Wind power ultra-short-term prediction error correction method and system based on meteorological data

Abstract

The invention discloses a wind power ultra-short-term prediction error correction method and system based on meteorological data, and relates to the technical field of data processing. The method comprises the following steps: acquiring a target meteorological time sequence; reading a predetermined meteorological analysis strategy, and analyzing the target meteorological time sequence based on the predetermined meteorological analysis strategy to obtain a target predicted wind energy resource value; traversing the predetermined feature indexes in multi-dimensional feature information obtained by performing multi-dimensional feature collection on the target wind power plant to obtain target feature information; performing simulation power generation on the target feature information in the digital twin wind power plant model to obtain simulation power generation capacity; the simulation generating capacity is corrected with the target predicted wind energy resource value as a coefficient, target predicted generating capacity is obtained, and the target predicted generating capacity refers to the generating capacity predicted value of the target wind power plant in the preset ultra-short period. The technical problem of insufficient wind power ultra-short-term prediction precision in the prior art is solved, and the technical effect of improving the wind power ultra-short-term generating capacity prediction accuracy is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for correcting wind power ultra-short-term forecast errors based on meteorological data. Background Art

[0002] Against the backdrop of global energy transition and sustainable development, the development and utilization of wind energy, a clean, renewable energy source, has garnered widespread attention and attention. With the continuous advancement of wind power technology and the rapid growth of installed wind power capacity, accurate forecasting of wind power generation has become a key technology for the development of the wind power industry. In particular, in the field of ultra-short-term wind power forecasting, accurately predicting the short-term power generation of wind farms is crucial for power system scheduling, optimizing energy allocation, and ensuring stable grid operation. However, wind power generation is affected by multiple factors, with meteorological conditions being one of the most significant. Changes in meteorological parameters such as wind speed, direction, temperature, and humidity directly impact the efficiency of wind turbines, and thus the power generation of wind farms. Therefore, accurately capturing and interpreting meteorological data, and integrating it with the actual conditions of wind farms to accurately forecast power generation, poses a significant challenge for ultra-short-term wind power forecasting technology. Summary of the Invention

[0003] The present application provides a method and system for correcting ultra-short-term wind power forecast errors based on meteorological data, which solves the technical problem of insufficient accuracy of ultra-short-term wind power forecasts in the prior art.

[0004] In view of the above problems, the present application provides a method and system for correcting wind power ultra-short-term forecast errors based on meteorological data.

[0005] In a first aspect of the present application, a method for correcting wind power ultra-short-term forecast errors based on meteorological data is provided, the method comprising:

[0006] Obtain a target meteorological time series, wherein the target meteorological time series refers to a time series of meteorological data of a target environment in a target wind farm; read a predetermined meteorological analysis strategy, and analyze the target meteorological time series based on the predetermined meteorological analysis strategy to obtain a target predicted wind energy resource value, wherein the target predicted wind energy resource value refers to a predicted value of a predetermined ultra-short-term wind energy resource; traverse predetermined characteristic indicators in the multidimensional feature information obtained by multi-dimensional feature collection of the target wind farm to obtain target feature information; simulate power generation for the target feature information in a digital twin wind farm model to obtain simulated power generation, wherein the digital twin wind farm model is a model of the target wind farm constructed based on the digital twin principle; correct the simulated power generation with the target predicted wind energy resource value as a coefficient to obtain a target predicted power generation, wherein the target predicted power generation refers to the predicted value of the power generation of the target wind farm in the predetermined ultra-short term.

[0007] A second aspect of the present application provides a wind power ultra-short-term forecast error correction system based on meteorological data, the system comprising:

[0008] A timing acquisition module, the timing acquisition module is used to acquire a target meteorological timing, the target meteorological timing refers to a time series of meteorological data of a target environment in a target wind farm; an analysis module, the analysis module is used to read a predetermined meteorological analysis strategy, and analyze the target meteorological timing based on the predetermined meteorological analysis strategy to obtain a target predicted wind energy resource value, wherein the target predicted wind energy resource value refers to a predicted value of a predetermined ultra-short-term wind energy resource; a feature extraction module, the feature extraction module is used to traverse predetermined feature indicators in the multidimensional feature information obtained by multi-dimensional feature collection of the target wind farm to obtain target feature information; a simulation module, the simulation module is used to simulate power generation of the target feature information in a digital twin wind farm model to obtain simulated power generation, wherein the digital twin wind farm model is a model of the target wind farm constructed based on the digital twin principle; a correction module, the correction module is used to correct the simulated power generation with the target predicted wind energy resource value as a coefficient to obtain a target predicted power generation, wherein the target predicted power generation refers to the predicted value of the power generation of the target wind farm in the predetermined ultra-short term.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, a target meteorological time series is obtained. The target meteorological time series refers to the time series of meteorological data for the target environment of the target wind farm. Next, a predetermined meteorological analysis strategy is read and analyzed based on the predetermined meteorological analysis strategy to obtain a target predicted wind energy resource value. The target predicted wind energy resource value refers to the predicted value of the wind energy resource for a predetermined ultra-short term. Next, predetermined characteristic indicators are traversed through the multidimensional feature information obtained by multi-dimensional feature collection of the target wind farm to obtain target feature information. Then, power generation is simulated using the target feature information in a digital twin wind farm model to obtain simulated power generation. The digital twin wind farm model is a model of the target wind farm constructed based on the digital twin principle. Finally, the simulated power generation is corrected using the target predicted wind energy resource value as a coefficient to obtain a target predicted power generation. The target predicted power generation refers to the predicted power generation value of the target wind farm for a predetermined ultra-short term. This solves the technical problem of insufficient accuracy in ultra-short-term wind power forecasting in the prior art, achieving the technical effect of improving the accuracy of ultra-short-term wind power forecasting. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A flow chart of a method for correcting wind power ultra-short-term forecast errors based on meteorological data provided in an embodiment of the present application;

[0013] Figure 2 This is a schematic diagram of the structure of a wind power ultra-short-term forecast error correction system based on meteorological data provided in an embodiment of the present application.

[0014] Description of the accompanying drawings: timing acquisition module 11, analysis module 12, feature extraction module 13, simulation module 14, correction module 15. DETAILED DESCRIPTION

[0015] The present application solves the technical problem of insufficient accuracy of ultra-short-term wind power prediction in the prior art by providing a method and system for correcting ultra-short-term wind power prediction errors based on meteorological data.

[0016] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0018] Example 1, as Figure 1 As shown, the present application provides a method for correcting wind power ultra-short-term forecast errors based on meteorological data, wherein the method includes:

[0019] A target meteorological time series is obtained, where the target meteorological time series refers to a time series of meteorological data of a target environment where a target wind farm is located.

[0020] In the process of ultra-short-term wind power forecasting, it is first necessary to obtain the time series of meteorological data of the target environment where the target wind farm is located, that is, the target meteorological time series. These meteorological data include key parameters such as wind speed, wind direction, temperature, and humidity. Their changes will directly affect the power generation efficiency of the wind farm.

[0021] A predetermined meteorological analysis strategy is read, and the target meteorological time series is analyzed based on the predetermined meteorological analysis strategy to obtain a target predicted wind energy resource value, wherein the target predicted wind energy resource value refers to a predicted value of a predetermined ultra-short-term wind energy resource.

[0022] The predetermined meteorological analysis strategy is formulated based on historical data and professional knowledge and is used to analyze and interpret meteorological data. By reading the predetermined meteorological analysis strategy and analyzing the target meteorological time series, the wind energy resource value of the target wind farm in the predetermined ultra-short term can be predicted, that is, the target predicted wind energy resource value.

[0023] Furthermore, the target predicted wind energy resource value is obtained, including:

[0024] The predetermined meteorological dimension is stored in the predetermined meteorological analysis strategy; the first meteorological time series of the first dimension in the target meteorological time series is extracted, and the first dimension refers to any one dimension in the predetermined meteorological dimensions; a regression fitting analysis is performed on the first meteorological scatter plot obtained based on the first meteorological time series to obtain a first fitting polynomial; the predetermined moment corresponding to the predetermined ultra-short term is used as the input value of the first fitting polynomial to obtain the first predicted meteorological parameter of the first dimension; the first predicted meteorological parameter is weightedly calculated using the coefficient of variation principle to obtain the target predicted wind energy resource value.

[0025] Specifically, a series of meteorological dimensions are stored in the predetermined meteorological analysis strategy. These dimensions are the basis for subsequent analysis. Each dimension represents an important aspect of meteorological data and has a direct impact on the prediction of wind energy resources. From the target meteorological time series, according to the predetermined meteorological dimensions, the first meteorological time series corresponding to the first dimension (such as wind speed) is extracted. The first meteorological time series contains continuous observation data of this dimension over a period of time. Based on the first meteorological time series, a first meteorological scatter plot is drawn. The scatter plot can intuitively show the distribution and trend between data points. The scatter plot is subjected to regression fitting analysis, and a suitable mathematical model (such as polynomial, linear regression, etc.) is selected to fit the data points to obtain the first fitting polynomial. The first fitting polynomial describes the change law of the first meteorological time series. The predetermined ultra-short-term corresponding The predetermined time (such as a specific time point in a certain hour in the future) is used as the input value of the first fitting polynomial, and the predicted meteorological parameters of the first dimension at that time (such as predicted wind speed) are obtained by calculation. This predicted value is based on historical data and mathematical models, and reflects the possibility of future meteorological conditions. Since wind energy resources are jointly affected by multiple meteorological dimensions, and the degree of influence of different dimensions on wind energy resources may be different, it is necessary to use the coefficient of variation principle to perform weighted calculation on the predicted meteorological parameters of each dimension. The coefficient of variation is a statistic that measures the degree of data variation and can reflect the stability and importance of meteorological parameters in different dimensions. By calculating the coefficient of variation of each dimension and determining the weight accordingly, the predicted meteorological parameters of each dimension are weighted and summed according to the weight, and finally the target predicted wind energy resource value is obtained.

[0026] Furthermore, the predetermined meteorological dimensions include at least a wind speed dimension, a wind direction dimension, and an air density dimension, and the air density dimension includes air temperature, air pressure, and air humidity.

[0027] The predetermined meteorological dimensions include at least wind speed, wind direction, and air density, and the air density dimension includes three sub-dimensions: air temperature, air pressure, and air humidity. Taking the speed dimension as an example, the same method can be used for other dimensions. Specifically, the first meteorological time series of the first dimension (such as the wind speed time series) is extracted from the target meteorological time series. A scatter plot is drawn for the meteorological time series of each dimension (such as the wind speed time series). The scatter plot is fitted using a regression analysis method (such as linear regression, polynomial regression, etc.) to obtain a first fitting polynomial. The predetermined time corresponding to the predetermined ultra-short term is used as the input value of the first fitting polynomial, and the first predicted meteorological parameter of the first dimension at that time (such as the predicted wind speed) is calculated.

[0028] The predetermined characteristic index is traversed in the multi-dimensional characteristic information obtained by collecting multi-dimensional characteristics of the target wind farm to obtain target characteristic information.

[0029] Furthermore, the predetermined characteristic indicators include terrain, unit energy conversion efficiency and unit operating status, wherein the terrain refers to the terrain of the target environment, and the unit energy conversion efficiency and the unit operating status refer to the energy conversion efficiency and operating status of the wind turbines in the target wind farm respectively.

[0030] The predetermined characteristic indicators include terrain, unit energy conversion efficiency, and unit operating status. Terrain refers to the terrain characteristics of the area where the target wind farm is located, such as altitude, slope, terrain undulation, and landform type (such as plains, hills, and mountains); unit energy conversion efficiency refers to the efficiency of the wind turbine in converting wind energy into electrical energy; and unit operating status refers to the current operating status of the wind turbine. Multi-dimensional feature collection is performed on the target wind farm, including but not limited to meteorological data (such as wind speed, wind direction, temperature, humidity, and air pressure), wind turbine operating data (such as power generation, power output, and fault records), terrain and geomorphological data (such as altitude, terrain undulation, and obstacle distribution), and other factors that may affect the performance of the wind farm, to obtain multi-dimensional feature information. The predetermined characteristic indicators are traversed in the collected multi-dimensional feature information, that is, for each predetermined characteristic indicator, the target feature information is extracted from the corresponding feature dimension, including terrain characteristics, unit energy conversion efficiency, and unit operating status.

[0031] Further, including:

[0032] Extracting a unit aging function from the multidimensional feature information, wherein the unit aging function refers to an aging function of a wind turbine in the target wind farm; extracting first historical meteorological data at a first historical moment in the target meteorological time series; correcting and adjusting the unit aging function according to the first historical meteorological data to obtain an effective aging function; analyzing the effective aging function to obtain a predicted aging degree of the wind turbine at a predetermined moment; and adjusting a predetermined unit operating state based on the predicted aging degree to obtain the unit operating state.

[0033] Extract the unit aging function from the multidimensional feature information. The unit aging function refers to the aging function of the wind turbine in the target wind farm. The aging function is a mathematical model that describes the gradual decline in performance of the wind turbine over time. The aging function is usually established based on the historical operation data, maintenance records, data provided by the manufacturer, and expert experience of the unit. Optionally, collect the historical operation data of the wind turbine, including power generation, power output, fault records, maintenance history, etc., and use statistical methods, machine learning algorithms or physical models to establish the relationship between unit aging and operating time and operating conditions to obtain the aging function; extract the first historical meteorological data at the first historical moment from the target meteorological time series, including wind speed, wind direction, temperature, humidity, etc.; meteorological conditions have a significant impact on the operation and aging process of wind turbines, for example For example, extreme wind speeds may cause accelerated wear of mechanical parts, while high temperatures may affect the life of electrical components. Therefore, the unit aging function needs to be calibrated and adjusted based on historical meteorological data to more accurately reflect the actual aging situation. Optionally, an expert team can evaluate the impact of different meteorological conditions on unit aging, and adjust the parameters or structure in the aging function based on the impact of meteorological data to obtain an effective aging function; the effective aging function is used to predict the aging degree of the wind turbine at a predetermined time in the future. The predetermined time can be used as input, and the corresponding aging value can be calculated through the aging function; based on the predicted aging degree, a corresponding maintenance plan can be formulated or the operating status of the unit can be adjusted to ensure the stable operation of the wind farm and maximize power generation, while obtaining the current operating status of the unit.

[0034] Further, including:

[0035] Acquire simulated meteorological data of the unit aging function; compare and obtain a first meteorological deviation between the first historical meteorological data and the simulated meteorological data; weight multiple deviation values ​​of multiple meteorological indicators in the first meteorological deviation to obtain a first correction coefficient; combine the first correction coefficient with the unit aging function to obtain a first aging degree at the first historical moment; and generate the effective aging function based on a first mapping relationship between the first historical moment and the first aging degree.

[0036] Preferably, simulated meteorological data generated by the unit aging function is obtained, and the simulated meteorological data is used to simulate the operation of the unit under different meteorological conditions; the first historical meteorological data at the first historical moment is compared with the simulated meteorological data, and the deviation between the two is calculated to obtain a first meteorological deviation, which reflects the difference between the actual meteorological conditions and the simulated conditions; according to the importance of each meteorological indicator on the aging of the unit, different weights are assigned to each meteorological indicator based on expert evaluation, and the deviations of each meteorological indicator are weighted using the assigned weights to obtain a comprehensive correction coefficient, namely the first correction coefficient, which reflects the degree of influence of the difference between the actual meteorological conditions and the simulated conditions on the aging of the unit; the calculated first correction coefficient is applied to the unit aging function to adjust the prediction result of the function at the first historical moment, thereby obtaining a first aging degree that is closer to the actual situation; based on the corrected aging degree prediction value, a mapping relationship between the historical moment and the aging degree is established, and these mapping relationships reflect the actual situation of the unit aging under different meteorological conditions; using interpolation, fitting or machine learning methods, a continuous and smooth effective aging function is generated based on these mapping relationships, and the effective aging function can more accurately predict the aging of the unit at different times and meteorological conditions in the future.

[0037] The target characteristic information is simulated for power generation in a digital twin wind farm model to obtain simulated power generation, wherein the digital twin wind farm model is a model of the target wind farm constructed based on the digital twin principle.

[0038] By collecting detailed data of the target wind farm, including topography, meteorological conditions (such as wind speed, wind direction, temperature, humidity, etc.), unit type and parameters, grid connection status, etc., a model of the target wind farm is constructed using digital twin technology; the target characteristic information is imported as input data into the digital twin wind farm model for simulation to obtain simulated power generation.

[0039] The simulated power generation is corrected using the target predicted wind energy resource value as a coefficient to obtain a target predicted power generation, wherein the target predicted power generation refers to a predicted value of power generation of the target wind farm in the predetermined ultra-short term.

[0040] Based on the power generation simulation of the digital twin wind farm model, the target predicted wind energy resource value is further used as a coefficient to correct the simulated power generation, thereby obtaining a more accurate target predicted power generation. Specifically, the ratio between the target predicted wind energy resource value and the wind energy resource value used in the simulation (or the average wind energy resource value) is used as the correction coefficient. This coefficient reflects the difference between the predicted wind energy resource and the wind energy resource used in the simulation. The simulated power generation is multiplied by the correction coefficient to obtain the corrected simulated power generation, namely the target predicted power generation. The target predicted power generation refers to the power generation forecast value of the target wind farm in the predetermined ultra-short term.

[0041] Furthermore, the method further includes verifying the target predicted power generation based on the actual power generation of the target wind farm at the predetermined time corresponding to the predetermined ultra-short term.

[0042] At each scheduled moment within a predetermined ultra-short period (e.g., every hour, every half hour, etc.), actual power generation data of the target wind farm is collected; for each scheduled moment, the error between the target predicted power generation and the actual power generation is calculated; if the error is small and evenly distributed, the prediction is relatively accurate; if the error is large or there is a clear deviation trend, the target predicted power generation needs to be further adjusted.

[0043] In summary, the embodiments of the present application have at least the following technical effects:

[0044] First, a target meteorological time series is obtained. The target meteorological time series refers to the time series of meteorological data for the target environment of the target wind farm. Next, a predetermined meteorological analysis strategy is read and analyzed based on the predetermined meteorological analysis strategy to obtain a target predicted wind energy resource value. The target predicted wind energy resource value refers to the predicted value of the wind energy resource for a predetermined ultra-short term. Next, predetermined characteristic indicators are traversed through the multidimensional feature information obtained by multi-dimensional feature collection of the target wind farm to obtain target feature information. Then, power generation is simulated using the target feature information in a digital twin wind farm model to obtain simulated power generation. The digital twin wind farm model is a model of the target wind farm constructed based on the digital twin principle. Finally, the simulated power generation is corrected using the target predicted wind energy resource value as a coefficient to obtain a target predicted power generation. The target predicted power generation refers to the predicted power generation value of the target wind farm for a predetermined ultra-short term. This solves the technical problem of insufficient accuracy in ultra-short-term wind power forecasting in the prior art, achieving the technical effect of improving the accuracy of ultra-short-term wind power forecasting.

[0045] The second embodiment is based on the same inventive concept as the method for correcting wind power ultra-short-term forecast errors based on meteorological data in the above embodiment. Figure 2 As shown, the present application provides a wind power ultra-short-term forecast error correction system based on meteorological data, wherein the system includes:

[0046] A time series acquisition module 11 is used to acquire a target meteorological time series, which refers to a time series of meteorological data of a target environment in a target wind farm; an analysis module 12 is used to read a predetermined meteorological analysis strategy and analyze the target meteorological time series based on the predetermined meteorological analysis strategy to obtain a target predicted wind energy resource value, wherein the target predicted wind energy resource value refers to a predicted value of a predetermined ultra-short-term wind energy resource; a feature extraction module 13 is used to extract predetermined characteristic indicators after performing multi-dimensional feature analysis on the target wind farm. Traverse the collected multidimensional feature information to obtain target feature information; a simulation module 14, the simulation module 14 is used to simulate power generation of the target feature information in the digital twin wind farm model to obtain simulated power generation, wherein the digital twin wind farm model is a model of the target wind farm constructed based on the digital twin principle; a correction module 15, the correction module 15 is used to correct the simulated power generation with the target predicted wind energy resource value as a coefficient to obtain the target predicted power generation, wherein the target predicted power generation refers to the predicted value of the power generation of the target wind farm in the predetermined ultra-short term.

[0047] Furthermore, the analysis module 12 is configured to perform the following method:

[0048] The predetermined meteorological dimension is stored in the predetermined meteorological analysis strategy; the first meteorological time series of the first dimension in the target meteorological time series is extracted, and the first dimension refers to any one dimension in the predetermined meteorological dimensions; a regression fitting analysis is performed on the first meteorological scatter plot obtained based on the first meteorological time series to obtain a first fitting polynomial; the predetermined moment corresponding to the predetermined ultra-short term is used as the input value of the first fitting polynomial to obtain the first predicted meteorological parameter of the first dimension; the first predicted meteorological parameter is weightedly calculated using the coefficient of variation principle to obtain the target predicted wind energy resource value.

[0049] Furthermore, the analysis module 12 is configured to perform the following method:

[0050] The predetermined meteorological dimensions include at least a wind speed dimension, a wind direction dimension, and an air density dimension, and the air density dimension includes air temperature, air pressure, and air humidity.

[0051] Furthermore, the feature extraction module 13 is used to perform the following method:

[0052] The predetermined characteristic indicators include terrain, unit energy conversion efficiency and unit operating status, wherein the terrain refers to the terrain of the target environment, and the unit energy conversion efficiency and the unit operating status refer to the energy conversion efficiency and operating status of the wind turbines in the target wind farm respectively.

[0053] Furthermore, the feature extraction module 13 is used to perform the following method:

[0054] Extracting a unit aging function from the multidimensional feature information, wherein the unit aging function refers to an aging function of a wind turbine in the target wind farm; extracting first historical meteorological data at a first historical moment in the target meteorological time series; correcting and adjusting the unit aging function according to the first historical meteorological data to obtain an effective aging function; analyzing the effective aging function to obtain a predicted aging degree of the wind turbine at a predetermined moment; and adjusting a predetermined unit operating state based on the predicted aging degree to obtain the unit operating state.

[0055] Furthermore, the feature extraction module 13 is used to perform the following method:

[0056] Acquire simulated meteorological data of the unit aging function; compare and obtain a first meteorological deviation between the first historical meteorological data and the simulated meteorological data; weight multiple deviation values ​​of multiple meteorological indicators in the first meteorological deviation to obtain a first correction coefficient; combine the first correction coefficient with the unit aging function to obtain a first aging degree at the first historical moment; and generate the effective aging function based on a first mapping relationship between the first historical moment and the first aging degree.

[0057] Furthermore, the correction module 15 is configured to execute the following method:

[0058] The target predicted power generation is verified based on the actual power generation of the target wind farm at a predetermined time corresponding to the predetermined ultra-short period.

[0059] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0060] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0061] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A method for correcting wind power ultra-short-term forecast errors based on meteorological data, characterized in that: The method comprises: Acquire a target meteorological time series, wherein the target meteorological time series refers to a time series of meteorological data of a target environment in which a target wind farm is located; Reading a predetermined meteorological analysis strategy, and analyzing the target meteorological time series based on the predetermined meteorological analysis strategy to obtain a target predicted wind energy resource value, wherein the target predicted wind energy resource value refers to a predicted value of a predetermined ultra-short-term wind energy resource; Traversing the predetermined characteristic index in the multi-dimensional characteristic information obtained by collecting multi-dimensional characteristics of the target wind farm to obtain target characteristic information; Simulating power generation for the target characteristic information in a digital twin wind farm model to obtain simulated power generation, wherein the digital twin wind farm model is a model of the target wind farm constructed based on the digital twin principle; The simulated power generation is corrected with the target predicted wind energy resource value as a coefficient to obtain the target predicted power generation, wherein the target predicted power generation refers to the predicted value of the power generation of the target wind farm in the predetermined ultra-short term.

2. The method for correcting wind power ultra-short-term forecast errors based on meteorological data according to claim 1 is characterized in that: include: The predetermined meteorological analysis strategy stores predetermined meteorological dimensions; Extracting a first meteorological time series of a first dimension in the target meteorological time series, where the first dimension refers to any one of the predetermined meteorological dimensions; Performing regression fitting analysis on a first meteorological scatter plot obtained based on the first meteorological time series to obtain a first fitting polynomial; Using the predetermined time corresponding to the predetermined ultra-short term as an input value of the first fitting polynomial to obtain the first predicted meteorological parameter of the first dimension; The first predicted meteorological parameter is weightedly calculated using the coefficient of variation principle to obtain the target predicted wind energy resource value.

3. The method for correcting wind power ultra-short-term forecast errors based on meteorological data according to claim 2 is characterized in that: The predetermined meteorological dimensions include at least a wind speed dimension, a wind direction dimension and an air density dimension, and the air density dimension includes air temperature, air pressure and air humidity.

4. The method for correcting wind power ultra-short-term forecast errors based on meteorological data according to claim 1 is characterized in that: The predetermined characteristic indicators include terrain, unit energy conversion efficiency and unit operating status, wherein the terrain refers to the terrain of the target environment, and the unit energy conversion efficiency and the unit operating status respectively refer to the energy conversion efficiency and operating status of the wind turbines in the target wind farm.

5. The method for correcting wind power ultra-short-term forecast errors based on meteorological data according to claim 4 is characterized in that: include: Extracting a unit aging function from the multidimensional feature information, wherein the unit aging function refers to an aging function of a wind turbine unit in the target wind farm; Extracting the first historical meteorological data at the first historical moment in the target meteorological time series; Correcting and adjusting the unit aging function according to the first historical meteorological data to obtain an effective aging function; Analyzing the effective aging function to obtain a predicted aging degree of the wind turbine generator set at a predetermined time; The predetermined unit operating state is adjusted based on the predicted aging degree to obtain the unit operating state.

6. The method for correcting wind power ultra-short-term forecast errors based on meteorological data according to claim 5 is characterized in that: include: Acquiring simulated meteorological data of the unit aging function; Comparing and obtaining a first meteorological deviation between the first historical meteorological data and the simulated meteorological data; Weighting a plurality of deviation values ​​of a plurality of meteorological indicators in the first meteorological deviation to obtain a first correction coefficient; Combining the first correction coefficient with the unit aging function to obtain a first aging degree at the first historical moment; The effective aging function is generated according to a first mapping relationship between the first historical moment and the first aging degree.

7. The method for correcting wind power ultra-short-term forecast errors based on meteorological data according to claim 1, characterized in that: The method also includes verifying the target predicted power generation based on the actual power generation of the target wind farm at a predetermined time corresponding to the predetermined ultra-short term.

8. The wind power ultra-short-term forecast error correction system based on meteorological data is characterized by: The system is used to implement the method for correcting wind power ultra-short-term prediction errors based on meteorological data according to any one of claims 1 to 7, comprising: A time series acquisition module, the time series acquisition module is used to acquire a target meteorological time series, the target meteorological time series refers to a time series of meteorological data of a target environment in a target wind farm; An analysis module, the analysis module is used to read a predetermined meteorological analysis strategy, and analyze the target meteorological time series based on the predetermined meteorological analysis strategy to obtain a target predicted wind energy resource value, wherein the target predicted wind energy resource value refers to a predicted value of a predetermined ultra-short-term wind energy resource; A feature extraction module, the feature extraction module is used to traverse the predetermined feature index in the multi-dimensional feature information obtained by collecting multi-dimensional features of the target wind farm to obtain target feature information; A simulation module, wherein the simulation module is used to simulate power generation of the target characteristic information in a digital twin wind farm model to obtain simulated power generation, wherein the digital twin wind farm model is a model of the target wind farm constructed based on the digital twin principle; A correction module is used to correct the simulated power generation using the target predicted wind energy resource value as a coefficient to obtain the target predicted power generation, wherein the target predicted power generation refers to the predicted value of the power generation of the target wind farm in the predetermined ultra-short term.

Images