Short-term wind power plant power prediction method, device, equipment and medium

Abstract

The invention provides a short-term wind power plant power prediction method and device, equipment and a medium, and belongs to the technical field of wind power data processing. The method comprises the steps of obtaining a predicted wind speed and a wind direction angle of a target height of a wind power plant, classifying and identifying the wind direction angle, and determining a time category and a wind direction category; after correcting the abnormal wind speed, calculating the total power at each moment by using a wind speed-total power curve, and calculating the average ratio of the power at each moment to the total power according to the wind speed and wind direction categories; and the wind power at each moment is obtained through product, and power prediction of the wind power plant is realized. According to the method, higher prediction precision and a finer time scale are realized by focusing on generation power prediction of the wind power plant in a specific time period and utilizing a simple statistical method and an empirical model, meanwhile, the technical complexity is reduced, and the operation efficiency of the wind power plant is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power data processing, and in particular to a short-term wind farm power prediction method, a short-term wind farm power prediction device, an electronic device and a computer-readable storage medium. Background Art

[0002] With the continuous development of computer technology, artificial intelligence technology and big data technology, although wind power prediction technology has made certain progress with the help of machine learning and deep learning, the existing big data model uses historical data to learn the laws of numerical weather forecasts and the relationship between them and the actual power of wind turbines, and adjusts the model parameters to perform linear or nonlinear learning. However, the prediction model is generally a black box model, the prediction principle is unknown, and the prediction principle cannot reflect the actual operation of wind turbines under different working conditions, and the prediction generally uses a single model for one field.

[0003] At present, big data methods such as model fusion or integrated models have been used to enhance learning capabilities and solve some problems of single model complexity.

[0004] However, as the model becomes more complex, the improvement in prediction accuracy is very limited. The reason is that machine learning cannot truly learn the physical laws of complex working conditions and wind turbine operation, cannot truly reflect actual working conditions, and cannot reflect the different power generation characteristics of wind farms under different working conditions and the traditional forecast errors of numerical weather forecasts. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a short-term wind farm power prediction method, device, equipment and medium to solve the above problems.

[0006] In order to achieve the above object, an embodiment of the present invention provides a short-term wind farm power prediction method, comprising:

[0007] Obtain the predicted wind speed and wind direction angle of the wind farm at multiple times at the target height;

[0008] Different categories of predicted wind direction angles at target heights at various times are identified, and the time categories of the predicted wind direction angles at target heights and the wind direction categories at various times at target heights are determined;

[0009] According to the predicted wind direction angle at each moment of the target height and the wind direction category at each moment of the target height, the predicted wind speed corresponding to the abnormal moment among multiple moments of the target height is identified and corrected to obtain the corrected predicted wind speed at each moment of the target height;

[0010] Matching the predicted wind speed at each moment of the corrected target height with a pre-constructed wind speed-total power curve to determine the total power at each moment of the target height; wherein the pre-constructed wind speed-total power curve is used to characterize the mapping relationship between the wind speed at different moments and its corresponding total power;

[0011] Determine the average ratio of the power at each moment of the target height to the total power according to the corrected predicted wind speed at each moment of the target height, the time category of each predicted wind direction angle at the target height, and the wind direction category at each moment of the target height;

[0012] The product of the total power at each moment of the target height and the average ratio of the power to the total power is calculated to obtain the power at each moment of the target height of the wind farm.

[0013] Optionally, the predicted wind speed and predicted wind direction angle of the wind farm at the target height at multiple times are determined by:

[0014] respectively obtaining the predicted wind speed and the predicted wind direction angle at multiple moments at adjacent heights below the target height and adjacent heights above the target height in the wind farm;

[0015] For each moment:

[0016] If the predicted wind speed at the adjacent height below the target height is less than or equal to, or greater than or equal to, the predicted wind speed at the adjacent height above the target height, then based on the ratio of the target height to the adjacent height below the target height, the preset surface friction coefficient, and the predicted wind speed at the adjacent height below the target height, the predicted wind speed at the target height is obtained, and the predicted wind direction angle below the target height is used as the predicted wind direction angle at the target height; or

[0017] If the predicted wind speeds at the adjacent height below the target height and the adjacent height above the target height are both greater than the preset wind speed, the predicted wind speed at the adjacent height above the target height shall be used as the predicted wind speed at the target height, and the predicted wind direction angle at the adjacent height above the target height shall be used as the predicted wind direction angle at the target height.

[0018] Optionally, based on the ratio of the target height to an adjacent height lower than the target height, a preset surface friction coefficient, and a predicted wind speed at an adjacent height lower than the target height, the predicted wind speed at the target height is obtained, including:

[0019] The following formula is used to calculate the ratio of the target height to the adjacent height below the target height, the preset surface friction coefficient, and the predicted wind speed at the adjacent height below the target height to obtain the predicted wind speed at the target height;

[0020] Among them, V crepresents the predicted wind speed at the target height, V represents the predicted wind speed at the adjacent height below the target height, and H c represents the target height, H represents the adjacent height below the target height, and a represents the preset surface friction coefficient.

[0021] Optionally, different categories of predicted wind direction angles at the target height at each moment are identified to determine the time category of each predicted wind direction angle at the target height and the wind direction category at each moment at the target height, including:

[0022] According to a plurality of predicted wind direction angles at the target height, the predicted wind direction angles at each moment at the target height are identified as wind direction categories, and the wind direction categories at each moment at the target height are determined;

[0023] According to multiple moments of the target height, time categories of the moments of the predicted wind direction angles at the target height are identified, and time categories of the predicted wind directions at the target height are determined.

[0024] Optionally, according to the predicted wind direction angle at each moment of the target height and the wind direction category at each moment of the target height, identifying and correcting the predicted wind speed corresponding to the abnormal moment among multiple moments of the target height to obtain the corrected predicted wind speed at each moment of the target height, including:

[0025] Calculate the ratio of the number of each wind direction category at the target height at the corresponding moment to the total number of wind direction categories at the target height at multiple moments, and determine the wind direction category whose ratio is greater than the preset ratio as the main wind direction category;

[0026] Calculate the difference between the predicted wind direction angle at each moment of the target height and the adjacent moments to obtain the predicted wind direction angle difference at each moment of the target height;

[0027] Determine the moment when the wind direction angle difference among multiple moments of the target height is greater than the preset wind direction angle difference and the wind direction category is not the main wind direction category as the initial abnormal moment of the target height;

[0028] Determine the abnormal moment of the target height when any adjacent moment among the initial abnormal moments is the initial abnormal moment as the abnormal moment of the target height;

[0029] Correct the predicted wind speed corresponding to the abnormal moment of the target height.

[0030] Optionally, determining an average ratio of power at each moment of the target height to the total power according to the corrected predicted wind speed at each moment of the target height, the time category of each predicted wind direction angle at the target height, and the wind direction category at each moment of the target height includes:

[0031] Matching the time category of each predicted wind direction angle at the target height and the wind direction category at each moment at the target height with a preset comprehensive classification matrix to obtain the comprehensive working condition category at each moment at the target height; wherein the preset comprehensive classification matrix includes different comprehensive working condition categories corresponding to different time categories and different wind direction categories;

[0032] According to the wind direction category at each moment of the target height and the abnormal moment of the target height, identify the small correction category at each moment of the target height;

[0033] According to the comprehensive working condition category and the small and micro correction category at each moment of the target height, the mapping relationship between the power at each moment of the target height and the total power is determined by a preset coefficient calculation matrix; wherein the preset coefficient calculation matrix includes the comprehensive working condition category, the small and micro correction category, and the mapping relationship between the power obtained according to the comprehensive working condition category and the small and micro correction category and the total power;

[0034] Matching the predicted wind speed at each moment of the corrected target height with at least one pre-constructed curve of the ratio of wind speed-power to total power, and determining the ratio of power to total power at each moment of at least one target height; wherein the pre-constructed curve of the ratio of wind speed-power to total power is used to characterize the mapping relationship between the wind speed at different moments and the corresponding ratio of power to total power;

[0035] According to the mapping relationship between the power at each moment of the target height and the total power, the ratio of the power at each moment of at least one target height to the total power is calculated to obtain the average ratio of the power at each moment of the target height to the total power.

[0036] Optionally, according to the wind direction category at each moment of the target height and the abnormal moment of the target height, the small correction category at each moment of the target height is identified, including:

[0037] If the wind direction category at the initial moment of the target height is the main wind direction category or the initial moment of the target height is an abnormal moment, the first subsequent moment when the wind direction category is not the main wind direction category and is not an abnormal moment is determined as the target initial moment of the target height;

[0038] In a case where the wind direction category at the target initial moment of the target height is not the main wind direction category and is not an abnormal moment, if after the target initial moment of the target height, the wind direction categories corresponding to multiple consecutive moments are not the main wind direction category, and the number of the multiple consecutive moments is a first preset number, then the small correction category at the target initial moment of the target height is determined as a slight correction, and the small correction category at the multiple consecutive moments after the target initial moment of the target height is determined as a slight correction, and the small correction category at the moments other than the target initial moment of the target height and the multiple consecutive moments after the target initial moment of the target height is determined as not requiring correction; or

[0039] In the case where the wind direction category at the target initial moment of the target height is not the main wind direction category and is not an abnormal moment, if after the target initial moment of the target height, the wind direction categories corresponding to multiple consecutive moments are not the main wind direction category, and the number of the multiple consecutive moments is less than a first preset number, then the small correction category at the target initial moment of the target height is determined as a slight correction, and the small correction category at the multiple consecutive moments after the target initial moment of the target height is determined as a medium correction, and the small correction category at the moments other than the target initial moment of the target height and the multiple consecutive moments after the target initial moment of the target height is determined as not requiring correction; or

[0040] When the wind direction category at the target initial moment of the target height is not the main wind direction category and is not an abnormal moment, if after the target initial moment of the target height, the wind direction categories corresponding to multiple consecutive moments are not the main wind direction category, and the number of consecutive moments is greater than a first preset number, then the small correction category at the target initial moment of the target height is determined as a minor correction, and the small correction category at the consecutive moments after the target initial moment of the target height is determined as a major correction, and the small correction category at moments other than the target initial moment of the target height and the consecutive moments after the target initial moment of the target height is determined as not requiring correction.

[0041] In a second aspect of an embodiment of the present invention, a short-term wind farm power prediction device is provided, comprising:

[0042] A data acquisition module is used to obtain the predicted wind speed and predicted wind direction angle of the wind farm at a target height at multiple times;

[0043] A category recognition module is used to perform different category recognition on the predicted wind direction angles at the target height at each moment, and determine the time category of each predicted wind direction angle at the target height and the wind direction category at each moment at the target height;

[0044] A wind speed correction module, for identifying and correcting the predicted wind speed corresponding to the abnormal moment among multiple moments of the target height according to the predicted wind direction angle at each moment of the target height and the wind direction category at each moment of the target height, so as to obtain the corrected predicted wind speed at each moment of the target height;

[0045] A power matching module is used to match the predicted wind speed at each moment of the corrected target height with a pre-constructed wind speed-total power curve to determine the total power at each moment of the target height; wherein the pre-constructed wind speed-total power curve is used to characterize the mapping relationship between the wind speed at different moments and its corresponding total power;

[0046] A ratio calculation module, for determining an average ratio of the power at each moment of the target height to the total power according to the corrected predicted wind speed at each moment of the target height, the time category of each predicted wind direction angle at the target height, and the wind direction category at each moment of the target height;

[0047] The power calculation module is used to calculate the product of the total power at each moment of the target height and the average ratio of the power to the total power, so as to obtain the power at each moment of the target height of the wind farm.

[0048] In a third aspect of the embodiments of the present invention, an electronic device is provided, including: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the machine-readable instructions are executed by the processor, the above-mentioned short-term wind farm power prediction method is executed.

[0049] In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, storing computer instructions. When the computer instructions are executed on a computer, the computer executes the above-mentioned short-term wind farm power prediction method.

[0050] Beneficial effects of the present invention:

[0051] (1) More targeted: The present invention focuses on the prediction of wind farm power generation for a specific time period (such as hourly or daily). Compared with the prior art, it is more focused on the needs of wind farms and avoids predicting redundant information for other weather phenomena and a wider geographical range.

[0052] (2) Improved prediction accuracy: By relying on the wind farm’s own data, the present invention can more accurately predict the power generation, especially in terms of considering the impact of local wind farms. Compared with the existing technology, the prediction accuracy is improved in the face of the complexity of atmospheric movement.

[0053] (3) Finer time scale: The present invention can realize power generation prediction within the next few hours to days. Compared with the existing technology, the prediction time range is finer and can better meet the short-term operation needs of the wind farm.

[0054] (4) Reduced technical complexity: The present invention adopts relatively simple statistical methods and empirical models, which greatly reduces the technical complexity compared to the complex atmospheric motion equations and numerical methods used in the prior art, making it easier to implement and apply.

[0055] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0057] Figure 1 It is a schematic flow chart of a short-term wind farm power prediction method provided by an embodiment of the present invention;

[0058] Figure 2 is a curve diagram of the relationship between wind speed and total power provided by an embodiment of the present invention;

[0059] Figure 3 is a schematic diagram of the proportion of comprehensive working condition categories provided by an embodiment of the present invention;

[0060] Figure 4 is a curve diagram of the relationship between the ratio of wind speed-power and total power provided by an embodiment of the present invention;

[0061] Figure 5 is a schematic diagram of a curve comparison of the power provided by an embodiment of the present invention and the corrected power;

[0062] Figure 6 It is a schematic diagram of the structure of a short-term wind farm power prediction device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0065] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0066] Embodiment 1

[0067] Please refer to Figure 1 , Figure 1 : is a flow chart of a short-term wind farm power prediction method provided by an embodiment of the present invention, the method comprising the following steps:

[0068] It is understandable that the method of setting the time category, risk category, minor correction category and comprehensive working condition category as digital labels in the present invention is to digitally label the categories, thereby improving the standardization, efficiency, accuracy and automation of information processing. The beneficial effects of setting the categories as digital labels can be used as a reference and will not be elaborated in detail later.

[0069] S100, obtaining predicted wind speed and predicted wind direction angle of the wind farm at a target height at multiple times;

[0070] Predicted wind speed refers to the forecast of wind speed in the future. Wind speed is a physical quantity that measures wind strength, usually in meters per second (m / s) or kilometers per hour (km / h).

[0071] The predicted wind direction angle is the prediction of the direction the wind will blow in the future. Wind direction angle is usually expressed in degrees (°), measured from a geographical location or a point on a compass.

[0072] In one embodiment, the predicted wind speed and wind direction angles at multiple moments at the target height of the wind farm are obtained by parsing the numerical weather forecast data file released by the meteorological center, wherein the numerical weather forecast data includes the predicted wind speed, predicted wind direction and near-ground temperature, humidity and humidity at different heights for the next 24 hours.

[0073] For ease of understanding, the following exemplary Table 1 is given:

[0074] Table 1 Numerical weather forecast data

[0075]

[0076] In one embodiment, the predicted wind speed and predicted wind direction angle of the wind farm at the target height at multiple times are determined by:

[0077] S110, respectively obtaining predicted wind speeds and predicted wind direction angles at multiple moments at adjacent heights below the target height and adjacent heights above the target height in the wind farm;

[0078] It should be noted that when the numerical weather forecast data includes weather forecast data for the target height, it can be directly adopted. However, when the numerical weather forecast data does not include weather forecast data for the target height, it is necessary to obtain the numerical weather forecast data of two adjacent heights of the target height, and then calculate the numerical weather forecast data of the target height based on the numerical weather forecast data of the two adjacent heights of the target height.

[0079] It is understandable that we believe that under normal meteorological modes, as the altitude increases, the predicted wind speed corresponding to the altitude should maintain the data logic characteristics of increasing successively, and the predicted wind speed that does not conform to the normal data logic should be corrected.

[0080] For each moment:

[0081] S120, if the predicted wind speed at the adjacent height below the target height is less than or equal to, or greater than or equal to, the predicted wind speed at the adjacent height above the target height, then based on the ratio of the target height to the adjacent height below the target height, a preset surface friction coefficient, and the predicted wind speed at the adjacent height below the target height, the predicted wind speed at the target height is obtained, and the predicted wind direction angle below the target height is used as the predicted wind direction angle at the target height; or

[0082] If the predicted wind speeds at the adjacent height below the target height and the adjacent height above the target height are both greater than the preset wind speed, the predicted wind speed at the adjacent height above the target height shall be used as the predicted wind speed at the target height, and the predicted wind direction angle at the adjacent height above the target height shall be used as the predicted wind direction angle at the target height.

[0083] In one embodiment, when the predicted wind speed at an adjacent height lower than the target height is less than or greater than the predicted wind speed at an adjacent height higher than the target height, the following formula is used for calculation:

[0084] S121, using the following formula, calculating the ratio of the target height to the adjacent height lower than the target height, the preset surface friction coefficient, and the predicted wind speed of the adjacent height lower than the target height to obtain the predicted wind speed of the target height;

[0085] Among them, V c represents the predicted wind speed at the target height, V represents the predicted wind speed at the adjacent height below the target height, and H c represents the target height, H represents the adjacent height below the target height, and a represents the preset surface friction coefficient.

[0086] Specifically, the preset surface friction coefficient is reasonably set according to the actual terrain conditions, and the embodiment of the present invention does not specifically limit this. For example, the surface friction coefficient of a mountainous area can be 0.3.

[0087] For ease of understanding, the following is explained with reference to Table 2:

[0088] Table 2 Numerical weather forecast data at different altitudes

[0089]

[0090] As shown in Table 2, the predicted wind speed at a height of 100 meters can be calculated using the predicted wind speed at a height of 90 meters and the predicted wind speed at a height of 120 meters. The specific calculation process is shown in step S121, which will not be described in detail here.

[0091] S200, performing different category recognition on the predicted wind direction angles of the target height at each moment, and determining the time category of each predicted wind direction angle of the target height and the wind direction category of the target height at each moment;

[0092] To facilitate understanding of step S200, an explanation is provided below in conjunction with Table 3:

[0093] Table 3 Forecast wind speed correction parameters

[0094]

[0095] In one embodiment, step S200 specifically includes:

[0096] S210, based on a plurality of predicted wind direction angles at the target height, identifying the wind direction category of the predicted wind direction angle at each moment at the target height, and determining the wind direction category at each moment at the target height;

[0097] In one embodiment, the preset wind direction angle range includes 16 ranges, a total of 16 tags, tag 0 is 348.75° to 33.75°, tag 1 is 33.75° to 54.125°, tag 2 is 54.125° to 74.5°, tag 3 is 74.5° to 94.875°, tag 4 is 94.875° to 115.25°, tag 5 is 115.25° to 135.625°, tag 6 is 135.625° to 155.00°, and tag 7 is 155.00° to 1 75.375°, label 8 is 175.375° to 195.75°, label 9 is 195.75° to 216.125°, label 10 is 216.125° to 236.50°, label 11 is 236.50° to 256.875°, label 12 is 256.875° to 277.25°, label 13 is 277.25° to 297.625°, label 14 is 297.625° to 318.00°, and label 15 is 318.00° to 348.75°. For example, the wind direction angle at 16:00 on 2024 / 4 / 29 in Table 3 above is 310.43°, so the wind direction category at this moment is label 14.

[0098] S220, based on multiple moments of the target height, time category recognition is performed on the moment of the predicted wind direction angle at the target height, and the time category of each predicted wind direction at the target height is determined.

[0099] In one embodiment, the preset time range includes 7 ranges, a total of 7 labels, label 0 is 0 o'clock to 5 o'clock, label 1 is 5 o'clock to 8 o'clock, label 2 is 8 o'clock to 11 o'clock, label 3 is 11 o'clock to 13 o'clock, label 4 is 13 o'clock to 17 o'clock, label 5 is 17 o'clock to 20 o'clock, and label 6 is 20 o'clock to 0 o'clock. For example, in Table 3 above, 2024 / 4 / 29 16:00 belongs to the range of label 4.

[0100] S300, identifying and correcting the predicted wind speed corresponding to the abnormal moment among multiple moments of the target height according to the predicted wind direction angle at each moment of the target height and the wind direction category at each moment of the target height, so as to obtain the corrected predicted wind speed at each moment of the target height;

[0101] In one embodiment, step S300 specifically includes:

[0102] S310, calculating the ratio of the number of each wind direction category at the target height at the corresponding moment to the total number of the target height at multiple moments, and determining the wind direction category whose ratio is greater than a preset ratio as the main wind direction category;

[0103] For example, as shown in Table 2 above, the number of predicted wind directions in the wind direction angle range of tag 12 is 14, the number of predicted wind directions in the wind direction angle range of tag 13 is 3, the number of predicted wind directions in the wind direction angle range of tag 11 is 3, and the number of predicted wind directions in the wind direction angle range of tag 11 is 1. Therefore, the main wind direction category is tag 12, that is, the angle range of the main wind direction category is 256.875° to 277.25°.

[0104] S320, calculating the difference between the predicted wind direction angle at each moment of the target height and the adjacent moments, and obtaining the predicted wind direction angle difference at each moment of the target height;

[0105] For example, as shown in Table 2 above, the predicted wind direction angle difference at 100 meters altitude on 2024 / 4 / 29 17:00 = the predicted wind direction angle at 100 meters altitude on 2024 / 4 / 29 16:00 - the predicted wind direction angle at 100 meters altitude on 2024 / 4 / 29 17:00 = (360-310.43)-(360-296.23) = -14.20°.

[0106] S330, determining a moment at which a wind direction angle difference among multiple moments of the target height is greater than a preset wind direction angle difference and the wind direction category is not a main wind direction category as an initial abnormal moment of the target height;

[0107] The preset wind direction angle difference is a manually defined difference in wind direction angles between adjacent moments, and can be reasonably set according to user needs or application scenarios, and the embodiments of the present invention do not specifically limit this.

[0108] Specifically as shown in Table 2 above, assuming that in this embodiment, the preset wind direction angle difference is 5°, then the abnormal moments greater than 5° and with a wind direction angle in the range of 256.875° to 277.25° include: 2024 / 4 / 29 19:00, 2024 / 4 / 29 22:00, 2024 / 4 / 29 23:00, 2024 / 4 / 30 0:00, 2024 / 4 / 30 1:00, 2024 / 4 / 30 2:00, 2024 / 4 / 30 3:00, 2024 / 4 / 30 4:00, 2024 / 4 / 30 7:00, 2024 / 4 / 30 8:00, 2024 / 4 / 30 9:00, 2024 / 4 / 30 10:00, 2024 / 4 / 30 12:00, 2024 / 4 / 30 13:00, 2024 / 4 / 30 14:00 and 2024 / 4 / 30 15:00.

[0109] S340, determining a moment in which any adjacent moments among the initial abnormal moments of the target height are both initial abnormal moments as the abnormal moment of the target height;

[0110] Specifically, after determining the abnormal moment in step S330, the wind direction angle of each abnormal moment is analyzed, that is, whether each abnormal moment and its adjacent moments are abnormal moments is determined. If only one of the adjacent moments is not an abnormal moment, the abnormal mark of the current abnormal moment is cancelled. If both adjacent moments are abnormal moments, the current abnormal moment is taken as the final abnormal moment. S350, the predicted wind speed corresponding to the abnormal moment of the target height is corrected.

[0111] Then the wind speed corresponding to the final abnormal moment is corrected, and the correction method is to reduce the wind speed to 90% of the original wind speed. For example, the predicted wind speed at the current abnormal moment is 5m / s, and the corrected predicted wind speed is 4.5m / s.

[0112] To facilitate understanding of step S300, an example is given below:

[0113] For example, as shown in Table 2 above, 2024 / 4 / 29 19:00 is an abnormal moment, but its adjacent moments are not abnormal moments, so the abnormal mark of 2024 / 4 / 29 19:00 is cancelled. The other abnormal moments are similarly determined, and the abnormal moments finally determined are 2024 / 4 / 29 23:00, 2024 / 4 / 30 0:00, 2024 / 4 / 30 1:00, 2024 / 4 / 30 2:00, 2024 / 4 / 30 3:0, 2024 / 4 / 30 8:00, 2024 / 4 / 30 9:00, 2024 / 4 / 30 13:00, 2024 / 4 / 30 14:00 and 2024 / 4 / 30 15:00, and then the wind speeds at these moments are corrected.

[0114] S400, matching the predicted wind speed at each moment of the target height after correction with a pre-constructed wind speed-total power curve to determine the total power at each moment of the target height; wherein the pre-constructed wind speed-total power curve is used to characterize the mapping relationship between the wind speed at different moments and its corresponding total power;

[0115] It should be noted that, when using the wind speed binning method, the predicted wind speed is first classified into 0-3, 3-12, and 12-75. 0-3m / s is classified at 1m / s, 3-12m / s is classified at 0.1m / s, and 12-75m / s is classified at 1m / s. In other words, the wind speed is classified in a refined manner, so that the ratio of wind speed at different scales to the current total power of the wind farm can be determined.

[0116] Specifically, Figure 2 It is a curve diagram drawn based on the data in Table 4, that is, a pre-constructed wind speed-total power curve. The following is an exemplary wind speed-total power mapping relationship table:

[0117] Table 4 Wind speed-total power mapping relationship table

[0118]

[0119]

[0120]

[0121] According to Table 4 and Figure 2 It can be known that each wind speed corresponds to the three powers of the lower boundary theoretical power, the average theoretical power and the upper boundary theoretical power, and in this embodiment, only the average theoretical power is needed, that is, the total power at each moment of the target height. The purpose of setting the lower boundary theoretical power and the upper boundary theoretical power is to constrain the average theoretical power so that it is within a reasonable and normal range.

[0122] In one embodiment, the wind speed in Table 4 is the historical average wind speed, and the total power in Table 9 is also the ratio of the historical total power, so the pre-constructed wind speed-total power curve is obtained based on the historical data fitting. The following is the fitting process of the pre-constructed wind speed-total power curve:

[0123] Step 1 (select the fitting function):

[0124] Polynomial fitting: You can choose 2nd or 3rd order polynomial and adjust it according to the actual situation.

[0125] Exponential fitting: Use the exponential function form: P = a*e^(b*v), where P is the total power, v is the wind speed, and a and b are fitting parameters.

[0126] Step 1 (select fitting method):

[0127] Least squares method: a commonly used fitting method that can be implemented through a variety of software.

[0128] Gradient descent method: Applicable to more complex function forms and requires a certain programming foundation.

[0129] Step 3 (fitting using software):

[0130] Python: Use the numpy library for polynomial fitting and the scipy.optimize library for exponential fitting.

[0131] MATLAB: Use the polyfit function for polynomial fitting and the fit function for exponential fitting.

[0132] Excel: Use the "Add Trendline" function for polynomial fits, but exponential fits require other software.

[0133] Step 4 (evaluation of fitting effect):

[0134] R^2 value: Goodness of fit index. The closer the value is to 1, the better the fit effect.

[0135] Residual analysis: Observe the residual distribution and determine whether the fitted model is appropriate.

[0136] S500, determining an average ratio of the power at each moment of the target height to the total power according to the corrected predicted wind speed at each moment of the target height, the time category of each predicted wind direction angle at the target height, and the wind direction category at each moment of the target height;

[0137] In one embodiment, step S500 specifically includes:

[0138] S511, matching the time category of each predicted wind direction angle at the target height and the wind direction category at each moment at the target height with the preset comprehensive classification matrix to obtain the comprehensive working condition category at each moment at the target height; wherein the preset comprehensive classification matrix includes different comprehensive working condition categories corresponding to different time categories and different wind direction categories

[0139] Specifically, a preset comprehensive classification matrix is ​​given as an example, as shown in Table 5 below:

[0140] Table 5 Comprehensive classification matrix

[0141] Time category\wind direction category (0，1，12，13，14，15) (3，4，5，6，7，8，9，10) (2，11) (0，6) 1 3 7 (1，2，3，4) 8 4 8 (5) 5 6 9

[0142] According to Table 5, the horizontal direction represents the wind direction categories, totaling 17 categories, and the vertical direction represents the time categories, totaling 7 categories.

[0143] Taking the wind direction angle (310.43) at 16:00 on 2024 / 4 / 29 in Table 3 as an example, its wind direction classification label is 14 and its time category label is 4. Then, through the comprehensive classification matrix in Table 4 above, it can be known that the comprehensive working condition category label at 16:00 on 2024 / 4 / 29 is 8.

[0144] In order to better understand the present invention, as shown in Table 6 below, all the data in Table 3 are classified into comprehensive working conditions:

[0145] Table 6 Comprehensive working condition categories of numerical weather forecast data

[0146]

[0147]

[0148] In addition, the proportion of comprehensive working conditions is counted, such as Figure 3 As shown, the proportion of comprehensive operating condition category 1 is 25%, the proportion of comprehensive operating condition category 2 is 19%, the proportion of comprehensive operating condition category 3 is 16%, the proportion of comprehensive operating condition category 4 is 8%, the proportion of comprehensive operating condition category 5 is 7%, the proportion of comprehensive operating condition category 6 is 8%, the proportion of comprehensive operating condition category 7 is 9%, the proportion of comprehensive operating condition category 8 is 6%, and the proportion of comprehensive operating condition category 9 is 2%.

[0149] S512, identifying the small correction category of the target height at each moment according to the wind direction category at each moment of the target height and the abnormal moment of the target height;

[0150] In one embodiment, step S512 specifically further includes:

[0151] If the wind direction category at the initial moment of the target height is the main wind direction category or the initial moment of the target height is an abnormal moment, the first subsequent moment when the wind direction category is not the main wind direction category and is not an abnormal moment is determined as the target initial moment of the target height;

[0152] In a case where the wind direction category at the target initial moment of the target height is not the main wind direction category and is not an abnormal moment, if after the target initial moment of the target height, the wind direction categories corresponding to multiple consecutive moments are not the main wind direction category, and the number of the multiple consecutive moments is a first preset number, then the small correction category at the target initial moment of the target height is determined as a slight correction, and the small correction category at the multiple consecutive moments after the target initial moment of the target height is determined as a slight correction, and the small correction category at the moments other than the target initial moment of the target height and the multiple consecutive moments after the target initial moment of the target height is determined as not requiring correction; or

[0153] In the case where the wind direction category at the target initial moment of the target height is not the main wind direction category and is not an abnormal moment, if after the target initial moment of the target height, the wind direction categories corresponding to multiple consecutive moments are not the main wind direction category, and the number of the multiple consecutive moments is less than a first preset number, then the small correction category at the target initial moment of the target height is determined as a slight correction, and the small correction category at the multiple consecutive moments after the target initial moment of the target height is determined as a medium correction, and the small correction category at the moments other than the target initial moment of the target height and the multiple consecutive moments after the target initial moment of the target height is determined as not requiring correction; or

[0154] When the wind direction category at the target initial moment of the target height is not the main wind direction category and is not an abnormal moment, if after the target initial moment of the target height, the wind direction categories corresponding to multiple consecutive moments are not the main wind direction category, and the number of consecutive moments is greater than a first preset number, then the small correction category at the target initial moment of the target height is determined as a minor correction, and the small correction category at the consecutive moments after the target initial moment of the target height is determined as a major correction, and the small correction category at moments other than the target initial moment of the target height and the consecutive moments after the target initial moment of the target height is determined as not requiring correction.

[0155] It is understandable that there are four minor correction categories, namely no correction required, slight correction, moderate correction and major correction, corresponding to the four levels of wind direction change. In Table 7, 0 means no correction required, 1 means slight correction, 2 means moderate correction, and 3 means major correction.

[0156] The first preset number is a preset threshold value used to determine the degree of influence of wind direction change on the small correction category, and can be reasonably set according to actual needs. The embodiment of the present invention does not make any specific limitation on this.

[0157] In order to better understand step S512, an example is given below in conjunction with Table 7:

[0158] Table 7. Small correction categories of numerical weather forecast data

[0159]

[0160]

[0161] For example: assuming that the first preset number is 8, since 2024 / 4 / 29 16:00 is the initial moment, and the main wind direction category at this moment is not the main wind direction and is not an abnormal moment, the small correction category at 2024 / 4 / 29 16:00 is a slight correction, and then the number of wind direction classifications at subsequent consecutive moments that are not the main wind direction category is determined. From Table 7, it can be seen that there are only 2 in total (2024 / 4 / 29 17:00 and 2024 / 4 / 29 18:00), which is less than the first preset number, then the small correction categories at 2024 / 4 / 29 17:00 and 2024 / 4 / 29 18:00 are moderate corrections, and the small correction categories of all moments after 2024 / 4 / 29 18:00 are determined as not requiring correction.

[0162] S513, according to the comprehensive working condition category and the small and micro correction category at each moment of the target height, determine the mapping relationship between the power at each moment of the target height and the total power through a preset coefficient calculation matrix; wherein the preset coefficient calculation matrix includes the comprehensive working condition category, the small and micro correction category, and the mapping relationship between the power obtained according to the comprehensive working condition category and the small and micro correction category and the total power;

[0163] Specifically, a preset coefficient calculation matrix is ​​given as an example, as shown in Table 8 below:

[0164] Table 8 Coefficient calculation matrix

[0165]

[0166] According to Table 8, it can be known that the horizontal direction represents the category of small corrections, 0 can be understood as no correction is required, 1 can be understood as a slight correction, 2 can be understood as a moderate correction, and 3 can be understood as a significant correction. The vertical direction represents the comprehensive operating condition category, a total of 9 categories, which have been mentioned in the above step S400 and will not be repeated here. In addition, type1, type2, type3 and type4 in Table 7 represent an operating condition respectively, and each operating condition corresponds to a ratio of the current wind farm power to the total power. Through the geometric relationship (i.e., mapping relationship) between type1, type2, type3 and type4, and then substituting the ratio of the wind farm power to the total power corresponding to type1, type2, type3 and type4, the average ratio of the wind farm power to the total power is finally obtained.

[0167] For example, at 16:00 on 2024 / 4 / 29, the wind direction angle is 310.43 degrees, the wind speed is 3.02 m / s, the wind direction category is 14, the time category is 3, the comprehensive working condition category is 2, and the minor correction category is 1. According to Table 7, the moment of 2024 / 4 / 29 16:00 (wind speed is 3.02 m / s, wind direction category is 14, time category is 3, comprehensive working condition category is 2, and minor correction category is 1) corresponds to the working condition type 1, that is, the mapping relationship between the power and the total power at 16:00 on 2024 / 4 / 29 is type 1.

[0168] S514, matching the predicted wind speed at each moment of the corrected target height with at least one pre-constructed curve of the ratio of wind speed-power to total power, and determining the ratio of power to total power at each moment of at least one target height; wherein the pre-constructed curve of the ratio of wind speed-power to total power is used to characterize the mapping relationship between the wind speed at different moments and the corresponding ratio of power to total power;

[0169] It should be noted that, when using the wind speed binning method, the predicted wind speed is first classified into 0-3, 3-12, and 12-75. 1m / s is used for classification during 0-3m / s, 0.1m / s is used for classification during 3-12m / s, and 1m / s is used for classification during 12-75m / s. In other words, the wind speed is classified in a refined manner, so that the ratio of the current wind farm power to the total power corresponding to the wind speed at the refined scale can be determined.

[0170] Specifically, Figure 4 It is a curve diagram drawn based on the data in Table 9. The following is an exemplary mapping relationship table between wind speed-power and total power:

[0171] Table 9 Wind speed-power and total power mapping relationship table

[0172]

[0173]

[0174]

[0175] According to Table 8 and Figure 4 It can be known that, for example, the wind speed at 16:00 on 2024 / 4 / 29 is 3.02m / s, which corresponds to type1, type2, type3 and type4, and at this time, the ratio of the current wind farm power to the total power corresponding to type1, type2, type3 and type4 is 1.

[0176] In one embodiment, the wind speed in Table 9 is the historical average wind speed, and the ratio of power to total power (i.e., type 1, type 2, type 3, and type 4) in Table 9 is also the ratio of historical power to historical total power. Therefore, the pre-constructed curve of the ratio of wind speed-power to total power is obtained based on the fitting of historical data. The following is the fitting process of the pre-constructed curve of the ratio of wind speed-power to total power:

[0177] Step 1 (select the fitting function):

[0178] You can consider using piecewise function or piecewise polynomial fitting and make adjustments based on actual conditions.

[0179] Step 2 (select fitting method):

[0180] Least squares method: Applicable to piecewise polynomial fitting.

[0181] Piecewise function fitting: You need to write a custom function for fitting.

[0182] Step 3 (fitting using software):

[0183] Python: Use the numpy library for polynomial fitting and write custom functions for piecewise function fitting.

[0184] MATLAB: Use the polyfit function for polynomial fitting and write custom functions for piecewise function fitting.

[0185] Step 4 (evaluation of fitting effect):

[0186] R^2 value: Goodness of fit index. The closer the value is to 1, the better the fit effect.

[0187] Residual analysis: Observe the residual distribution and determine whether the fitted model is appropriate.

[0188] S515, calculating the ratio of the power at each moment of at least one target height to the total power according to the mapping relationship between the power at each moment of the target height and the total power, and obtaining the average ratio of the power at each moment of the target height to the total power.

[0189] Specifically, the wind speed of 3.02 m / s at 16:00 on 2024 / 4 / 29 only corresponds to the type 1 condition, so the ratio of the current wind farm power to the total power corresponding to type 1 is assigned to it, that is, the average ratio of the current wind farm power to the total power corresponding to the wind speed of 3.02 m / s is 1. For the calculation of the ratio of the current wind farm power to the total power at other times, refer to Table 8 and Figure 4 As shown, no further description is given here.

[0190] S600, calculating the product of the total power at each moment of the target height and the average ratio of the power to the total power, to obtain the power at each moment of the target height of the wind farm.

[0191] In one embodiment, step S600 is specifically calculated using the following formula:

[0192] in, Indicates P i The predicted power at a given time point, Indicates P i The wind speed V corresponding to the time point j The total power of the corresponding wind farm is Indicates P i At a certain moment, the wind speed V j 、Wind direction D i and time T m The average ratio of wind farm power to total power obtained by the comprehensive classification method.

[0193] Specifically, in order to better show the power prediction results at each moment, please refer to the following Table 9:

[0194]

[0195]

[0196]

[0197] After predicting the predicted power at each time of the target height, the actual power at each time of the target height is obtained. The relationship between each time of the target height and the predicted power and the actual power is as follows: Figure 5 As shown, the prediction accuracy is then calculated using the following formula: Among them, n represents the number of statistical samples within the statistical time, i represents the i-th statistical sample, P Mirepresents the actual power of the i-th sample of the wind farm, P Pi It represents the predicted power of the i-th sample of the wind farm, and Cap represents the installed capacity of the wind farm.

[0198] The calculated accuracy can reach over 85%, and the error between the predicted power and the actual power is approximately within 0.02m / s-0.3m / s.

[0199] Beneficial effects of the present invention:

[0200] (1) More targeted: The present invention focuses on the prediction of wind farm power generation for a specific time period (such as hourly or daily). Compared with the prior art, it is more focused on the needs of wind farms and avoids predicting redundant information for other weather phenomena and a wider geographical range.

[0201] (2) Improved prediction accuracy: By relying on the wind farm’s own data, the present invention can more accurately predict the power generation, especially in terms of considering the impact of local wind farms. Compared with the existing technology, the prediction accuracy is improved in the face of the complexity of atmospheric movement.

[0202] (3) Finer time scale: The present invention can realize power generation prediction within the next few hours to days. Compared with the existing technology, the prediction time range is finer and can better meet the short-term operation needs of the wind farm.

[0203] (4) Reduced technical complexity: The present invention adopts relatively simple statistical methods and empirical models, which greatly reduces the technical complexity compared to the complex atmospheric motion equations and numerical methods used in the prior art, making it easier to implement and apply.

[0204] Embodiment 2

[0205] Based on the same inventive concept, Figure 6 As shown, the embodiment of the present invention also provides a short-term wind farm power prediction device 200, comprising:

[0206] The data acquisition module 210 is used to obtain the predicted wind speed and predicted wind direction angle of the wind farm at a target height at multiple times;

[0207] The category recognition module 220 is used to perform different category recognition on the predicted wind direction angle of the target height at each moment, and determine the time category of each predicted wind direction angle of the target height and the wind direction category of each moment of the target height;

[0208] The wind speed correction module 230 is used to identify and correct the predicted wind speed corresponding to the abnormal moment among multiple moments of the target height according to the predicted wind direction angle at each moment of the target height and the wind direction category at each moment of the target height, so as to obtain the corrected predicted wind speed at each moment of the target height;

[0209] The power matching module 240 is used to match the predicted wind speed at each moment of the target height after correction with the pre-constructed wind speed-total power curve to determine the total power at each moment of the target height; wherein the pre-constructed wind speed-total power curve is used to characterize the mapping relationship between the wind speed at different moments and its corresponding total power;

[0210] The ratio calculation module 250 is used to determine the average ratio of the power at each moment of the target height to the total power according to the corrected predicted wind speed at each moment of the target height, the time category of each predicted wind direction angle at the target height, and the wind direction category at each moment of the target height;

[0211] The power calculation module 260 is used to calculate the product of the total power at each moment of the target height and the average ratio of the power to the total power to obtain the power at each moment of the target height of the wind farm.

[0212] It should be understood that the device corresponds to the above-mentioned short-term wind farm power prediction method embodiment, and can execute the various steps involved in the above-mentioned method embodiment. The specific functions of the device can be found in the above description. To avoid repetition, the detailed description is appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or fixed in the operating system (OS) of the device.

[0213] Embodiment 3

[0214] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, including: a processor and a memory, the memory storing machine-readable instructions executable by the processor, and the machine-readable instructions executing the above-mentioned short-term wind farm power prediction method when executed by the processor.

[0215] In a typical configuration, an electronic device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0216] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0217] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0218] Embodiment 4

[0219] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on a computer, the computer executes the above-mentioned short-term wind farm power prediction method.

[0220] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0221] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0222] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0223] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0224] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0225] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0226] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0227] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A short-term wind farm power prediction method, characterized in that: include: Obtain the predicted wind speed and wind direction angle of the wind farm at multiple times at the target height; Different categories of predicted wind direction angles at target heights at various times are identified, and the time categories of the predicted wind direction angles at target heights and the wind direction categories at various times at target heights are determined; According to the predicted wind direction angle at each moment of the target height and the wind direction category at each moment of the target height, the predicted wind speed corresponding to the abnormal moment among multiple moments of the target height is identified and corrected to obtain the corrected predicted wind speed at each moment of the target height; Matching the predicted wind speed at each moment of the corrected target height with a pre-constructed wind speed-total power curve to determine the total power at each moment of the target height; wherein the pre-constructed wind speed-total power curve is used to characterize the mapping relationship between the wind speed at different moments and its corresponding total power; Determine the average ratio of the power at each moment of the target height to the total power according to the corrected predicted wind speed at each moment of the target height, the time category of each predicted wind direction angle at the target height, and the wind direction category at each moment of the target height; The product of the total power at each moment of the target height and the average ratio of the power to the total power is calculated to obtain the power at each moment of the target height of the wind farm.

2. The short-term wind farm power prediction method according to claim 1, characterized in that: The predicted wind speed and wind direction angle of the wind farm at the target height at multiple times are determined by the following method: respectively obtaining the predicted wind speed and the predicted wind direction angle at multiple moments at adjacent heights below the target height and adjacent heights above the target height in the wind farm; For each moment: If the predicted wind speed at the adjacent height below the target height is less than or equal to, or greater than or equal to, the predicted wind speed at the adjacent height above the target height, then based on the ratio of the target height to the adjacent height below the target height, the preset surface friction coefficient, and the predicted wind speed at the adjacent height below the target height, the predicted wind speed at the target height is obtained, and the predicted wind direction angle below the target height is used as the predicted wind direction angle at the target height; or If the predicted wind speeds at the adjacent height below the target height and the adjacent height above the target height are both greater than the preset wind speed, the predicted wind speed at the adjacent height above the target height shall be used as the predicted wind speed at the target height, and the predicted wind direction angle at the adjacent height above the target height shall be used as the predicted wind direction angle at the target height.

3. The short-term wind farm power prediction method according to claim 2, characterized in that: Based on the ratio of the target height to the adjacent height below the target height, the preset surface friction coefficient, and the predicted wind speed of the adjacent height below the target height, the predicted wind speed at the target height is obtained, including: The following formula is used to calculate the ratio of the target height to the adjacent height below the target height, the preset surface friction coefficient, and the predicted wind speed at the adjacent height below the target height to obtain the predicted wind speed at the target height; Among them, V c represents the predicted wind speed at the target height, V represents the predicted wind speed at the adjacent height below the target height, and H c represents the target height, H represents the adjacent height below the target height, and a represents the preset surface friction coefficient.

4. The short-term wind farm power prediction method according to claim 1, characterized in that: Different categories of predicted wind direction angles at target height at each moment are identified, and the time category of each predicted wind direction angle at target height and the wind direction category at each moment at target height are determined, including: According to a plurality of predicted wind direction angles at the target height, the predicted wind direction angles at each moment at the target height are identified as wind direction categories, and the wind direction categories at each moment at the target height are determined; According to multiple moments of the target height, time categories of the moments of the predicted wind direction angles at the target height are identified, and time categories of the predicted wind directions at the target height are determined.

5. The short-term wind farm power prediction method according to claim 1, characterized in that: According to the predicted wind direction angle at each moment of the target height and the wind direction category at each moment of the target height, the predicted wind speed corresponding to the abnormal moment among multiple moments of the target height is identified and corrected to obtain the corrected predicted wind speed at each moment of the target height, including: Calculate the ratio of the number of each wind direction category at the target height at the corresponding moment to the total number of wind direction categories at the target height at multiple moments, and determine the wind direction category whose ratio is greater than the preset ratio as the main wind direction category; Calculate the difference between the predicted wind direction angle at each moment of the target height and the adjacent moments to obtain the predicted wind direction angle difference at each moment of the target height; Determine the moment when the wind direction angle difference among multiple moments of the target height is greater than the preset wind direction angle difference and the wind direction category is not the main wind direction category as the initial abnormal moment of the target height; Determine the abnormal moment of the target height when any adjacent moment among the initial abnormal moments is the initial abnormal moment as the abnormal moment of the target height; Correct the predicted wind speed corresponding to the abnormal moment of the target height.

6. The short-term wind farm power prediction method according to claim 5, characterized in that: According to the corrected predicted wind speed at each moment of the target height, the time category of each predicted wind direction angle at the target height, and the wind direction category at each moment of the target height, the average ratio of the power at each moment of the target height to the total power is determined, including: Matching the time category of each predicted wind direction angle at the target height and the wind direction category at each moment at the target height with a preset comprehensive classification matrix to obtain the comprehensive working condition category at each moment at the target height; wherein the preset comprehensive classification matrix includes different comprehensive working condition categories corresponding to different time categories and different wind direction categories; According to the wind direction category at each moment of the target height and the abnormal moment of the target height, identify the small correction category at each moment of the target height; According to the comprehensive working condition category and the small and micro correction category at each moment of the target height, the mapping relationship between the power at each moment of the target height and the total power is determined by a preset coefficient calculation matrix; wherein the preset coefficient calculation matrix includes the comprehensive working condition category, the small and micro correction category, and the mapping relationship between the power obtained according to the comprehensive working condition category and the small and micro correction category and the total power; Matching the predicted wind speed at each moment of the corrected target height with at least one pre-constructed curve of the ratio of wind speed-power to total power, and determining the ratio of power to total power at each moment of at least one target height; wherein the pre-constructed curve of the ratio of wind speed-power to total power is used to characterize the mapping relationship between the wind speed at different moments and the corresponding ratio of power to total power; According to the mapping relationship between the power at each moment of the target height and the total power, the ratio of the power at each moment of at least one target height to the total power is calculated to obtain the average ratio of the power at each moment of the target height to the total power.

7. The short-term wind farm power prediction method according to claim 6, characterized in that: According to the wind direction category at each moment of the target height and the abnormal moment of the target height, the minor correction category at each moment of the target height is identified, including: If the wind direction category at the initial moment of the target height is the main wind direction category or the initial moment of the target height is an abnormal moment, the first subsequent moment when the wind direction category is not the main wind direction category and is not an abnormal moment is determined as the target initial moment of the target height; In a case where the wind direction category at the target initial moment of the target height is not the main wind direction category and is not an abnormal moment, if after the target initial moment of the target height, the wind direction categories corresponding to multiple consecutive moments are not the main wind direction category, and the number of the multiple consecutive moments is a first preset number, then the small correction category at the target initial moment of the target height is determined as a slight correction, and the small correction category at the multiple consecutive moments after the target initial moment of the target height is determined as a slight correction, and the small correction category at the moments other than the target initial moment of the target height and the multiple consecutive moments after the target initial moment of the target height is determined as not requiring correction; or In the case where the wind direction category at the target initial moment of the target height is not the main wind direction category and is not an abnormal moment, if after the target initial moment of the target height, the wind direction categories corresponding to multiple consecutive moments are not the main wind direction category, and the number of the multiple consecutive moments is less than a first preset number, then the small correction category at the target initial moment of the target height is determined as a slight correction, and the small correction category at the multiple consecutive moments after the target initial moment of the target height is determined as a medium correction, and the small correction category at the moments other than the target initial moment of the target height and the multiple consecutive moments after the target initial moment of the target height is determined as not requiring correction; or When the wind direction category at the target initial moment of the target height is not the main wind direction category and is not an abnormal moment, if after the target initial moment of the target height, the wind direction categories corresponding to multiple consecutive moments are not the main wind direction category, and the number of consecutive moments is greater than a first preset number, then the small correction category at the target initial moment of the target height is determined as a minor correction, and the small correction category at the consecutive moments after the target initial moment of the target height is determined as a major correction, and the small correction category at moments other than the target initial moment of the target height and the consecutive moments after the target initial moment of the target height is determined as not requiring correction.

8. A short-term wind farm power prediction device, characterized in that: include: A data acquisition module is used to obtain the predicted wind speed and predicted wind direction angle of the wind farm at a target height at multiple times; A category recognition module is used to perform different category recognition on the predicted wind direction angles at the target height at each moment, and determine the time category of each predicted wind direction angle at the target height and the wind direction category at each moment at the target height; A wind speed correction module, for identifying and correcting the predicted wind speed corresponding to the abnormal moment among multiple moments of the target height according to the predicted wind direction angle at each moment of the target height and the wind direction category at each moment of the target height, so as to obtain the corrected predicted wind speed at each moment of the target height; A power matching module is used to match the predicted wind speed at each moment of the corrected target height with a pre-constructed wind speed-total power curve to determine the total power at each moment of the target height; wherein the pre-constructed wind speed-total power curve is used to characterize the mapping relationship between the wind speed at different moments and its corresponding total power; A ratio calculation module, for determining an average ratio of the power at each moment of the target height to the total power according to the corrected predicted wind speed at each moment of the target height, the time category of each predicted wind direction angle at the target height, and the wind direction category at each moment of the target height; The power calculation module is used to calculate the product of the total power at each moment of the target height and the average ratio of the power to the total power, so as to obtain the power at each moment of the target height of the wind farm.

9. An electronic device, characterized in that: include: A processor and a memory, the memory storing machine programs executable by the processor The machine-readable instructions are used to perform the short-term wind farm power prediction method according to any one of claims 1 to 7 when the machine-readable instructions are executed by the processor.

10. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on a computer, the computer is enabled to execute the short-term wind farm power forecasting method according to any one of claims 1 to 7.

Images