Wind farm wake velocity distribution inversion method, device, equipment and storage medium

Abstract

The application discloses a wind farm wake velocity distribution inversion method, device, equipment and a storage medium. The method comprises the following steps: acquiring the actual thrust load on the top of each wind turbine tower, the rotating speed of each wind turbine, the pitch angle, the cut-in wind speed and the cut-out wind speed; based on the actual thrust load on the top of each wind turbine tower, the rotating speed of each wind turbine, the pitch angle, the cut-in wind speed, the cut-out wind speed and a wind turbine thrust load prediction model function, the inflow velocity of each wind turbine is obtained; based on the inflow velocity of each wind turbine, the wind farm wake velocity distribution is obtained through a wind farm wake velocity model. Through the application, the technical problem of high economic cost of measuring the wind farm wake velocity distribution in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of energy technology, and in particular to a method, apparatus, equipment, and storage medium for inverting the wake velocity distribution of a wind farm. Background Technology

[0002] Within a wind farm, each wind turbine is affected by the wakes of its upstream and downstream units. By coordinating the operation of each turbine to alter the intensity and direction of its wake, the impact of wake losses on the total power output of the wind farm can be minimized, thereby improving the wind farm's power generation efficiency. This method of improving wind farm efficiency requires an accurate description of the wake effect within the wind farm and a timely response to changing wind conditions.

[0003] In existing technologies, lidar is mainly used as a wind speed measuring device to measure the wake of a wind farm. However, lidar is limited by the intensity of the laser beam and the scanning rate, and it is usually unable to measure the velocity distribution of the wake of a wind farm. If lidar is widely deployed in a wind farm, although it can measure the velocity distribution of the wake of a wind farm, this method is not only less accurate, but also more expensive. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and storage medium for inverting the wake velocity distribution of a wind farm, which can solve the technical problems of low accuracy and high economic cost in measuring the wake velocity distribution of wind farms in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] In a first aspect, embodiments of the present invention provide a method for inverting the wake velocity distribution of a wind farm, the method comprising:

[0007] Obtain the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, and cut-out wind speed of each wind turbine;

[0008] Based on the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, cut-out wind speed, and the wind turbine thrust load prediction model function, the inflow velocity of each wind turbine is obtained.

[0009] Based on the inflow velocity of each wind turbine, the wake velocity distribution of the wind farm is obtained through the wind farm wake velocity model.

[0010] Secondly, embodiments of the present invention provide a wind farm wake velocity distribution inversion device, the device comprising:

[0011] The information acquisition module is configured to acquire the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, and cut-out wind speed of each wind turbine.

[0012] The first calculation module is configured to obtain the inflow velocity of each wind turbine based on the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, cut-out wind speed, and the wind turbine thrust load prediction model function.

[0013] The second calculation module is configured to obtain the wake velocity distribution of the wind farm based on the inflow velocity of each wind turbine, using a wind farm wake velocity model.

[0014] Optionally, in one embodiment, the second computing module is configured to:

[0015] Substituting the inflow velocity of each wind turbine into the second preset formula, the loss distribution of the wake velocity of each wind turbine is calculated.

[0016] The wake velocity distribution of the wind farm is obtained by superimposing the loss distribution of the wake velocity of each wind turbine using the wake velocity model of the wind farm.

[0017] Thirdly, embodiments of the present invention also provide an electronic device, including: a memory and a processor; the processor is used to read and execute a computer program stored in the memory to implement the steps of the aforementioned wind farm wake velocity distribution inversion method.

[0018] Fourthly, embodiments of the present invention also provide a computer storage medium storing computer-executable instructions, which, when executed, implement the steps of the aforementioned wind farm wake velocity distribution inversion method.

[0019] Fifthly, embodiments of the present invention also provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the wind farm wake velocity distribution inversion method as described above.

[0020] The beneficial effects of the technical solutions provided by the embodiments of the present invention include:

[0021] The method obtains the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, and cut-out wind speed of each wind turbine. Based on the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, cut-out wind speed, and wind turbine thrust load prediction model function, the inflow velocity of each wind turbine is obtained. The actual thrust load on the top of the wind turbine tower is used as a key parameter for the safe operation of wind turbine units. Relevant measurement devices have been widely deployed in the operation and maintenance of existing wind farms. Therefore, the application of this method does not require the addition of additional sensors, which greatly reduces the economic cost.

[0022] The wake velocity distribution model of the wind farm is obtained by superimposing the wake loss velocity model of the wind turbine. For the parameters in the wake velocity distribution model of the wind farm, the wind turbine inflow velocity calculated by thrust is used for parameter identification, rather than empirical parameters in existing patents or literature. This can reflect the real-time wake velocity distribution of the applied wind farm, and has higher accuracy and better applicability.

[0023] This invention solves the technical problem of high economic cost in measuring the wake velocity distribution of wind farms in the prior art. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart illustrating an embodiment of the wind farm wake velocity distribution inversion method of the present invention;

[0026] Figure 2 for Figure 1 A detailed flowchart of step S30;

[0027] Figure 3 This is a schematic diagram of the coordinate system at the base of the wind turbine tower according to the present invention;

[0028] Figure 4 This is a schematic diagram of the wind farm coordinate system and the wind turbine tower base coordinate system of the present invention;

[0029] Figure 5 This is a schematic diagram of the functional modules of an embodiment of the wind farm wake velocity distribution inversion device of the present invention;

[0030] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0033] In a first aspect, embodiments of the present invention provide a method for inverting the wake velocity distribution of a wind farm.

[0034] In one embodiment, reference is made to Figure 1 , Figure 1 This is a schematic flowchart of an embodiment of the wind farm wake velocity distribution inversion method of the present invention. Figure 1 As shown, the wind farm wake velocity distribution inversion method includes:

[0035] Step S10: Obtain the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, and cut-out wind speed of each wind turbine.

[0036] In this embodiment, wind turbine tower sensors are used to measure the actual thrust load on all wind turbine towers in the wind farm, and to obtain the rotational speed, pitch angle, cut-in wind speed, and cut-out wind speed of each wind turbine. The rotational speed, pitch angle, cut-in wind speed, and cut-out wind speed of the wind turbine are the basic parameters for the actual design, control, and operation and maintenance of wind turbines.

[0037] Step S20: Based on the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, cut-out wind speed, and the wind turbine thrust load prediction model function, the inflow velocity of each wind turbine is obtained.

[0038] In some specific embodiments, step S20 includes:

[0039] The inflow velocity of each wind turbine is calculated by substituting the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, cut-out wind speed, and the wind turbine thrust load prediction model function into the first preset formula.

[0040] The first preset formula is as follows:

[0041]

[0042] In the formula, f obj To optimize the objective function of the problem, T model V is the wind turbine thrust load prediction model function. rotor Let ω be the inflow velocity of the wind turbine, θ be the rotational speed of the wind turbine, and T be the pitch angle of the wind turbine. s V represents the actual thrust load on the top of the wind turbine tower. cut_in For the wind turbine's cut-in wind speed, V cut_out The wind speed cut-off for the wind turbine; "st" is an abbreviation for "subject to," meaning "subject to."

[0043] In this embodiment, the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, cut-out wind speed, and the wind turbine thrust load prediction model function are sequentially substituted into the first preset formula. By performing inversion, the inflow velocity V for each wind turbine can be obtained. rotor In mathematics, the symbol min is used to represent the minimum value in a set of numbers, or the minimum value of a function.

[0044] Using the actual thrust load on the top of the wind turbine tower as a key parameter for the safe operation of wind turbine units, and considering the widespread deployment of relevant measurement devices in existing wind farm operations and maintenance, this method eliminates the need for additional sensors, significantly reducing economic costs. In actual wind turbine operation, wind speed and tower thrust load show a good correlation, and the inflow velocity of the wind turbine can be quickly and accurately obtained using either the momentum blade element theory method or the lookup table method.

[0045] Step S30: Based on the inflow velocity of each wind turbine, the wake velocity distribution of the wind farm is obtained through the wind farm wake velocity model.

[0046] In some specific embodiments, reference is made to Figure 2 , Figure 2 for Figure 1 A detailed flowchart of step S30. (See attached diagram.) Figure 2 As shown, step S30 includes:

[0047] Step S301: Substitute the inflow velocity of each wind turbine into the second preset formula to calculate the loss distribution of the wake velocity of each wind turbine.

[0048] In this embodiment, for the loss distribution of the wake velocity of the i-th wind turbine, the inflow velocity of the i-th wind turbine is substituted into the second preset formula to calculate the loss distribution Δu of the wake velocity of the i-th wind turbine. i The second preset formula is:

[0049]

[0050] In the formula, Δu i Let V be the loss distribution of the wake velocity of the i-th wind turbine, i = 1, 2, ..., n, where n is the number of wind turbines in the wind farm. rotor,i Let C be the inflow velocity of the i-th wind turbine. T,i Let be the thrust coefficient of the i-th wind turbine. ρ is the air density, d i Let σ be the diameter of the i-th wind turbine. y,i Let σ be the width of the wake of the i-th wind turbine in the y-direction. z,i Let z be the width of the wake of the i-th wind turbine in the z-direction. h,iLet be the nacelle height of the i-th wind turbine;

[0051] σ y,i and σ z,i Determined by the following method:

[0052]

[0053] In the formula, α i For y i The coefficient of wreath dilation in the direction, β i For z i The coefficient of wreath dilation in the direction, C y,i For y i The initial wake of the direction, C z,i For z i The initial wake of the direction, refer to Figure 3 , Figure 3 This is a schematic diagram of the coordinate system at the base of the wind turbine tower according to the present invention. Figure 3 As shown, o i (x i ,y i ,z i Let be the coordinate system of the base of the i-th wind turbine. In mathematics, the function exp(x) represents the natural exponential function, that is, the exponential function with the real number e (e≈2.71828) as the base, and its expression is exp(x)=ex.

[0054] Similarly, by substituting the inflow velocity of each wind turbine into the second preset formula, the loss distribution of the wake velocity of each wind turbine can be obtained.

[0055] Step S302: The loss distribution of the wake velocity of each wind turbine is superimposed using the wind farm wake velocity model to obtain the wind farm wake velocity distribution.

[0056] In some specific embodiments, step S302 includes:

[0057] Substitute the loss distribution of the wake velocity of each wind turbine into the wake velocity model of the wind farm to calculate the wake velocity distribution of the wind farm.

[0058] The wake velocity model for a wind farm is as follows:

[0059]

[0060] In the formula, U(X,Y,Z) represents the wake velocity distribution of the wind farm, and V ∞ Let Δu be the inflow velocity of the wind farm. i Let o be the loss distribution of the wake velocity of the i-th wind turbine. i (x i ,y i ,z iLet O(X,Y,Z) be the coordinate system at the base of the i-th wind turbine, and let O(X,Y,Z) be the coordinate system of the wind farm, where i = 1, 2, ..., n, and n is the number of wind turbines in the wind farm. i ,Y i Z i ) represents the coordinates of the base of the i-th wind turbine in the wind farm coordinate system.

[0061] In this embodiment, refer to Figure 4 , Figure 4 This is a schematic diagram of the wind farm coordinate system and the wind turbine tower base coordinate system of the present invention. Figure 4 As shown, o i (x i ,y i ,z i Let O(X,Y,Z) be the coordinate system at the base of the i-th wind turbine, and let O(X,Y,Z) be the coordinate system of the wind farm. i ,Y i Z i Let be the coordinates of the base of the i-th wind turbine in the wind farm coordinate system. Substitute the loss distribution of the wake velocity of each wind turbine into the second preset formula. By superimposing the data, the wake velocity distribution of the wind farm can be calculated.

[0062] In this embodiment, the wind farm wake velocity model is a three-dimensional wake model, which is suitable for describing wakes under different atmospheric stability conditions. The wind farm wake velocity distribution model is obtained by superimposing wind turbine wake deficit velocity models. For the parameters in the wind farm wake velocity distribution model, the inflow velocity of the wind turbine calculated from the thrust is used for parameter identification, rather than empirical parameters from existing patents or literature. This reflects the real-time velocity distribution of the applied wind farm wake, exhibiting higher accuracy and better applicability.

[0063] When performing parameter identification, for the parameter α in the wake velocity distribution U of the wind farm i β i C y,i With C z,i The parameters are fitted by transforming the problem into an optimization problem. To satisfy the requirement that the number of equations in the optimization problem is greater than the number of unknowns, the actual thrust load on the top of each wind turbine tower measured by sensors at m consecutive time points (m≥4) is used as the input, i.e. The subscript i refers to the i-th wind turbine, and the superscript j refers to time j. The inflow velocity of the i-th wind turbine at time j is calculated.

[0064] The unknowns that need to be solved are the parameters of the wind farm wake velocity model U, which form the unknown vector.

[0065] b=[α1C y,1 β1C z,1…α n C y,n β n C z,n ] T

[0066] The optimal objective function is

[0067]

[0068] Solving the above optimization problem yields the parameters in the wind farm wake velocity distribution model. Substituting these parameters into the second preset formula and the wind farm wake velocity model, the wind farm wake velocity distribution can be obtained.

[0069] In this embodiment, the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, and cut-out wind speed of each wind turbine are obtained. Based on the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, cut-out wind speed, and wind turbine thrust load prediction model function, the inflow velocity of each wind turbine is obtained. The actual thrust load on the top of the wind turbine tower is used as a key parameter for the safe operation of the wind turbine. Related measurement devices are already widely deployed in the operation and maintenance of existing wind farms. Therefore, the application of this method does not require the addition of additional sensors, which greatly reduces the economic cost. The wind farm wake velocity distribution model is obtained by superimposing the wind turbine wake loss velocity model. For the parameters in the wind farm wake velocity distribution model, the wind turbine inflow velocity calculated by thrust is used for parameter identification, rather than the empirical parameters in existing patents or literature. This can reflect the real-time velocity distribution of the wind farm wake, and has higher accuracy and better applicability. This embodiment solves the technical problem of high economic cost in measuring the wake velocity distribution of wind farms in the prior art.

[0070] Secondly, embodiments of the present invention also provide a wind farm wake velocity distribution inversion device.

[0071] In one embodiment, reference is made to Figure 5 , Figure 5 This is a functional module diagram of an embodiment of the wind farm wake velocity distribution inversion device of the present invention. Figure 5 As shown, the wind farm wake velocity distribution inversion device includes:

[0072] The information acquisition module 10 is configured to acquire the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed and cut-out wind speed of each wind turbine;

[0073] The first calculation module 20 is configured to obtain the inflow velocity of each wind turbine based on the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, cut-out wind speed, and wind turbine thrust load prediction model function.

[0074] The second calculation module 30 is configured to obtain the wake velocity distribution of the wind farm based on the inflow velocity of each wind turbine, using a wind farm wake velocity model.

[0075] Optionally, in one embodiment, the first computing module 20 is configured to:

[0076] The inflow velocity of each wind turbine is calculated by substituting the actual thrust load on the top of each wind turbine tower, the rotational speed, pitch angle, cut-in wind speed, cut-out wind speed, and the wind turbine thrust load prediction model function into the first preset formula.

[0077] The first preset formula is as follows:

[0078]

[0079] In the formula, f obj To optimize the objective function of the problem, T model V is the wind turbine thrust load prediction model function. rotor Let ω be the inflow velocity of the wind turbine, θ be the rotational speed of the wind turbine, and T be the pitch angle of the wind turbine. s V represents the actual thrust load on the top of the wind turbine tower. cut_in For the wind turbine's cut-in wind speed, V cut_out The wind speed cut-off for the wind turbine; "st" is an abbreviation for "subject to," meaning "subject to."

[0080] Optionally, in one embodiment, the second computing module 30 is configured to:

[0081] Substituting the inflow velocity of each wind turbine into the second preset formula, the loss distribution of the wake velocity of each wind turbine is calculated.

[0082] The wake velocity distribution of the wind farm is obtained by superimposing the loss distribution of the wake velocity of each wind turbine using the wake velocity model of the wind farm.

[0083] Optionally, in one embodiment, the second computing module 30 is configured to:

[0084] For the velocity deficit distribution of the wake of the i-th wind turbine, the inflow velocity of the i-th wind turbine is substituted into the second preset formula to calculate the velocity deficit distribution of the wake of the i-th wind turbine. The second preset formula is:

[0085]

[0086] In the formula, Δu i Let V be the loss distribution of the wake velocity of the i-th wind turbine, i = 1, 2, ..., n, where n is the number of wind turbines in the wind farm. rotor,i Let C be the inflow velocity of the i-th wind turbine. T,i Let be the thrust coefficient of the i-th wind turbine. ρ is the air density, d i Let σ be the diameter of the i-th wind turbine. y,i Let σ be the width of the wake of the i-th wind turbine in the y-direction. z,i Let z be the width of the wake of the i-th wind turbine in the z-direction. h,i Let be the nacelle height of the i-th wind turbine;

[0087] σ y,i and σ z,i Determined by the following method:

[0088]

[0089] In the formula, α i For y i The coefficient of wreath dilation in the direction, β i For z i The coefficient of wreath dilation in the direction, C y,i For y i The initial wake of the direction, C z,i For z i The initial wake of the direction, o i (x i ,y i ,z i Let be the coordinate system of the base of the i-th wind turbine.

[0090] Optionally, in one embodiment, the second computing module 30 is configured to:

[0091] Substitute the loss distribution of the wake velocity of each wind turbine into the wake velocity model of the wind farm to calculate the wake velocity distribution of the wind farm.

[0092] The wake velocity model for a wind farm is as follows:

[0093]

[0094] In the formula, U(X,Y,Z) represents the wake velocity distribution of the wind farm, and V ∞ Let Δu be the inflow velocity of the wind farm. i Let o be the loss distribution of the wake velocity of the i-th wind turbine. i (x i ,y i ,z iLet O(X,Y,Z) be the coordinate system at the base of the i-th wind turbine, and let O(X,Y,Z) be the coordinate system of the wind farm, where i = 1, 2, ..., n, and n is the number of wind turbines in the wind farm. i ,Y i Z i ) represents the coordinates of the base of the i-th wind turbine in the wind farm coordinate system.

[0095] The functions of each module in the wind farm wake velocity distribution inversion device correspond to the steps in the above-mentioned wind farm wake velocity distribution inversion method embodiment, and their functions and implementation processes will not be described in detail here.

[0096] Thirdly, embodiments of the present invention also provide an electronic device, the structure of which is as follows: Figure 6 As shown, it includes: a memory and a processor, wherein the processor is used to read and execute the computer program stored in the memory to implement the aforementioned method for inverting the wake velocity distribution of a wind farm.

[0097] Fourthly, embodiments of the present invention also provide a computer storage medium storing computer-executable instructions, which, when executed, implement the aforementioned method for inverting the wake velocity distribution of a wind farm.

[0098] Fifthly, embodiments of the present invention provide a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the wind farm wake velocity distribution inversion method embodiments described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0099] Finally, it should be noted that while some processes described in the embodiments of the present invention include multiple operations or steps that appear in a specific order, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of the present invention, or may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0100] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A wind farm wake velocity distribution inversion method, characterized in that, The method comprises: obtaining the actual thrust load at the top of each wind turbine tower, the rotational speed of each wind turbine, the pitch angle, the cut-in wind speed and the cut-out wind speed; substituting the actual thrust load at the top of each wind turbine tower, the rotational speed of each wind turbine, the pitch angle, the cut-in wind speed, the cut-out wind speed and the wind turbine thrust load prediction model function into a first preset formula in sequence to calculate the inflow speed of each wind turbine; the first preset formula is as follows: wherein is the objective function of the optimization problem, is the wind turbine thrust load prediction model function, is the inflow velocity of the wind turbine, is the rotational speed of the wind turbine, is the pitch angle of the wind turbine, is the actual thrust load experienced at the top of the wind turbine tower, is the cut-in wind speed of the wind turbine, is the cut-out wind speed of the wind turbine, s.t. is the abbreviation for subject to, meaning "subject to constraints"; based on the inflow speed of each wind turbine, the wake velocity distribution of the wind farm is obtained through a wind farm wake velocity model.

2. A wind farm wake velocity distribution inversion method according to claim 1 characterised in that, The step of obtaining the wake velocity distribution of the wind farm based on the inflow speed of each wind turbine through the wind farm wake velocity model comprises: substituting the inflow speed of each wind turbine into a second preset formula to calculate the loss distribution of the wake velocity of each wind turbine; superimposing the loss distribution of the wake velocity of each wind turbine through the wind farm wake velocity model to obtain the wake velocity distribution of the wind farm.

3. A wind farm wake velocity distribution inversion method according to claim 2, characterised in that, The step of substituting the inflow speed of each wind turbine into a second preset formula to calculate the loss distribution of the wake velocity of each wind turbine comprises: for the loss distribution of the wake velocity of the i-th wind turbine, substituting the inflow speed of the i-th wind turbine into a second preset formula to calculate the loss distribution of the wake velocity of the i-th wind turbine, and the second preset formula is as follows: wherein, is the deficit distribution of the wake velocity of the i-th wind turbine, i = 1, 2,..., n, n being the number of wind turbines in the wind farm, is the inflow velocity of the i-th wind turbine, is the thrust coefficient of the i-th wind turbine, , is the air density, is the diameter of the i-th wind turbine, is the wake width of the i-th wind turbine in the y-direction, is the wake width of the i-th wind turbine in the z-direction, is the hub height of the i-th wind turbine; and Determined by the following method: wherein is the wake expansion coefficient in the is the wake expansion coefficient in the is the initial wake in the is the initial wake in the is the tower base coordinate system of the i-th wind turbine.

4. The wind farm wake velocity distribution inversion method of claim 2, wherein, The step of superimposing the loss distribution of the wake velocity of each wind turbine through the wind farm wake velocity model to obtain the wake velocity distribution of the wind farm comprises: substituting the loss distribution of the wake velocity of each wind turbine into the wind farm wake velocity model to calculate the wake velocity distribution of the wind farm; the wind farm wake velocity model is as follows: wherein is the wind farm wake velocity distribution, is the inflow velocity of the wind farm, is the deficit distribution of the i-th wind turbine wake velocity, is the tower bottom coordinate system of the i-th wind turbine, is the wind farm coordinate system, i = 1, 2,..., n, n is the number of wind turbines in the wind farm, is the tower bottom coordinate of the i-th wind turbine in the wind farm coordinate system.

5. A wind farm wake velocity distribution inversion apparatus, characterized by, The device comprises: an information acquisition module configured to obtain the actual thrust load at the top of each wind turbine tower, the rotational speed of each wind turbine, the pitch angle, the cut-in wind speed and the cut-out wind speed; a first calculation module configured to substitute the actual thrust load at the top of each wind turbine tower, the rotational speed of each wind turbine, the pitch angle, the cut-in wind speed, the cut-out wind speed and the wind turbine thrust load prediction model function into a first preset formula in sequence to calculate the inflow speed of each wind turbine; the first preset formula is as follows: wherein is the objective function of the optimization problem, is the wind turbine thrust load prediction model function, is the inflow velocity of the wind turbine, is the rotational speed of the wind turbine, is the pitch angle of the wind turbine, is the actual thrust load experienced at the top of the wind turbine tower, is the cut-in wind speed of the wind turbine, is the cut-out wind speed of the wind turbine, s.t. is the abbreviation for subject to, meaning "subject to constraints"; a second calculation module configured to obtain the wake velocity distribution of the wind farm based on the inflow speed of each wind turbine through a wind farm wake velocity model.

6. A wind farm wake velocity distribution inversion apparatus according to claim 5, characterised in that, The second calculation module is configured to: substitute the inflow speed of each wind turbine into a second preset formula to calculate the loss distribution of the wake velocity of each wind turbine; superimpose the loss distribution of the wake velocity of each wind turbine through the wind farm wake velocity model to obtain the wake velocity distribution of the wind farm.

7. An electronic device, comprising: comprise: a memory and a processor; the processor is configured to read and execute a computer program stored in the memory to implement the steps of the wind farm wake velocity distribution inversion method according to any one of claims 1-4.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions, and the computer executable instructions execute to implement the steps of the wind farm wake velocity distribution inversion method according to any one of claims 1-4.

9. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instructions, when executed by the processor, implement the steps of the wind farm wake velocity distribution inversion method according to any one of claims 1-4.

Images