Wind power plant control method, device, equipment, storage medium and product

Abstract

The invention discloses a wind power plant control method, device and equipment, a storage medium and a product, and relates to the technical field of wind power plant control. According to the method, the prediction state data of each fan in the wind power plant at the same moment after the current moment is obtained, a local optimization target is set for each fan, calculation of the local optimal solution is carried out, and global optimization is carried out on the plurality of local optimal solutions through the global optimization algorithm, so that the optimization efficiency of the wind power plant is improved. Real-time mutual influence of a plurality of fans in the wind power plant is considered, a global optimal solution (namely, optimized fan state parameters) of the whole wind power plant is finally obtained, and the fans are controlled according to the global optimal solution, so that the rotor overlapping area between the fans can be effectively reduced, the overall active power of the wind power plant is maximized, the optimal power generation benefit is realized, and the wind power generation efficiency is improved. And the power generation efficiency of the wind power plant is improved.

Description

Technical Field

[0001] The present application relates to the technical field of wind farm control, and particularly relates to a wind farm control method, device, equipment, storage medium and product. Background Art

[0002] In the related art, with the continuous improvement of offshore wind turbine manufacturing technology, wind turbine installation technology and wind farm operation and maintenance technology, the prospect of offshore wind power generation is very broad. Among them, floating wind farms can generate higher energy and have less environmental impact.

[0003] During the operation of a wind farm, the wake effect has a serious impact on the output of the active power of the power station.

[0004] Therefore, how to minimize the impact of the wake effect on the power generation efficiency of a wind farm is an urgent problem to be solved at present. Summary of the Invention

[0005] The main purpose of the present application is to provide a wind farm control method, device, equipment, storage medium and product, aiming to solve the technical problem of how to minimize the impact of the wake effect on the power generation efficiency of a wind farm.

[0006] To achieve the above object, the present application proposes a wind farm control method, and the wind farm control method includes: Obtain the predicted state data of each wind turbine in the wind farm at the same moment after the current moment; For each of the wind turbines, calculate the local optimal solution of the corresponding wind turbine state based on the predicted state data, the predicted state data of the neighboring wind turbines of the wind turbine, and a local optimization objective; wherein, the local optimization objective is to minimize the sum of the rotor overlapping areas of the wind turbine and each of the neighboring wind turbines; Based on a global optimization objective, globally optimize the local optimal solutions of the states of multiple wind turbines to obtain the optimized wind turbine state parameters corresponding to the current moment; wherein, the global optimization objective is to maximize the total power generation of multiple wind turbines; Use the optimized wind turbine state parameters to control multiple wind turbines.

[0007] In some embodiments, the calculating the local optimal solution of the corresponding wind turbine state based on the predicted state data, the predicted state data of the neighboring wind turbines of the wind turbine, and the local optimization objective includes: Based on the predicted state data, the predicted state data of the neighboring wind turbines of the wind turbine, and the local optimization objective, establish an objective function; the objective function includes a yaw deviation penalty term with respect to the free incoming wind direction; Based on the objective function, calculate the local optimal solution of the corresponding wind turbine state.

[0008] In some embodiments, the yaw deviation penalty term constrains the axial induction coefficient to 1 / 3.

[0009] In some embodiments, obtaining the predicted state data of each wind turbine in the wind farm at the same moment after the current moment includes: Obtaining the real-time state data of each wind turbine in the wind farm at the current moment, where the real-time state data includes the yaw angle relative to the free inflow wind direction, the axial induction coefficient, and the platform parameters of the platform where the wind turbine is located; For each wind turbine, using the real-time data as input and performing prediction using a pre-trained wind turbine state prediction model to obtain the predicted state data of the wind turbine at the same moment, where the predicted state data includes the platform parameters of the platform where the wind turbine is located.

[0010] In some embodiments, the platform parameters include the downwind platform parameters and / or the crosswind platform parameters of the platform where the wind turbine is located relative to the free inflow wind direction.

[0011] In some embodiments, calculating the corresponding local optimal solution of the wind turbine state based on the predicted state data, the predicted state data of the neighboring wind turbines of the wind turbine, and the local optimization objective includes: Based on the platform parameters of the wind turbine at the same moment and the platform parameters of the neighboring wind turbines of the wind turbine at the same moment, determining the platform parameters corresponding to the wind turbine when the rotor overlapping area with the neighboring wind turbines is the smallest as the optimal platform parameters; Based on a preset optimization algorithm, calculating the yaw angle and the axial induction coefficient required to change from the platform parameters to the optimal platform parameters as the local optimal solution.

[0012] In addition, to achieve the above object, the present application also proposes a wind farm control device, which includes: A prediction module, configured to obtain the predicted state data of each wind turbine in the wind farm at the same moment after the current moment; A local optimization module, configured to, for each wind turbine, calculate the corresponding local optimal solution of the wind turbine state based on the predicted state data, the predicted state data of the neighboring wind turbines of the wind turbine, and the local optimization objective; where the local optimization objective is to minimize the sum of the rotor overlapping areas of the wind turbine with each neighboring wind turbine; A global optimization module, configured to globally optimize multiple local optimal solutions of the wind turbine states based on the global optimization objective to obtain the optimized wind turbine state parameters corresponding to the current moment; where the global optimization objective is to maximize the total power generation of multiple wind turbines; A control optimization module for controlling multiple wind turbines by using the optimized wind turbine state parameters.

[0013] In addition, to achieve the above object, the present application also provides a wind farm control device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the wind farm control method as described above.

[0014] In addition, to achieve the above object, the present application also provides a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the wind farm control method as described above are implemented.

[0015] In addition, to achieve the above object, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the wind farm control method as described above are implemented.

[0016] One or more technical solutions proposed by the present application have at least the following technical effects: By obtaining the predicted state data of each wind turbine in the wind farm at the same moment after the current moment, not only a local optimization target is set for each wind turbine to calculate the local optimal solution, but also the global optimization algorithm is used to globally optimize multiple local optimal solutions, taking into account the real-time mutual influence of multiple wind turbines in the wind farm, and finally obtaining the global optimal solution of the entire wind farm (i.e., the optimized wind turbine state parameters), and controlling the wind turbines accordingly, which can effectively reduce the rotor overlap area between wind turbines, thereby maximizing the total active power of the wind farm, achieving the optimal power generation benefit, and improving the power generation efficiency of the wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0018] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0019] Figure 1 Shows a schematic flow chart of the wind farm control method provided by an embodiment of the present application; Figure 2 Shows a schematic architecture diagram of a simulation tool provided by an exemplary embodiment of the present application; Figure 3 The structural schematic diagram of the fan state prediction model provided by an exemplary embodiment of the present application is shown; Figure 4 The structural schematic diagram of the wind farm control device provided by an embodiment of the present application is shown; Figure 5 The structural schematic diagram of the wind farm control equipment provided by an embodiment of the present application is shown.

[0020] The realization of the purpose, functional characteristics and advantages of the present application will be further described in conjunction with the embodiments with reference to the accompanying drawings. Specific embodiments

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solution of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, the following will be described in detail in conjunction with the accompanying drawings of the specification and specific embodiments.

[0023] The main solution of the embodiment of the present application is: obtaining the predicted state data of each fan in the wind farm at the current moment; for each of the fans, calculating the corresponding local optimal solution based on the predicted state data, the predicted state data of the neighbor fans of the fan, and the local optimization objective; wherein, the local optimization objective is to minimize the sum of the rotor overlapping areas of the fan and each of the neighbor fans; based on the global optimization objective, globally optimizing a plurality of the local optimal solutions to obtain the optimized parameters corresponding to the current moment; wherein, the global optimization objective is to maximize the total power generation of a plurality of the fans, and the optimized parameters include the optimized yaw angle and the axial induction coefficient; using the optimized parameters to control a plurality of the fans.

[0024] In the related art, due to the randomness, volatility and reverse peak shaving characteristics of wind power itself, it is necessary to generate electricity in clusters to ensure its safe grid connection and tracking of the power demand of the power system. The resources of offshore wind farms are stable and rich. In recent years, with the continuous improvement of the manufacturing technology of offshore wind turbines, the fan installation technology and the operation and maintenance technology of wind farms, the prospect of offshore wind power generation is very broad. Among them, compared with fixed offshore wind farms, floating wind farms can generate higher energy and have lower environmental impacts, but the investment cost is higher, so it is necessary to focus on the economic benefits of the operation and power generation of floating wind farms.

[0025] During the operation of the wind farm, the wake effect has a serious impact on the output of the active power of the electric field. Under extreme conditions, the power loss of the downstream fans can reach 50%.

[0026] In summary, how to minimize the impact of wake effects on the power generation efficiency of a wind farm and maximize the power generation benefit of the wind farm is an urgent problem to be solved currently.

[0027] Based on this, the present application provides a solution, enabling multiple wind turbines in a wind farm to minimize the rotor overlap area between each other, thereby minimizing the impact of wake effects on the power generation efficiency of the wind farm and improving the overall power generation efficiency of the wind farm.

[0028] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a wind farm control device capable of implementing the above functions. Hereinafter, taking the wind farm control device as an example, this embodiment and the following embodiments will be described.

[0029] Referring to Figure 1 , Figure 1 FIG. shows a schematic flowchart of a wind farm control method provided by an embodiment of the present application. The wind farm control method can be applied to a wind farm control device and includes the following steps S110 to S140: Step S110, obtaining the predicted state data of each wind turbine in the wind farm at the same moment after the current moment.

[0030] In this embodiment, the wind farm refers to a floating wind farm, and each wind turbine therein can correspond to a floating platform. The floating platform can move within a certain range. In this embodiment, the movable characteristic of the platform is utilized to minimize the rotor overlap area between the wind turbines, thereby maximizing the active power (i.e., power generation efficiency) of the entire wind farm.

[0031] In this embodiment, multiple wind turbines can be arranged in a preset array. The rotors (i.e., wind turbines) of adjacent wind turbines may overlap in the direction of the incoming wind, thereby causing the generation of wake effects.

[0032] Among them, the wake effect refers to that when the wind passes through the wind turbine, due to the rotation of the turbine blades, the wind speed and direction change, thereby forming a disturbed airflow called "wake" behind the turbine, and this wake will have an impact on other turbines downstream.

[0033] In this embodiment, a fixed control period can be preset. That is, the "same moment after the current moment" in this embodiment can refer to one or more moments corresponding to after one or more control periods after the current moment. As a preference, in this embodiment, it can refer to the next moment after one control period after the current moment. For ease of understanding, the next moment referred to in the subsequent embodiments is the moment corresponding to after one control period after the current moment.

[0034] To avoid the influence of wake effect on other wind turbines, in this embodiment, first, based on the wind turbine state prediction model, the platform parameters of each wind turbine's platform at the next moment are predicted. It can be understood that based on the prediction results, we can use the optimization algorithm in the subsequent embodiments to solve the solution that minimizes the overall wake effect of the wind farm, and then make relevant adjustments to the wind turbines based on this solution, so that the final overall active power is maximized and the optimal power generation benefit is achieved.

[0035] In this embodiment, the real-time state data of each wind turbine in the wind farm at the current moment can be obtained; for each wind turbine, the real-time state data is used as the input, and the pre-trained wind turbine state prediction model is used to perform the prediction to obtain the predicted state data of the wind turbine at the next moment. The predicted state data includes the platform parameters of the platform at the next moment.

[0036] Among them, the real-time state data includes the yaw angle relative to the free inflow wind direction, the axial induction coefficient, and the platform parameters of the platform where it is located. The free inflow wind direction refers to the direction of the natural wind in the actual environment, and the yaw angle refers to the angle between the axis of the wind turbine and the free inflow wind direction. The axial induction coefficient is a parameter in wind turbine aerodynamics used to describe the velocity change in the axial direction when the inflow wind passes through the wind turbine blades.

[0037] The platform parameters can include the downwind platform parameters and / or the crosswind platform parameters of the platform where the wind turbine is located relative to the free inflow wind direction. As a preference, in this embodiment, the platform parameters include the downwind platform position, the downwind platform speed, the crosswind platform position, and the crosswind platform speed of the platform where the wind turbine is located. It can be understood that the "platform position" referred to in this embodiment is based on the overall wind farm, and the platforms where different wind turbines are located are all in the same preset wind farm coordinate system.

[0038] In some embodiments, the wind turbine state prediction model can be pre-trained based on a large amount of simulation data. Specifically, we can first build a simulation tool for a floating wind farm, and the overall input and output of the simulation tool can be as Figure 2 shown. Among them, we can preset the simulation parameters such as the yaw angle, the axial induction coefficient, and the free inflow wind speed of each wind turbine during the simulation. After the definition is completed, relevant other related data can be calculated based on these, specifically including the following ①-③: ① The aerodynamic module can calculate the effective wind speed incident on each floating wind turbine rotor according to the aforementioned set simulation parameters; where the effective wind speed refers to the wind speed actually acting on the wind turbine rotor on the wind turbine rotor plane, considering the yaw angle of the wind turbine, the change of wind direction, and the movement of the wind turbine itself. In this embodiment, the axial induction coefficient can be set to randomly vary between 0.2 and 0.4, and the yaw angle varies between -10° and 10°.

[0039] ② The floating dynamics module receives the effective wind speed from the aerodynamic module. Using the effective wind speed and the aforementioned simulation parameters, the rate of change of the wind turbine state (for predicting future state behavior) and the active power of each wind turbine can be calculated. It can be understood that in the simulation tool, we need to predict the behavior of the wind turbine at the next moment based on the rate of change of the wind turbine to achieve the simulation.

[0040] ③ The motion of the corresponding platform is determined according to the sum of the aerodynamic thrust, hydrodynamic drag, added mass force of each wind turbine, and the mooring rope tension. Among them, the wind turbine rotor is regarded as a brake disc, and the aerodynamic thrust is estimated according to the vortex theory. The hydrodynamic drag and added mass force can be calculated using the Morison formula (where the parameters involved are all pre-set values before the start of the simulation), and the drag and added mass of all submerged components (the same as above, pre-set) are added to provide the total hydrodynamic force. The mooring rope tension is obtained by solving the static catenary problem of being partially stationary on the seabed or completely lifted above the seabed.

[0041] Based on the simulation tool constructed above in ①-③, we can simulate the operation of the wind farm and collect a certain amount of sample data, so as to perform model training to obtain the above-mentioned wind turbine state prediction model.

[0042] Exemplarily, the simulation tool can be run for 100,000 time steps, and the corresponding simulation data can be obtained at each time step during the operation. Use a feedforward neural network for model training, and its neural network structure can be as Figure 3 shown. Among them, the input layer contains 6 input neurons, corresponding to 4 wind turbine states (the position and speed of the platform in the downwind and crosswind directions) and 2 wind turbine inputs (axial induction coefficient and yaw angle relative to the main free incoming wind direction). This input layer conveys the input data to a hidden layer containing 20 neurons with a non-linear sigmoid activation function, and then the hidden layer feeds into the output layer, which contains the predicted state of the wind turbine corresponding to the next sampling moment, that is, the position and speed of the platform in the downwind and crosswind directions at the next moment. As an example, during the model training process, 60 seconds can be set as the prediction period, that is, the neural network performs a prediction at intervals of 60 seconds to complete the training.

[0043] After the wind turbine status prediction model is trained and applied to step S110, the previously obtained real-time status data can be used as the input of the wind turbine status prediction model, and the model outputs to obtain the predicted status data for the next moment (i.e., the position and speed of the platform in the downwind and crosswind directions at the next moment).

[0044] Step S120: For each wind turbine, calculate the corresponding local optimal solution of the wind turbine status based on the predicted status data, the predicted status data of the neighboring wind turbines of the wind turbine, and the local optimization objective.

[0045] As mentioned above, the overall objective to be achieved in this application is to minimize the rotor overlap area between wind turbines for the entire wind farm. To achieve this overall objective, in this embodiment, a local optimization objective can be set for each wind turbine first. The local optimization objective can be set as: maximizing the power generation of its neighboring units (i.e., itself and all adjacent wind turbines), that is, minimizing the sum of the rotor overlap areas between the wind turbine and each neighboring wind turbine.

[0046] It can be understood that the predicted status data represents the status of the platform where the wind turbine is located at the next moment without intervention. However, such a status may not necessarily achieve the status corresponding to the local optimization objective we constructed, that is, it may not necessarily minimize the rotor overlap area. For this reason, in this embodiment, the platform parameters corresponding to the case where the rotor overlap area between the wind turbine and its neighboring wind turbines is minimized can be determined first based on the platform parameters of the neighboring wind turbines of the wind turbine at the next moment, and used as the optimal platform parameters. Simply put, determining the optimal platform parameters means determining a platform parameter that conforms to our concept and can minimize the sum of the rotor overlap areas between the wind turbine and each neighboring wind turbine.

[0047] Based on this, a corresponding objective function can be constructed, and on the basis of the local optimization objective, the objective function is solved by a preset optimization algorithm to calculate the yaw angle and axial induction coefficient required to change the platform parameters from the real-time data to the optimal platform parameters as the local optimal solution.

[0048] As an example, assume that in the current real-time data, the platform parameter is A, and its yaw angle and axial induction coefficient are collectively referred to as x. The platform parameter corresponding to the predicted status data predicted by the wind turbine status prediction model is B, that is, if there is no interference, the platform parameter in the real-time data collected at the next moment will be B.

[0049] Assume that we have determined that the predicted status data of the neighboring wind turbines of the current wind turbine are all fixed values that have been determined. Then we can calculate the current optimal platform parameter C through the foregoing method, that is, when the platform parameter at the next moment is C, the rotor overlap area between the current wind turbine and its neighboring wind turbines is minimized and the active power is maximized.

[0050] Based on this, our goal is to change B in the prediction to C by interfering with x. By setting the objective function and the optimization algorithm, we can gradually solve for y, that is, the values (yaw angle and axial induction coefficient) that need to be interfered with when we want to change B to C.

[0051] When we actively adjust the yaw angle and the axial induction coefficient to y, we can locally achieve the local optimization goal.

[0052] In some embodiments, to avoid excessive displacement of the platform where the wind turbine is located, when establishing the objective function, a penalty term can be added to the objective function. The penalty term can be a yaw deviation penalty term relative to the free inflow wind direction, that is, to constrain the yaw angle of the wind turbine within a preset constraint range. Additionally, a constraint on the axial induction coefficient by the yaw deviation penalty term can also be set. For example, it can be set that the axial induction coefficient is always constrained at the optimal value, that is, 1 / 3.

[0053] Step S130, based on the global optimization goal, globally optimize the local optimal solutions of multiple wind turbine states to obtain the optimized wind turbine state parameters corresponding to the current moment.

[0054] In this embodiment, multiple wind turbines in the wind farm can achieve real-time data communication. During the local optimization process, one local optimization result can affect another local optimization process in real time. For example, assume that after the optimization of wind turbine A, its local optimal solution has been determined, that is, the platform parameters at the next moment will no longer be the predicted B but will be C. For the neighboring wind turbine B of wind turbine A, if the platform parameters of wind turbine A at the next moment change after local optimization, then its own optimization strategy will also change accordingly, because the local optimization in step S120 is always related to the platform parameters of the neighboring wind turbine at the next moment.

[0055] Therefore, we can design a global optimization algorithm with the global optimization goal as the purpose of the global optimization algorithm to dynamically and globally optimize the local optimal solutions of each wind turbine. In the continuous iteration process, the global optimal solution for the entire wind farm can be achieved. At this time, we can obtain the final optimized wind turbine state parameters for each wind turbine in the wind farm, that is, the yaw angle and the axial induction coefficient that can achieve the global optimization goal.

[0056] Step S140, use the optimized wind turbine state parameters to control multiple wind turbines.

[0057] For each wind turbine, the optimized wind turbine state parameters are used for control, so that the positions and angles between the wind turbines can be actively adjusted, minimizing the rotor overlap area between the wind turbines, thereby achieving the highest active power and ensuring the power generation efficiency.

[0058] This embodiment provides a wind farm control method. By obtaining the predicted state data of each wind turbine in the wind farm at the same moment after the current moment, not only local optimization objectives are set for each wind turbine to calculate local optimal solutions, but also a global optimization algorithm is used to globally optimize multiple local optimal solutions, taking into account the real-time mutual influence of multiple wind turbines in the wind farm. Finally, the global optimal solution of the entire wind farm (i.e., the optimized wind turbine state parameters) is obtained, and the wind turbines are controlled accordingly, which can effectively reduce the rotor overlap area between the wind turbines, thereby maximizing the total active power of the wind farm, achieving the optimal power generation efficiency, and improving the power generation efficiency of the wind farm.

[0059] This application also provides a wind farm control device. Please refer to Figure 4 , the wind farm control device 100 includes: A prediction module 110, configured to obtain the predicted state data of each wind turbine in the wind farm at the same moment after the current moment; A local optimization module 120, configured to calculate the corresponding local optimal solution of the wind turbine state for each of the wind turbines based on the predicted state data, the predicted state data of the neighboring wind turbines of the wind turbine, and a local optimization objective; wherein, the local optimization objective is to minimize the sum of the rotor overlap areas between the wind turbine and each of the neighboring wind turbines; A global optimization module 130, configured to globally optimize multiple local optimal solutions of the wind turbine states based on a global optimization objective to obtain the optimized wind turbine state parameters corresponding to the current moment; wherein, the global optimization objective is to maximize the total power generation of multiple wind turbines; A control optimization module 140, configured to control multiple wind turbines by using the optimized wind turbine state parameters.

[0060] The wind farm control device 100 provided by this application adopts the wind farm control method in the above embodiment, and can solve the technical problem of how to minimize the influence of the wake effect on the power generation efficiency of the wind farm. Compared with the prior art, the beneficial effects of the wind farm control device 100 provided by this application are the same as those of the wind farm control method provided by the above embodiment, and other technical features in the wind farm control device 100 are the same as those disclosed in the method of the above embodiment, and will not be elaborated here.

[0061] The present application provides a wind farm control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the wind farm control method in Embodiment 1 above.

[0062] Reference is made below Figure 5 , which shows a schematic structural diagram of a wind farm control device suitable for implementing the embodiments of the present application. The wind farm control device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The wind farm control device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0063] As Figure 5 shown, the wind farm control device 200 may include a processing device 210 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 220 or a program loaded from a storage device 230 into a random access memory (RAM: Random Access Memory) 240. In the RAM 240, various programs and data required for the operation of the wind farm control device are also stored. The processing device 210, the ROM 220, and the RAM 240 are connected to each other through a bus 250. An input / output (I / O) interface 260 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 260: an input device 270 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 280 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 230 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 290. The communication device 290 may allow the wind farm control device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a wind farm control device having various systems, it should be understood that it is not required to implement or include all the systems shown. More or fewer systems may be alternatively implemented or included.

[0064] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 230, or installed from a ROM 220. When the computer program is executed by a processing device 210, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.

[0065] The wind farm control device provided by the present application adopts the wind farm control method in the above-mentioned embodiments, and can solve the technical problem of how to minimize the influence of wake effects on the power generation efficiency of the wind farm. Compared with the prior art, the beneficial effects of the wind farm control device provided by the present application are the same as those of the wind farm control method provided by the above-mentioned embodiments, and other technical features in the wind farm control device are the same as those disclosed in the method of the previous embodiment, and will not be elaborated here.

[0066] It should be understood that each part disclosed in the present application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0067] As described above, the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0068] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the wind farm control method in the above-mentioned embodiments.

[0069] The computer-readable storage medium provided by the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium can be transmitted by any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0070] The above computer-readable storage medium may be included in a wind farm control device; or it may exist independently without being assembled into the wind farm control device.

[0071] The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by a wind farm control device, the wind farm control device can write computer program code for performing the operations of the present application in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages - such as Java, Smalltalk, C++; and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0073] The modules described in the embodiments of the present application can be implemented in software or in hardware. In some cases, the name of the module does not constitute a limitation on the unit itself.

[0074] The readable storage medium provided by the present application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned wind farm control method, and can solve the technical problem of how to minimize the impact of wake effects on the power generation efficiency of the wind farm. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as those of the wind farm control method provided by the above embodiments, and will not be elaborated here.

[0075] The present application also provides a computer program product, including a computer program, which when executed by a processor implements the steps of the wind farm control method as described above.

[0076] The computer program product provided by the present application can solve the technical problem of how to minimize the impact of wake effects on the power generation efficiency of the wind farm. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the wind farm control method provided by the above embodiments, and will not be elaborated here.

[0077] The above are only some embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A wind farm control method, characterized in that: The wind farm control method comprises: Obtain the predicted status data of each wind turbine in the wind farm at the same time after the current time; For each of the wind turbines, based on the predicted state data, the predicted state data of the neighboring wind turbines of the wind turbine, and a local optimization target, a corresponding local optimal solution of the wind turbine state is calculated; wherein the local optimization target is to minimize the sum of the rotor overlap areas of the wind turbine and each of the neighboring wind turbines; Based on the global optimization goal, a plurality of local optimal solutions of the wind turbine states are globally optimized to obtain optimized wind turbine state parameters corresponding to the current moment; wherein the global optimization goal is to maximize the total power generation of the plurality of wind turbines; The optimized fan state parameters are used to control the plurality of fans.

2. The wind farm control method according to claim 1, characterized in that: The calculating the corresponding local optimal solution of the wind turbine state based on the predicted state data, the predicted state data of the neighboring wind turbines of the wind turbine and the local optimization target includes: Establishing an objective function based on the predicted state data, the predicted state data of neighboring wind turbines of the wind turbine, and a local optimization target; the objective function includes a yaw deviation penalty term relative to the free inflow wind direction; Based on the objective function, a corresponding local optimal solution of the wind turbine state is calculated.

3. The wind farm control method according to claim 2, characterized in that: The yaw deviation penalty term constrains the axial inductance coefficient of the wind turbine to 1 / 3.

4. The wind farm control method according to any one of claims 1 to 3, characterized in that: The obtaining of the predicted state data of each wind turbine in the wind farm at the same time after the current time includes: Acquire the real-time status data of each wind turbine in the wind farm at the current moment, wherein the real-time status data includes the yaw angle, the axial induction coefficient and the platform parameters of the platform relative to the free inflow wind direction; For each wind turbine, the real-time status data is used as input, and a pre-trained wind turbine status prediction model is used to perform prediction to obtain the predicted status data of the wind turbine at the same moment, wherein the predicted status data includes platform parameters of the platform.

5. The wind farm control method according to claim 4, characterized in that: The platform parameters include downwind platform parameters and / or crosswind platform parameters of the platform where the wind turbine is located relative to the free inflow wind direction.

6. The wind farm control method according to claim 4, characterized in that: The calculating the corresponding local optimal solution of the wind turbine state based on the predicted state data, the predicted state data of the neighboring wind turbines of the wind turbine and the local optimization target includes: Based on the platform parameters of the wind turbine at the same time and the platform parameters of the neighboring wind turbines at the same time, determining the platform parameters corresponding to the wind turbine when the rotor overlap area with the neighboring wind turbine is minimized as the optimal platform parameters; Based on a preset optimization algorithm, the yaw angle and axial induction coefficient required to change from the platform parameters to the optimal platform parameters are calculated as the local optimal solution.

7. A wind farm control device, characterized in that: The wind farm control device comprises: A prediction module is used to obtain the predicted state data of each wind turbine in the wind farm at the same time after the current time; A local optimization module, for calculating, for each of the wind turbines, a local optimal solution of the corresponding wind turbine state based on the predicted state data, the predicted state data of the neighboring wind turbines of the wind turbine, and a local optimization target; wherein the local optimization target is to minimize the sum of the rotor overlap areas of the wind turbine and each of the neighboring wind turbines; A global optimization module, used to globally optimize the local optimal solutions of the plurality of wind turbine states based on a global optimization objective, to obtain optimized wind turbine state parameters corresponding to the current moment; wherein the global optimization objective is to maximize the total power generation of the plurality of wind turbines; A control and tuning module is used to use the optimized fan state parameters to control the plurality of fans.

8. A wind farm control device, characterized in that: The wind farm control device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the wind farm control method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the wind farm control method according to any one of claims 1 to 6 are implemented.

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

Images