Wind farm measured data correction method and device, electronic equipment and storage medium

Abstract

The application provides a wind farm measured data correction method and device, electronic equipment and a storage medium. The method comprises the following steps: determining wind speed data of a target moment of wind farm measurement, wherein the wind speed data comprises wind speed data corresponding to each layer height of a wind tower of the wind farm; determining whether the wind speed data of the target moment is abnormal based on wind speed data of a previous moment, wind speed data in a first target period, a wind speed limit interval and a wind speed change threshold of adjacent layer heights; and in the case that the wind speed data of the target moment is abnormal, correcting the wind speed data of the target moment according to a change trend of latest target numerical weather prediction (NWP) data, so as to realize correction of wind farm measured data and improve the accuracy of wind farm measured wind speed data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new energy power systems, and particularly relates to a wind farm measured data correction method and device, an electronic device and a storage medium. BACKGROUND

[0002] With the increase of wind farm construction, the wind measurement tower equipment of power station is also increasing, in addition, some wind farms have been running for many years, and the wind measurement tower equipment has been aging. These increase the probability of deviation of wind speed collection data of the wind measurement tower. In addition, because the requirements of the power grid for the data quality of new energy power stations and the requirements of the power prediction accuracy index are gradually increasing, the influence of the deviation of the wind measurement data on the operation and maintenance of the wind farm is more prominent.

[0003] Because of the abnormality of the wind measurement equipment during operation, interference in the wind measurement data collection communication process and other reasons, the last collected wind speed data may be deviated, and the wind measurement tower data is the basic data required for the operation of the power station, especially the power prediction of the power station. The error data collected will seriously affect the normal operation of the power station and the accuracy of the power prediction of the power station.

[0004] However, the wind measurement tower equipment belongs to special facilities, and maintenance requires climbing construction (climbing a steel tower of more than one hundred meters), and the calibration and replacement of the wind measurement equipment is long (at least more than one month is required), the abnormal situation of the wind measurement data is relatively frequent and can be improved by itself under the condition of wind speed conversion, and it is impossible to climb the tower and check the equipment every time the data fails. Therefore, it is necessary to detect abnormal data and complete data correction. SUMMARY

[0005] The present application provides a wind farm measured data correction method, device, electronic device and storage medium, which solves the defect that the wind speed data collected by the wind farm in the prior art is inaccurate, and realizes the correction of the wind farm measured data.

[0006] The present application provides a wind farm measured data correction method, comprising:

[0007] determining the wind speed data of a target time of a wind farm measurement, the wind speed data comprising wind speed data corresponding to each layer height of a wind measurement tower of the wind farm;

[0008] determining whether the wind speed data of the target time is abnormal based on the wind speed data of the previous time, the wind speed data in the first target period, the wind speed limit interval and the adjacent layer height wind speed change threshold, and in the case that the wind speed data of the target time is abnormal, correcting the wind speed data of the target time according to the change trend of the latest target numerical weather prediction (NWP) data.

[0009] The wind farm measured data correction method provided in the application comprises the following steps:

[0010] Before the wind speed data of the target time is corrected according to the change trend of the latest target numerical weather prediction (NWP) data, the method further comprises the following steps:

[0011] The latest NWP data of the target time is obtained; or,

[0012] The latest NWP data of two time points adjacent to the target time is obtained, and the NWP data of the target time is calculated by using an interpolation method based on the NWP data of the two time points.

[0013] The wind farm measured data correction method provided in the application comprises the following steps:

[0014] Whether the wind speed data of the target time jumps is determined based on the wind speed data of the time point before the target time, and in the case that the wind speed data of the target time jumps, the wind speed data of the target time is corrected based on the change trend of the NWP data;

[0015] Whether the wind speed data of the target time is a dead value is determined based on the wind speed data of each time point in the first target time period, and in the case that the wind speed data of the target time is a dead value, the wind speed data of the target time is corrected based on the change trend of the target NWP data and the adjustment coefficient of each layer height;

[0016] Whether the wind speed data of the target time is out of limit is determined based on the wind speed limit value interval, and in the case that the wind speed data of the target time is out of limit, the wind speed data of the target time is corrected based on the change trend of the target NWP data and the adjustment coefficient of each layer height;

[0017] Whether the wind speed data of the target time is reasonable is determined based on the adjacent layer height wind speed change threshold, and in the case that the wind speed data of the target time is unreasonable, the wind speed data of the target time is corrected based on the change trend of the target NWP data and the adjustment coefficient of each layer height.

[0018] The wind farm measured data correction method provided in the application comprises the following steps:

[0019] determining a random number within a target range, and determining a wind speed increasing / decreasing trend of a near time period based on a variation trend of the NWP data, wherein the wind speed increasing / decreasing trend comprises an increasing trend and a decreasing trend;

[0020] in a case where the wind speed increasing / decreasing trend is the increasing trend, adding the random number to wind speed data of a time period before the target time to obtain modified wind speed data of the target time; or,

[0021] in a case where the wind speed increasing / decreasing trend is the decreasing trend, subtracting the random number from wind speed data of a time period before the target time to obtain modified wind speed data of the target time.

[0022] According to the wind farm measured data correction method provided by the application, the wind speed data of the target time is determined based on wind speed data of each time in the first target time period, and the wind speed data of the target time is determined based on the wind speed data of the target time.

[0023] obtaining wind speed data of each time in the first target time period, wherein the first target time period is a time period before the target time;

[0024] determining a wind speed difference value of each two times among the times and the target time, and determining whether the wind speed data of each height of the target time exists a dead value based on the wind speed difference value of each two times and a second threshold value.

[0025] According to the wind farm measured data correction method provided by the application, the wind speed data of the target time is determined based on the variation trend of the target NWP data and the adjustment coefficient of each height, and the wind speed data of the target time is corrected.

[0026] determining a deviation value of NWP data of each two adjacent times in the second target time period based on the variation trend of the target NWP data, wherein the second target time period comprises a time period before the target time and a time period after the target time;

[0027] in a case where the number of positive values is greater than the number of negative values in the deviation value of NWP data of each two adjacent times, increasing the NWP data of the target time and multiplying the adjustment coefficient of the corresponding height to obtain modified wind speed data of the target time; or,

[0028] in a case where the number of negative values is greater than the number of positive values in the deviation value of NWP data of each two adjacent times, decreasing the NWP data of the target time and multiplying the adjustment coefficient of the corresponding height to obtain modified wind speed data of the target time.

[0029] The application further provides a wind farm measured data correction device, comprising:

[0030] a data determining module configured to determine wind speed data of a target time point of the wind farm measured data, the wind speed data comprising wind speed data corresponding to each layer height of a wind measurement tower of the wind farm;

[0031] a data correction module configured to determine whether the wind speed data of the target time point is abnormal based on wind speed data of a previous time point, wind speed data within a first target period, a wind speed limit interval, and a wind speed change threshold of adjacent layer heights, and correct the wind speed data of the target time point according to a latest target numerical weather prediction (NWP) data change trend in a case where the wind speed data of the target time point is abnormal.

[0032] The present application also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the wind farm measured data correction method according to any one of the above embodiments when executing the program.

[0033] The present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the steps of the wind farm measured data correction method according to any one of the above embodiments.

[0034] The present application also provides a computer program product comprising a computer program, wherein the computer program is executable by a processor to implement the steps of the wind farm measured data correction method according to any one of the above embodiments.

[0035] The wind farm measured data correction method, device, electronic device, and storage medium provided by the present application determine whether the wind speed data of a target time point is abnormal based on wind speed data of a previous time point, wind speed data within a target period, a wind speed limit interval, and a wind speed change threshold of adjacent layer heights, and correct the wind speed data of the target time point based on a change trend of target NWP data in a case where the wind speed data of the target time point is abnormal, thereby improving the accuracy of wind farm measured wind speed data. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0037] Figure 1 is a flowchart of the wind farm measured data correction method provided by the present application;

[0038] Figure 2 is one of the flowcharts of the wind speed data correction method provided by the present application;

[0039] Figure 3 is a flowchart of the method for correcting wind speed data provided by the present application;

[0040] Figure 4 is a structural schematic diagram of the wind farm measured data correction device provided by the present application;

[0041] Figure 5 is a structural schematic diagram of the electronic device provided by the present application. DETAILED DESCRIPTION

[0042] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0043] The wind farm measured data correction method of the present application will be described below. Figures 1-3

[0044] As shown in the figure, the wind farm measured data correction method includes step 101 and step 102. Figure 1

[0045] Step 101, determining the wind speed data of the target time of the wind farm measurement, the wind speed data including the wind speed data corresponding to each layer height of the wind farm measurement tower.

[0046] It should be noted that a wind measurement tower needs to be constructed during the construction and operation of the wind farm, and the wind measurement tower is used to measure real-time wind speed data at different layer heights. Generally, the wind measurement tower includes 5 to 7 layers, including the hub layer. The layer height of each layer of the wind measurement tower is also the corresponding height of the measured wind speed, which is 10 m, 30 m, 50 m, 70 m, 90 m, etc.

[0047] That is, the wind speed data obtained by the wind farm measurement includes wind speed data corresponding to each layer height.

[0048] The wind farm measured data correction method of the present application is corrected in time sequence, the data of the previous time is corrected first, and then the data of the next time is corrected based on the corrected data of the previous time. The target time is the current time to be corrected, which can be the current time or a non-current time, which is not limited here.

[0049] ​​Step 102, determining whether the wind speed data at the target time is abnormal based on the wind speed data at the previous time, the wind speed data in the first target period, the wind speed limit interval and the adjacent layer height wind speed change threshold, and in the case that the wind speed data at the target time is abnormal, correcting the wind speed data at the target time according to the change trend of the latest target numerical weather prediction (NWP) data.

[0050] It should be noted that, because there are multiple prediction results for the wind speed value at the same time, the latest prediction value for the time should be taken, which is generally the prediction value for the next day published the day before. That is, the target numerical weather prediction (NWP) data is the latest prediction result obtained from the on-site prediction system of the wind farm, which includes the predicted wind speed data.

[0051] Optionally, the wind speed data at the target time can be determined based on the wind speed data at the previous time of the target time, the first target period is a period of time before the target time, the wind speed data in the first target period can be determined whether the wind speed data at the target time is a dead value, that is, data that is not refreshed, the wind speed limit interval can be used to determine whether the wind speed data at the target time is out of range, and based on the wind speed data at the target time corresponding to each layer height, it can be determined whether the wind speed data at the target time is unreasonable. If the wind speed data has jump, dead value, out of range and unreasonable data, it is considered that the wind speed data is abnormal, and the wind speed data at the target time is corrected based on the change trend of the NWP data.

[0052] It can be understood that the change trend of the NWP data includes the rising and falling trend and the deviation value of each adjacent time NWP data.

[0053] As shown in Figure 2 , whether the collected wind speed data has jump, dead value, out of range and whether it is unreasonable data can be determined in sequence, and the jump, dead value, out of range and unreasonable data are processed to obtain the corrected wind speed data.

[0054] The wind farm measured data correction method provided by the embodiment of the application determines whether the wind speed data at the target time is abnormal based on the wind speed data at the previous time, the wind speed data in the first target period, the wind speed limit interval and the adjacent layer height wind speed change threshold, and in the case that the wind speed data at the target time is abnormal, the wind speed data at the target time is corrected based on the change trend of the target NWP data, which improves the accuracy of the corrected wind farm measured wind speed data.

[0055] Optionally, the target NWP data includes the NWP data at the target time.

[0056] The target NWP data also includes NWP data of time points before and after the target time point. According to the NWP data of multiple time points, the wind speed change trend of a period of time including the target time point can be obtained, such as the wind speed difference of each adjacent time point, and whether the wind speed in the period of time is a growth trend or a decline trend.

[0057] Before the wind speed data of the target time point is corrected according to the change trend of the latest target numerical weather prediction (NWP) data, the method further comprises:

[0058] obtaining the latest NWP data of the target time point; or

[0059] obtaining the latest NWP data of two time points adjacent to the target time point, and calculating the NWP data of the target time point by using an interpolation method based on the NWP data of the two time points.

[0060] It can be understood that the resolution of the NWP data and the resolution of the measured wind speed value can be different. For example, the resolution of the NWP data is 15 minutes, that is, there is a wind speed prediction every 15 minutes, and the time resolution of the measured wind speed value is 5 minutes, that is, the wind speed is measured every 5 minutes. Therefore, the target time point can not have a corresponding predicted wind speed value.

[0061] In the case that the target time point has a corresponding predicted wind speed value, the NWP data of the target time point is obtained.

[0062] In the case that the target time point does not have a corresponding predicted wind speed value, the NWP data of two time points adjacent to the target time point is obtained, and the NWP data of the target time point is calculated by using an interpolation method based on the NWP data of the two time points.

[0063] The NWP data of the two adjacent time points can be the NWP data of two time points before and after the target time point. Taking the resolution of the wind speed prediction value data as 15 minutes and the time resolution of the measured wind speed value as 5 minutes as an example, two cases in which the target time point does not have a corresponding predicted wind speed value are described.

[0064] I. The target time point is 5 minutes apart from the time point corresponding to the previous NWP data.

[0065] WSP t = WSP t-1 + (WSP t+1 -WSP t-1 ) / 3

[0066] II. The target time point is 10 minutes apart from the time point corresponding to the previous NWP data.

[0067] WSP t = WSPt-1 + 2 * (WSP t+1 - WSP t-1 ) / 3

[0068] wherein, WSP t is the NWP data of the target moment, WSP t-1 is the NWP data of the previous moment, and WSP t+1 is the NWP data of the next moment.

[0069] For other resolutions, the same can be deduced, which is not described here.

[0070] The wind farm measured data correction method provided by the embodiment of the application obtains the NWP data of two moments adjacent to the target moment, and calculates the NWP data of the target moment by using an interpolation method based on the NWP data of the two moments, so that the accuracy of the obtained NWP data of the target moment is improved in the case that there is no corresponding predicted wind speed value at the target moment, and the accuracy of the corrected wind farm measured wind speed data is improved.

[0071] Optionally, as shown in FIG. 1, step 102 comprises steps 301, 302, 303 and 304. Figure 3

[0072] Step 301 determines whether the wind speed data of the target moment jumps based on the wind speed data of the previous moment of the target moment, and corrects the wind speed data of the target moment based on the change trend of the NWP data in the case that the wind speed data of the target moment jumps.

[0073] Optionally, the wind speed data of the previous moment of the target moment is obtained, and the wind speed change trend of the adjacent period is determined.

[0074] The wind speed data of the target moment is determined to jump based on the wind speed data of the previous moment of the target moment and a first threshold value.

[0075] In the case that the wind speed data of the target moment jumps, a random number in the target range is determined, and the wind speed increase / decrease trend of the adjacent period is determined based on the change trend of the NWP data, wherein the wind speed increase / decrease trend comprises an upward trend and a downward trend.

[0076] In the case that the wind speed increase / decrease trend is the upward trend, the wind speed data of the previous moment of the target moment is increased by the random number to obtain the corrected wind speed data of the target moment; or,

[0077] In the case that the wind speed increase / decrease trend is the downward trend, the wind speed data of the previous moment of the target moment is reduced by the random number to obtain the corrected wind speed data of the target moment.​

[0078] the wind speed data WS of the previous time point of the target time point t-1 and the wind speed data WS of the target time point t the absolute value of the difference ΔWR.

[0079] ΔWR = |WS t - WS t-1 |

[0080] If ΔWR is greater than a first threshold value, it is considered that the wind speed data of the target time point has a jump. The first threshold value can be between 5 m / s to 8 m / s, for example, the first threshold value is 6 m / s.

[0081] It should be noted that if the wind speed data of the previous time point is corrected, the corrected wind speed data is taken for calculation, and the wind speed data of the same height is calculated for the difference.

[0082] The wind speed change trend includes an upward trend and a downward trend, and the wind speed change trend can be determined according to the wind speed data before the target time point.

[0083] In the case of an upward trend of the wind speed change trend, the wind speed data of the previous time point is increased by a random number as the corrected wind speed data of the target time point. In the case of a downward trend of the wind speed change trend, the wind speed data of the previous time point is subtracted by a random number as the corrected wind speed data of the target time point.

[0084] The size of the random number can be set according to the actual situation, and the following is an example with a target range of 2 to 4.

[0085] In the case of an upward trend of the wind speed change trend:

[0086] WS t = WS t-1 + Rand(2, 4);

[0087] In the case of a downward trend of the wind speed change trend:

[0088] WS t = WS t-1 - Rand(2, 4);

[0089] Wherein, Rand(2, 4) represents a random number of 2 to 4.

[0090] Step 302, determine whether the wind speed data of the target time point is a dead value based on the wind speed data of each time point in the first target period, and in the case that the wind speed data of the target time point is a dead value, correct the wind speed data of the target time point based on the change trend of the target NWP data and the adjustment coefficient of each height.

[0091] Optionally, wind speed data of each time point in the first target period is acquired;

[0092] The wind speed difference value between each two time points is determined, and based on the wind speed difference value between each two time points and a second threshold value, it is determined whether the wind speed data of each layer height at the target time point has a dead value;

[0093] In the case that the wind speed data at the target time point has a dead value, the wind speed data at the target time point is corrected based on the change trend of the target NWP data and the adjustment coefficient of each layer height.

[0094] The first target period is a time period before the target time point, and the length of the first target period can be set according to actual conditions.

[0095] For example, in the case that the time resolution of the measured wind speed value is 5 minutes, the target period is determined to be 30 minutes before the target time point. The wind speed data of each time point in the target period includes: WS t-5 , WS t-4 , WS t-3 , WS t-2 , WS t-1 , and the wind speed data of 5 time points.

[0096] The wind speed difference value between each two time points can be calculated, or the wind speed difference value between each adjacent two time points can be calculated. Taking the calculation of the wind speed difference value between each adjacent two time points as an example, it includes: Det1 = |WS t-5 - WS t-4 |, Det2 = |WS t-4 - WS t-3| , Det3 = |WS t-3 - WS t-2 |, Det4 = |WS t-2 - WS t-1 |, and Det5 = |WS t-1 - WS t |.

[0097] The maximum value DET in the difference value is determined:

[0098] DET = Max (Det1, Det2, Det3, Det4, Det5)

[0099] If DET is less than the second threshold value, it is determined that the wind speed data at the target time point is a dead value, and the wind speed data at the target time point is corrected based on the change trend of the target NWP data and the adjustment coefficient of each layer height. The second threshold value can be between 0.01-0.0001, for example, 0.001.

[0100] It should be noted that when determining whether it is a dead value, the wind speed data of the same layer height is compared to determine whether the wind speed data of a certain layer is a dead value.

[0101] Based on the change trend of the target NWP data and the adjustment coefficient of each layer height, the wind speed data of the target time is corrected, including:

[0102] Based on the change trend of the target NWP data, the deviation value of the NWP data of each two adjacent time points in the second target time period is determined, and the second target time period includes a time period before the target time and a time period after the target time.

[0103] In the deviation value of the NWP data of each two adjacent time points, if the number of positive values is greater than the number of negative values, the NWP data of the target time is increased and multiplied by the adjustment coefficient of the corresponding layer height to obtain the corrected wind speed data of the target time; or,

[0104] In the deviation value of the NWP data of each two adjacent time points, if the number of positive values is greater than the number of negative values, the NWP data of the target time is increased and multiplied by the adjustment coefficient of the corresponding layer height to obtain the corrected wind speed data of the target time.

[0105] It can be understood that a plurality of numerical weather forecast wind speed values near the target time are taken, and the length of the second target time period is not specifically limited. Taking the data of six time points in the second target time period as an example, including the wind speed value WSP t-2 , WSP t-1 , the wind speed value WSP t of the target time, and the wind speed value WSP t+1 , WSP t+2 , WSP t+3 after the target time.

[0106] Because there are multiple prediction results for the wind speed value at the same time, the latest prediction value should be taken, which is generally the prediction value published the day before.

[0107] The deviation of the prediction values of the adjacent two time points is calculated, including: Det′1=WSP t-1 -WSP t-2 , Det′2=WSP t -WSP t-1 , Det′3=WSP t+1 -WSP t , Det′4=WSP t+2 -WSP t+1 , Det′5=WSP t+3 -WSP t+2 .

[0108] The number of positive values and negative values of the above five deviation values is compared, and if the number of positive values is larger, the correction value is increased by the deviation amount Det'3 based on the NWP data at the original target time, and if the number of positive values is larger, the correction value is reduced by the deviation amount Det'3 based on the NWP data at the original target time. It should be noted that the data after increasing or decreasing is not adjusted for the layer height, and the data after increasing or decreasing can be multiplied by the adjustment coefficient corresponding to the layer height, and the wind speed data with a dead value is corrected.

[0109] The layer height adjustment coefficient defines the adjustment coefficient corresponding to the hub layer height of the wind tower as 1, and in other layer heights, the coefficient is greater than 1 if it is higher than the hub layer, and the coefficient is less than 1 if it is lower than the hub layer, and the coefficient sequence from small to large is set in order from low to high. In order to ensure the rationality of the adjustment coefficient, the optimization coefficient for different layer height wind speed prediction in the numerical weather prediction space resolution calculation method is referred to. Taking 70 meters as the hub layer as an example, the final determination of the layer height adjustment coefficient is shown in Table 1:

[0110] Table 1 Layer height adjustment coefficient table

[0111]

[0112] Step 303, determining whether the wind speed data at the target time is out of limit based on the wind speed limit interval, and in the case that the wind speed data at the target time is out of limit, correcting the wind speed data at the target time based on the change trend of the target NWP data and the adjustment coefficient of each layer height.

[0113] Optionally, the wind speed limit interval is determined.

[0114] The wind speed limit interval is determined based on the wind speed limit interval.

[0115] In the case that the wind speed data at the target time is out of limit, the wind speed data at the target time is corrected based on the change trend of the target NWP data and the adjustment coefficient of each layer height.

[0116] Optionally, the wind speed limit interval can be adjusted according to the actual situation, for example, the wind speed limit interval is taken as 0m / s to 75m / s, and if it exceeds the wind speed limit interval, it is determined that the wind speed is out of limit.

[0117] In the case that the wind speed data at the target time is out of limit, the wind speed data with a dead value can be corrected based on the change trend of the target NWP data and the adjustment coefficient of each layer height. The correction method is consistent with step 302, and the adjustment coefficient of each layer is the same as the adjustment coefficient in Table 1, which will not be described here.

[0118] Step 304, determining whether the wind speed data at the target time is reasonable based on the adjacent height wind speed change threshold value, and in the case that the wind speed data at the target time is unreasonable, correcting the wind speed data at the target time based on the change trend of the target NWP data and the adjustment coefficient of each height.

[0119] Optionally, the wind speed difference value of each two adjacent heights at the target time is determined.

[0120] Based on the wind speed difference value and the adjacent height wind speed change threshold value, it is determined whether the wind speed data at the target time is reasonable.

[0121] In the case that the wind speed data at the target time is unreasonable, the wind speed data at the target time is corrected based on the change trend of the target NWP data and the adjustment coefficient of each height.

[0122] It can be understood that steps 301-303 need to refer to the wind speed data or the wind speed limit interval of other time to determine whether the wind speed data at the target time is abnormal, and the same layer data is compared, and step 304 compares the wind speed data of each height at the target time to determine whether the wind speed data at the target time is abnormal.

[0123] Optionally, the change of the wind speed value of the adjacent height within a preset time period cannot exceed the adjacent height wind speed change threshold value. The preset time period can be five minutes, and the adjacent height wind speed change threshold value can be 4 m / s.

[0124] Taking the wind speed WS of any height at the target time x and the wind speed WS of the adjacent height at the same time y , the deviation Det of the two wind speeds is calculated xy = | WS x - WS y |, if Det xy ≥ 4, it is considered that WS x and WS y data logic is unreasonable.

[0125] In the case that the wind speed data at the target time is logically unreasonable, the wind speed data as a dead value can be corrected based on the change trend of the target NWP data and the adjustment coefficient of each height. The correction method is consistent with step 302, and the adjustment coefficient of each height is the same as the adjustment coefficient in table 1, which will not be repeated here.

[0126] The wind farm measured data correction method provided by the embodiment of the present application determines whether the wind speed data at the target moment is abnormal based on the wind speed data at the previous moment, the wind speed data in the target period, the wind speed limit interval and the adjacent layer height wind speed change threshold, and in the case that the wind speed data at the target moment is abnormal, the wind speed data at the target moment is corrected based on the change trend of the target NWP data. In addition, the data is gradually corrected in the order of first performing data out-of-limit check and correction, then performing data non-refresh check and correction, then performing data jump check and correction, and finally performing data inter-logic relationship check and correction. The reason is that according to the analysis of a large amount of historical data according to the determination rules of the four abnormal conditions, the probability of the occurrence of the above four abnormal conditions decreases from high to low, that is, the abnormal conditions that are more likely to occur are given priority to check and correct, and the subsequent steps are more likely to appear the qualified condition, so as to reduce the program running time and ensure the real-time of the data, and improve the accuracy of the corrected wind farm measured wind speed data.

[0127] Optionally, the current wind speed data after the above four-step correction can be recalculated according to the abnormality determination standard of each step to ensure that each item is qualified. It should be noted that the first step to the fourth step should be done in order, and if the correction result is still unqualified, the adjustment can be performed again according to the optimization scheme in the step. However, in order to avoid the mutual influence after the adjustment of different steps and fall into a dead loop, it is suggested to stop the re-correction after completing two rounds of debugging. According to the calculation, only one round of optimization can ensure that the data qualified rate is above 95%.

[0128] The wind farm measured data correction device provided by the present application is described below. The wind farm measured data correction device described below can be correspondingly referred to the wind farm measured data correction method described above.

[0129] As shown in Figure 4 , the wind farm measured data correction device comprises a data determination module 410 and a data correction module 420.

[0130] The data determination module 410 is configured to determine the wind speed data of the target moment of the wind farm measurement, and the wind speed data comprises the wind speed data corresponding to each layer height of the wind tower of the wind farm.

[0131] The data correction module 420 is configured to determine whether the wind speed data at the target moment is abnormal based on the wind speed data at the previous moment, the wind speed data in the first target period, the wind speed limit interval and the adjacent layer height wind speed change threshold, and in the case that the wind speed data at the target moment is abnormal, the wind speed data at the target moment is corrected according to the change trend of the latest target numerical weather prediction (NWP) data.

[0132] Optionally, the target NWP data comprises NWP data of the target time point.

[0133] The data determination module 410 is further configured to:

[0134] acquire the latest NWP data of the target time point; or

[0135] acquire the latest NWP data of two time points adjacent to the target time point, and calculate the NWP data of the target time point by interpolation based on the NWP data of the two time points.

[0136] Optionally, the data correction module 420 is specifically configured to:

[0137] determine whether the wind speed data of the target time point jumps based on the wind speed data of a time point before the target time point, and correct the wind speed data of the target time point based on the change trend of the NWP data in the case that the wind speed data of the target time point jumps;

[0138] determine whether the wind speed data of the target time point is a dead value based on the wind speed data of each time point in the first target time period, and correct the wind speed data of the target time point based on the change trend of the target NWP data in the case that the wind speed data of the target time point is a dead value;

[0139] determine whether the wind speed data of the target time point is out of limit based on the wind speed limit interval, and correct the wind speed data of the target time point based on the change trend of the target NWP data and the adjustment coefficient of each layer height in the case that the wind speed data of the target time point is out of limit;

[0140] determine whether the wind speed data of the target time point is reasonable based on the adjacent layer height wind speed change threshold, and correct the wind speed data of the target time point based on the change trend of the target NWP data and the adjustment coefficient of each layer height and the adjustment coefficient of each layer height in the case that the wind speed data of the target time point is unreasonable.

[0141] Optionally, the correction of the wind speed data of the target time point based on the change trend of the NWP data comprises:

[0142] determining a random number in a target range, and determining a wind speed increasing / decreasing trend of an adjacent time period based on the change trend of the NWP data, wherein the wind speed increasing / decreasing trend comprises an upward trend and a downward trend;

[0143] in the case that the wind speed increasing / decreasing trend is the upward trend, increasing the wind speed data of a time point before the target time point by the random number to obtain the corrected wind speed data of the target time point; or

[0144] In the case that the wind speed increasing and decreasing trend is a decreasing trend, the wind speed data of the target time point is obtained by subtracting the random number from the wind speed data of the time point before the target time point.

[0145] Optionally, the determining whether the wind speed data of the target time point is a dead value based on the wind speed data of each time point in the first target time period comprises:

[0146] Obtaining the wind speed data of each time point in the first target time period, wherein the first target time period is a time period before the target time point;

[0147] Determining the wind speed difference value of each two time points from the target time point and the time points, and determining whether the wind speed data of each layer height of the target time point has a dead value based on the wind speed difference value of each two time points and a second threshold value.

[0148] Optionally, the modifying the wind speed data of the target time point based on the variation trend of the target NWP data and the adjustment coefficient of each layer height comprises:

[0149] Determining the deviation value of the NWP data of each two adjacent time points in the second target time period based on the variation trend of the target NWP data, wherein the second target time period comprises a time period before the target time point and a time period after the target time point;

[0150] In the case that the number of positive values is greater than the number of negative values in the deviation value of the NWP data of each two adjacent time points, increasing the NWP data of the target time point, and multiplying the adjustment coefficient of the corresponding layer height to obtain the modified wind speed data of the target time point; or,

[0151] In the case that the number of negative values is greater than the number of positive values in the deviation value of the NWP data of each two adjacent time points, decreasing the NWP data of the target time point, and multiplying the adjustment coefficient of the corresponding layer height to obtain the modified wind speed data of the target time point.

[0152] The wind farm measured data correction device provided by the application can realize Figures 1-3 The method embodiment realizes each process and achieves the same technical effect, and thus details are not repeated here.

[0153] Figure 5 An example of an electronic device is shown in the physical structure diagram, such as Figure 5As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the wind farm measured data correction method, which includes:

[0154] Determining wind speed data measured at a target time in a wind farm, wherein the wind speed data includes wind speed data corresponding to each floor height of a wind tower in the wind farm;

[0155] Based on the wind speed data at the previous moment, the wind speed data within the first target period, the wind speed limit interval and the wind speed change threshold of the adjacent floor height, it is determined whether the wind speed data at the target moment is abnormal. If the wind speed data at the target moment is abnormal, the wind speed data at the target moment is corrected according to the change trend of the latest target numerical weather forecast NWP data.

[0156] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0157] On the other hand, the present invention further provides a computer program product, comprising a computer program, which may be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the wind farm measured data correction method provided by the above methods, which includes:

[0158] Determining wind speed data measured at a target time in a wind farm, wherein the wind speed data includes wind speed data corresponding to each floor height of a wind tower in the wind farm;

[0159] Determine whether the wind speed data of the target moment is abnormal based on the wind speed data of the previous moment, the wind speed data in the first target period, the wind speed limit interval and the adjacent layer height wind speed change threshold, and in the case that the wind speed data of the target moment is abnormal, correct the wind speed data of the target moment according to the change trend of the latest target numerical weather prediction (NWP) data.

[0160] In another aspect, the application further provides a non-transitory computer readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the wind farm measured data correction method provided by the above method, and the method comprises:

[0161] Determine the wind speed data of the target moment measured by the wind farm, and the wind speed data comprises wind speed data corresponding to each layer height of the wind farm wind measurement tower;

[0162] Determine whether the wind speed data of the target moment is abnormal based on the wind speed data of the previous moment, the wind speed data in the first target period, the wind speed limit interval and the adjacent layer height wind speed change threshold, and in the case that the wind speed data of the target moment is abnormal, correct the wind speed data of the target moment according to the change trend of the latest target numerical weather prediction (NWP) data.

[0163] The device embodiments described above are only schematic, wherein the units illustrated as separate components can or can not be physically separate, and the components illustrated as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme. Those skilled in the art can understand and implement without creative labor.

[0164] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software plus necessary universal hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0165] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; and although the present application has been described in detail with reference to the foregoing embodiments, it should be appreciated by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features thereof can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A wind farm measured data correction method, characterized in that, The method comprises: determining wind speed data of a target time point of a wind farm, wherein the wind speed data comprises wind speed data corresponding to each layer height of a wind measurement tower of the wind farm; determining whether the wind speed data of the target time point is abnormal based on wind speed data of a previous time point, wind speed data within a first target period, a wind speed limit value interval, and a wind speed change threshold value of adjacent layer heights, and in the case that the wind speed data of the target time point is abnormal, correcting the wind speed data of the target time point according to a change trend of the latest target NWP data; wherein the determination of whether the wind speed data of the target time point is abnormal based on the wind speed data of the previous time point, the wind speed data within the first target period, the wind speed limit value interval, and the wind speed change threshold value of adjacent layer heights, and the correction of the wind speed data of the target time point according to the change trend of the latest target NWP data in the case that the wind speed data of the target time point is abnormal comprises: determining whether the wind speed data of the target time point jumps based on the wind speed data of the previous time point of the target time point, and in the case that the wind speed data of the target time point jumps, correcting the wind speed data of the target time point based on the change trend of the NWP data; determining whether the wind speed data of the target time point is a dead value based on the wind speed data of each time point within the first target period, and in the case that the wind speed data of the target time point is a dead value, correcting the wind speed data of the target time point based on the change trend of the target NWP data and an adjustment coefficient of each layer height; determining whether the wind speed data of the target time point is out of limit based on the wind speed limit value interval, and in the case that the wind speed data of the target time point is out of limit, correcting the wind speed data of the target time point based on the change trend of the target NWP data and the adjustment coefficient of each layer height; determining whether the wind speed data of the target time point is reasonable based on the wind speed change threshold value of adjacent layer heights, and in the case that the wind speed data of the target time point is unreasonable, correcting the wind speed data of the target time point based on the change trend of the target NWP data and the adjustment coefficient of each layer height.

2. The wind farm measurement data correction method according to claim 1, characterized in that, The target NWP data comprises NWP data of the target time point; before the correction of the wind speed data of the target time point according to the change trend of the latest target NWP data, the method further comprises: obtaining the latest NWP data of the target time point; or obtaining the latest NWP data of two time points adjacent to the target time point, and calculating the NWP data of the target time point by an interpolation method based on the NWP data of the two time points. The correction of the wind speed data of the target time point based on the change trend of the NWP data comprises:

3. The wind farm measurement data revision method according to claim 1 or 2, characterized by, determining a random number within a target range, and determining a wind speed increasing / decreasing trend of an adjacent time period based on the change trend of the NWP data, wherein the wind speed increasing / decreasing trend comprises an upward trend and a downward trend; in the case that the wind speed increasing / decreasing trend is the upward trend, increasing the wind speed data of the previous time point of the target time point by the random number to obtain the wind speed data of the target time point after correction; or in the case that the wind speed increasing / decreasing trend is the downward trend, decreasing the wind speed data of the previous time point of the target time point by the random number to obtain the wind speed data of the target time point after correction. In a case where the wind speed increasing and decreasing trend is a decreasing trend, the wind speed data of the target time point is obtained by subtracting the random number from the wind speed data of the time point before the target time point.

4. The wind farm measurement data correction method according to claim 1 or 2, characterized by, The method comprises: acquiring wind speed data of each time point in a first target time period, wherein the first target time period is a time period before the target time point; determining a wind speed difference value between each two time points among the target time point and the time points, and determining whether the wind speed data of each layer height at the target time point has a dead value based on the wind speed difference value between each two time points and a second threshold value.

5. The wind farm measurement data correction method according to claim 1 or 2, characterized by, The method comprises: determining a deviation value of NWP data between each two adjacent time points in a second target time period based on the change trend of the target NWP data, wherein the second target time period comprises a time period before the target time point and a time period after the target time point; in a case where the number of positive values is greater than the number of negative values among the deviation values of NWP data between each two adjacent time points, increasing the NWP data of the target time point and multiplying the adjustment coefficient of the corresponding layer height to obtain the wind speed data of the target time point after correction; or in a case where the number of negative values is greater than the number of positive values among the deviation values of NWP data between each two adjacent time points, decreasing the NWP data of the target time point and multiplying the adjustment coefficient of the corresponding layer height to obtain the wind speed data of the target time point after correction.

6. A wind farm measured data correction device characterized by comprising: The method comprises: a data determination module configured to determine wind speed data of a target time point measured by a wind farm, wherein the wind speed data comprises wind speed data corresponding to each layer height of a wind measurement tower of the wind farm; a data correction module configured to determine whether the wind speed data of the target time point is abnormal based on wind speed data of a time point before the target time point, wind speed data in a first target time period, a wind speed limit value interval, and a wind speed change threshold value of adjacent layer heights, and correct the wind speed data of the target time point according to a latest change trend of target NWP data in a case where the wind speed data of the target time point is abnormal. The data correction module is specifically configured to: determine whether the wind speed data of the target time point jumps based on the wind speed data of a time point before the target time point, and correct the wind speed data of the target time point based on the change trend of the NWP data in a case where the wind speed data of the target time point jumps; determine whether the wind speed data of the target time point is a dead value based on the wind speed data of each time point in the first target time period, and correct the wind speed data of the target time point based on the change trend of the target NWP data and the adjustment coefficient of each layer height in a case where the wind speed data of the target time point is a dead value; determine whether the wind speed data of the target time point is out of limit based on the wind speed limit value interval, and correct the wind speed data of the target time point based on the change trend of the target NWP data and the adjustment coefficient of each layer height in a case where the wind speed data of the target time point is out of limit; Determine whether the wind speed data at the target time is reasonable based on the adjacent layer height wind speed variation threshold value, and in the case that the wind speed data at the target time is unreasonable, correct the wind speed data at the target time based on the variation trend of the target NWP data and the adjustment coefficient of each layer height.

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the steps of the wind farm measured data correction method according to any one of claims 1 to 5 when executing the program.

8. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the wind farm measured data correction method according to any one of claims 1 to 5.

9. A computer program product comprising a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the wind farm measured data correction method according to any one of claims 1 to 5. The computer program, when executed by the processor, implements the steps of the wind farm measured data correction method according to any one of claims 1 to 5.

Images