Method, device and equipment for cleaning wind measurement data of wind power plant and medium

Abstract

The invention belongs to the technical field of wind measurement data cleaning, and particularly relates to a wind power plant wind measurement data cleaning method, device and equipment and a medium. The method comprises the following steps of: firstly, carrying out preliminary screening on data through threshold value checking, wind speed increasing and wind shear checking; and then the high-resolution reanalysis data and meteorological station data are combined, the atmospheric stability is judged, a wind profile formula is corrected, and the data are cleaned according to the atmospheric stability and the theoretical wind speed. And finally, the data is further screened and filled based on spatial and temporal distribution characteristics of the data, so that the reliability of the data is improved. The accuracy of the wind measurement data of the wind power plant is improved, and powerful data guarantee is provided for wind power prediction.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind measurement data cleaning, and in particular relates to a method, device, equipment and medium for cleaning wind measurement data of a wind farm. Background Art

[0002] Wind power forecasting relies on historical power generation data, meteorological conditions and equipment information of wind farms, and predicts future wind power output by establishing a relationship between wind speed and wind power output. However, actual wind measurement data is often inaccurate or missing due to factors such as sensor failure, data transmission problems and environmental interference, which affects the accuracy of the prediction model. Therefore, it is particularly important to ensure data quality and effective cleaning. Most of the existing data repair methods are limited to a single site or short-term time series, lacking cross-site and long-term spatiotemporal correlation repair, which affects the repair accuracy and model stability. In addition, it is difficult to obtain high-quality data for wind farms in remote areas due to insufficient wind towers. Reanalysis data (such as ERA5) and meteorological station data can effectively make up for the gaps and errors in wind measurement data and provide more accurate wind speed forecasts. Finally, the change of wind speed at different heights is affected by atmospheric stability, but the existing repair method ignores this factor, resulting in low repair accuracy. Through accurate atmospheric stability analysis and wind speed profile modeling, the wind speed repair accuracy can be improved, thereby improving the accuracy of wind power forecasting. Summary of the invention

[0003] The object of the present invention is to provide a method, device, equipment and medium for cleaning wind farm wind measurement data, so as to solve the problem of cleaning wind measurement data in the prior art.

[0004] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for cleaning wind farm wind measurement data, comprising the following steps: Acquire original wind measurement data of the current wind farm, and select first wind measurement data satisfying a first preset threshold and a first preset jump value from the original wind measurement data; Performing wind speed increment and wind shear verification on the first wind measurement data to obtain second wind measurement data that passes the verification; Determine the Monin-Obukhov length moment by moment; perform stability correction on the wind profile formula according to the Monin-Obukhov length to obtain a revised wind profile formula; determine the theoretical wind speed of the current wind farm at different heights moment by moment according to the revised wind profile formula; perform data screening according to the wind speed deviation between the theoretical wind speed and the second wind measurement data to obtain the third wind measurement data whose wind speed deviation is within a preset deviation range; Verify the wind direction deflection law of the third wind measurement data moment by moment based on the Monin-Obukhov length to obtain fourth wind measurement data that meets a preset wind direction change threshold; Calculate the rolling mean and the rolling standard deviation of the fourth wind measurement data in the given rolling window respectively; calculate the deviation range according to the rolling mean and the rolling standard deviation, and select the fifth wind measurement data that meets the deviation range; Obtain the weighted average wind speed and weighted average wind direction of multiple neighboring wind power stations within a preset distance of the current wind farm; calculate the wind speed deviation value and wind direction deviation value of the fifth wind measurement data according to the weighted average wind speed and weighted average wind direction; and screen out the sixth wind measurement data that meets the preset wind speed deviation threshold and wind direction deviation threshold according to the wind speed deviation value and wind direction deviation value; The missing data in the sixth wind measurement data are filled to obtain the final wind measurement data after data cleaning.

[0005] Furthermore, the wind profile formula is corrected for stability according to the Monin-Obukhov length to obtain a revised wind profile formula. The theoretical wind speed of the current wind farm at different heights is determined moment by moment according to the revised wind profile formula, where: The wind profile formula includes the logarithmic wind profile formula and the power-law wind profile formula; the logarithmic wind profile formula is corrected according to the Monin-Obukhov length and the correction function to obtain the first correction formula; the power-law wind profile formula is corrected according to the Monin-Obukhov length and the correction power exponent to obtain the second correction formula; The reference height and reference wind speed of the current wind farm are determined moment by moment; and the theoretical wind speed of the current wind farm at different heights is calculated moment by moment based on the reference height and reference wind speed, and the first correction formula or the second correction formula.

[0006] Furthermore, the reference height and reference wind speed of the current wind farm are determined, including: Determine the geographic location of wind towers in current wind farms; If a data reference point exists within a preset distance of the geographical location, the 10-meter wind speed data of the data reference point is obtained moment by moment; it is determined whether the deviation between the data reference point and the 10-meter wind speed data of the wind tower meets the preset deviation threshold; if the wind speed deviation does not meet the deviation threshold, the 10-meter wind speed data of the data reference point is used as the reference wind speed, and 10 meters is used as the reference height; wherein the data reference point is a meteorological station, or the nearest grid point determined according to the resolution of the reanalysis data; If there is no data reference point within the preset distance of the geographical location, or the deviation between the data reference point and the 10-meter wind speed data of the wind tower meets the preset deviation threshold, a height is selected from the current wind farm at each moment as the reference height, and the wind speed at the corresponding height is used as the reference wind speed.

[0007] Furthermore, the Monin-Obukhov length of the current wind farm is determined moment by moment, including: Determine the reference height and reference wind speed of the current wind farm moment by moment, and calculate the friction speed based on the reference height and reference wind speed; Determine the current sensible heat flux of the wind farm moment by moment; The Monin-Obukhov length of the current wind farm is calculated moment by moment according to the friction velocity and sensible heat flux of the current wind farm.

[0008] Furthermore, the weighted average wind speed and weighted average wind direction of multiple neighboring wind power stations within a preset distance of the current wind farm are obtained, including: Determine a plurality of neighboring wind farms within a preset distance of the current wind farm; Determine the weight of each adjacent wind power station according to the distance between each adjacent wind power station and the current wind farm; According to the weights of each adjacent wind power station, the weighted average wind speed and weighted average wind direction of the adjacent wind power stations are calculated respectively.

[0009] Furthermore, the missing data in the sixth wind measurement data are filled to obtain the final wind measurement data after data cleaning, including: At a certain moment, if there is wind measurement data at least at a certain height of the current wind farm, the theoretical wind measurement data is calculated according to the wind profile formula correction form, and the missing wind measurement data is filled with the theoretical wind measurement data; if the wind measurement data at all heights of the current wind farm are missing, the wind measurement data at different times at the same height are interpolated for time series data; The wind measurement data after time series data interpolation processing is filled with weighted average of neighboring wind power stations to obtain the final wind measurement data.

[0010] In a second aspect, the present invention provides a wind farm wind measurement data cleaning device, comprising: A first cleaning module is used to obtain original wind measurement data of the current wind farm, and filter out first wind measurement data that meets a first preset threshold and a first preset jump value from the original wind measurement data; A second cleaning module is used to perform wind speed increment and wind shear verification on the first wind measurement data to obtain second wind measurement data that passes the verification; The third cleaning module is used to determine the Monin-Obukhov length of the current wind farm moment by moment; correct the wind profile formula according to the Monin-Obukhov length to obtain the wind profile formula correction formula; determine the theoretical wind speed of the current wind farm at different heights according to the wind profile formula correction formula; perform data screening according to the wind speed deviation between the theoretical wind speed and the second wind measurement data, and obtain the third wind measurement data whose wind speed deviation is within a preset deviation range; A fourth cleaning module verifies the wind direction deflection law of the third wind measurement data moment by moment based on the Monin-Obukhov length to obtain fourth wind measurement data that meets a preset wind direction change threshold; A fifth cleaning module is used to calculate the rolling mean and the rolling standard deviation of the fourth wind measurement data in a given rolling window respectively; calculate the deviation range according to the rolling mean and the rolling standard deviation, and select the fifth wind measurement data that meets the deviation range; The sixth cleaning module is used to obtain the weighted wind speed average value and the weighted wind direction average value of multiple neighboring wind power stations within a preset distance of the current wind farm; calculate the wind speed deviation value and the wind direction deviation value of the fifth wind measurement data according to the weighted wind speed average value and the weighted wind direction average value; and screen out the sixth wind measurement data that meets the preset wind speed deviation threshold and wind direction deviation threshold according to the wind speed deviation value and the wind direction deviation value; The seventh cleaning module is used to fill in the missing data in the sixth wind measurement data to obtain the final wind measurement data after data cleaning.

[0011] Furthermore, in the third cleaning module, the wind profile formula is corrected for stability according to the Monin-Obukhov length to obtain a corrected wind profile formula; the theoretical wind speed of the current wind farm at different heights is determined moment by moment according to the corrected wind profile formula, wherein: The wind profile formula includes the logarithmic wind profile formula and the power-law wind profile formula; the logarithmic wind profile formula is corrected according to the Monin-Obukhov length and the correction function to obtain the first correction formula; the power-law wind profile formula is corrected according to the Monin-Obukhov length and the correction power exponent to obtain the second correction formula; The reference height and reference wind speed of the current wind farm are determined moment by moment; and the theoretical wind speed of the current wind farm at different heights is calculated moment by moment based on the reference height and reference wind speed, and the first correction formula or the second correction formula.

[0012] According to a third aspect of the present invention, an electronic device is provided, comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the wind farm wind measurement data cleaning method as described above.

[0013] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the wind farm wind measurement data cleaning method as described above is implemented.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention combines high-resolution reanalysis data and meteorological station data, based on relevant theories such as atmospheric stability and boundary layer wind profiles, and improves the accuracy of wind measurement data through a multi-step data cleaning process, including preliminary screening, wind speed increment and wind shear verification, theoretical wind speed verification, rolling deviation verification, adjacent wind power station data verification, and abnormal and vacant data filling. Each step carries out targeted processing for possible data anomalies or errors, thereby effectively reducing the impact of inaccurate or missing data on wind power forecasting. The ability to improve the accuracy of wind power forecasting is of great significance to the operation and maintenance of wind farms, the stable operation of power grids, and the full utilization of renewable energy.

[0015] For abnormal and missing data, the present invention proposes a method of filling theoretical wind measurement data and time series data interpolation processing based on a wind profile model, as well as a weighted average filling method of neighboring wind power stations.

[0016] The present invention improves the robustness of the method by introducing data of neighboring wind power stations for verification and filling. In the absence of sufficient local data reference points, more extensive data resources can be used to optimize data quality.

[0017] In summary, the present invention solves the problem of inaccurate or missing wind measurement data in the prior art through a wind farm wind measurement data cleaning method, and provides more reliable data support for wind power prediction. A wind farm wind measurement data cleaning device, electronic device and computer-readable storage medium provided by the present invention also solve the problems raised in the background technology section. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 A schematic diagram of a flow chart of a method for cleaning wind farm wind measurement data according to an embodiment of the present invention; Figure 2 This is a structural block diagram of a wind farm wind measurement data cleaning device according to an embodiment of the present invention; Figure 3 The present invention is a structural block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0020] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present application belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention.

[0021] Example 1 like Figure 1 As shown, a method for cleaning wind farm wind measurement data includes the following steps: S1. Acquire original wind measurement data of the current wind farm, and select first wind measurement data satisfying a first preset threshold and a first preset jump value from the original wind measurement data.

[0022] Specifically, step S1 includes: obtaining original wind measurement data at different heights of the wind farm, which is long time series data. Verifying the abnormal threshold and abnormal jump value of the original wind measurement data, recording the verified data as the first wind measurement data, and marking the data that fails the verification as NaN.

[0023] As an example, according to the Regulations on Real-time Monitoring of Solar Energy Resources in Photovoltaic Power Stations (Energy Standard, NB / T 32012-2013), the normal threshold ranges for wind speed and wind direction are 0-60 respectively. m / s In plain areas without significant terrain obstruction, the wind speed ranges at 10m, 30m, 50m and 70m under normal weather conditions are approximately: 2-8 m / s , 3-10 m / s , 4-12 m / s and 5-14 m / s , and can reach 30 respectively under extreme weather conditions m / s , 40 m / s , 45 m / s and 50 m / s The wind measurement data should be within the normal threshold range, otherwise it is abnormal over-threshold data. In addition, according to the "Regulations on Real-time Monitoring of Solar Energy Resources in Photovoltaic Power Stations" (Energy Industry Standard, NB / T 32012-2013), the maximum change value of wind speed in 5 minutes should not exceed 20 m / s , the jump value of wind direction should not exceed 360°. The jump value of continuous data should not exceed this standard, otherwise it is abnormal jump data. The data verified in this step will be checked in the next step.

[0024] S2. Perform wind speed increment and wind shear verification on the first wind measurement data to obtain second wind measurement data that passes the verification.

[0025] Specifically, step S2 includes: using the wind speed increasing law and the horizontal wind shear rate (α) to quantify the wind speed variation between different heights, obtaining the second wind measurement data that has passed the verification, and marking the data that has not passed the verification as NaN.

[0026] It should be noted that the wind speed will gradually increase with height, so the wind speed at different heights is checked at each time step to see if it complies with the increasing law. If the wind speed at a certain height does not increase, the wind speed at that height is marked as NaN.

[0027] In addition, using α To quantify the wind speed variation between different heights. The specific formula is: (1) Among them, z1 and z2 are adjacent heights, U z1 and U z2 is the wind speed at the corresponding height. Under normal atmospheric conditions, the shear rate of wind speed near the ground is usually not too large. If the shear rate of a certain height segment is far beyond the reasonable range (0.1~0.5 ( m / s) / m ), it indicates that the data is inaccurate. The data verified in this step will be checked in the next step. S3. Determine the Monin-Obukhov length moment by moment; perform stability correction on the wind profile formula according to the Monin-Obukhov length to obtain a revised wind profile formula; determine the theoretical wind speed of the current wind farm at different heights moment by moment according to the revised wind profile formula; perform data screening based on the wind speed deviation between the theoretical wind speed and the second wind measurement data to obtain the third wind measurement data whose wind speed deviation is within a preset deviation range.

[0028] Specifically, determining the Monin-Obukhov length of the current wind farm moment by moment includes: determining a reference height and a reference wind speed of the current wind farm moment by moment, and calculating a friction speed based on the reference height and the reference wind speed; determining a sensible heat flux at a corresponding moment; and calculating the Monin-Obukhov length according to the friction speed and the sensible heat flux at the corresponding moment.

[0029] Specifically, the reference height and reference wind speed of the current wind farm are determined moment by moment, including: determining the geographical location of the wind tower in the current wind farm; if there is a data reference point within a preset distance of the geographical location, obtaining the 10-meter wind speed data of the data reference point at the corresponding moment; judging whether the deviation between the data reference point and the 10-meter wind speed data of the wind tower meets the preset deviation threshold; if the wind speed deviation does not meet the deviation threshold, taking the 10-meter wind speed data of the data reference point at the corresponding moment as the reference wind speed, and 10 meters as the reference height; wherein the data reference point is a meteorological station, or the nearest grid point determined according to the resolution of the reanalysis data; if there is no data reference point within the preset distance of the geographical location, or the deviation between the data reference point and the 10-meter wind speed data of the wind tower meets the preset deviation threshold, selecting a height at the corresponding moment from the current wind farm as the reference height, and the wind speed at the corresponding height as the reference wind speed.

[0030] As an example, the geographical location information of the weather station is used to determine the weather station closest to the wind tower of the current wind farm (the default maximum distance is 30 kilometers. Beyond this distance, it is considered that there is no weather station that meets the requirements). If there is no weather station that meets the requirements, the latitude and longitude information of the reanalysis data is combined to determine the nearest grid point to the wind tower of the wind power station. With the current moment as the center, a time window (such as 5 minutes) is set to solve the problem of time misalignment that may exist between different data sources. For the current wind farm, if the nearest weather station exists, obtain the 10-meter wind data closest to the current moment within the specified time window moment by moment. If there is no weather station data, obtain the 10-meter wind data in the reanalysis data in the same way. Compare the 10-meter wind speed of the wind tower with the difference between the weather station or reanalysis data. If the wind speed difference is greater than the set threshold, select the 10-meter wind speed in the weather station or reanalysis data as the reference wind speed. Otherwise, the 10-meter wind speed of the wind tower is selected as the reference wind speed. At this time, the reference height If there is no weather station or reanalysis data, select a height from the wind farm's own data as (lower height is preferred), the wind speed at the corresponding height is If the reference height and reference wind speed are both valid data, proceed to the next step.

[0031] Specifically, the friction speed is calculated based on the reference height and reference wind speed (unit: m / s ): (2) Where H is the sensible heat flux, k is the von Kármán constant, which is approximately 0.4; Indicates the roughness length of the surface. You can look up the table according to the surface type. For details, refer to Table 1.

[0032] Table 1 Reference table of land use types and surface roughness length in China

[0033] Specifically, the sensible heat flux of the current wind farm is determined moment by moment, including: taking the current moment as the center, setting a time window (such as 5 minutes) to solve the time misalignment problem that may exist between different data sources. Dynamically select multi-source data to calculate the sensible heat flux H (unit: W / m 2 ), that is, the amount of heat passing through a unit area per unit time, and its calculation formula is as follows: (3) Among them, C H represents the heat exchange coefficient, which is approximately 0.001; U represents the ground wind speed (unit: m / s );T s and T a Represents the surface temperature and air temperature respectively (unit: K ).

[0034] Optionally, for a certain wind power station, if there is a nearest meteorological station (the distance between the two is no more than 30 kilometers), obtain the relevant meteorological observation data closest to the current time in the specified time window moment by moment. If there is no meteorological station data, determine the reanalysis grid point closest to the wind power station, and calculate H by obtaining the corresponding grid point data. If the reanalysis data itself already includes the variable H, the above formula is no longer used for calculation.

[0035] Specifically, the Monin-Obukhov length of the current wind farm is determined moment by moment, including: The Monin-Obukhov length L is calculated by using H. The calculation formula of Monin-Obukhov length L is as follows: (4) Where g is the acceleration due to gravity, which is approximately 9.81 m / s 2 ; T represents the atmospheric temperature (unit: K ); ρ represents air density, which is 1.225 kg / m 3 ;c p represents the specific heat capacity of air, which is approximately 1004 J / (kg⋅K) .

[0036] ① Unstable conditions (L<0): Surface heating triggers strong turbulence, with convection dominating.

[0037] ② Neutral conditions (L→∞): The surface heat flux is close to zero, and the turbulence is moderate, mainly caused by wind speed shear.

[0038] ③ Stable conditions (L>0): Surface cooling induces weak turbulence, and stratification is dominant.

[0039] Specifically, the wind profile formula includes the logarithmic wind profile formula and the power-law wind profile formula, which determine the theoretical wind speed of the current wind farm at different heights moment by moment, including: According to the Monin-Obukhov length and the correction function, the logarithmic wind profile formula is corrected to obtain the first correction form; according to the Monin-Obukhov length and the corrected power exponent, the power-law wind profile formula is corrected to obtain the second correction form; the reference height and reference wind speed of the current wind farm are determined moment by moment; according to the reference height and reference wind speed, as well as the first correction form or the second correction form, the theoretical wind speed of the current wind farm at different heights is calculated moment by moment.

[0040] As an example, using L, we introduce the correction function A stability correction is made to the logarithmic wind profile formula.

[0041] (5) Correction function In the form of: (6) The power-law wind profile formula is corrected for stability by modifying the power exponent using L.

[0042] (7) Where Λ is the wind speed profile index, and its value is related to the stability condition: (8) As an example, select the logarithmic wind profile or power-law wind profile after stability correction and combine it moment by moment. and Calculate the theoretical wind speed at different heights. Verify the actual wind speed at each height at the corresponding time to ensure that they are within the deviation range of the theoretical wind speed. Set the deviation percentage P (unit: %) to determine the deviation range. If the difference is not within the deviation range, the actual wind measurement data at the corresponding time and height is considered abnormal and marked as NaN.

[0043] (9) in, V 理论 is the theoretical wind speed, V 实际 is the actual wind speed.

[0044] S4. Verify the wind direction deflection law of the third wind measurement data moment by moment based on the Monin-Obukhov length to obtain fourth wind measurement data that meets a preset wind direction change threshold.

[0045] Specifically, the wind direction deflection law of the third wind measurement data is verified moment by moment based on the Monin-Obukhov length, including: checking the wind direction deflection law in combination with the Monin-Obukhov length L moment by moment. Under stable atmospheric conditions (L>0), the wind direction usually deflects slowly with increasing altitude. Usually, there will be no drastic wind direction changes between 10 meters and 70 meters in altitude. If the continuous wind direction change exceeds a reasonable wind direction change threshold, the test will not pass.

[0046] S5. Calculate the rolling mean and the rolling standard deviation of the fourth wind measurement data in the given rolling window respectively; calculate the deviation range according to the rolling mean and the rolling standard deviation, and select the fifth wind measurement data that meets the deviation range.

[0047] Specifically, step S5 includes: (1) After setting the rolling window (e.g., 5 minutes), for the time series data at each height, calculate the rolling mean (rolling_mean) and rolling standard deviation (rolling_std) of the wind speed within the window.

[0048] (2) Calculate the deviation range based on the rolling mean and rolling standard deviation of the wind speed. Check the actual wind speed at each moment. If the actual wind speed exceeds the deviation range, the data is considered abnormal and marked as NaN.

[0049] (3) The treatment method for wind direction is the same as that for wind speed.

[0050] Deviation range = rolling_mean ± multiple × rolling_std; the default multiple of standard deviation is 2.

[0051] S6. Obtain the weighted average wind speed and weighted average wind direction of multiple neighboring wind power stations within a preset distance of the current wind farm; calculate the wind speed deviation value and wind direction deviation value of the fifth wind measurement data based on the weighted average wind speed and weighted average wind direction; and screen out the sixth wind measurement data that meets the preset wind speed deviation threshold and wind direction deviation threshold based on the wind speed deviation value and wind direction deviation value.

[0052] Specifically, the weighted average wind speed and weighted average wind direction of multiple neighboring wind power stations within a preset distance of the current wind farm are obtained, including: determining multiple neighboring wind power stations within a preset distance of the current wind farm; determining the weight of each neighboring wind power station according to the distance between each neighboring wind power station and the current wind farm; and calculating the weighted average wind speed and weighted average wind direction of the neighboring wind power stations according to the weight of each neighboring wind power station.

[0053] As an example, S6 includes: (1) Calculate the distance between the current wind farm and other wind power stations (the default maximum is 30 kilometers. Beyond this distance, it is considered that there are no neighboring wind power stations that meet the requirements). Find all neighboring wind power stations within this range from the current wind farm and extract their wind speed and direction data. If there are multiple neighboring wind power stations that meet the conditions (the number of neighboring wind power stations is greater than 1), proceed to the next step.

[0054] (2) Calculate the weight based on the distance between the neighboring wind power station and the current site, and then calculate the weighted average of the wind speeds of the neighboring wind power stations. The weight is inversely proportional to the site distance (the closer the distance, the greater the weight).

[0055] (3) Compare the wind speed data of the current site with the weighted average wind speed to check the deviation of the actual wind speed. Set the wind speed deviation threshold to ≤5 m / s If the deviation of the actual wind speed exceeds the threshold, it is marked as an anomaly and recorded as a NaN value.

[0056] Wind direction is handled in the same way as wind speed, where the wind direction deviation threshold is ≤30°.

[0057] S7. Fill the missing data, i.e., NaN values, in the sixth wind measurement data to obtain the final wind measurement data after data cleaning.

[0058] Specifically, the missing data in the sixth wind measurement data, that is, the NaN value, is filled to obtain the final wind measurement data after data cleaning, including: for a moment, if the current wind farm has wind measurement data at least at a certain height, the theoretical wind measurement data is calculated according to the wind profile formula correction form, and the missing wind measurement data is filled with the theoretical wind measurement data; if the wind measurement data at all heights of the current wind farm are missing, the wind measurement data at different times at the same height are interpolated for time series data; the wind measurement data after the time series data interpolation process is weighted averaged with neighboring wind power stations to obtain the final wind measurement data.

[0059] As an example, step S7 includes: (1) Filling based on the wind profile model. Fill in the wind measurement data at different heights at the same time according to the calculation results of the wind profile formula correction. If the wind measurement data at all heights of the current wind farm at a certain time are missing, skip this step and proceed to the next step.

[0060] (2) Perform time series data interpolation. For wind measurement data at different times at the same height, select different interpolation methods based on the data characteristics before and after the current time. Interpolation methods include linear interpolation, forward interpolation, backward interpolation, and cubic spline interpolation. If the data is still a NaN value after interpolation, proceed to the next step. The processing method for wind direction is the same as that for wind speed.

[0061] ① Linear interpolation requires at least one valid wind measurement data at each time.

[0062] Set at time and There is an effective wind speed, and its corresponding value is and , for the current moment Interpolation is performed to obtain , the formula is: (10) ② Forward interpolation requires valid wind measurement data at the previous moment.

[0063] Set at time There is an effective wind speed, and its corresponding value is , for the current moment Interpolation is performed to obtain , the formula is: (11) ③ Backward interpolation requires valid wind measurement data at the next moment.

[0064] Set at time There is an effective wind speed, and its corresponding value is , for the current moment Interpolation is performed to obtain , the formula is: (12) ④ Cubic spline interpolation requires at least one valid wind measurement data before and after each moment. In order to ensure the continuity and smoothness of the interpolation function, ideally, there should be at least two valid wind measurement data before and after the interpolation moment, so that the spline interpolation can be more accurate.

[0065] For the moment , the corresponding interpolation for: (13) in Based on time interval The cubic polynomial defined is, , , and are the polynomial coefficients of the interval and need to be calculated by the following conditions: Define interval length : (14) By introducing the second-order derivatives at the nodes , construct a tridiagonal system of equations: (15) , Determined according to boundary conditions.

[0066] Construct a tridiagonal system of equations to solve the matrix m: (16) Where A is a tridiagonal matrix with dimension n×n; is the second-order derivative to be solved; b is the vector constructed by the wind speed difference.

[0067] After solving the matrix m, calculate the polynomial coefficients: (17) (3) Use weighted average filling of neighboring wind power stations. If the number of neighboring wind power stations that meet the conditions around the current wind farm is greater than 1, the weighted average value is calculated based on the wind measurement data of the neighboring wind power stations, and the result is used to fill in the missing data of the current wind farm.

[0068] Example 2 like Figure 2 As shown, based on the same inventive concept as the above embodiment, the present invention also provides a wind farm wind measurement data cleaning device, comprising: A first cleaning module is used to obtain original wind measurement data of the current wind farm, and filter out first wind measurement data that meets a first preset threshold and a first preset jump value from the original wind measurement data; A second cleaning module is used to perform wind speed increment and wind shear verification on the first wind measurement data to obtain second wind measurement data that passes the verification; The third cleaning module is used to determine the Monin-Obukhov length of the current wind farm moment by moment; correct the wind profile formula according to the Monin-Obukhov length to obtain the wind profile formula correction formula; determine the theoretical wind speed of the current wind farm at different heights according to the wind profile formula correction formula; perform data screening according to the wind speed deviation between the theoretical wind speed and the second wind measurement data, and obtain the third wind measurement data whose wind speed deviation is within a preset deviation range; A fourth cleaning module is used to verify the wind direction deflection law of the third wind measurement data moment by moment based on the Monin-Obukhov length to obtain fourth wind measurement data that meets a preset wind direction change threshold; A fifth cleaning module is used to calculate the rolling mean and the rolling standard deviation of the fourth wind measurement data in a given rolling window respectively; calculate the deviation range according to the rolling mean and the rolling standard deviation, and select the fifth wind measurement data that meets the deviation range; The sixth cleaning module is used to obtain the weighted wind speed average value and the weighted wind direction average value of multiple neighboring wind power stations within a preset distance of the current wind farm; calculate the wind speed deviation value and the wind direction deviation value of the fifth wind measurement data according to the weighted wind speed average value and the weighted wind direction average value; and screen out the sixth wind measurement data that meets the preset wind speed deviation threshold and wind direction deviation threshold according to the wind speed deviation value and the wind direction deviation value; The seventh cleaning module is used to fill the missing data, i.e., NaN values, in the sixth wind measurement data to obtain the final wind measurement data after data cleaning.

[0069] Furthermore, in the third cleaning module, the wind profile formula is corrected for stability according to the Monin-Obukhov length to obtain a corrected wind profile formula; the theoretical wind speed of the current wind farm at different heights is determined moment by moment according to the corrected wind profile formula, wherein: The wind profile formula is corrected for stability according to the Monin-Obukhov length to obtain a corrected wind profile formula; wherein the wind profile formula includes a logarithmic wind profile formula and a power-law wind profile formula; the logarithmic wind profile formula is corrected according to the Monin-Obukhov length and the correction function to obtain a first corrected formula; the power-law wind profile formula is corrected according to the Monin-Obukhov length and the corrected power exponent to obtain a second corrected formula; The reference height and reference wind speed of the current wind farm are determined moment by moment; and the theoretical wind speed of the current wind farm at different heights is calculated moment by moment based on the reference height and reference wind speed, and the first correction formula or the second correction formula.

[0070] Example 3 like Figure 3 As shown, the present invention also provides an electronic device 100 for implementing a method for cleaning wind farm wind measurement data; The electronic device 100 includes a memory 101 , at least one processor 102 , a computer program 103 stored in the memory 101 and executable on the at least one processor 102 , and at least one communication bus 104 .

[0071] The memory 101 may be used to store a computer program 103 . The processor 102 implements the steps of a method for cleaning wind farm wind measurement data in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101 .

[0072] The memory 101 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0073] At least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0074] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a method for cleaning wind farm wind measurement data, and the processor 102 can execute the plurality of instructions to implement: Acquire original wind measurement data of the current wind farm, and select first wind measurement data satisfying a first preset threshold and a first preset jump value from the original wind measurement data; Performing wind speed increment and wind shear verification on the first wind measurement data to obtain second wind measurement data that passes the verification; Determine the Monin-Obukhov length moment by moment; perform stability correction on the wind profile formula according to the Monin-Obukhov length to obtain a revised wind profile formula; determine the theoretical wind speed of the current wind farm at different heights moment by moment according to the revised wind profile formula; perform data screening according to the wind speed deviation between the theoretical wind speed and the second wind measurement data to obtain the third wind measurement data whose wind speed deviation is within a preset deviation range; Verify the wind direction deflection law of the third wind measurement data moment by moment based on the Monin-Obukhov length to obtain fourth wind measurement data that meets a preset wind direction change threshold; Calculate the rolling mean and the rolling standard deviation of the fourth wind measurement data in the given rolling window respectively; calculate the deviation range according to the rolling mean and the rolling standard deviation, and select the fifth wind measurement data that meets the deviation range; Obtain the weighted average wind speed and weighted average wind direction of multiple neighboring wind power stations within a preset distance of the current wind farm; calculate the wind speed deviation value and wind direction deviation value of the fifth wind measurement data according to the weighted average wind speed and weighted average wind direction; and screen out the sixth wind measurement data that meets the preset wind speed deviation threshold and wind direction deviation threshold according to the wind speed deviation value and wind direction deviation value; The missing data in the sixth wind measurement data, i.e., NaN values, are filled to obtain the final wind measurement data after data cleaning.

[0075] Example 4 If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0076] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 produce 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.

[0078] 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.

[0079] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0080] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for cleaning wind farm wind measurement data, characterized in that: The steps include: Acquire original wind measurement data of the current wind farm, and select first wind measurement data satisfying a first preset threshold and a first preset jump value from the original wind measurement data; Performing wind speed increment and wind shear verification on the first wind measurement data to obtain second wind measurement data that passes the verification; Determine the Monin-Obukhov length moment by moment; perform stability correction on the wind profile formula according to the Monin-Obukhov length to obtain a revised wind profile formula; determine the theoretical wind speed of the current wind farm at different heights moment by moment according to the revised wind profile formula; Data is screened according to the wind speed deviation between the theoretical wind speed and the second wind measurement data to obtain third wind measurement data whose wind speed deviation is within a preset deviation range; Verify the wind direction deflection law of the third wind measurement data moment by moment based on the Monin-Obukhov length to obtain fourth wind measurement data that meets a preset wind direction change threshold; respectively calculating the rolling mean and the rolling standard deviation of the fourth wind measurement data within a given rolling window; The deviation range is calculated according to the rolling mean and the rolling standard deviation, and the fifth wind measurement data that meets the deviation range is selected; Obtain the weighted average wind speed and weighted average wind direction of multiple neighboring wind power stations within a preset distance of the current wind farm; calculate the wind speed deviation value and wind direction deviation value of the fifth wind measurement data according to the weighted average wind speed and weighted average wind direction; and screen out the sixth wind measurement data that meets the preset wind speed deviation threshold and wind direction deviation threshold according to the wind speed deviation value and wind direction deviation value; The missing data in the sixth wind measurement data are filled to obtain the final wind measurement data after data cleaning.

2. The wind farm wind measurement data cleaning method according to claim 1, characterized in that: The wind profile formula is corrected for stability according to the Monin-Obukhov length to obtain the revised wind profile formula. The theoretical wind speed of the current wind farm at different heights is determined moment by moment according to the revised wind profile formula, where: The wind profile formula includes the logarithmic wind profile formula and the power-law wind profile formula; the logarithmic wind profile formula is corrected according to the Monin-Obukhov length and the correction function to obtain the first correction formula; the power-law wind profile formula is corrected according to the Monin-Obukhov length and the correction power exponent to obtain the second correction formula; The reference height and reference wind speed of the current wind farm are determined moment by moment; and the theoretical wind speed of the current wind farm at different heights is calculated moment by moment based on the reference height and reference wind speed, and the first correction formula or the second correction formula.

3. The method for cleaning wind farm wind measurement data according to claim 1, characterized in that: Determine the reference height and reference wind speed of the current wind farm moment by moment, including: Determine the geographic location of wind towers in current wind farms; If a data reference point exists within a preset distance of the geographical location, the 10-meter wind speed data of the data reference point is obtained moment by moment; it is determined whether the deviation between the data reference point and the 10-meter wind speed data of the wind tower meets the preset deviation threshold; if the wind speed deviation does not meet the deviation threshold, the 10-meter wind speed data of the data reference point is used as the reference wind speed, and 10 meters is used as the reference height; wherein the data reference point is a meteorological station, or the nearest grid point determined according to the resolution of the reanalysis data; If there is no data reference point within the preset distance of the geographical location, or the deviation between the data reference point and the 10-meter wind speed data of the wind tower meets the preset deviation threshold, a height is selected from the current wind farm at each moment as the reference height, and the wind speed at the corresponding height is used as the reference wind speed.

4. The method for cleaning wind farm wind measurement data according to claim 1, characterized in that: Determine the Monin-Obukhov length of the current wind farm at each moment, including: Determine the reference height and reference wind speed of the current wind farm moment by moment, and calculate the friction speed based on the reference height and reference wind speed; Determine the current sensible heat flux of the wind farm moment by moment; The Monin-Obukhov length of the current wind farm is calculated moment by moment according to the friction velocity and sensible heat flux of the current wind farm.

5. The method for cleaning wind farm wind measurement data according to claim 1, characterized in that: Get the weighted average wind speed and weighted average wind direction of multiple neighboring wind farms within a preset distance of the current wind farm, including: Determine a plurality of neighboring wind farms within a preset distance of the current wind farm; Determine the weight of each adjacent wind power station according to the distance between each adjacent wind power station and the current wind farm; According to the weights of each adjacent wind power station, the weighted average wind speed and weighted average wind direction of the adjacent wind power stations are calculated respectively.

6. The method for cleaning wind farm wind measurement data according to claim 1, characterized in that: Fill the missing data in the sixth wind measurement data to obtain the final wind measurement data after data cleaning, including: At a certain moment, if there is wind measurement data at least at a certain height of the current wind farm, the theoretical wind measurement data is calculated according to the wind profile formula correction form, and the missing wind measurement data is filled with the theoretical wind measurement data; if the wind measurement data at all heights of the current wind farm are missing, the wind measurement data at different times at the same height are interpolated for time series data; The wind measurement data after time series data interpolation processing is filled with weighted average of neighboring wind power stations to obtain the final wind measurement data.

7. A wind farm wind measurement data cleaning device, characterized in that: include: A first cleaning module is used to obtain original wind measurement data of the current wind farm, and filter out first wind measurement data that meets a first preset threshold and a first preset jump value from the original wind measurement data; A second cleaning module is used to perform wind speed increment and wind shear verification on the first wind measurement data to obtain second wind measurement data that passes the verification; The third cleaning module is used to determine the Monin-Obukhov length of the current wind farm moment by moment; correct the wind profile formula according to the Monin-Obukhov length to obtain the wind profile formula correction formula; determine the theoretical wind speed of the current wind farm at different heights moment by moment according to the wind profile formula correction formula; perform data screening according to the wind speed deviation between the theoretical wind speed and the second wind measurement data, and obtain the third wind measurement data whose wind speed deviation is within a preset deviation range; A fourth cleaning module verifies the wind direction deflection law of the third wind measurement data moment by moment based on the Monin-Obukhov length to obtain fourth wind measurement data that meets a preset wind direction change threshold; a fifth cleaning module, used for respectively calculating a rolling mean and a rolling standard deviation of the fourth wind measurement data within a given rolling window; The deviation range is calculated according to the rolling mean and the rolling standard deviation, and the fifth wind measurement data that meets the deviation range is selected; The sixth cleaning module is used to obtain the weighted wind speed average value and the weighted wind direction average value of multiple neighboring wind power stations within a preset distance of the current wind farm; calculate the wind speed deviation value and the wind direction deviation value of the fifth wind measurement data according to the weighted wind speed average value and the weighted wind direction average value; and screen out the sixth wind measurement data that meets the preset wind speed deviation threshold and wind direction deviation threshold according to the wind speed deviation value and the wind direction deviation value; The seventh cleaning module is used to fill in the missing data in the sixth wind measurement data to obtain the final wind measurement data after data cleaning.

8. The wind farm wind measurement data cleaning device according to claim 7, characterized in that: In the third cleaning module, the stability of the wind profile formula is corrected according to the Monin-Obukhov length to obtain the wind profile formula correction form; the theoretical wind speed of the current wind farm at different heights is determined moment by moment according to the wind profile formula correction form, where: The wind profile formula includes the logarithmic wind profile formula and the power-law wind profile formula; the logarithmic wind profile formula is corrected according to the Monin-Obukhov length and the correction function to obtain the first correction formula; the power-law wind profile formula is corrected according to the Monin-Obukhov length and the correction power exponent to obtain the second correction formula; The reference height and reference wind speed of the current wind farm are determined moment by moment; and the theoretical wind speed of the current wind farm at different heights is calculated moment by moment based on the reference height and reference wind speed, and the first correction formula or the second correction formula.

9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the wind farm wind measurement data cleaning method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, the wind farm wind measurement data cleaning method according to any one of claims 1 to 6 is implemented.

Images