing. Compared with the previous prediction model, this method uses the gradient boosting model for residual modeling and uses the prediction error to correct the initial prediction results to improve the overall prediction accuracy. The MSE is reduced to 0.08°C, compared with 0.12°C without residual modeling, the error is reduced, indicating that post-processing effectively improves the prediction accuracy. It increased to 0.67, compared with 0.49 before residual modeling, indicating that the explanatory ability of the model has been enhanced and can more accurately describe the impact of wind farms on surface temperature.

[0085] Figure 4 This is a schematic diagram of the effect of wind farms on the surface temperature and the change of observed values ​​over hours. This figure shows the effect of wind farms on the surface temperature observed by the Fengyun-4 satellite ( ) and the adjusted predicted value after residual modeling ( ) within 24 hours of a day. The impact of wind farms has obvious daily variation characteristics, that is, cooling during the day and heating at night. The two curves in the figure represent the observed value and the predicted value respectively. The overall change trends of the two curves are relatively consistent, indicating that the model can effectively capture the daily variation pattern of the impact of wind farms on surface temperature.

[0086] Figure 5 The following is a comparison diagram of the hourly change of the wind farm’s impact on the surface temperature after post-processing and the observed value. Each black dot represents the predicted value of the wind farm’s impact on the surface temperature within one hour ( ) and the corresponding observed value ( ), in this figure, MSE=0.01°C, , indicating that the prediction accuracy of the model is greatly improved after post-processing optimization.

[0087] Furthermore, in the embodiment of the present disclosure, a method for predicting the impact of a wind farm on the ground surface temperature is provided. Figure 6 As shown, the method comprises the following steps: Step S610, obtaining meteorological variable data corresponding to the wind farm operation period in the target wind farm area.

[0088] Step S620, inputting meteorological variable data into a prediction model of the impact of wind farms on the surface temperature, and obtaining data on the impact of wind farms on the surface temperature in the target wind farm area; wherein the prediction model of the impact of wind farms on the surface temperature is trained according to the method for constructing a prediction model of the impact of wind farms on the surface temperature as in the above-mentioned embodiment.

[0089] It should be noted that, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0090] Next, in the embodiment of the present disclosure, a device for constructing a prediction model of the impact of a wind farm on the ground surface temperature is also provided. Figure 7 As shown in , the wind farm impact prediction model 700 can be composed of a temperature data acquisition module 701, a meteorological data acquisition module 702, an impact data acquisition module 703 and a prediction model construction module 704. Among them: the temperature data acquisition module can be used to determine the spatial range of the wind farm area and the control area based on satellite remote sensing data, and use the spatial range to obtain the wind farm surface temperature data and the control surface temperature data; the meteorological data acquisition module can be used to simulate the meteorological variable data of the wind farm area using a meteorological numerical model, and use the wind speed variable in the meteorological variable to screen the wind farm operation period; the impact data acquisition module can be used to determine the difference between the wind farm surface temperature data and the control surface temperature data within the wind farm operation period, so as to obtain the impact data of the wind farm on the surface temperature; the prediction model construction module can be used to take the meteorological variable data corresponding to the wind farm operation period as input and the impact data as output, and construct a prediction model of the wind farm impact on the surface temperature based on a machine learning algorithm.

[0091] In the embodiment of the present disclosure, a device for predicting the impact of a wind farm on the ground surface temperature is also provided. Figure 8As shown in , the prediction device 800 for the impact of a wind farm on the ground surface temperature may be composed of a target data acquisition module 801 and an impact prediction module 802. The data acquisition module 801 may be used to acquire meteorological variable data corresponding to the wind farm operation period in the target wind farm area; the impact prediction module 802 may be used to input the meteorological variable data into the prediction model for the impact of the wind farm on the ground surface temperature, and obtain the impact data of the wind farm on the ground surface temperature in the target wind farm area; the prediction model for the impact of the wind farm on the ground surface temperature is trained according to the construction method of the prediction model for the impact of the wind farm on the ground surface temperature in the above-mentioned embodiment.

[0092] It should be noted that the specific details of each part of the above-mentioned wind farm impact on surface temperature prediction model construction device have been described in detail in the implementation method of the wind farm impact on surface temperature construction model construction method part, the undisclosed details can be found in the implementation method content of the method part, and thus will not be repeated here.

[0093] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the method for constructing the above-mentioned wind farm impact prediction model on the ground surface temperature is also provided.

[0094] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware embodiments, complete software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0095] Refer to the following Figure 7 hereinafter describes an electronic device 900 according to such an embodiment of the present disclosure. Fig. 9 The electronic device 900 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0096] like Fig. 9 As shown, the electronic device 900 is in the form of a general computing device. The components of the electronic device 900 may include but are not limited to: at least one processing unit 910, at least one storage unit 920, a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910), and a display unit 940.

[0097] The storage unit stores program codes, which can be executed by the processing unit 910, so that the processing unit 910 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0098] The storage unit 920 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 921 and / or a cache memory unit 922 , and may further include a read-only memory unit (ROM) 923 .

[0099] The storage unit 920 may also include a program / utility 924 having a set (at least one) of program modules 925, such program modules 925 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0100] The bus 930 may be a memory unit bus, a peripheral bus, or a local bus of any bus structure.

[0101] The electronic device 900 may also communicate with one or more external devices 970 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 900, and / or communicate with any device that enables the electronic device 900 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 950. In addition, the electronic device 900 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 960. As shown, the network adapter 960 communicates with other modules of the electronic device 900 through a bus 930. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0102] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0103] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of the present specification.

[0104] refer to Fig.10 As shown, a program product 1000 for implementing the method for constructing the above-mentioned wind farm impact prediction model on the surface temperature according to an embodiment of the present disclosure is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0105] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0106] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0107] The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, electromagnetic waves, etc., or any suitable combination of the foregoing.

[0108] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0109] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for constructing a prediction model for the impact of a wind farm on ground surface temperature, characterized in that: include: Determine the spatial range of the wind farm area and the reference area based on satellite remote sensing data, and obtain the wind farm surface temperature data and the reference surface temperature data using the spatial range; Using a meteorological numerical model to simulate meteorological variable data in the wind farm area, and using wind speed variables in the meteorological variables to select the wind farm operation period; During the operation period of the wind farm, determining the difference between the surface temperature data of the wind farm and the reference surface temperature data to obtain the impact data of the wind farm on the surface temperature; With the meteorological variable data corresponding to the operating period of the wind farm as input and the impact data as output, a prediction model for the impact of the wind farm on the surface temperature is constructed based on a machine learning algorithm.

2. The method for constructing a prediction model of the impact of a wind farm on ground surface temperature according to claim 1, characterized in that: Also includes: Calculating a prediction residual based on a prediction result of the prediction model and the influencing data; Constructing a residual prediction model based on the prediction residual and the meteorological variable data; The residual prediction model is used to post-process the prediction results of the prediction model of the wind farm's impact on the ground surface temperature, so as to obtain a final prediction result of the wind farm's impact on the ground surface temperature.

3. The method for constructing a prediction model of the impact of a wind farm on ground surface temperature according to claim 1, characterized in that: The determining of the spatial range of the wind farm area and the reference area based on satellite remote sensing data, and obtaining the wind farm surface temperature data and the reference surface temperature data using the spatial range, includes: Determine the spatial distribution position of wind turbines in the wind farm area by using satellite remote sensing data, and generate the spatial range of the wind farm area based on the spatial distribution of the wind turbines; Generating an initial spatial range of a control area in the outer space of the wind farm area, and obtaining geographic feature data of the control area using satellite remote sensing data; Based on the geographic feature data, the spatial range of the control area is screened to determine the spatial range of the control area that is consistent with the geographic background of the wind farm area; Based on the spatial ranges of the wind farm area and the reference area, the surface temperature data of the wind farm and the reference surface temperature data are respectively acquired from satellite remote sensing data.

4. The method for constructing a prediction model of the impact of a wind farm on ground surface temperature according to claim 1, characterized in that: The method of simulating meteorological variable data of the wind farm area by using a meteorological numerical model and selecting the wind farm operation period by using wind speed variables in the meteorological variables includes: Based on meteorological reanalysis data, meteorological numerical model simulation is used to obtain hourly meteorological variable data in the wind farm area; According to the wind speed variable in the meteorological variable data, a time period in which the wind speed meets the preset wind turbine operating conditions is determined to screen out the wind farm operating time period.

5. The method for constructing a prediction model of the impact of a wind farm on ground surface temperature according to claim 1, characterized in that: Determining the difference between the wind farm surface temperature data and the reference surface temperature data during the operation period of the wind farm to obtain the impact data of the wind farm on the surface temperature includes: Determining the average surface temperature of the wind farm area and the control area at the same time; The difference between the average ground temperature of the wind farm area and the average ground temperature of the control area is calculated moment by moment to obtain the impact data of the wind farm on the ground temperature.

6. The method for constructing a prediction model of the impact of a wind farm on ground surface temperature according to claim 1, characterized in that: The method uses the meteorological variable data corresponding to the wind farm operation period as input and the impact data as output, and constructs a prediction model of the impact of the wind farm on the surface temperature based on a machine learning algorithm, including: A plurality of prediction models are constructed by using a machine learning algorithm, and the meteorological variable data corresponding to the operation period of the wind farm is used as input, and the impact data is used as output to train the plurality of prediction models respectively; The prediction accuracy of the multiple prediction models is evaluated using the validation set data, and the machine learning model with the highest prediction accuracy is selected as the prediction model for the impact of the wind farm on the surface temperature.

7. The method for constructing a prediction model of the impact of a wind farm on ground surface temperature according to claim 2, characterized in that: The constructing of a residual prediction model based on the prediction residual and the meteorological variable data comprises: The meteorological variable data corresponding to the wind farm operation period is used as input, the prediction residual is used as output, and a residual prediction model is constructed using a linear regression calibration algorithm.

8. The method for constructing a prediction model of the impact of a wind farm on ground surface temperature according to claim 1, characterized in that: The method uses the meteorological variable data corresponding to the wind farm operation period as input and the impact data as output, and constructs a prediction model of the impact of the wind farm on the surface temperature based on a machine learning algorithm, including: An input matrix is ​​constructed based on meteorological variable data corresponding to the operation period of the wind farm, and a target vector is constructed based on the data of the impact of the wind farm on the surface temperature; A training sample set is extracted from the input matrix and the target vector using a bootstrap sampling method, and a random forest model is constructed based on the training sample set. The decision tree ensemble is composed of independently trained decision trees: in, represents the ensemble of decision trees for the random forest model, Indicates A decision tree; Determine the optimal feature partitioning node based on information gain and recursively construct a binary decision tree: in, Indicates A decision tree on the feature The optimal partitioning of As the classification criteria, Indicates the selection The index of the feature that reaches the maximum value, Represents feature index The value range is 1 to n , n Represents the total number of features, and the information gain calculation formula is: ,in, represents data entropy, By feature Performing conditional entropy after partitioning, and constructing a decision tree structure based on the optimal partitioning; The predicted value of the wind farm for the surface temperature is calculated based on the trained random forest model, and the prediction results of all decision trees are used for weighted calculation: in, Represents the time step The final predicted value of Indicates A decision tree for input samples The prediction output is used to obtain a prediction model of the impact of the wind farm on the surface temperature.

9. A method for predicting the impact of a wind farm on ground surface temperature, characterized in that: include: Obtain meteorological variable data corresponding to the wind farm operation period in the target wind farm area; Inputting the meteorological variable data into a prediction model of the impact of wind farms on ground surface temperature to obtain data on the impact of wind farms on ground surface temperature in a target wind farm area; The prediction model of the impact of a wind farm on the ground surface temperature is obtained by training according to the method for constructing a prediction model of the impact of a wind farm on the ground surface temperature as claimed in any one of claims 1 to 8.

10. A device for constructing a prediction model of the impact of a wind farm on ground surface temperature, characterized in that: include: A temperature data acquisition module, used to determine the spatial range of the wind farm area and the reference area based on satellite remote sensing data, and to acquire the wind farm surface temperature data and the reference surface temperature data using the spatial range; A meteorological data acquisition module, used to simulate meteorological variable data of the wind farm area by using a meteorological numerical model, and to select the operation period of the wind farm by using the wind speed variable in the meteorological variable; An impact data acquisition module, used to determine the difference between the surface temperature data of the wind farm and the reference surface temperature data during the operation period of the wind farm, so as to obtain the impact data of the wind farm on the surface temperature; The prediction model building module is used to take the meteorological variable data corresponding to the operating period of the wind farm as input and the impact data as output, and to build a prediction model of the impact of the wind farm on the surface temperature based on a machine learning algorithm.

Images