Wind power prediction method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of clean energy, and discloses a wind power prediction method and device, computer equipment and a storage medium. The wind power prediction method comprises the following steps: acquiring geographic features of a target wind power station; constructing a bidirectional coupling weather forecast model based on the geographic features; performing bidirectional coupling on the WRF model and the CFD model based on a bidirectional coupling weather forecast model by taking a first preset duration as a period to obtain first weather forecast data; performing downscaling processing on the first weather forecast data to obtain wind speed characteristics of the target wind power plant station; inputting the wind speed characteristics into a pre-constructed wind power prediction model to obtain a wind power prediction result; according to the method, the geographic features of the target wind power plant can be taken as the reference, the bidirectional coupling correction is carried out based on the weather forecast data of different spatial scales, the more accurate wind speed features are obtained, finally, the wind power prediction is carried out by adopting the wind speed features, and the method has the advantage of more accurate wind power prediction.

Description

Technical Field

[0001] The present invention relates to the field of clean energy technology, and in particular to a wind power prediction method, device, computer equipment and storage medium. Background Art

[0002] As the proportion of renewable energy in the power system continues to increase, accurate prediction of wind power generation is of great significance for grid dispatching, power trading and ensuring power supply stability.

[0003] Traditional wind power prediction methods use independent atmospheric models such as the Weather Research and Forecasting Model (WRF) model and wake models such as the Jensen model to simulate meteorological conditions to obtain predicted meteorological data, and further input the predicted meteorological data into a power prediction model to perform power prediction to obtain wind power prediction results; among the above wind power prediction methods, the WRF model performs well in wind speed forecasting on ultra-short-term and short-term time scales, but has problems such as poor grid resolution and difficulty in capturing local terrain features, resulting in inaccurate wind power prediction; for wind power prediction with higher grid resolution, computational fluid dynamics (CFD) models are usually used for microscopic simulation to achieve it; however, CFD models have difficulty responding to large-scale meteorological condition changes in real time. When there is a sudden change in the boundary layer due to meteorological changes such as the passage of a front, the wind speed forecast is inaccurate, resulting in inaccurate wind power prediction.

[0004] Therefore, there is an urgent need to propose a wind power prediction method to solve the problem of inaccurate wind power prediction in related technologies. Summary of the Invention

[0005] The present invention provides a wind power prediction method, device, computer equipment and storage medium to solve the problem of inaccurate wind power prediction in related technologies.

[0006] In a first aspect, the present invention provides a wind power prediction method, which includes: obtaining the geographical features of a target wind farm; constructing a bidirectionally coupled meteorological forecast model based on the geographical features; wherein the bidirectionally coupled meteorological forecast model includes a WRF model and a CFD model; with a first preset time length as a period, bidirectionally coupling the WRF model and the CFD model based on the bidirectionally coupled meteorological forecast model to obtain first meteorological forecast data; during the bidirectional coupling process, driving the WRF model to perform meteorological forecast based on a first constraint condition to obtain second meteorological forecast data; driving the CFD model to perform meteorological forecast based on the second meteorological forecast data and the geographical features to obtain the first meteorological forecast data; wherein the first constraint condition is determined by the geographical features or the geographical features and the first meteorological forecast data; downscaling the first meteorological forecast data to obtain the wind speed characteristics of the target wind farm; inputting the wind speed characteristics into a pre-constructed wind power prediction model to obtain a wind power prediction result.

[0007] As an exemplary embodiment, the bidirectional coupling of the WRF model and the CFD model based on the bidirectional coupling meteorological forecast model includes: extracting the boundary layer height and the vertical wind shear profile in the second meteorological forecast data; inputting the boundary layer height and the vertical wind shear profile as the second constraint conditions into the CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data; extracting the equivalent roughness field in the first meteorological forecast data; wherein the equivalent roughness field is obtained by wake induction by the CFD model; and inputting the equivalent roughness field as the first constraint condition into the WRF model for coupling.

[0008] As an exemplary embodiment, the boundary layer height and the vertical wind shear profile are input as the second constraint conditions into the CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data, including: calculating the domain height of the CFD model based on the boundary layer height and the geographical features; extracting the Richardson number as boundary layer state information in the second meteorological forecast data; determining the number of vertical stratified grid layers based on the boundary layer state information; and inputting the domain height, the number of vertical stratified grid layers, the boundary layer height and the vertical wind shear profile as the second constraint conditions into the CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data.

[0009] As an exemplary embodiment, the wind power prediction method also includes: obtaining a preset Richardson number threshold; determining atmospheric stratification stability information based on the Richardson number and the preset Richardson number threshold; updating the turbulence model parameters of the CFD model based on the atmospheric stratification stability information to obtain a first corrected CFD model; inputting the domain height, the number of vertical stratified grid layers, the boundary layer height and the vertical wind shear profile as the second constraint conditions into the first corrected CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data.

[0010] As an exemplary embodiment, the wind power prediction method also includes: if the geographical features meet the preset ocean geographical features, obtaining the ocean meteorological data of the target wind farm station in the hybrid coordinate ocean model data based on the geographical features; wherein the ocean meteorological data includes sea surface temperature and ocean mixed layer depth; determining the sea-air flux parameters of the WRF model based on the ocean mixed layer depth; with a second preset time length as the update period, interpolating the sea surface temperature into the outer grid of the WRF model based on the spatiotemporal characteristics of the sea surface temperature, and adding the sea-air flux parameters to the first constraint condition to obtain a third constraint condition; driving the WRF model based on the third constraint condition to obtain third meteorological forecast data.

[0011] As an exemplary embodiment, after interpolating the sea surface temperature into the outer grid of the WRF model based on the spatial characteristics of the sea surface temperature and adding the sea-air flux parameter to the first constraint condition, the wind power prediction method also includes: extracting ocean temperature data, air temperature data and ocean mixed layer heat flux data in the third meteorological forecast data; calculating the temperature difference based on the ocean temperature data and the air temperature data; updating the turbulence model parameters of the CFD model based on the temperature difference to obtain a second corrected CFD model; and driving the second corrected CFD model based on the third meteorological forecast data to obtain the first meteorological forecast data.

[0012] As an exemplary embodiment, the wind power prediction method also includes: extracting local wind speed change data from the first meteorological forecast data; updating the mixed coordinate ocean model data based on the local wind speed change data to obtain updated ocean mixed layer heat flux data; and adding the updated ocean mixed layer heat flux data to the first constraint condition.

[0013] In a second aspect, the present invention provides a wind power prediction device, which includes: an acquisition module for acquiring the geographical features of a target wind farm; a model construction module for constructing a bidirectionally coupled meteorological forecast model based on the geographical features; wherein the bidirectionally coupled meteorological forecast model includes a WRF model and a CFD model; a bidirectional coupling module for bidirectionally coupling the WRF model and the CFD model based on the bidirectionally coupled meteorological forecast model with a first preset time period as a period to obtain first meteorological forecast data; during the bidirectional coupling process, the WRF model is driven to perform meteorological forecast based on a first constraint condition to obtain second meteorological forecast data; based on the second meteorological forecast data and the geographical features, the CFD model is driven to perform meteorological forecast to obtain the first meteorological forecast data; wherein the first constraint condition is determined by the geographical features or the geographical features and the first meteorological forecast data; a downscaling module for downscaling the first meteorological forecast data to obtain the wind speed characteristics of the target wind farm; and a wind power prediction module for inputting the wind speed characteristics into a pre-constructed wind power prediction model to obtain a wind power prediction result.

[0014] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the wind power prediction method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the wind power prediction method of the first aspect or any corresponding embodiment thereof.

[0016] The present invention provides a wind power prediction method, device, computer equipment and storage medium. The wind power prediction method includes: obtaining the geographical features of the target wind farm station; constructing a bidirectional coupling meteorological forecast model based on the geographical features; wherein the bidirectional coupling meteorological forecast model includes a WRF model and a CFD model; with a first preset time length as a period, bidirectionally coupling the WRF model and the CFD model based on the bidirectional coupling meteorological forecast model to obtain first meteorological forecast data; in the process of the bidirectional coupling, driving the WRF model to perform meteorological forecast based on a first constraint condition to obtain second meteorological forecast data; driving the CFD model to perform meteorological forecast based on the second meteorological forecast data and the geographical features to obtain the first meteorological forecast data; wherein the first constraint condition is determined by the geographical features or the geographical features and the first meteorological forecast data; downscaling the first meteorological forecast data to obtain the wind speed characteristics of the target wind farm station; inputting the wind speed characteristics into the pre-constructed wind power prediction model to obtain wind power rate prediction results; in the above-mentioned wind power prediction method, the WRF model can provide accurate second meteorological forecast data to the CFD model based on geographical features, and the CFD model can determine the first meteorological forecast data in response to the large-scale meteorological condition changes of the second meteorological forecast data of a larger spatial scale provided by the WRF model, such as the sudden change of the boundary layer caused by the passage of the front, and further use the first meteorological forecast data as a new first constraint to re-drive the WRF model. The WRF model can respond to the first meteorological forecast data of a smaller spatial scale provided by the CFD model to input a more accurate first constraint, thereby obtaining an updated second meteorological forecast data based on the more accurate first constraint; in the above-mentioned bidirectional coupling process, the first meteorological forecast data finally obtained can be based on the geographical features of the target wind farm station, and bidirectional coupling correction is performed based on the meteorological forecast data of large spatial scale and small spatial scale, finally obtaining more accurate first meteorological forecast data, further obtaining more accurate wind speed characteristics, and finally using the wind speed characteristics to predict wind power, which has the advantage of more accurate wind power prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 is a schematic flow chart of a wind power prediction method according to an embodiment of the present invention; Figure 2is a structural block diagram of a wind power prediction device according to an embodiment of the present invention; Figure 3 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0020] According to an embodiment of the present invention, an embodiment of a wind power prediction method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0021] In this embodiment, a wind power prediction method is provided. Figure 1 FIG. 1 is a flow chart of a method for predicting wind power according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps: Step S101: Acquire the geographical features of the target wind farm.

[0022] For example, the geographical feature may include geographical data information, wherein the geographical data information may include latitude and longitude coordinates, altitude, wind turbine hub height, etc.

[0023] Exemplarily, the target wind farm station may be a wind farm station cluster.

[0024] For example, the target wind farm station may be an offshore wind farm station cluster near the ocean.

[0025] Step S102: constructing a bidirectional coupled weather forecast model based on the geographical features; wherein the bidirectional coupled weather forecast model includes a WRF model and a CFD model.

[0026] In this embodiment, the bidirectionally coupled meteorological forecast model includes a WRF model and a CFD model; wherein the WRF model can focus on simulating large-scale, mesoscale and microscale atmospheric conditions (wind, temperature, air pressure, humidity, turbulence, etc.), and does not consider the impact of the wind turbine itself on the airflow; the CFD model forecast model can simulate actual fluid flow conditions, and its basic principle is to numerically solve the differential equations that control fluid flow to obtain the discrete distribution of the flow field of the fluid flow in a continuous area, thereby approximately simulating the fluid flow conditions; in order to enable both the WRF model and the CFD model to adaptively perform meteorological forecasts considering the geographical characteristics of the target wind farm station, in this embodiment, a bidirectionally coupled meteorological forecast model is constructed based on the geographical characteristics; specifically, when constructing the bidirectionally coupled meteorological forecast model, the WRF model and the CFD model are separately constructed based on the geographical characteristics, and a data interface is configured for the WRF model when the input data from the CFD model is a constraint condition, and a data interface is configured for the CFD model when the input data from the WRF model is a constraint condition.

[0027] Step S103, with a first preset time length as a period, bidirectionally couple the WRF model and the CFD model based on the bidirectional coupling meteorological forecast model to obtain first meteorological forecast data; during the bidirectional coupling process, drive the WRF model to perform meteorological forecast based on the first constraint condition to obtain second meteorological forecast data; drive the CFD model to perform meteorological forecast based on the second meteorological forecast data and the geographical features to obtain first meteorological forecast data; wherein, the first constraint condition is determined by the geographical features or the geographical features and the first meteorological forecast data.

[0028] Traditional wind power prediction methods use independent atmospheric models such as the Weather Research and Forecasting Model (WRF model) and wake models such as the Jensen model to simulate meteorological conditions to obtain predicted meteorological data, and further input the predicted meteorological data into a power prediction model to perform power prediction to obtain wind power prediction results; among the above wind power prediction methods, the WRF model performs well in wind speed forecasting on ultra-short-term and short-term time scales, but has problems such as poor grid resolution and difficulty in capturing local terrain features, resulting in inaccurate wind power prediction; for wind power prediction with finer grid resolution, computational fluid dynamics (CFD model) is usually used for microscopic simulation to achieve it; however, CFD models have difficulty responding to large-scale meteorological condition changes in real time. When there is a sudden change in the boundary layer due to meteorological changes such as the passage of a front, the wind speed forecast is inaccurate, resulting in inaccurate wind power prediction.

[0029] To solve the above problem, in this embodiment, the WRF model and the CFD model are bidirectionally coupled to fully consider the advantages of their respective input data to obtain weather forecast data that considers the advantages of both forecast modules.

[0030] Exemplarily, after the bidirectional coupling model is constructed, the WRF model and the CFD model are bidirectionally coupled with a first preset time period.

[0031] For example, the first preset duration may be 30 minutes.

[0032] Specifically, for the first coupling cycle, that is, the initial coupling process of the bidirectional coupling model, the geographical features are used as the first constraint condition to drive the WRF model to obtain the second weather forecast data; based on the second weather forecast data and the geographical features, the CFD model is driven to obtain the first weather forecast data; further, the geographical features and the first weather forecast data are used as the first constraint condition to drive the WRF model to obtain the second weather forecast data, and based on the second weather forecast data and the geographical features, the CFD model is driven to obtain the first weather forecast data, thereby completing the bidirectional coupling of the WRF model and the CFD model.

[0033] For non-first coupling cycles, the geographical features and the first meteorological forecast data are used as the first constraint conditions to drive the WRF model to obtain the second meteorological forecast data. The first meteorological forecast data can be obtained by driving the CFD model based on the second meteorological forecast data and the geographical features, thereby completing the bidirectional coupling of the WRF model and the CFD model.

[0034] Exemplarily, the spatial resolution of the second meteorological forecast data is 3 km, including boundary layer parameter data such as boundary layer height and vertical wind shear profile.

[0035] Illustratively, the spatial resolution of the first meteorological forecast data is 300 m, including wind farm overall resistance coefficient data, wind speed data, wind direction data, and the like.

[0036] In the above coupling mode, the WRF model can provide accurate second meteorological forecast data to the CFD model based on geographical features. The CFD model can determine the first meteorological forecast data in response to the second meteorological forecast data of a larger spatial scale provided by the WRF model, such as the large-scale meteorological condition changes of the boundary layer caused by the passage of the front, and further re-drive the WRF model with the first meteorological forecast data as a new first constraint condition. The WRF model can respond to the first meteorological forecast data of a smaller spatial scale provided by the CFD model and input a more accurate first constraint condition, thereby obtaining updated second meteorological forecast data based on the more accurate first constraint condition. In the above bidirectional coupling process, the first meteorological forecast data finally obtained can be based on the geographical features of the target wind farm station, and can be bidirectionally corrected based on the meteorological forecast data of large spatial scale and small spatial scale, so as to finally obtain more accurate first meteorological forecast data.

[0037] Step S104: downscaling the first meteorological forecast data to obtain wind speed characteristics of the target wind farm.

[0038] After obtaining the first weather forecast data, downscaling is performed on the first weather forecast data to obtain the wind speed characteristics of the target wind farm.

[0039] Exemplarily, after obtaining the first weather forecast data, interpolation is performed based on the first weather forecast data to obtain the third weather forecast data.

[0040] Exemplarily, the resolution of the third weather forecast data is 10m.

[0041] After obtaining the third weather forecast data, the wind speed characteristics of the target wind farm are determined based on the geographical location of the target wind farm and the third weather forecast data.

[0042] Step S105: input the wind speed characteristics into a pre-built wind power prediction model to obtain a wind power prediction result.

[0043] The present invention provides a wind power prediction method, which includes: obtaining the geographical features of a target wind farm; constructing a bidirectionally coupled meteorological forecast model based on the geographical features; wherein the bidirectionally coupled meteorological forecast model includes a WRF model and a CFD model; with a first preset time length as a period, bidirectionally coupling the WRF model and the CFD model based on the bidirectionally coupled meteorological forecast model to obtain first meteorological forecast data; in the process of the bidirectional coupling, driving the WRF model to perform meteorological forecast based on a first constraint condition to obtain second meteorological forecast data; driving the CFD model to perform meteorological forecast based on the second meteorological forecast data and the geographical features to obtain first meteorological forecast data; wherein the first constraint condition is determined by the geographical features or the geographical features and the first meteorological forecast data; downscaling the first meteorological forecast data to obtain wind speed characteristics of the target wind farm; inputting the wind speed characteristics into a pre-constructed wind power prediction model to obtain a wind power prediction result; In the wind power prediction method, the WRF model can provide accurate second meteorological forecast data to the CFD model based on geographical features. The CFD model can determine the first meteorological forecast data in response to the large-scale meteorological condition changes of the second meteorological forecast data of a larger spatial scale provided by the WRF model, such as the sudden change of the boundary layer caused by the passage of the front, and further use the first meteorological forecast data as a new first constraint to re-drive the WRF model. The WRF model can respond to the first meteorological forecast data of a smaller spatial scale provided by the CFD model to input a more accurate first constraint, thereby obtaining updated second meteorological forecast data based on the more accurate first constraint. In the above-mentioned bidirectional coupling process, the first meteorological forecast data finally obtained can be based on the geographical features of the target wind farm station, and bidirectional coupling correction is performed based on the meteorological forecast data of large spatial scale and small spatial scale, finally obtaining more accurate first meteorological forecast data, further obtaining more accurate wind speed characteristics, and finally using the wind speed characteristics to predict wind power, which has the advantage of more accurate wind power prediction.

[0044] As an exemplary embodiment, the multi-round bidirectional coupling based on the WRF model and the CFD model includes: extracting the boundary layer height and the vertical wind shear profile in the second meteorological forecast data; inputting the boundary layer height and the vertical wind shear profile as the second constraint conditions into the CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data; extracting the equivalent roughness field in the first meteorological forecast data; wherein the equivalent roughness field is obtained by wake induction by the CFD model; and inputting the equivalent roughness field as the first constraint condition into the WRF model for coupling.

[0045] As mentioned above, it is difficult for the CFD model to respond to large-scale meteorological condition changes in real time, and the wind speed forecast is inaccurate when there is a sudden change in the boundary layer due to meteorological changes such as the passage of a front. For the second meteorological forecast data with a larger spatial scale, the boundary layer height and the vertical wind shear profile can more accurately reflect the large-scale meteorological condition changes of the target wind farm station. Therefore, in order to solve the problem that the CFD model is difficult to respond to large-scale meteorological condition changes in real time, the boundary layer height and the vertical wind shear profile are extracted from the second meteorological forecast data. The boundary layer height and the vertical wind shear profile are input as the second constraint conditions into the CFD model for transient wake meteorological simulation to obtain the first meteorological forecast data.

[0046] However, the WRF model has problems such as poor grid resolution and difficulty in capturing local terrain features. For the first meteorological forecast data with a smaller spatial scale, the equivalent roughness field can more accurately reflect the local terrain features of the target wind farm. Therefore, in order to solve the problems of poor grid resolution and difficulty in capturing local terrain features in the WRF model, the equivalent roughness field is input as the first constraint condition into the WRF model for coupling, thereby obtaining relatively accurate second meteorological forecast data.

[0047] As an exemplary embodiment, the boundary layer height and the vertical wind shear profile are input into the CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data, including: calculating the domain height of the CFD model based on the boundary layer height and the geographical features; extracting the Richardson number as boundary layer state information in the second meteorological forecast data; determining the number of vertical stratified grid layers based on the boundary layer state information; and inputting the domain height, the number of vertical stratified grid layers, the boundary layer height and the vertical wind shear profile as the second constraint conditions into the CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data.

[0048] In this embodiment, the CFD model is optimized by calculating the domain height of the CFD model according to the boundary layer height; at the same time, the boundary parameters of the CFD model are further optimized by the Richardson number that characterizes the boundary layer state information, so that the CFD model can determine the first meteorological forecast data in response to the second meteorological forecast data of a larger spatial scale provided by the WRF model, such as the large-scale meteorological condition changes of the boundary layer caused by the passage of the front.

[0049] In one embodiment, the WRF model can obtain the boundary layer height by calculating the Bulk Richardson Number (Ri), calculating the vertical distribution of turbulent kinetic energy, calculating the potential temperature gradient threshold and / or calculating the entrainment layer thickness, and transfer the obtained boundary layer height to the CFD model.

[0050] For example, the height at which the turbulent kinetic energy decays to 10% of the ambient value is used as the boundary layer height.

[0051] For example, the height at which the vertical temperature gradient exceeds 0.005 K / m for the first time is taken as the boundary layer height.

[0052] Exemplarily, the height at which the entrainment layer occupies 15%-20% is taken as the boundary layer height.

[0053] As an exemplary embodiment, the domain height of the CFD model is calculated by formula (1): HCFD=α*PBLH+β*Hterrain (1) In formula (1), HCFD represents the calculated domain height of the CFD model, PBLH represents the boundary layer height, and Hterrain represents the terrain height, which is determined by the geographical features. α is set to 1.2, and β is set to 0.3. β is used as the terrain height compensation coefficient and is set to 0.3 to prevent truncation of steep terrain.

[0054] In this embodiment, the vertical layered network in the CFD model is further optimized based on the second meteorological forecast data; illustratively, the Richardson number is extracted from the second meteorological forecast data as boundary layer state information; the number of vertical layered grid layers is determined based on the boundary layer state information; specifically, the number of vertical layered grid layers is inversely correlated with the Richardson number.

[0055] For example, after extracting the Richardson number, when Ri<0, the boundary layer state is confirmed to be unstable stratification; when 0≤Ri<0.25, the boundary layer state is confirmed to be neutral stratification; when Ri>0.25, the boundary layer state is confirmed to be stable stratification; further, for the number of vertical layered network layers in the CFD model, the number of vertical layered grid layers corresponding to the unstable layer is 50; the number of vertical layered grid layers corresponding to the neutral layer is 40, and the number of vertical layered grid layers corresponding to the stable layer is 30.

[0056] For example, for the grid in the CFD model, a spring approximation method is used to smoothly transition the grid to avoid sudden changes.

[0057] As an exemplary embodiment, the wind power prediction method further includes: determining, based on the boundary layer height, an MPI domain decomposition of a CFD model grid corresponding to each boundary layer height.

[0058] In this embodiment, computing resources are allocated to the CFD model based on the boundary layer height. For example, when the MPI domain decomposition of the CFD model grid corresponding to each boundary layer height is determined based on the boundary layer height, more computing nodes are allocated to areas where the boundary layer height is greater than a preset value, and mesh coarsening is enabled for areas where the boundary layer height is less than or equal to the preset value to reduce resource allocation.

[0059] As an exemplary embodiment, after calculating the domain height of the CFD model based on the boundary layer height and the geographical features, the wind power prediction method further includes: obtaining the initial domain height within a previous preset time period; calculating the difference between the domain height and the initial domain height; when the difference is greater than a preset value, adjusting the difference to the preset value to obtain a corrected difference; and correcting the corresponding domain height based on the corrected difference.

[0060] In this embodiment, the preset value may be 0.2 times the initial domain height, so that the adjustment range of the domain height in each round of bidirectional coupling process does not exceed 20% of that in the previous coupling process.

[0061] As an exemplary embodiment, in the second meteorological forecast data, after extracting the boundary layer height, the method further includes: calculating the difference in boundary layer heights between adjacent grid points as a boundary layer height difference; marking a boundary layer height whose boundary layer height difference is greater than the boundary layer height difference as an outlier; performing median filtering on the outlier to obtain a corrected boundary layer height; in this embodiment, an outlier is determined based on the difference in boundary layer heights between two adjacent points, and median filtering is performed on the outlier.

[0062] As an exemplary embodiment, the wind power prediction method also includes: obtaining a preset Richardson number threshold; determining atmospheric stratification stability information based on the Richardson number and the preset Richardson number threshold; updating the turbulence model parameters of the CFD model based on the atmospheric stratification stability information to obtain a first corrected CFD model; inputting the domain height, the number of vertical stratified grid layers, the boundary layer height and the vertical wind shear profile as the second constraint conditions into the first corrected CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data.

[0063] In this embodiment, atmospheric stratification stability information is determined based on the Richardson number and the preset Richardson number threshold, and different turbulence models are further selected for the CFD model according to different atmospheric stratification stability information.

[0064] For example, the preset Richardson number threshold is 0.25; after extracting the Richardson number, when 0≤Ri<0.25, the boundary layer state is confirmed to be neutral stratification; when Ri>0.25, the boundary layer state is confirmed to be stable stratification.

[0065] Here, illustratively, the turbulence model may include a k-ε model and a k-ω SST model.

[0066] Exemplarily, the k-ε model is selected for the neutral junction to obtain the first modified CFD model.

[0067] Exemplarily, the k-ωSST model is selected for the stable layered structure to obtain the first modified CFD model.

[0068] For example, during the bidirectional coupling process, the preset Richardson number threshold may be modified based on the geographical features and the local details output by the CFD model. Specifically, the preset Richardson number threshold is modified using formula (2): Ricadjusted=0.25*(1+0.1*z0 / H) (2) In formula (2), Ricadjusted represents the preset Richardson number threshold after correction, z0 represents the terrain roughness output by the CFD model, and H represents the terrain height, which is determined by the geographical features.

[0069] In one embodiment, for the Richardson number within a preset range, a model weighted fusion method is used for transition; wherein the preset range can be [0.2, 0.3]. Specifically, the turbulence result after fusion can be obtained by formula (3): (3) In formula (3), represents the turbulence result after fusion, represents the turbulence prediction result using the k-ε model, It represents the turbulence prediction result obtained when the k-ωSST model is selected, w is the fusion weight, w=(0.3-Ri) / 0.1.

[0070] Furthermore, a method of training a random forest classifier can be used to update the turbulence model parameters of the CFD model based on the atmospheric stratification stability information; when training the random forest classifier, the Richardson number and the corresponding meteorological data in the first predicted meteorological data are input to learn the correspondence between the Richardson number or the Richardson number and the corresponding meteorological data and the corresponding turbulence model and / or the correspondence between the Richardson number and the corresponding meteorological data and the prediction result.

[0071] The above-mentioned embodiment of the present invention can achieve more accurate wind power prediction by bidirectionally coupling the WRF model with the CFD model, compared with the related art that uses an independent atmospheric model such as the WRF model and a wake model such as the Jensen model to simulate meteorological conditions to obtain predicted meteorological data; however, the inventors have found that for offshore wind farms located at sea, the atmospheric stability output by the CFD model does not take into account the interaction of the ocean boundary layer, resulting in inaccurate wind speed characteristics output by the bidirectional coupling model, and ultimately inaccurate power prediction of the target wind farm; when the relevant parameters of the ocean boundary layer are ignored in the CFD model, the output results of the CFD model are seriously distorted due to multiple influencing factors such as the lack of physical processes, failure of turbulence simulation and imbalance of energy transfer, thereby affecting the output state of meteorological data; specifically, first, the ocean boundary layer (Ocean Boundary Layer) The Ocean Boundary Layer (OBL) is a thin layer approximately 50-200 meters below the ocean surface. Failure to consider the OBL in CFD models results in significant errors in simulated wind speed profiles, with errors exceeding 30% in surface shear stress calculations and 20-50% in predicted ocean current velocities. Furthermore, failure to account for ocean stability parameters (such as the Richardson number) in CFD models leads to miscalculation of the turbulent viscosity coefficient and distortion of eddy diffusion capacity. Furthermore, simulation schemes that lack corrections for sensible and latent heat exchange coefficients due to sea surface roughness can result in predictions of tropical cyclone paths exceeding 100 kilometers and errors in sea surface temperature (SST) simulations reaching 1-3°C. Consequently, ignoring OBL parameters and failing to account for OBL interactions essentially disrupts the energy and material cycles of the coupled air-sea system. These errors are amplified in CFD models through turbulence closure schemes, boundary conditions, and buoyancy effects. Consequently, high-precision ocean CFD must include OBL parameters; otherwise, unacceptable deviations will result.

[0072] To solve the above problem, as an exemplary embodiment, the wind power prediction method also includes: if the geographical features meet the preset ocean geographical features, obtaining the ocean meteorological data of the target wind farm station in the hybrid coordinate ocean model data based on the geographical features; wherein the ocean meteorological data includes sea surface temperature and ocean mixed layer depth; determining the sea-air flux parameters of the WRF model based on the ocean mixed layer depth; with a second preset time length as the update period, interpolating the sea surface temperature into the outer grid of the WRF model based on the spatiotemporal characteristics of the sea surface temperature, and adding the sea-air flux parameters to the first constraint condition to obtain a third constraint condition; driving the WRF model based on the third constraint condition to obtain third meteorological forecast data.

[0073] Exemplarily, the preset ocean geographical feature is a geographical feature corresponding to a target wind farm that is located at sea.

[0074] Exemplarily, after obtaining the geographical features, terrain features and landform features are extracted from the geographical features; when the terrain features and landform features meet the preset ocean terrain features and preset ocean landform features corresponding to the offshore wind farm set at sea, it is confirmed that the geographical features meet the preset ocean geographical features.

[0075] Illustratively, after obtaining the geographical features, the geographical location is extracted from the geographical features; when the geographical location satisfies a preset geographical location corresponding to an offshore wind farm set at sea, it is confirmed that the geographical features meet the preset ocean geographical features.

[0076] In this embodiment, the marine meteorological data is used as a constraint condition of the WRF model to consider the interaction with the ocean boundary layer to achieve wind power prediction considering ocean conditions.

[0077] Specifically, based on the geographic features, marine meteorological data of the target wind farm is obtained from Hybrid Coordinate Ocean Model (HYCOM) data, where the marine meteorological data includes sea surface temperature and ocean mixed layer depth. Furthermore, based on the ocean mixed layer depth, an air-sea flux parameter of the WRF model is determined, and the sea surface temperature is interpolated into the outer grid of the WRF model based on the spatiotemporal characteristics of the sea surface temperature, ultimately driving the WRF model to obtain third meteorological forecast data. Exemplarily, the second preset duration is greater than or equal to 30 minutes.

[0078] Exemplarily, the second preset duration is 30 minutes.

[0079] As an exemplary embodiment, after interpolating the sea surface temperature into the outer grid of the WRF model based on the spatial characteristics of the sea surface temperature and adding the sea-air flux parameter to the first constraint condition, the wind power prediction method also includes: extracting ocean temperature data, air temperature data and ocean mixed layer heat flux data in the third meteorological forecast data; calculating the temperature difference based on the ocean temperature data and the air temperature data; updating the turbulence model parameters of the CFD model based on the temperature difference to obtain a second corrected CFD model; and driving the second corrected CFD model based on the third meteorological forecast data to obtain the first meteorological forecast data.

[0080] In this embodiment, the turbulence model of the CFD model is corrected based on the third weather forecast data output by the WRF model; specifically, in the third weather forecast data, ocean temperature data, air temperature data and ocean mixed layer heat flux data are extracted; the temperature difference is calculated based on the ocean temperature data and the air temperature data; when the temperature difference is greater than 2°C, the boundary layer state is confirmed to be a strongly unstable stratification, and at this time, the LES large eddy simulation is selected as the turbulence model of the CFD model based on the strongly unstable stratification; when the temperature difference is greater than 0.5°C and less than or equal to 2°C, the boundary layer state is confirmed to be a weakly unstable stratification, and at this time, the k-ε model is selected as the turbulence prediction model based on the weakly unstable stratification layer; when the temperature difference is less than -0.5°C, the boundary layer state is confirmed to be a neutral layer, and at this time, the k-ωSST model is selected as the turbulence model of the CFD model based on the neutral layer.

[0081] As an exemplary embodiment, the method further includes: extracting local wind speed change data from the first meteorological forecast data; updating the HYCOM data based on the local wind speed change data to obtain updated ocean mixed layer heat flux data; and adding the updated ocean mixed layer heat flux data to the first constraint condition.

[0082] In this embodiment, the local wind speed changes caused by the wind turbine wake are fed back to the HYCOM data to consider the impact of the wind turbine wake on the ocean mixed layer energy balance and update the ocean mixed layer heat flux data more accurately.

[0083] This embodiment provides a wind power prediction device, such as Figure 2 As shown, including: An acquisition module 501 is used to acquire geographical features of a target wind farm; A model building module 502 is configured to build a bidirectional coupled weather forecast model based on the geographical features; wherein the bidirectional coupled weather forecast model includes a WRF model and a CFD model; A bidirectional coupling module 503 is configured to bidirectionally couple the WRF model and the CFD model based on the bidirectionally coupled weather forecast model with a first preset time period to obtain first weather forecast data; during the bidirectional coupling process, drive the WRF model to perform weather forecast based on a first constraint condition to obtain second weather forecast data; and drive the CFD model to perform weather forecast based on the second weather forecast data and the geographical features to obtain first weather forecast data; wherein the first constraint condition is determined by the geographical features or by the geographical features and the first weather forecast data; A downscaling module 504 is configured to perform downscaling processing on the first meteorological forecast data to obtain wind speed characteristics of the target wind farm; The wind power prediction module 505 is configured to input the wind speed characteristics into a pre-built wind power prediction model to obtain a wind power prediction result.

[0084] It should be noted here that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments.

[0085] It should be noted that the above modules as part of the device can be implemented through software or hardware, wherein the hardware environment includes a grid environment.

[0086] An embodiment of the present invention also provides a computer device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus, the memory is used to store computer programs; the processor is used to execute the method in any of the above embodiments by running the computer program stored in the memory.

[0087] Figure 3 is a structural block diagram of an optional computer device according to an embodiment of the present application, such as Figure 3 As shown, it includes a processor 10, a communication interface 20, a memory 30 and a communication bus 40, wherein the processor 10, the communication interface 20 and the memory 30 communicate with each other through the communication bus 40, wherein, Memory 30, for storing computer programs; The processor 10 is configured to implement the wind power prediction method according to any of the above embodiments when executing the computer program stored in the memory 30 .

[0088] Optionally, in this embodiment, the communication bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0089] The communication interface is used for communication between the above-mentioned computer device and other devices.

[0090] The memory may include RAM, or may include non-volatile memory, such as at least one disk memory. Alternatively, the memory may also be at least one storage device located away from the aforementioned processor.

[0091] The above-mentioned processor can be a general-purpose processor, which can include but is not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0092] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0093] It can be understood by those skilled in the art that Figure 3 The structure shown is for illustration only. The device for implementing any one of the methods in the above embodiments may be a terminal device, which may be a smart phone (such as an Android phone, an IOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, or other terminal devices. Figure 3 It does not limit the structure of the above electronic device. For example, the terminal device may also include Figure 3 More or fewer components (such as grid interfaces, display devices, etc.) as shown in, or with Figure 3 Different configurations shown.

[0094] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which can include: a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0095] As an exemplary embodiment, the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute any one of the method steps of the present embodiment when run.

[0096] Optionally, in this embodiment, the above-mentioned storage medium can be used to execute the program code of the method steps of the embodiment of the present application.

[0097] Optionally, in this embodiment, the storage medium may be located on at least one grid device among the multiple grid devices in the grid shown in the above embodiment.

[0098] Optionally, in this embodiment, the storage medium is configured to store data for executing the method in the above embodiment.

[0099] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0100] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a ROM, a RAM, a mobile hard disk, a magnetic disk, or an optical disk.

[0101] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0102] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above-mentioned computer-readable storage medium. Based on this understanding, the technical solution of this application, or the part that contributes to the existing technology, 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 a number of instructions for causing one or more computer devices (such as personal computers, servers, or grid devices) to execute all or part of the steps of the method in the above embodiments.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is merely a logical functional division. In actual implementation, there may be other division methods, such as combining or integrating multiple units or components into another system, or ignoring or not implementing some features. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interface, indirect coupling or communication connection of units or modules, and may be electrical or other forms.

[0104] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple grid units. Some or all of the units may be selected based on actual needs to achieve the purpose of the solution provided in this embodiment.

[0105] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0106] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0107] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A wind power prediction method, characterized in that: The wind power prediction method comprises: Obtain the geographical characteristics of the target wind farm; Constructing a bidirectional coupled weather forecast model based on the geographical features; wherein the bidirectional coupled weather forecast model includes a WRF model and a CFD model; The WRF model and the CFD model are bidirectionally coupled based on the bidirectionally coupled weather forecast model with a first preset time period to obtain first weather forecast data; during the bidirectional coupling process, the WRF model is driven to perform weather forecast based on a first constraint condition to obtain second weather forecast data; and the CFD model is driven to perform weather forecast based on the second weather forecast data and the geographical feature to obtain the first weather forecast data; wherein the first constraint condition is determined by the geographical feature or by the geographical feature and the first weather forecast data; downscaling the first meteorological forecast data to obtain wind speed characteristics of the target wind farm; The wind speed characteristics are input into a pre-built wind power prediction model to obtain a wind power prediction result.

2. The wind power prediction method according to claim 1, wherein: The bidirectionally coupling the WRF model and the CFD model based on the bidirectionally coupled meteorological forecast model includes: extracting the boundary layer height and vertical wind shear profile from the second meteorological forecast data; Inputting the boundary layer height and the vertical wind shear profile as second constraint conditions into the CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data; Extracting an equivalent roughness field from the first meteorological forecast data; wherein the equivalent roughness field is obtained by performing wake induction on the CFD model; The equivalent roughness field is input as the first constraint condition into the WRF model for coupling.

3. The wind power prediction method according to claim 2, wherein: The step of inputting the boundary layer height and the vertical wind shear profile as second constraints into the CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data includes: Calculating a domain height of a CFD model based on the boundary layer height and the geographic feature; extracting the Richardson number from the second weather forecast data as boundary layer state information; determining the number of vertically layered grid layers based on the boundary layer state information; The domain height, the number of vertical stratified grid layers, the boundary layer height and the vertical wind shear profile are input as the second constraint conditions into the CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data.

4. The wind power prediction method according to claim 3, wherein: The wind power prediction method further includes: Get the preset Richardson number threshold; determining atmospheric stratification stability information based on the Richardson number and the preset Richardson number threshold; updating the turbulence model parameters of the CFD model based on the atmospheric stratification stability information to obtain a first modified CFD model; The domain height, the number of vertical stratified grid layers, the boundary layer height and the vertical wind shear profile are input as the second constraint conditions into the first modified CFD model to perform transient wake meteorological simulation to obtain the first meteorological forecast data.

5. The wind power prediction method according to claim 1, wherein: The wind power prediction method further includes: If the geographical feature satisfies the preset ocean geographical feature, obtaining ocean meteorological data of the target wind farm station in the hybrid coordinate ocean model data based on the geographical feature; wherein the ocean meteorological data includes sea surface temperature and ocean mixed layer depth; Determining an air-sea flux parameter of the WRF model based on the ocean mixed layer depth; interpolating the sea surface temperature into the outer grid of the WRF model based on the spatiotemporal characteristics of the sea surface temperature with a second preset time period as an update period, and adding the air-sea flux parameter to the first constraint condition to obtain a third constraint condition; The WRF model is driven based on the third constraint condition to obtain third weather forecast data.

6. The wind power prediction method according to claim 5, characterized in that: After interpolating the sea surface temperature into the outer grid of the WRF model based on the spatial characteristics of the sea surface temperature and adding the air-sea flux parameter to the first constraint condition, the wind power prediction method further includes: Extracting ocean temperature data, air temperature data, and ocean mixed layer heat flux data from the third weather forecast data; calculating a temperature difference based on the ocean temperature data and the air temperature data; updating the turbulence model parameters of the CFD model based on the temperature difference to obtain a second modified CFD model; The second modified CFD model is driven based on the third weather forecast data to obtain the first weather forecast data.

7. The wind power prediction method according to claim 6, wherein: The wind power prediction method further includes: Extracting local wind speed change data from the first weather forecast data; updating the hybrid coordinate ocean model data based on the local wind speed change data to obtain updated ocean mixed layer heat flux data; The updated ocean mixed layer heat flux data is added to the first constraint.

8. A wind power prediction device, characterized in that: The wind power prediction device comprises: An acquisition module is used to obtain the geographical features of the target wind farm; A model building module, configured to build a bidirectional coupled weather forecast model based on the geographical features; wherein the bidirectional coupled weather forecast model includes a WRF model and a CFD model; a bidirectional coupling module, configured to bidirectionally couple the WRF model and the CFD model based on the bidirectionally coupled weather forecast model with a first preset time period to obtain first weather forecast data; during the bidirectional coupling process, drive the WRF model to perform weather forecast based on a first constraint condition to obtain second weather forecast data; and drive the CFD model to perform weather forecast based on the second weather forecast data and the geographical features to obtain the first weather forecast data; wherein the first constraint condition is determined by the geographical features or by the geographical features and the first weather forecast data; a downscaling module, configured to perform downscaling processing on the first meteorological forecast data to obtain wind speed characteristics of the target wind farm; The wind power prediction module is used to input the wind speed characteristics into a pre-built wind power prediction model to obtain a wind power prediction result.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the wind power prediction method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the wind power prediction method according to any one of claims 1 to 7.

Images