Wind power prediction method and device for multiple anemometer towers

Abstract

The invention discloses a wind power prediction method and device for multiple anemometer towers, and belongs to the field of wind power prediction. The method comprises the following steps: establishing a wind speed coupling model for converting traditional wind speed data into radar wind measurement data according to a conversion model of an inertial coordinate system with respect to a traditional wind speed coordinate system, and establishing a radar wind measurement correction model according to a conversion relation of the inertial coordinate system with respect to a radar coordinate system; inputting the traditional wind speed data and the radar data of the single anemometer tower into the wind speed coupling model and the radar wind measurement correction model respectively to obtain first wind measurement data and second wind measurement data in sequence; calculating fusion data of a single anemometer tower according to the first anemometer data and the second anemometer data, and fusing the fusion data of all single anemometer towers to obtain multi-tower anemometer data; and performing prediction according to the multi-tower wind measurement data to obtain wind speed prediction data at a future moment, and performing calculation to obtain a power prediction result of the wind power plant. The accuracy of wind power plant generation power prediction can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power prediction, and in particular to a method and device for predicting wind power for multiple wind towers. Background Art

[0002] A wind tower is a high tower used to assess wind energy resources. It collects data through sensors at multiple heights such as wind speed, wind direction, and temperature, providing a basis for wind farm site selection, wind turbine layout, and equipment selection. Wind farm power refers to the power generation capacity of the entire farm, which mainly depends on wind speed distribution, wind turbine performance, and layout efficiency. The application of wind towers can improve power generation efficiency and reduce investment risks.

[0003] In the related art, usually only wind measurement data from traditional measuring devices or radar data from wind measurement radars are used to predict wind farm power. This prediction method relying on single data often leads to inaccurate wind farm power prediction results due to the limitations of the data source.

[0004] Based on this, there is an urgent need for a wind power prediction method and device for multiple wind towers to solve the above technical problems. Summary of the invention

[0005] The present invention provides a method and device for predicting wind power using multiple wind towers, which can improve the accuracy of wind farm power prediction. The technical solution is as follows: In one aspect, a method for wind power prediction for multiple wind towers is provided, the method comprising: According to the conversion model of the inertial coordinate system with respect to the traditional wind speed coordinate system, a wind speed coupling model for converting the traditional wind speed data into the radar wind measurement data is established, and according to the conversion relationship of the inertial coordinate system with respect to the radar coordinate system, a radar wind measurement correction model is established; Inputting the traditional wind speed data and radar data of a single wind measurement tower into the wind speed coupling model and the radar wind measurement correction model respectively, and obtaining the first wind measurement data and the second wind measurement data in sequence; Calculating fused data of a single wind measurement tower according to the first wind measurement data and the second wind measurement data, and fusing the fused data of all single wind measurement towers in the target area to obtain multi-tower wind measurement data; Predictions are made based on the multi-tower wind measurement data to obtain wind speed prediction data for future moments, and power prediction results of the wind farm are calculated based on the wind speed prediction data.

[0006] On the other hand, a wind power prediction device for multiple wind towers is provided, the device comprising: A modeling module is used to establish a wind speed coupling model for converting traditional wind speed data into radar wind measurement data according to a conversion model of an inertial coordinate system with respect to a traditional wind speed coordinate system, and to establish a radar wind measurement correction model according to a conversion relationship of an inertial coordinate system with respect to a radar coordinate system; A first calculation module is used to input the traditional wind speed data and radar data of a single wind measurement tower into the wind speed coupling model and the radar wind measurement correction model respectively, and obtain the first wind measurement data and the second wind measurement data in sequence; A second calculation module is used to calculate the fusion data of a single wind measurement tower according to the first wind measurement data and the second wind measurement data, and to fuse the fusion data of all single wind measurement towers in the target area to obtain multi-tower wind measurement data; The third calculation module is used to make predictions based on the multi-tower wind measurement data to obtain wind speed prediction data at a future time, and calculate the power prediction result of the wind farm based on the wind speed prediction data.

[0007] On the other hand, a computer device is provided, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of the above-mentioned method for wind power prediction for multiple wind towers.

[0008] On the other hand, a computer-readable storage medium is provided, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the steps of the wind power prediction method for multiple wind towers are implemented.

[0009] On the other hand, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the wind power prediction method for multiple wind towers are implemented.

[0010] The technical solution provided by the present invention can at least bring the following beneficial effects: through the relationship between the inertial coordinate system, the traditional wind speed coordinate system and the radar coordinate system, the traditional wind measurement data measured by a single wind tower is converted into radar data, and the converted radar data is fused with the corrected real radar data to obtain fused data with higher accuracy, and finally the wind power is predicted based on the fused data of multiple wind towers in the target area to obtain a more accurate power prediction value. This method combines the wind speed behind the wind rotor surface measured by the traditional anemometer and the wind speed directly in front of the wind rotor surface measured by the detection radar to obtain more representative and comprehensive fused wind speed data, and at the same time uses the optimized prediction model to perform power prediction, which greatly improves the accuracy of wind farm power prediction. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0012] Figure 1 It is a flow chart of a method for predicting wind power using multiple wind towers provided in one embodiment of the present invention; Figure 2 It is a structural diagram of a wind power prediction device for multiple wind towers provided by an embodiment of the present invention; Figure 3 It is a hardware architecture diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0014] As mentioned above, existing methods usually only use single tower traditional wind speed data, or only use radar measurement results to correct traditional wind speed data to achieve wind farm power prediction. This method is affected by the limitations of wind speed data, resulting in low accuracy of power prediction results.

[0015] Based on this, the idea of ​​the present invention is to calculate the fusion data reconstructed by fusing the traditional wind speed data and the radar data through the conversion relationship between the traditional wind speed coordinate system and the radar coordinate system, and use The specific implementation of the above concept is described below.

[0016] Please refer to Figure 1 , an embodiment of the present invention provides a method for predicting wind power for multiple wind towers, the method comprising: Step 100, establishing a wind speed coupling model for converting traditional wind speed data into radar wind measurement data according to a conversion model of an inertial coordinate system with respect to a traditional wind speed coordinate system, and establishing a radar wind measurement correction model according to a conversion relationship of an inertial coordinate system with respect to a radar coordinate system; Step 102, inputting the traditional wind speed data and radar data of a single wind measurement tower into the wind speed coupling model and the radar wind measurement correction model respectively, and obtaining first wind measurement data and second wind measurement data in sequence; Step 104, calculating fused data of a single wind tower according to the first wind measurement data and the second wind measurement data, and fusing the fused data of all single wind towers in the target area to obtain multi-tower wind measurement data; Step 106, predicting based on the multi-tower wind measurement data to obtain wind speed prediction data for the future time, and calculating the power prediction result of the wind farm based on the wind speed prediction data.

[0017] In the embodiment of the present invention, the traditional wind measurement data measured by a single wind tower is converted into radar data through the relationship between the inertial coordinate system, the traditional wind speed coordinate system and the radar coordinate system, and the converted radar data is fused with the corrected real radar data to obtain fused data with higher accuracy. Finally, wind power is predicted based on the fused data of multiple wind towers in the target area to obtain a more accurate power prediction value. This method combines the wind speed behind the wind rotor surface measured by the traditional anemometer and the wind speed directly in front of the wind rotor surface measured by the detection radar to obtain more representative and comprehensive fused wind speed data. At the same time, the optimized prediction model is used for power prediction, which greatly improves the accuracy of wind farm power prediction.

[0018] Described below Figure 1 How the various steps are performed.

[0019] First, for step 100, based on the conversion model of the inertial coordinate system with respect to the traditional wind speed coordinate system, a wind speed coupling model for converting traditional wind speed data into radar wind measurement data is established, and based on the conversion relationship between the inertial coordinate system and the radar coordinate system, a radar wind measurement correction model is established.

[0020] Since wind speed can be described as a set of three-dimensional wind speed vectors at each time and space point, in order to convert traditional wind speed data, it is necessary to establish a traditional wind speed vector field coordinate system in the entire space in front of the wind turbine to describe the conversion relationship between traditional wind speed data and the inertial coordinate system.

[0021] For example, in the embodiment of the present invention, the subscript F is used to represent the traditional wind speed coordinate system, and the subscript G is used to represent the inertial coordinate system. In order to facilitate subsequent calculations and processing, the origins of the two coordinate systems are set on the hub of the wind turbine, and the two origins coincide.

[0022] Considering the horizontal inflow angle in the inertial coordinate system rotating around the z-axis of the inertial coordinate system and the vertical inflow angle rotated about the y-axis , we can get the conversion equations of the three wind speed components from the traditional wind speed coordinate system to the inertial coordinate system at any wind measuring point i: Among them, the first transformation matrix from the traditional wind speed coordinate system to the inertial coordinate system is for: Then the conversion matrix from the inertial coordinate system to the traditional wind speed coordinate system is for: Furthermore, in order to facilitate calculation, the embodiment of the present invention uses an uneven flow model for wind speed, that is, the lateral and vertical wind components are both 0, and the longitudinal wind component is determined according to wind field characteristic data including the average stream wind speed, the linear horizontal shear coefficient, the linear vertical shear coefficient, the horizontal inflow angle and the vertical inflow angle, that is, the inertial coordinate is The calculation model of wind speed component at wind measuring point i in the inertial coordinate system is: Substituting the first transformation matrix into the above formula, we can get the first transformation model of the inertial coordinate system with respect to the traditional wind speed coordinate system: in, is the wind speed component at wind measuring point i in the inertial coordinate system; is the coordinate of wind measuring point i in the inertial coordinate system; is the coordinate of wind measuring point i in traditional wind speed coordinates; is the inverse matrix of the first transformation matrix; is the mean longitudinal wind speed; is the linear horizontal shear coefficient; is the linear vertical shear coefficient.

[0023] Since the detection radar installed on the wind tower is easily affected by the vibration of the wind tower, this will cause deviations in the fusion results when data fusion is performed directly in the coordinate system of the detection radar, affecting the accuracy of subsequent calculations. At the same time, considering that the above process establishes a conversion relationship between the traditional wind speed coordinate system and the inertial coordinate system, this embodiment converts the radar data into the inertial coordinate system that is the same as the traditional wind speed coordinate system, thereby facilitating subsequent data fusion.

[0024] Specifically, in the detection radar coordinate system, the correction data includes the yaw angle around the Z axis , the rotation around the 𝑋 axis is the roll angle , the rotation around the Y axis is the pitch angle The radar wind measurement data is measured based on the detection radar coordinate system. The detection radar wind measurement data is converted from the detection radar coordinate system to the inertial coordinate system, and the detection radar measurement error is corrected to make the measurement data accurate and reliable.

[0025] According to the above correction data and the spatial relationship between the detection radar and the inertial coordinate system, the second transformation matrix from the radar coordinate system to the inertial coordinate system can be obtained: : According to the second conversion matrix, the radar wind measurement correction model is established: Wherein, L represents the radar coordinate system; is the second transformation matrix; is the coordinate of wind measurement point i in the radar coordinate system; is the coordinate of the radar launch point in the inertial coordinate system; is the initial line-of-sight wind speed data in the radar coordinate system; It is the second wind measurement data corrected in the inertial coordinate system.

[0026] Since the inertial coordinate system is fixed at the center of the hub and rotates with the yaw system of the wind turbine, the yaw angle is 0, and the yaw transfer matrix is ​​the unit matrix. By establishing the transformation matrix of the radar coordinate system with respect to the inertial coordinate system, the radar wind measurement data error caused by the wind tower vibration is corrected, and the accuracy of wind speed fusion is improved.

[0027] Furthermore, according to the geometric relationship between the radar coordinate system and the inertial coordinate system, it can be concluded that the radar is The measurement result of the wind measuring point i can be obtained by the wind speed component of the point in the inertial coordinate system The calculation results are: Combining the above formula with the first conversion model, we can get the wind speed coupling model: in, is the projection focal length of the wind speed component at wind measuring point i in the inertial coordinate system; This is the first wind measurement data.

[0028] With respect to step 102, conventional wind speed data and radar data of a single wind tower are input into the wind speed coupling model and the radar wind measurement correction model respectively, so as to obtain first wind measurement data and second wind measurement data in sequence.

[0029] After obtaining the wind speed coupling model and the radar wind measurement correction model through the above steps, the traditional wind speed data of a single wind measurement tower can be input into the wind speed coupling model to obtain the first wind measurement data, and the radar data can be input into the radar wind measurement correction model to obtain the second wind measurement data.

[0030] It is worth noting that the wind speed calculated by the wind speed coupling model is It can be regarded as the representation of radar wind measurement data in the inertial coordinate system, and the wind speed can be calculated by the traditional wind speed data in the inertial coordinate system. Therefore, by inputting the traditional wind speed data into the model, the traditional wind speed data can be successfully converted into radar data in the inertial coordinate system, and then integrated with the radar correction data in the same inertial coordinate system.

[0031] With respect to step 104, fused data of a single wind tower is calculated according to the first wind measurement data and the second wind measurement data, and the fused data of all single wind towers in the target area are fused to obtain multi-tower wind measurement data.

[0032] In the embodiment of the present invention, taking into account the measurement time error between the traditional wind measurement data and the radar data, a time-aligned weighted fusion processing method is used to calculate the fused data. Assuming that the time of the first wind measurement data v1 calculated from the traditional wind measurement data is t1, the time of the second wind measurement data v2 calculated from the radar data is t2, and the target time is t, the wind measurement data is aligned: Weighted calculation based on time proximity: In the formula, is the weight of the first wind measurement data; is the weight of the second wind measurement data; A very small constant to prevent division by zero; To fuse data; Furthermore, after obtaining the fused data of a single wind tower, the fused data of all single wind towers in the target area are fused using likelihood estimation to obtain multi-tower wind measurement data: Assume that the fused data of each wind tower is the true wind speed V The result of superimposing Gaussian noise: In the formula, is the fused data of the nth wind tower; is the measurement noise variance of the nth wind tower.

[0033] Since each wind tower is independent of each other, the likelihood function is constructed as follows: Where N is the number of wind towers; Take the natural logarithm to simplify the likelihood function, and use the simplified result to simplify V Derivative is set to 0, and the multi-tower wind data is solved for: The multi-tower wind measurement data of multiple wind measurement towers can be obtained through the above method.

[0034] With respect to step 106, prediction is performed based on the multi-tower wind measurement data to obtain wind speed prediction data at a future time, and a power prediction result of the wind farm is calculated based on the wind speed prediction data.

[0035] In an embodiment of the present invention, wind speed prediction data for future moments are obtained in the following manner: original multi-tower wind measurement data at different moments are accumulated to obtain a multi-tower wind speed sequence with respect to time; a differential equation is established based on the multi-tower wind speed sequence, and the general solution of the differential equation is estimated by least squares to establish a prediction model for wind speed prediction; the original multi-tower wind measurement data is input into the prediction model, and the wind speed prediction data for future moments is obtained as output.

[0036] Specifically, assume that the sequence composed of the original multi-tower wind measurement data is: Where m is the prediction time point, m=1,2,3,…M; is the wind speed at time m; Accumulate the sequence to get a new sequence: Since the above sequence has an exponential growth trend and the growth law has the form of a solution to a first-order differential equation, a first-order differential equation can be constructed as shown below: in, a is the evolution function, which can be expressed as and evolutionary trends; b is the mutual transformation relationship between action quantity and reaction data.

[0037] The general solution to this first-order differential equation is: Parameter column The least squares estimate of is: The calculation results are: Substituting the original multi-tower wind measurement data, we can get the wind speed forecast data for the next moment: In an embodiment of the present invention, calculating the power prediction result of a wind farm based on wind speed prediction data includes: substituting the wind speed prediction data into a wind turbine power characteristic curve established by historical power data of the wind turbine to calculate an initial power prediction value; performing a wavelet transform on the initial power prediction value to obtain an approximate component characterizing a low-frequency trend and a detail component reflecting high-frequency fluctuations; inputting the transformed signal component into a trained prediction model to obtain a weight matrix for predicting the signal component; calculating the prediction value of the signal component based on the weight matrix, and linearly superimposing the prediction results using an inverse wavelet transform to obtain a final rate prediction result.

[0038] Specifically, first define the wind turbine power curve as shown below: In the formula, v cutin is the cut-in wind speed; v e is the rated wind speed; v cutout To cut out the wind speed; P e is the rated power; v is the real-time wind speed; k is the power-wind speed relationship index.

[0039] Substituting the wind speed prediction value calculated in the above steps into the power curve can obtain the initial power prediction value. Since power can be regarded as a discrete signal with time as the independent variable, by performing wavelet decomposition on the power time series, an approximate component representing the low-frequency trend and multiple detail components representing the high-frequency fluctuations can be obtained: In the formula, is the power time series; is the approximate component decomposed; is the kth high frequency component; m is the wavelet decomposition scale; t is the time node Furthermore, it is necessary to train the prediction model. In this embodiment, the BP neural network is optimized to obtain the prediction model. The traditional BP neural network uses the GD method to update the weights, but this method has certain limitations, namely, the overall minimum value cannot be obtained when the gradient descends and the time required for BP neural network training is relatively long.

[0040] Therefore, this embodiment provides an improved method by adding a momentum term during the weight update process: In the formula, is the updated weight; is the learning efficiency of the neural network; is the error between the predicted value and the actual value; z is the number of iterations, z=1,2,…; Takes 0 to 1.

[0041] The optimized iteration refers to the result of the previous iteration. If the gradient directions of the two iterations are consistent, the momentum term will increase the current weight update amplitude, otherwise, it will reduce the update amplitude.

[0042] Furthermore, the historical data is decomposed according to the above wavelet decomposition process, and the corresponding multiple power signal components are obtained. The components are input into the optimized neural network for training to obtain a trained prediction model, and finally the transformed signal components are input into the trained prediction model to obtain a weight matrix for predicting the signal components; the predicted values ​​of the signal components are calculated according to the weight matrix, and the prediction results are linearly superimposed using inverse wavelet transform to obtain the final rate prediction result. The above training process is well known to those skilled in the art and will not be described in detail here.

[0043] Please refer to Figure 2 The embodiment of the present invention provides a wind power prediction device for multiple wind towers, the device comprising: A modeling module 200 is used to establish a wind speed coupling model for converting traditional wind speed data into radar wind measurement data according to a conversion model of an inertial coordinate system with respect to a traditional wind speed coordinate system, and to establish a radar wind measurement correction model according to a conversion relationship of an inertial coordinate system with respect to a radar coordinate system; A first calculation module 202 is used to input the traditional wind speed data and radar data of a single wind tower into the wind speed coupling model and the radar wind measurement correction model respectively, and obtain the first wind measurement data and the second wind measurement data in sequence; A second calculation module 204 is used to calculate the fusion data of a single wind measurement tower according to the first wind measurement data and the second wind measurement data, and to fuse the fusion data of all single wind measurement towers in the target area to obtain multi-tower wind measurement data; The third calculation module 206 is used to make predictions based on the multi-tower wind measurement data to obtain wind speed prediction data at a future time, and calculate the power prediction result of the wind farm based on the wind speed prediction data.

[0044] In the embodiment of the present invention, the conversion model is established in the following manner: Horizontal inflow angle according to wind speed in inertial coordinate system and vertical inflow angle , calculate the first transformation matrix of the wind speed component at the wind measurement point from the traditional wind speed coordinate system to the inertial coordinate system : Among them, G represents the inertial coordinate system; F represents the traditional wind speed coordinate system; According to the coordinates of the target wind measuring point in the inertial coordinate system and the wind characteristic data, a wind speed component calculation model of the wind measuring point at the coordinates is established; According to the first conversion matrix and the wind speed component calculation model, a first conversion model of the inertial coordinate system with respect to the traditional wind speed coordinate system is established: in, is the wind speed component at wind measuring point i in the inertial coordinate system; is the coordinate of wind measuring point i in the inertial coordinate system; is the coordinate of wind measuring point i in traditional wind speed coordinates; is the inverse matrix of the first transformation matrix; is the mean longitudinal wind speed; is the linear horizontal shear coefficient; is the linear vertical shear coefficient.

[0045] In the embodiment of the present invention, it is characterized in that the wind speed coupling model is established by the following formula: in, is the projection focal length of the wind speed component at wind measuring point i in the inertial coordinate system; This is the first wind measurement data.

[0046] In the embodiment of the present invention, it is characterized in that the radar wind measurement correction model is established in the following manner: According to the correction data of the radar coordinates and the spatial relationship between the detection radar and the inertial coordinate system, a second conversion matrix of the coordinates of the radar wind measurement point from the radar coordinate system to the inertial coordinate system is calculated; According to the second conversion matrix, the radar wind measurement correction model is established: Wherein, L represents the radar coordinate system; is the second transformation matrix; is the coordinate of wind measurement point i in the radar coordinate system; is the coordinate of the radar launch point in the inertial coordinate system; is the initial line-of-sight wind speed data in the radar coordinate system; It is the second wind measurement data corrected in the inertial coordinate system.

[0047] In an embodiment of the present invention, it is characterized in that the prediction based on the multi-tower wind measurement data to obtain the wind speed prediction data at a future time includes: The original multi-tower wind measurement data at different times are accumulated and processed to obtain the multi-tower wind speed sequence with respect to time; A differential equation is established according to the multi-tower wind speed sequence, and a least squares estimation is performed on the general solution of the differential equation to establish a prediction model for wind speed prediction; The original multi-tower wind measurement data is input into the prediction model, and the wind speed prediction data at the future moment is obtained as output.

[0048] In an embodiment of the present invention, the step of calculating the power prediction result of the wind farm according to the wind speed prediction data includes: Substituting the wind speed prediction data into a wind turbine generator set power characteristic curve established by historical power data of the wind turbine generator set, and calculating an initial power prediction value; Performing wavelet transformation on the initial power prediction value to obtain an approximate component representing a low-frequency trend and a detail component representing a high-frequency fluctuation; Inputting the transformed signal components into the trained prediction model to obtain a weight matrix for predicting the signal components; The predicted value of the signal component is calculated according to the weight matrix, and the predicted result is linearly superimposed by using inverse wavelet transform to obtain the final rate prediction result.

[0049] It should be noted that the wind power prediction device for multiple wind towers provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the wind power prediction device for multiple wind towers provided in the above embodiment and the wind power prediction method embodiment for multiple wind towers belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0050] The embodiment of the present application also provides a computer device, please refer to Figure 3 The computer device includes a processor and a memory, wherein at least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the wind power prediction method for multiple wind towers provided in the above-mentioned method embodiments.

[0051] An embodiment of the present application also provides a computer-readable storage medium, on which is stored at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the wind power prediction method for multiple wind towers provided in the above-mentioned method embodiments.

[0052] An embodiment of the present application further provides a computer program product, which includes a computer program. A processor of a computer device reads the computer program from a computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the wind power prediction method for multiple wind towers described in any of the above embodiments.

[0053] For the convenience of description, the above system or device is described by dividing it into various modules or units according to its functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0054] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0055] Finally, it should be noted that, in this article, relational terms such as first, second, third and fourth are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0056] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for predicting wind power using multiple wind towers, characterized in that: The method comprises: According to the conversion model of the inertial coordinate system with respect to the traditional wind speed coordinate system, a wind speed coupling model for converting the traditional wind speed data into the radar wind measurement data is established, and according to the conversion relationship of the inertial coordinate system with respect to the radar coordinate system, a radar wind measurement correction model is established; Inputting the traditional wind speed data and radar data of a single wind measurement tower into the wind speed coupling model and the radar wind measurement correction model respectively, and obtaining the first wind measurement data and the second wind measurement data in sequence; Calculating fused data of a single wind measurement tower according to the first wind measurement data and the second wind measurement data, and fusing the fused data of all single wind measurement towers in the target area to obtain multi-tower wind measurement data; Predictions are made based on the multi-tower wind measurement data to obtain wind speed prediction data for future moments, and power prediction results of the wind farm are calculated based on the wind speed prediction data.

2. The method according to claim 1, characterized in that The conversion model is established in the following way: Horizontal inflow angle according to wind speed in inertial coordinate system and vertical inflow angle , calculate the first transformation matrix of the wind speed component at the wind measurement point from the traditional wind speed coordinate system to the inertial coordinate system : Among them, G represents the inertial coordinate system; F represents the traditional wind speed coordinate system; According to the coordinates of the target wind measuring point in the inertial coordinate system and the wind characteristic data, a wind speed component calculation model of the wind measuring point at the coordinates is established; According to the first conversion matrix and the wind speed component calculation model, a first conversion model of the inertial coordinate system with respect to the traditional wind speed coordinate system is established: in, is the wind speed component at wind measuring point i in the inertial coordinate system; is the coordinate of wind measuring point i in the inertial coordinate system; is the coordinate of wind measuring point i in traditional wind speed coordinates; is the inverse matrix of the first transformation matrix; is the mean longitudinal wind speed; is the linear horizontal shear coefficient; is the linear vertical shear coefficient.

3. The method according to claim 2, characterized in that The wind speed coupling model is established by the following formula: in, is the projection focal length of the wind speed component at wind measuring point i in the inertial coordinate system; This is the first wind measurement data.

4. The method according to claim 1, characterized in that The radar wind measurement correction model is established in the following way: According to the correction data of the radar coordinates and the spatial relationship between the detection radar and the inertial coordinate system, a second conversion matrix of the coordinates of the radar wind measurement point from the radar coordinate system to the inertial coordinate system is calculated; According to the second conversion matrix, the radar wind measurement correction model is established: Wherein, L represents the radar coordinate system; is the second transformation matrix; is the coordinate of wind measurement point i in the radar coordinate system; is the coordinate of the radar launch point in the inertial coordinate system; is the initial line-of-sight wind speed data in the radar coordinate system; It is the second wind measurement data corrected in the inertial coordinate system.

5. The method according to claim 1, characterized in that The method of performing prediction based on the multi-tower wind measurement data to obtain wind speed prediction data at a future time includes: The original multi-tower wind measurement data at different times are accumulated and processed to obtain the multi-tower wind speed sequence with respect to time; A differential equation is established according to the multi-tower wind speed sequence, and a least squares estimation is performed on the general solution of the differential equation to establish a prediction model for wind speed prediction; The original multi-tower wind measurement data is input into the prediction model, and the wind speed prediction data at the future moment is obtained as output.

6. The method according to claim 5, characterized in that The calculating the power prediction result of the wind farm according to the wind speed prediction data comprises: Substituting the wind speed prediction data into a wind turbine generator set power characteristic curve established by historical power data of the wind turbine generator set, and calculating an initial power prediction value; Performing wavelet transformation on the initial power prediction value to obtain an approximate component representing a low-frequency trend and a detail component representing a high-frequency fluctuation; Inputting the transformed signal components into the trained prediction model to obtain a weight matrix for predicting the signal components; The predicted value of the signal component is calculated according to the weight matrix, and the predicted result is linearly superimposed by using inverse wavelet transform to obtain the final rate prediction result.

7. A wind power prediction device for multiple wind towers, characterized in that: The device comprises: A modeling module is used to establish a wind speed coupling model for converting traditional wind speed data into radar wind measurement data according to a conversion model of an inertial coordinate system with respect to a traditional wind speed coordinate system, and to establish a radar wind measurement correction model according to a conversion relationship of an inertial coordinate system with respect to a radar coordinate system; A first calculation module is used to input the traditional wind speed data and radar data of a single wind measurement tower into the wind speed coupling model and the radar wind measurement correction model respectively, and obtain the first wind measurement data and the second wind measurement data in sequence; A second calculation module is used to calculate the fusion data of a single wind measurement tower according to the first wind measurement data and the second wind measurement data, and to fuse the fusion data of all single wind measurement towers in the target area to obtain multi-tower wind measurement data; The third calculation module is used to make predictions based on the multi-tower wind measurement data to obtain wind speed prediction data at a future time, and calculate the power prediction result of the wind farm based on the wind speed prediction data.

8. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of any one of the methods described in claims 1-6.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The method comprises a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images