Arrangement array verification method and device, storage medium and electronic device

Abstract

The invention discloses an arrangement array verification method and device, a storage medium and an electronic device.The method comprises the steps that N arrangement arrays corresponding to a target wind power plant are obtained, N initial population codes are determined according to the N arrangement arrays, M draught fans exist in each arrangement array, N is an integer greater than or equal to 1, and N is an integer greater than or equal to 2; the distance between any two adjacent fans meets a minimum spacing function, and M and N are positive integers; processing the N initial population codes through a preset fitness function to obtain N groups of adaptive data; and determining target applicable data from the N groups of adaptive data according to a numerical value size rule and a weight preference requirement of the design object, and performing construction verification on the target wind power plant according to the target arrangement array corresponding to the target applicable data. The problem that the arrangement optimization of the fan array and the actual construction cost cannot be effectively balanced is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of wind power, in particular, to a method and device for checking arrangement array, a storage medium and an electronic device. BACKGROUND

[0002] In the traditional design of offshore wind farms, it is often assumed that the wind speed is uniformly distributed in the field, so an equal-interval wind turbine array layout is usually adopted. Although this method is simple and easy to implement, it has obvious limitations in practical applications. Since offshore wind farms are usually located close to the coastline, they are affected by the terrain, buildings and other offshore structures on land, and the distribution of wind speed in the field is often irregular. This irregular distribution can exacerbate the wake effect, directly affecting the overall power generation efficiency of the wind farm. Moreover, the traditional optimization method for offshore wind turbine arrays mainly focuses on single-objective optimization, usually focusing on maximizing power generation, but less considering practical constraints such as construction cost, environmental impact and layout flexibility, resulting in insufficient applicability of the scheme under complex conditions.

[0003] To address the problem that the arrangement optimization of the wind turbine array and the actual construction cost cannot be effectively balanced in the related art, no effective solution has been proposed so far.

[0004] Therefore, it is necessary to improve the related art to overcome the defects in the related art. SUMMARY

[0005] The embodiments of the present application provide a method and device for checking arrangement array, a storage medium and an electronic device to at least solve the problem that the arrangement optimization of the wind turbine array and the actual construction cost cannot be effectively balanced.

[0006] According to an aspect of the embodiments of the present application, a method for checking arrangement array is provided, comprising: obtaining N arrangement arrays corresponding to a target wind farm, and determining N initial population encodings according to the N arrangement arrays, wherein there are M wind turbines in each arrangement array, the distance between any adjacent wind turbines satisfies a minimum spacing function, M and N are positive integers; processing the N initial population encodings through a preset fitness function to obtain N sets of adaptive data; determining target applicable data from the N sets of adaptive data according to a numerical size rule and a weight preference requirement of the design object, and performing construction verification on the target wind farm according to the target arrangement array corresponding to the target applicable data.

[0007] In an example embodiment, before the N initial population encodings are processed by the preset fitness function to obtain N sets of adaptive data, the method further comprises: obtaining a first function for calculating the wake loss corresponding to each initial population encoding; obtaining a second function for calculating the power generation corresponding to each initial population; obtaining a third function for calculating the construction cost corresponding to each initial population; and aggregating the first function, the second function, the third function, and the corresponding weight parameters to obtain the preset fitness function.

[0008] In an example embodiment, before the first function for calculating the wake loss corresponding to each initial population encoding is obtained, the method further comprises: determining the wake velocity of each wind turbine in each initial population encoding according to a wake formula, wherein the wake formula is: v(x) = v0(1 - CT / kx) , v(x) is the wake velocity, v0 is the free stream velocity, CT is the thrust coefficient of the wind turbine, k is the wake expansion coefficient, and x is the distance between wind turbines.

[0009] In an example embodiment, aggregating the first function, the second function, the third function, and the corresponding weight parameters to obtain the preset fitness function comprises: obtaining the maximum power generation, the maximum construction cost, and the maximum wake loss allowed by the target wind farm; determining the target wake loss corresponding to the first function, the target power generation corresponding to the second function, and the target construction cost corresponding to the third function; and substituting the maximum power generation P max , the maximum construction cost C max , the maximum wake loss, the target wake loss, the target power generation P total , and the target construction cost C layout into a target fitness function template to obtain the preset fitness function, wherein the target fitness function template is: f(x) = W1f1(x) + W2f2(x) + W3f3(x) , W1, W2, and W3 are weight coefficients, and W1 + W2 + W3 = 1.

[0010] In an example embodiment, determining the target applicable data from the N sets of adaptive data according to the numerical size rule and the weight preference requirement of the design object comprises: obtaining the adjustment target and the adjustment constraint condition set by the design object for the target wind farm; determining the weight preference requirement according to the adjustment content corresponding to the adjustment target; and determining the numerical size rule according to the condition content corresponding to the adjustment constraint condition.

[0011] In an example embodiment, after the target wind farm is subjected to construction verification according to the target arrangement array corresponding to the target applicable data, the method further comprises: in the case where the verification result of the construction verification indicates that there is deviation in the current construction, adjusting the pre-installation position of the wind turbine according to the target arrangement array; and in the case where the verification result of the construction verification indicates that there is no deviation in the current construction, identifying the wind turbine position that has been completed installation in the target arrangement array.

[0012] According to another aspect of the embodiments of the present application, a verification device for an array is also provided, comprising: an obtaining module, configured to obtain N arrays corresponding to a target wind farm, and determine N initial population encodings according to the N arrays, wherein each array contains M wind turbines, the distance between any adjacent wind turbines satisfies a minimum distance function, M and N are positive integers; a processing module, configured to process the N initial population encodings by using a preset fitness function to obtain N groups of adaptive data; and a determining module, configured to determine target adaptive data from the N groups of adaptive data according to a numerical size rule and a weight preference requirement of a design object, and perform construction verification on the target wind farm according to a target array corresponding to the target adaptive data.

[0013] According to still another aspect of the embodiments of the present application, a computer readable storage medium is also provided, and the computer readable storage medium stores a computer program, wherein the computer program is configured to execute the above-mentioned verification method for an array when running.

[0014] According to still another aspect of the embodiments of the present application, an electronic device is also provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-mentioned verification method for an array by using the computer program.

[0015] According to still another aspect of the embodiments of the present application, a computer program product is also provided, comprising a computer program, and the computer program executes the above-mentioned verification method for an array when executed by a processor.

[0016] By the present application, N arrangement arrays corresponding to the target wind farm are obtained, and integer coding is used to represent N initial population encodings according to the position coordinates of each wind turbine, wherein each arrangement array contains M wind turbines, and the distance between any two wind turbines is at least equal to L (4 to 7 times the diameter of the wind turbine) defined by the minimum spacing function, and M and N are positive integers. By using a pre-set fitness function, the power generation, construction cost and wake effect are calculated respectively, and N initial population encodings are processed to obtain N sets of adaptive data. According to the numerical size rule and the weight preference of the decision maker, a Pareto optimal solution set satisfying the three objectives of maximizing power generation, minimizing construction cost and minimizing wake effect is selected from the N sets of adaptive data. When the pre-set iteration number is reached or the Pareto optimal solution set is stable, the optimal scheme is output, that is, one or more arrangement arrays satisfying the specific weight preference are selected from the Pareto optimal solution set as the construction verification basis of the target wind farm. The problem that the arrangement optimization of the wind turbine array and the actual construction cost cannot be effectively balanced is solved, the best balance point between multiple optimization objectives is effectively found, the limitations of the traditional single-objective optimization method in dealing with complex offshore wind farm layout and construction conditions are overcome, and a scientific, reasonable, efficient and environmentally friendly design scheme for the planning and construction of offshore wind power projects is provided. BRIEF DESCRIPTION OF DRAWINGS

[0017] The drawings incorporated into the specification and forming a part thereof illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the application.

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, those skilled in the art can obtain other drawings according to these drawings without any creative effort.

[0019] Figure 1 is a hardware structure block diagram of a computer terminal of a verification method of an arrangement array according to an embodiment of the present application;

[0020] Figure 2 is a flowchart of a verification method of an arrangement array according to an embodiment of the present application;

[0021] Figure 3 is a flowchart of an offshore wind turbine array optimization method based on a multi-objective and genetic algorithm according to an embodiment of the present application;

[0022] Figure 4 is a structure block diagram of a verification device of an arrangement array according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the personnel in the technical field better understand the scheme of the present application, the technical scheme in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor should be within the scope of protection of the present application.

[0024] It should be noted that the terms first, second, etc. in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms include and have and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to the clearly listed steps or units, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal, a mobile terminal or a similar computing device. Taking the running on a computer terminal as an example, Figure 1 is a hardware structure block diagram of a computer terminal of a method for checking an arrangement array according to an embodiment of the present application. As Figure 1 shown, the computer terminal can include one or more (only one is shown in Figure 1 ) processor 102 (the processor 102 can include but is not limited to a central processing unit (CPU) or a programmable logic device (FPGA) and the like processing device) and a memory 104 for storing data, wherein the above-mentioned computer terminal can further include a transmission device 106 for communication function and an input and output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only schematic, which does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal can include more or less components than Figure 1 shown, or have a different configuration from Figure 1 shown.

[0026] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as a computer program corresponding to the adjustment method of the monitoring network point in the embodiments of the present application. The processor 102 performs various functional applications and data processing by running the computer programs stored in the memory 104, that is, implements the above method. The memory 104 can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged with respect to the processor 102, and the remote memory can be connected to the computer terminal through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0027] The transmission device 106 is used to receive or send data via a network. Specific examples of the above network can include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC) which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, RF) module which is used to communicate with the Internet in a wireless manner.

[0028] In the embodiments, a verification method of an arrangement array is provided, Figure 2 is a flowchart of a verification method of an arrangement array according to the embodiments of the present application, as shown in Figure 2 The flowchart includes the following steps S202-S206:

[0029] Step S202: Obtain N arrangement arrays corresponding to a target wind farm, and determine N initial population encodings according to the N arrangement arrays, wherein there are M wind turbines in each arrangement array, the distance between any adjacent wind turbines satisfies a minimum spacing function, and M and N are positive integers.

[0030] It can be understood that in the starting stage of the optimization process, a plurality of wind turbine array layout schemes need to be constructed as inputs of the algorithm, and these layouts are referred to as arrangement arrays. For a specific wind farm (target wind farm), the algorithm generates N different arrangement arrays, and each array contains M wind turbines. In order to ensure the feasibility of the wind turbine layout, a certain minimum safety distance must be maintained between any adjacent wind turbines, and this distance is defined by the minimum spacing function, which is usually 4 to 7 times the diameter of the wind turbine. In this step, each arrangement array is converted into an initial population encoding, and the encoding contains the position coordinate information of each wind turbine.

[0031] Step S204: Process the N initial population encodings through a preset fitness function to obtain N sets of adaptive data; that is, once the initial population encodings of the N arrangement arrays are obtained, a preset fitness function is used to evaluate the performance of the arrangement arrays. The fitness function comprehensively considers the optimization degree of multiple objectives such as power generation, construction cost and wake effect, and the performance evaluation result of each arrangement array is referred to as a set of adaptive data. In this step, each set of adaptive data reflects the performance of the corresponding arrangement array on each optimization objective.

[0032] Step S206: Determine the target adaptive data from the N sets of adaptive data according to the numerical size rule and the weight preference requirement of the design object, and perform construction verification on the target wind farm according to the target arrangement array corresponding to the target adaptive data.

[0033] That is, after obtaining N sets of adaptive data, the algorithm needs to select the arrangement scheme that best meets the design requirements, i.e., the target adaptive data, from these data according to the target weight set by the designer in advance (i.e., the emphasis on power generation, construction cost, etc.) and the numerical size rule (such as maximum or minimum priority). Due to the multi-objective optimization characteristics of genetic algorithm, multiple Pareto optimal solutions may be generated, which achieve optimal balance between different objectives. Designers can choose the most suitable arrangement array from these optimal solutions according to their own preferences (such as more emphasis on cost or power generation).

[0034] Finally, the selected target arrangement array will be used to guide the actual construction of the target wind farm, and the feasibility of the scheme will be further confirmed through construction verification, including evaluating the construction cost, whether the actual distance between wind turbines meets the safety requirements, and the actual power generation efficiency and other key indicators.

[0035] The above steps, obtain N corresponding to the target wind farm array, and according to the position coordinates of each wind turbine, using integer coding to represent N initial population coding, wherein each array contains M wind turbines, and ensure that the distance between any two wind turbines is at least equal to L (4 to 7 times the diameter of the wind turbine) defined by the minimum spacing function, M, N are positive integers. Through the preset fitness function, the power generation, construction cost and wake effect are calculated respectively, and N initial population coding is processed to obtain N adaptive data. According to the numerical size rule and the weight preference of the decision maker, the Pareto optimal solution set meeting the three objectives of maximizing power generation, minimizing construction cost and minimizing wake effect is selected from N adaptive data. When the preset iteration number is reached or the Pareto optimal solution set is stable, the optimal scheme is output, that is, one or more array arrangements meeting the specific weight preference are selected from the Pareto optimal solution set as the construction verification basis of the target wind farm. The problem of balancing the optimization of wind turbine array and the actual construction cost is solved, the best balance point between multiple optimization objectives is effectively found, the limitations of traditional single objective optimization method in dealing with complex offshore wind farm layout and construction conditions are overcome, and a scientific, reasonable, efficient and environmentally friendly design scheme for the planning and construction of offshore wind power projects is provided.

[0036] In an exemplary embodiment, before N initial population coding is processed by the preset fitness function to obtain N adaptive data, the above method further comprises: obtaining a first function for calculating the wake loss corresponding to each initial population coding; obtaining a second function for calculating the power generation corresponding to each initial population coding; obtaining a third function for calculating the construction cost corresponding to each initial population coding; and obtaining the preset fitness function by aggregating the first function, the second function, the third function and the corresponding weight parameters.

[0037] Wake loss refers to the fact that in an offshore wind farm, the wake generated by the front row of wind turbines will affect the wind speed of the rear row of wind turbines, thereby reducing the power generation efficiency. In order to measure this factor, a mathematical model, the first function, needs to be established, which can predict the wind speed decay of each wind turbine according to the layout, relative position and wind speed distribution of the wind turbine. This function will be applied to each initial population coding to calculate the total wake loss under the array arrangement.

[0038] Power generation is the most direct concern in wind farm operation. In order to estimate the potential power generation of each array arrangement, a second function needs to be constructed, which is usually based on the specification parameters of the wind turbine (such as swept area, rotor diameter), wind resource data (such as average wind speed, wind direction, etc.) and wake model (taking into account the influence of wind speed decay). Through the second function, the expected power generation of each array arrangement in a year can be calculated, providing a basis for economic benefit evaluation.

[0039] Construction cost involves the economic evaluation of wind farm construction, including wind turbine installation costs, cable laying costs, foundation construction costs, etc. The purpose of constructing the third function is to accurately calculate the total cost of each array in the construction phase, taking into account factors such as water depth, turbine spacing, and construction path planning, to ensure that the design scheme is not only efficient but also economically feasible.

[0040] In the multi-objective optimization scenario, pursuing the optimal solution of a single target often leads to the deterioration of other targets, so it is necessary to evaluate comprehensively by setting up a fitness function. This function combines the results of the above three functions (wake loss, power generation, and construction cost) in a weighted difference manner, while considering the importance of each target (weight parameter). By adjusting these weights, designers can flexibly balance the needs between targets, such as placing more emphasis on power generation when needed, or emphasizing construction cost control when the budget is limited.

[0041] In summary, the process of constructing the preset fitness function is to integrate multiple key factors in wind turbine array design into a unified evaluation system, and through the iterative optimization of genetic algorithms, to find a layout scheme that performs well in power generation efficiency, cost control, and ecological impact.

[0042] In an exemplary embodiment, before obtaining the first function for calculating the wake loss corresponding to each initial population encoding, the above method further comprises: determining the wake velocity of each wind turbine in each initial population encoding according to the wake formula, wherein the wake formula is: , v(x) is the wake velocity, v0 is the free stream velocity, CT is the wind turbine thrust coefficient, k is the wake expansion coefficient, and x is the wind turbine spacing.

[0043] In an exemplary embodiment, the preset fitness function is obtained by aggregating the first function, the second function, the third function, and the corresponding weight parameters, including: obtaining the maximum power generation, the maximum construction cost, and the maximum wake loss allowed by the target wind farm; determining the target wake loss corresponding to the first function, the target power generation corresponding to the second function, and the target construction cost corresponding to the third function; substituting the maximum power generation P max , the maximum construction cost C max , the maximum wake loss, the target wake loss, the target power generation P total , and the target construction cost C layout into the target fitness function template to obtain the preset fitness function, wherein the target fitness function template is: , W1, W2, and W3 are weight coefficients, and W1+W2+W3=1.

[0044] In an exemplary embodiment, the target applicable data is determined from the N groups of adaptive data according to the numerical size rule and the weight preference requirement of the design object, comprising: obtaining the adjustment target and the adjustment constraint condition set by the design object for the target wind farm; determining the weight preference requirement according to the adjustment content corresponding to the adjustment target; and determining the numerical size rule according to the condition content corresponding to the adjustment constraint condition.

[0045] At the beginning of the optimization design, the design object needs to clearly define its main expectations for the wind farm and the conditions that must be followed, i.e. the adjustment target and the adjustment constraint condition. The adjustment target may include maximizing power generation, minimizing construction cost, minimizing environmental impact, etc., while the adjustment constraint condition involves hard rules such as the minimum safety distance between wind turbines, sea terrain restrictions, etc. For example, the design object may want to maximize power generation efficiency as much as possible while controlling the construction cost within a certain budget on the premise of ensuring safety distance. The weight preference requirement reflects the priority of the design object in achieving multiple adjustment targets. For example, if the design object values power generation more than construction cost, then the weight of power generation (W1) will be higher than the weight of construction cost (W2) in the fitness function. This weight allocation is highly personalized and depends on the specific needs of the project and the strategic considerations of the designer. The determination of the weight preference requirement is made before the algorithm iteration to guide the subsequent optimization process and ensure that the final selected arrangement array can best meet the core demands of the designer. The numerical size rule is mainly used to compare and select the optimal solution from the N groups of adaptive data under the premise of meeting all adjustment constraint conditions. These rules may include minimizing construction cost, maximizing power generation, minimizing wake effect, etc. For example, the designer may establish a rule to prefer arrangement schemes with lower construction cost and higher power generation. The numerical size rule helps the algorithm to sort and select among multi-objective optimization results, ensuring that the output arrangement array not only meets the constraint conditions but also performs well in design objectives.

[0046] After the design objectives, constraint conditions, and the weight preference and numerical size rules of the designer are determined, the algorithm will select arrangement arrays from the N groups of adaptive data that can meet all constraint conditions and best reflect the design objectives. The target applicable data represents the set of optimal solutions that have been comprehensively considered, and they form the Pareto frontier, i.e. the solution that cannot be further improved in any objective without sacrificing another objective under the current optimization target. The designer can choose the most suitable arrangement scheme from this frontier according to their own preferences as the final construction guidance data.

[0047] In an exemplary embodiment, after the construction verification of the target wind farm according to the target arrangement array corresponding to the target applicable data, the above-mentioned method further comprises: in the case that the verification result of the construction verification indicates that there is deviation in the current construction, adjusting the pre-installation position of the wind turbine according to the target arrangement array; in the case that the verification result of the construction verification indicates that there is no deviation in the current construction, identifying the wind turbine position that has completed installation in the target arrangement array.

[0048] Optionally, the construction verification refers to the on-site installation according to the target arrangement array obtained in the design stage during the construction of the wind farm, and comparison with the expected scheme to ensure that the actual installation position is accurate and correct, and to check whether the construction quality meets the design requirements. This process may involve testing of wind turbine foundations, cable laying, seabed conditions and other aspects.

[0049] If the verification result of the construction verification shows that there is deviation, that is, the actual installation position does not match the position preset in the target arrangement array, or it is found during the construction process that some constraint conditions (such as terrain, submarine pipeline layout) are not fully considered, which means that the current construction scheme needs to be adjusted.

[0050] When the construction deviation is detected, the optimization method will start the adjustment mechanism of the pre-installation position. This step usually includes:

[0051] Re-evaluation: re-evaluate the performance of the target arrangement array in terms of power generation, cost and environmental impact based on the actual detected deviation to ensure that the adjusted scheme still meets the optimization target.

[0052] Dynamic adjustment: use the iterative characteristics of genetic algorithms to automatically adjust the pre-installation position of the affected wind turbine through the principles of population evolution and natural selection. This adjustment process may need to re-run the algorithm until a new arrangement scheme is found that performs well on all targets while eliminating the construction deviation.

[0053] If the verification result of the construction verification shows that the actual construction is completely consistent with the target arrangement array and there is no deviation, the next step will be to record and identify the wind turbine position that has completed installation. This identification process is crucial for construction management and later operation and maintenance, ensuring that all installation activities are consistent with the design documents, and facilitating the construction team and operation and maintenance personnel to reference and locate.

[0054] The step of identifying the wind turbine position may include:

[0055] Position confirmation: use GPS positioning, aerial image analysis and other technical means to accurately confirm the actual installation position of each wind turbine.

[0056] Record and update: record the confirmed fan position data in the construction log, and update it in the project management software or design file in real time to reflect the construction progress and actual situation.

[0057] Quality control: further quality inspection is conducted on the installed fan, including electrical connection, structural stability, etc., to ensure that it meets the design standards and safety specifications.

[0058] Through the above adjustment and identification mechanism, various uncertainties in the design to construction process can be effectively dealt with, ensuring the accuracy and reliability of the design scheme in actual application, and improving the construction efficiency and quality control level, providing strong technical support for the construction and operation of the wind farm.

[0059] Obviously, the above-described embodiments are only part of the embodiments of the present application, not all. In order to better understand the above method, the following describes the above process in combination with the embodiments, but does not limit the technical solutions of the embodiments of the present application, specifically:

[0060] The optional embodiment of the present application provides a limited constraint-based offshore wind turbine array optimization method, which comprises: introducing a limited movement constraint, i.e. wind turbine position constraint, on the basis of which wind turbine arrangement design of the wind farm is carried out, and on the basis of the above, fine design of the wind turbine position is carried out to reduce the wake effect and improve the overall power generation efficiency of the wind farm.

[0061] As an optional implementation, Figure 3 is a flowchart of the multi-objective and genetic algorithm-based offshore wind turbine array optimization method according to the embodiments of the present application, which comprises the following steps:

[0062] Step 1: determine the optimization target and constraint condition. Optionally, the optimization target includes: maximizing the power generation by evaluating the power generation efficiency of the wind turbine under different arrangements through the wake model. Minimize the construction cost by considering the wind turbine spacing, foundation construction and operation path. Minimize the wake effect by minimizing the wind speed attenuation of the rear row of wind turbines.

[0063] Optionally, the constraint condition includes: wind turbine spacing, which is used to determine the minimum spacing L between wind turbines, for example, the wind turbine spacing is usually 4-7 times the diameter of the wind turbine. Position movement range: that is, under the condition of determining the position of the first row of wind turbines, the movement direction range of the rear row of wind turbines is limited to an integer multiple of 45°.

[0064] Step 2: population initialization, specifically including the following steps:

[0065] Step S302, gene coding representation, each population individual represents the arrangement scheme of the wind turbine array, which is represented by integer coding. Then individual={(x1,y1),(x2,y2),…(xi ,y i ..., (x) N ,y N )}, (x i ,y i (i) represents the location coordinates of the i-th wind turbine. N represents the total number of wind turbines in the wind farm.

[0066] Step S304: Determine the initial position of the first row of fans. For example, if they are arranged at equal intervals along the main wind direction x-axis with a spacing of L, then the position of the first fan in the first row on the x-axis should be: x i = (i-1)×L, y i =0, i=1,2,3,……,N i N1 represents the number of fans in the first row.

[0067] Step S306: Determine the initial position of the subsequent exhaust fans after the first row. Optionally, the position of each fan is randomly generated within the following range, satisfying finite constraints: for example, the movement direction of the rear exhaust fan is horizontal, and after the movement, the angle between the line connecting the first and rear exhaust fans and the y-axis is less than or equal to ±45°; or the rear exhaust fans are positioned in front of or behind the first row of fans. The corresponding movement distance is: △x = k × L / 10, k ∈ {0, 1, 2, ..., 10}. The corresponding position calculation formula is as follows: ,in, In This represents the x-coordinate of the j-th fan in the previous row of fans. This represents the Y-coordinate of the j-th fan in the previous row of fans, where θ is the angle of movement direction. The value for lateral movement is 0°, and the value is set to ±90° in front of and behind the previous row of fans, and ±45° in the left and right rear of the previous row of fans.

[0068] Step S308: Generate the initial population. Specifically, randomly generate P individuals (wind turbine array layout scheme), ensuring that each individual satisfies the minimum spacing constraint between wind turbines. The minimum spacing constraint between wind turbines is: Among them, x i、 y i The coordinates of the front fan position ， x j、 y j These are the coordinates of the rear fan's position.

[0069] Step 3: Fitness function calculation. Calculate the fitness value for each individual in the population. The objectives include maximizing power generation, minimizing construction costs, and minimizing wake effects.

[0070] (1) The power generation calculation includes: tail flow model selection, such as using Jensen model, PorteAgel model or other complex tail flow simulation model, the specific formula is: , v(x) is the tail flow wind speed; v0 is the free flow wind speed; CT is the fan thrust coefficient, k is the tail flow expansion coefficient, and x is the fan spacing. Further, using the tail flow model, the attenuation degree of the actual wind speed vi of each fan in the array is calculated, .

[0071] (2) Calculate the power generation, including calculating the total power generation of the array for each arrangement scheme, and the calculation formula is as follows:

[0072] , ρ is the air density; A is the fan swept area; v i is the actual wind speed of the i-th fan; η is the fan efficiency.

[0073] (3) Construction cost calculation, considering the fan foundation construction and cable laying path optimization, the cost function is:

[0074] , α is the single fan foundation construction cost; β is the cable unit length laying cost; di is the distance from the i-th fan to the bus point. N is the total number of fans.

[0075] Determine the multi-objective fitness function of the wind farm, that is, construct a multi-objective normalized fitness function, and combine weight optimization. Multi-objective fitness function: , wherein Pmax is the maximum power generation, Cmax is the maximum construction cost, the maximum tail flow loss is the actual tail flow loss, the actual power generation of the wind farm is Ptotal, the actual construction cost of the wind farm is Clayout. W1, W2, W3: target weight coefficient. Then through the refinement of population initialization and fitness calculation, the optimization process can better adapt to the actual constraints and improve the multi-objective optimization effect.

[0076] Step 4: Output the optimal scheme, for example, the above function stops iteration when the preset iteration number or the Pareto solution set is stable. Then, the Pareto optimal frontier is output, and the user can select the scheme according to the weight preference (such as paying more attention to power generation or cost control). Finally, according to the selected optimal scheme, the final verification of the tail flow effect and the construction path is carried out.

[0077] In summary, by adopting a multi-objective optimization framework, multiple objective functions such as maximizing power generation, minimizing wake effect, and minimizing construction cost of the wind farm are incorporated into the model, while considering the limited constraints (moving direction and distance) of the wind turbine position. Through the population evolution characteristics of the genetic algorithm, the Pareto efficiency of the candidate scheme is evaluated in each iteration, and the wind turbine layout is dynamically adjusted. Compared with the traditional single-objective optimization method, this method realizes the dynamic balance between the objectives, can adapt to complex wind speed fields and spatial restrictions, and shows higher efficiency and flexibility in solving nonlinear multi-constraint problems.

[0078] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present application.

[0079] In the present embodiment, a verification device for arranging an array is also provided, which is used to implement the above embodiments and preferred embodiments, and will not be described again. As used below, the term module can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware or a combination of software and hardware is also possible and contemplated.

[0080] Figure 4 is a structural block diagram of a verification device for arranging an array according to an embodiment of the present application, which comprises:

[0081] The acquisition module 42 is configured to acquire N arrangement arrays corresponding to a target wind farm, and determine N initial population encodings according to the N arrangement arrays, wherein there are M wind turbines in each arrangement array, the distance between any adjacent wind turbines satisfies a minimum spacing function, and M and N are positive integers;

[0082] The processing module 44 is configured to process the N initial population encodings by using a preset fitness function, to obtain N sets of adaptive data.

[0083] The determination module 46 is configured to determine target adaptive data from the N sets of adaptive data according to a numerical size rule and a weight preference requirement of a design object, and perform construction verification on the target wind farm according to a target arrangement array corresponding to the target adaptive data.

[0084] The device obtains N arrangement arrays corresponding to a target wind farm, and uses integer coding to represent N initial population encodings according to the position coordinates of each wind turbine, wherein each arrangement array contains M wind turbines, and the distance between any two wind turbines is at least equal to L (4 to 7 times the diameter of the wind turbine) defined by a minimum spacing function, and M and N are positive integers. Through a preset fitness function, the power generation, construction cost and wake effect are calculated respectively, and N initial population encodings are processed to obtain N sets of adaptive data. According to the numerical size rule and the weight preference of the decision maker, a Pareto optimal solution set satisfying the three objectives of maximizing power generation, minimizing construction cost and minimizing wake effect is selected from the N sets of adaptive data. When the preset iteration number is reached or the Pareto optimal solution set is stable, the optimal scheme is output, that is, one or more arrangement arrays satisfying the specific weight preference are selected from the Pareto optimal solution set as the construction verification basis of the target wind farm. The problem of ineffective balance between wind turbine array arrangement optimization and actual construction cost is solved, the best balance point between multiple optimization objectives is effectively found, the limitations of traditional single-objective optimization methods in dealing with complex offshore wind farm layout and construction conditions are overcome, and a scientific, reasonable, efficient and environmentally friendly design scheme for the planning and construction of offshore wind power projects is provided.

[0085] In an exemplary embodiment, the device further comprises a function module for obtaining a first function for calculating the wake loss corresponding to each initial population encoding before processing the N initial population encodings through the preset fitness function to obtain N sets of adaptive data; obtaining a second function for calculating the power generation corresponding to each initial population; obtaining a third function for calculating the construction cost corresponding to each initial population; and obtaining the preset fitness function by aggregating the first function, the second function, the third function and the corresponding weight parameters.

[0086] In an exemplary embodiment, the function module is further configured to determine the wake wind speed of each wind turbine in each initial population encoding according to a wake formula before obtaining the first function for calculating the wake loss corresponding to each initial population encoding, wherein the wake formula is: v(x) is the wake wind speed, v0 is the free flow wind speed, CT is the wind turbine thrust coefficient, k is the wake expansion coefficient, and x is the wind turbine spacing.

[0087] In an exemplary embodiment, the function module is further configured to obtain the maximum power generation, the maximum construction cost and the maximum wake loss allowed by the target wind farm; determine the target wake loss corresponding to the first function, the target power generation corresponding to the second function, and the target construction cost corresponding to the third function; and calculate the maximum power generation P max , the maximum construction cost C max , the maximum wake loss, the target wake loss, the target power generation P total, target construction cost C layout , the target fitness function template is: , W1, W2, W3 are weight coefficients, and W1+W2+W3=1.

[0088] In an exemplary embodiment, the determination module is further configured to obtain an adjustment target and an adjustment constraint condition set for the target wind farm by the design object, determine a weight preference requirement according to an adjustment content corresponding to the adjustment target, and determine a numerical size rule according to a condition content corresponding to the adjustment constraint condition.

[0089] In an exemplary embodiment, the device further includes an indication module configured to, after the construction verification of the target wind farm according to the target arrangement array corresponding to the target applicable data, adjust the pre-installation position of the wind turbine according to the target arrangement array in a case where a verification result of the construction verification indicates that there is a deviation in the current construction, and identify a wind turbine position that has been completed installation in the target arrangement array in a case where the verification result of the construction verification indicates that there is no deviation in the current construction.

[0090] Embodiments of the present application also provide a computer readable storage medium having a computer program stored therein, wherein the computer program is configured to execute the steps in any of the method embodiments described above when running.

[0091] Optionally, in the present embodiment, the storage medium can be configured to store a computer program for executing the following steps:

[0092] S1, obtaining N arrangement arrays corresponding to a target wind farm, and determining N initial population encodings according to the N arrangement arrays, wherein each arrangement array includes M wind turbines, the distance between any adjacent wind turbines satisfies a minimum spacing function, M and N are positive integers;

[0093] S2, processing the N initial population encodings by a preset fitness function to obtain N sets of adaptive data;

[0094] S3, determining target applicable data from the N sets of adaptive data according to a numerical size rule and a weight preference requirement of a design object, and performing construction verification on the target wind farm according to a target arrangement array corresponding to the target applicable data.

[0095] In an exemplary embodiment, the computer readable storage medium can include, but is not limited to, a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0096] The specific examples in the embodiments can refer to the examples described in the above embodiments and exemplary embodiments, which will not be repeated here.

[0097] The embodiments of the present application further provide a computer program product comprising a computer program which, when executed by a processor, performs the steps of any of the above method embodiments.

[0098] The embodiments of the present application further provide another computer program product comprising a non-volatile computer-readable storage medium storing a computer program which, when executed by a processor, performs the steps of any of the above method embodiments.

[0099] The embodiments of the present application further provide an electronic device comprising a memory and a processor, the memory storing a computer program, and the processor being configured to execute the computer program to perform the steps of any of the above method embodiments.

[0100] Optionally, in the embodiments, the processor can be configured to perform the following steps by the computer program:

[0101] S1, obtaining N arrangement arrays corresponding to a target wind farm, and determining N initial population encodings according to the N arrangement arrays, wherein there are M wind turbines in each arrangement array, the distance between any adjacent wind turbines satisfies a minimum spacing function, M and N are positive integers;

[0102] S2, processing the N initial population encodings by a preset fitness function to obtain N groups of adaptive data;

[0103] S3, determining target applicable data from the N groups of adaptive data according to a numerical size rule and a weight preference requirement of a design object, and performing construction verification on the target wind farm according to a target arrangement array corresponding to the target applicable data.

[0104] In an exemplary embodiment, the electronic device can further comprise a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0105] The specific examples in the embodiments can refer to the examples described in the above embodiments and exemplary embodiments, which will not be repeated here.

[0106] It is apparent that those skilled in the art can, without departing from the spirit of the present application, make various changes and modifications of the modules or steps of the present application described above, which can be implemented by general computing devices, and can be centralized on a single computing device or distributed on a network composed of multiple computing devices, and can be implemented by program codes executable by computing devices, so that they can be stored in storage devices and executed by computing devices, and in some cases, the steps shown or described can be executed in different order, or can be made into individual integrated circuit modules, or multiple modules or steps can be made into a single integrated circuit module. Thus, the present application is not limited to any particular combination of hardware and software.

[0107] The above description is only the preferred embodiments of the present application, and it should be pointed out that those skilled in the art can make several improvements and refinements without departing from the principles of the present application, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A verification method for an array of arrangements, characterized in that, include: Obtain N wind turbine layouts corresponding to the target wind farm, and determine N initial population codes based on the N wind turbine layouts. Each wind turbine layout contains M wind turbines, and the distance between any adjacent wind turbines satisfies the minimum spacing function. M and N are positive integers. The N initial population codes are processed by a preset fitness function to obtain N sets of fitness data; Based on the numerical size rules and the weight preference requirements of the design object, the target applicable data is determined from the N sets of adaptive data, and the construction verification of the target wind farm is carried out according to the target layout array corresponding to the target applicable data.

2. The verification method for the array according to claim 1, characterized in that, Before processing the N initial population codes using a preset fitness function to obtain N sets of fitness data, the method further includes: Obtain the first function used to calculate the tail loss corresponding to each initial population code; Obtain the second function used to calculate the power generation corresponding to each initial population; Obtain the third function used to calculate the construction cost corresponding to each initial population; By summing the first function, the second function, the third function, and the corresponding weight parameters, a preset fitness function is obtained.

3. The verification method for the array arrangement according to claim 2, characterized in that, Before obtaining the first function used to calculate the tail loss corresponding to each initial population code, the method further includes: The wake velocity of each wind turbine in each initial population code is determined according to the wake formula, wherein the wake formula is: v(x) is the wake velocity, v0 is the free flow velocity, CT is the fan thrust coefficient, k is the wake spread coefficient, and x is the fan spacing.

4. The verification method for the array arrangement according to claim 2, characterized in that, By summing the first function, the second function, the third function, and the corresponding weight parameters, a preset fitness function is obtained, including: Obtain the maximum allowable power generation, maximum construction cost, and maximum wake loss of the target wind farm; Determine the target wake loss corresponding to the first function, the target power generation corresponding to the second function, and the target construction cost corresponding to the third function; The maximum power generation P max The maximum construction cost C max The maximum wake loss, the target wake loss, and the target power generation P total The target construction cost C layout Substituting these values ​​into the target fitness function template yields the preset fitness function, wherein the target fitness function template is: W1, W2, and W3 are weighting coefficients, and W1 + W2 + W3 = 1.

5. The verification method for the array according to claim 1, characterized in that, Target applicable data are determined from the N sets of adaptive data based on numerical magnitude rules and the weight preference requirements of the design object, including: Obtain the adjustment target and adjustment constraints set for the target wind farm in the design object; The weight preference requirements are determined based on the adjustment content corresponding to the adjustment target. The numerical size rules are determined based on the conditions corresponding to the adjusted constraints.

6. The verification method for the array according to claim 1, characterized in that, After performing construction verification on the target wind farm based on the target layout array corresponding to the applicable target data, the method further includes: If the verification result of the construction verification indicates that there is a deviation in the current construction, the pre-installation position of the fan shall be adjusted according to the target layout array; If the verification result of the construction verification indicates that there is no deviation in the current construction, the positions of the wind turbines that have been installed in the target array are marked.

7. A verification device for an array of arrays, characterized in that, Applications include power generation equipment clusters, including: The acquisition module is used to acquire N wind turbine arrays corresponding to the target wind farm and determine N initial population codes based on the N wind turbine arrays. Each wind turbine array contains M wind turbines, and the distance between any adjacent wind turbines satisfies the minimum spacing function. M and N are positive integers. The processing module is used to process the N initial population codes through a preset fitness function to obtain N sets of fitness data; The determination module is used to determine the target applicable data from the N sets of adaptive data according to the numerical size rules and the weight preference requirements of the design object, and to perform construction verification of the target wind farm according to the target layout array corresponding to the target applicable data.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 6.

9. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 6 through the computer program.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images