Wind power plant layout optimization method based on Gaussian wake flow model and improved genetic algorithm

Abstract

The invention discloses a wind power plant layout optimization method based on a Gaussian wake flow model and an improved genetic algorithm, and the method employs a wake flow analysis model with higher precision, namely an Ishihara-Qian wake flow model, to evaluate the power generation amount of a wind power plant, and the model can efficiently and accurately predict the wind speed loss and additional turbulence intensity of a fan wake flow region. The variation rate and the crossover rate of the genetic algorithm are improved according to the population fitness, so that the two parameters can be dynamically adjusted according to the population fitness during each iteration, and when the fitness difference in one population is small (the population is relatively uniform), the corresponding crossover rate or variation rate is increased, so that the diversity of the population is increased, and the robustness of the genetic algorithm is improved. And falling into a local optimal solution is avoided.

Description

Technical Field

[0001] The invention belongs to the field of wind power generation layout technology, and in particular relates to a wind farm layout optimization method based on a Gaussian wake model and an improved genetic algorithm. Background Art

[0002] As a renewable and clean energy, the development and utilization of wind energy has become an important development trend. In the actual application of wind farms, when the wind speed flows through the wind turbines, flow characteristics such as reduced downstream wind speed and increased turbulence intensity will appear. This phenomenon is called the wake effect. As the downstream distance increases, the impact of the wake effect will decrease. In large wind farms, in order to improve land utilization and economic benefits, as many wind turbines as possible need to be installed in a limited space to maximize power generation. Therefore, the position arrangement between wind turbines is particularly critical. The wake effect is one of the key factors that determine the spacing and arrangement of wind turbines. How to reduce the impact of the wake effect under limited conditions and maximize power generation has become one of the research hotspots in this field.

[0003] At present, many studies on wind turbine layout optimization schemes often use Jensen-type wake models, which are simple but have limited accuracy. In addition, genetic algorithms, as the most commonly used algorithm in wind turbine layout optimization, have low computational efficiency when dealing with multiple constraints such as boundary conditions, machine spacing safety, and infeasible space. Under these constraints, minimizing the impact of wake effects is a multivariate non-convex problem. There are a large number of potential layout schemes and a large number of local optimal solutions, making it difficult to obtain a global optimal solution. Summary of the invention

[0004] In view of this, the present invention aims to propose a wind farm layout optimization method based on a Gaussian wake model and an improved genetic algorithm, which minimizes the wake effect of the wind farm and reduces the possibility of falling into a local optimal solution by utilizing an improved three-dimensional wake analytical model and a genetic algorithm.

[0005] In a first aspect, the present invention proposes a wind farm layout optimization method based on a Gaussian wake model and an improved genetic algorithm, comprising:

[0006] Obtain target wind farm information;

[0007] The Ishihara-Qian wake model is used to describe the total power generation of the wind farm based on the target wind farm information;

[0008] The target wind farm is gridded, and the maximum total power generation of the wind farm is taken as the optimization goal. The improved genetic algorithm is used to optimize the grid position of the wind farm units to obtain the wind farm layout plan;

[0009] Among them, the crossover rate and mutation rate of the improved genetic algorithm are calculated according to the population fitness.

[0010] Furthermore, the total power generation of the wind farm is described based on the target wind farm information using the Ishihara-Qian wake model, including:

[0011] Convert the initial wind turbine layout of the wind farm to the main wind direction according to the given wind direction;

[0012] Calculate the wind speed loss and additional turbulence generated by the upstream wind turbine of the nth wind turbine in the wind farm at the nth wind turbine according to the unit specification parameters along the wind direction;

[0013] The average wind speed at the rotor plane of the nth wind turbine is calculated based on the wind speed deficit, and the average turbulence at the nth wind turbine is calculated based on the additional turbulence;

[0014] The power generation of the nth wind turbine is calculated based on the average wind speed and average turbulence on the wind rotor plane, and the total power generation of the wind farm is calculated based on the power generation of each wind turbine.

[0015] Further, calculating the average wind speed on the rotor plane at the nth wind turbine according to the wind speed loss includes:

[0016] Considering the wind speed deficit caused by the upstream wind turbine of the nth wind turbine at the nth wind turbine, the total wind speed deficit at the nth wind turbine is calculated as follows:

[0017] ,

[0018] in, represents the wind speed loss caused by the mth upstream fan of the nth fan at the nth fan, Indicates the background wind speed loss, is the downwind position of the center of the wind turbine hub in the coordinate system, and are the coordinates of the crosswind direction and the vertical direction in the coordinate system respectively;

[0019] The average wind speed at the rotor plane is calculated based on the total wind speed loss at the nth wind turbine as follows:

[0020] ,

[0021] in, is the effective wind speed of the wind turbine rotor surface of the nth wind turbine, is the blade swept area of ​​the nth fan, represents the integral over the wind rotor plane.

[0022] Further, calculating the average turbulence at the nth fan according to the additional turbulence includes:

[0023] The turbulence superposition correction term is introduced into the additional turbulence as follows:

[0024]

[0025]

[0026]

[0027] in, The distance from any point in the yz plane to the hub center of the mth upstream fan of the nth fan is represented by , H is the height of the fan hub center, represents the y-axis coordinate of the mth upstream fan; is the secant length of the intersection area between the tail flow of the mth upstream wind turbine and wind turbine l, , wind turbine l is the wind turbine closest to the mth upstream wind turbine in the wind farm, represents the fan wake width, .

[0028] Furthermore, the power generation of the nth wind turbine is calculated based on the average wind speed and average turbulence on the rotor plane as follows:

[0029] ,

[0030] in, is the air density, is the blade swept area of ​​the nth fan, is the effective wind speed of the wind turbine rotor surface of the nth wind turbine, is the power generation efficiency of the nth wind turbine, is the fan power factor.

[0031] Furthermore, the total power generation of the wind farm is calculated based on the power generation of each wind turbine, including:

[0032] The given wind farm layout is calculated based on the power generation of each wind turbine as follows: In ambient wind speed ,wind direction and turbulence The overall power generation under:

[0033]

[0034] in, represents the power generation of the nth wind turbine, i and j represent the wind speed condition and wind direction condition respectively, and N represents the number of wind turbines;

[0035] Considering different wind direction and wind speed distribution frequencies, the total power generation of the wind farm is calculated as follows:

[0036]

[0037] Among them, I and J represent the total number of wind speed conditions and wind direction conditions, respectively. Indicates the frequency of wind direction and speed distribution.

[0038] Furthermore, the crossover rate and mutation rate of the improved genetic algorithm are calculated according to the population fitness including:

[0039] When the improved genetic algorithm is used to optimize the grid position of wind farm units, the maximum fitness and average fitness of the population at the tth iteration are calculated. The crossover rate at the tth iteration is calculated based on the maximum fitness and average fitness of the population as follows: and mutation rate :

[0040]

[0041]

[0042] in, It represents the difference between the maximum fitness and the average fitness of the population at the tth iteration, and it represents the maximum fitness recorded during the tth iteration. ,

[0043] Right now , and is the sensitivity factor that characterizes the speed of probability change, is a constant.

[0044] In a second aspect, the present invention provides a wind farm layout optimization device, comprising:

[0045] A wind farm information acquisition module is used to acquire target wind farm information;

[0046] A power generation calculation module is used to describe the total power generation of the wind farm based on the target wind farm information using the Ishihara-Qian wake model;

[0047] The layout optimization module is used to grid the target wind farm, take the maximum total power generation of the wind farm as the optimization goal, use the improved genetic algorithm to optimize the grid position of the wind farm units, and obtain the wind farm layout plan; among which, the crossover rate and mutation rate of the improved genetic algorithm are calculated according to the population fitness.

[0048] In a third aspect, the present invention provides an electronic device comprising a memory storing computer executable instructions and a processor, wherein when the computer executable instructions are executed by the processor, the device executes the various steps of the wind farm layout optimization method based on the Gaussian wake model and the improved genetic algorithm provided in the first aspect.

[0049] In a fourth aspect, the present invention provides a readable storage medium storing a computer executable program, which, when executed, can implement the various steps of the wind farm layout optimization method based on the Gaussian wake model and the improved genetic algorithm provided in the first aspect.

[0050] It can be seen from the above technical solutions that the present invention has the following beneficial effects:

[0051] The present invention provides a wind farm layout optimization method based on a Gaussian wake model and an improved genetic algorithm. The Ishihara-Qian wake model, a wake analysis model with higher accuracy, is used to evaluate the power generation of a wind farm. The model can efficiently and accurately predict the wind speed loss and additional turbulence intensity in the wind turbine wake area. The present invention also improves the mutation rate and crossover rate of the genetic algorithm according to the fitness of the population, so that the two parameters of each iteration can be dynamically adjusted according to the fitness of the population. When the fitness difference in a population is small (the population is relatively uniform), the corresponding crossover rate or mutation rate increases, thereby increasing the diversity of the population and avoiding falling into a local optimal solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0053] Figure 1 It is a flow chart of a method for optimizing wind farm layout based on a Gaussian wake model and an improved genetic algorithm provided by an embodiment of the present invention;

[0054] Figure 2 It is a crossover and mutation logic diagram of the improved genetic algorithm provided by an embodiment of the present invention;

[0055] Figure 3 is a wind condition distribution probability histogram provided by an embodiment of the present invention;

[0056] Figure 4 is a comparison diagram of the fitness of the improved genetic algorithm provided by an embodiment of the present invention and the traditional genetic algorithm under wind condition 1 as a function of the number of algorithm iterations;

[0057] Figure 5 is a comparison diagram of the fitness of the improved genetic algorithm provided by an embodiment of the present invention and the traditional genetic algorithm under wind condition 2 as a function of the number of algorithm iterations;

[0058] Figure 6It is a schematic diagram of the layout comparison of wind turbines after the wind farm layout is optimized by the improved genetic algorithm provided by the embodiment of the present invention and the traditional genetic algorithm under wind condition 1;

[0059] Figure 7 It is a schematic diagram of the comparison of wind turbine layout after the wind farm layout is optimized by the improved genetic algorithm provided by the embodiment of the present invention and the traditional genetic algorithm under wind condition 2;

[0060] Figure 8 It is a comparison diagram of the wake of wind turbines after the wind farm layout is optimized by the improved genetic algorithm provided by the embodiment of the present invention and the traditional genetic algorithm under wind condition 1;

[0061] Fig. 9 is a schematic structural diagram of a wind farm layout optimization device provided by an embodiment of the present invention;

[0062] Fig.10 This is a diagram of the electronic device architecture provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] like Figure 1 As shown, an embodiment of the present invention provides a wind farm layout optimization method based on a Gaussian wake model and an improved genetic algorithm, comprising the following steps:

[0065] Step S110: Obtain target wind farm information.

[0066] In this step, the target wind farm information obtained includes wind resource data and unit specification parameters, and the boundary of the wind farm is fitted into a polygon to obtain the boundary points of the site.

[0067] In a further implementation, the target wind farm and wind turbine locations are gridded, and for safety reasons, the wind turbine spacing d can be set to be no less than 3D, where D is the diameter of the wind turbine impeller. Specifically, the site is divided into K grids and the grids are numbered. The center of each grid is a possible installation location for a wind turbine. If the number of wind turbines to be optimized is N, the layout plan of the wind farm can be represented by an array consisting of N real numbers.

[0068] Step S120: using the Ishihara-Qian wake model to describe the total power generation of the wind farm based on the target wind farm information.

[0069] Step S130. Grid the target wind farm, take the maximum total power generation of the wind farm as the optimization goal, use the improved genetic algorithm to optimize the grid position of the wind farm units, and obtain the wind farm layout plan; wherein the crossover rate and mutation rate of the improved genetic algorithm are calculated according to the population fitness.

[0070] In a further embodiment, step S120 includes the following steps:

[0071] Step S121: Convert the initial wind turbine layout of the wind farm to the main wind direction according to the given wind direction.

[0072] Step S122: Calculate the wind speed loss and additional turbulence generated by the upstream wind turbine of the nth wind turbine in the wind farm at the nth wind turbine according to the unit specification parameters along the wind direction.

[0073] Step S123. Calculate the average wind speed at the rotor plane of the n-th wind turbine according to the wind speed loss, and calculate the average turbulence at the n-th wind turbine according to the additional turbulence.

[0074] Step S124: Calculate the power generation of the nth wind turbine based on the average wind speed and the average turbulence on the wind rotor plane, and calculate the total power generation of the wind farm based on the power generation of each wind turbine.

[0075] The embodiment of the present invention adopts the Ishihara-Qian wake model with higher accuracy to evaluate the overall power generation of the wind farm under given information. In the process of analyzing the model, the given parameters to be used include the given wind turbine layout X of the wind farm, the wind turbine hub height H, the ambient wind speed U i ,wind direction and turbulence .

[0076] Before introducing the Ishihara-Qian wake model to simulate and analyze the wind farm, the following definitions are made:

[0077] For a given wind farm with N wind turbines, the wind turbine layout When calculating the power generation in each wind direction, it is necessary to transform its coordinates so that the future flow direction is aligned with the wind farm direction. It should be noted that the wind turbine n increases in sequence along the x direction in any wind direction. For any wind turbine in the wind farm, its power generation It can be calculated by the following formula:

[0078] ,

[0079] in, is the air density, is the blade swept area of ​​the nth fan, is the effective wind speed of the wind turbine rotor surface of the nth wind turbine, is the power generation efficiency of the nth wind turbine, is the fan power coefficient, It can be calculated by the following formula:

[0080]

[0081] in, Indicates wind direction The wind speed distribution on the rotor surface of the next n-th wind turbine, is the blade swept area of ​​the nth fan, represents the integral over the wind rotor plane.

[0082] For a given model of wind turbine, due to its wind wheel area , Power generation efficiency , and power factor curve It is known that we only need to obtain the effective inflow velocity of the fan: The power generation can be predicted. In order to accurately reflect the overall power generation of the wind farm, the embodiment of the present invention takes into account the wake effect and uses the Ishihara-Qian model to accurately predict the effect of the wind turbine wake on the plane speed of each wind turbine rotor. impact.

[0083] Specifically, the wind speed is divided into I intervals from the cut-in wind speed to the cut-out wind speed according to the set interval (the wind speed corresponding to each interval is recorded as U i ), the wind direction is divided into J intervals according to the set interval (the wind direction corresponding to each interval is recorded as ), and statistically analyze the probability distribution of different wind speeds and wind directions, as well as the turbulence at different wind speeds In a more preferred embodiment, if the turbulence at different wind speeds No statistical data is available, but it can be calculated based on the International Electrotechnical Commission standard IEC 61400-1.

[0084] The Ishihara-Qian wake model also incorporates the effect of turbulence on the wake wind speed loss. Therefore, it is necessary to introduce the effective inflow turbulence of the wind turbine surface into each wind turbine. , the specific calculation method is as follows:

[0085]

[0086] in, Represents the distribution of the standard deviation of the pulsating wind speed on the rotor surface of the nth wind turbine.

[0087] In the Ishihara-Qian wake model, for any wind turbine n in a wind farm, the wind speed loss in its wake is and the additional turbulence generated It can be calculated as follows:

[0088]

[0089]

[0090]

[0091]

[0092] in, is the coordinate relative to the hub center of the nth wind turbine, is the height of the hub center of the nth wind turbine, is the wind wheel diameter, represents the fan wake width, as well as These are the Ishihara-Qian wake model parameters, as shown in Table 1 below:

[0093] Table 1

[0094]

[0095] in, represents the fan thrust coefficient, which is about Function of thrust coefficient curve Determined by the aerodynamic characteristics of the fan and generally provided by the designer of the specific model of fan.

[0096] For wind direction Wind speed distribution on the rotor surface of the next nth wind turbine , linear superposition is used to consider the wind speed loss caused by the n-1 wind turbines upstream at the nth wind turbine, and the total wind speed loss at the nth wind turbine is calculated as follows:

[0097] ,

[0098] in, represents the wind speed loss caused by the mth upstream fan of the nth fan at the nth fan, Indicates the background wind speed loss, is the downwind position of the center of the wind turbine hub in the coordinate system, and are the crosswind and vertical coordinates in the coordinate system respectively.

[0099] The average wind speed at the rotor plane of the nth wind turbine is calculated based on the total wind speed loss calculated above as follows:

[0100] ,

[0101] in, is the effective wind speed of the wind turbine rotor surface of the nth wind turbine, is the blade swept area of ​​the nth fan, represents the integral over the wind rotor plane.

[0102] In addition, the Ishihara-Qian wake model also considers the superposition effect of additional turbulence. Directly superimposing the additional turbulence intensities of two wind turbines using the linear square sum principle cannot reproduce the turbulence superposition results in the actual flow field. Therefore, in addition to considering the additional turbulence caused by the mth upstream wind turbine at the nth wind turbine, it is also necessary to introduce a correction term to consider the turbulence superposition effect brought by the wind turbine closest to the mth upstream wind turbine. According to the aforementioned additional turbulence The calculation expression of the corrected standard deviation of the pulsating wind speed on the rotor surface of the nth wind turbine is It can be calculated as follows:

[0103]

[0104]

[0105]

[0106] in, The distance from any point in the yz plane to the hub center of the mth upstream fan of the nth fan is represented by , H is the height of the fan hub center, represents the y-axis coordinate of the mth upstream fan; is the secant length of the intersection area between the tail flow of the mth upstream wind turbine and wind turbine l, , wind turbine l is the wind turbine closest to the mth upstream wind turbine in the wind farm, represents the fan wake width, .

[0107] The calculated Substitute the above inflow turbulence into The calculation expression is the average turbulence at the nth wind turbine. From the above calculation process, it can be seen that the turbulence is directly related to the standard deviation of the wind speed, which affects the mean wind speed of the wind turbine, and thus indirectly affects the power generation of each wind turbine. Considering the turbulence superposition, according to the above power generation The calculation expression can be used to calculate the power generation at the nth wind turbine.

[0108] By performing the above calculation for each wind turbine, we can describe the performance of a given wind turbine layout X at an ambient wind speed U. i ,wind direction and turbulence The overall power generation under:

[0109]

[0110] in, represents the power generation of the nth wind turbine, i and j represent the wind speed condition and wind direction condition respectively, and n represents the number of wind turbines.

[0111] Frequency distribution of wind speed in known wind direction In this case, the total power generation of the wind farm can be calculated, which is also the optimization model for layout optimization:

[0112]

[0113] Among them, I and J represent the total number of wind speed conditions and the total number of wind direction conditions, respectively.

[0114] In a more preferred implementation, the above optimization objective function is used as an individual of the genetic algorithm, and considering that the higher the fitness of an individual is, the greater the probability of it being selected is, the embodiment of the present invention adopts a tournament selection method.

[0115] After the target wind farm is gridded, each grid center represents the installation location of a wind turbine. Since the genetic algorithm encoding may generate the same gene during the crossover process, that is, the same number appears in a certain arrangement array, resulting in two wind turbines appearing at the center of a grid, the same gene can be extracted before individual crossover, and crossover is performed at different gene parts. The embodiment of the present invention improves the traditional genetic algorithm as follows:

[0116] Traverse all individuals in population C, for each pair of adjacent individuals Do the following:

[0117]

[0118]

[0119]

[0120] in, represents the offspring individuals after crossover, for The kth element of , m represents the latitude of S, that is, the number of genes shared by the crossed parent individuals, and are all random numbers between [0,1]. represents the crossover rate of the t-th iteration. The embodiment of the present invention calculates the crossover rate as follows:

[0121]

[0122] in, It represents the difference between the maximum fitness and the average fitness of the population at the tth iteration, and it represents the maximum fitness recorded during the tth iteration. ,

[0123] Right now , It is a sensitivity factor that characterizes how fast the probability changes.

[0124] During the mutation operation, the mutation range should be non-existing genes. The embodiment of the present invention also considers dynamically adjusting the mutation rate based on the fitness difference of the population. for:

[0125]

[0126] in, is a sufficiently large number to ensure Within a reasonable range, parameters Same effect During mutation, a random gene of a parent individual mutates into another gene that is not present in the parent individual.

[0127] In summary, the logic of crossover and mutation of the improved genetic algorithm in the embodiment of the present invention is as follows: Figure 2 As shown, each round of iteration dynamically adjusts the crossover rate according to the fitness of the population. and mutation rate , so that when the fitness difference in a population is small (the population is relatively uniform), the corresponding crossover rate / mutation rate increases, thereby increasing the diversity of the population and avoiding the local optimal solution. On the contrary, when the fitness difference is large (there may be some excellent individuals in the population), the crossover rate and mutation rate decrease to achieve the purpose of inheriting excellent genes. When the number of iterations of the genetic algorithm reaches the set number of cycles or the target solution converges, the layout optimization results of the wind farm can be output, and the position coordinates of each wind turbine can be decoded and output.

[0128] In order to verify the effectiveness of the layout optimization method proposed in the present invention, an experimental example is given below.

[0129] Consider a square offshore wind farm site with a boundary length and width of 5 km and 40 wind turbines deployed in the wind farm. The wind farm site is gridded into 10*10 grid areas, where the center of each grid point is the potential deployment location of the wind turbine.

[0130] Consider two wind conditions, as follows:

[0131] Wind condition 1: constant wind direction and speed (225°, 8m / s)

[0132] Wind condition 2: 36 wind directions, constant wind speed (8m / s), wind direction from 0° to 360° with intervals of 10°, as follows Figure 3 As shown, the horizontal axis represents wind direction, and the vertical axis represents wind direction distribution probability.

[0133] The turbulence is calculated according to the International Electrotechnical Commission standard IEC 61400-1:

[0134]

[0135] in, is the reference turbulence when the wind speed is 15m / s, taken as 0.12, b=5.6m / s, is the wind speed passing through the fan.

[0136] The specifications of the wind turbines installed in the wind farm are shown in Table 2.

[0137]

[0138] The algorithm parameters for optimization and solution based on the improved genetic algorithm are shown in Table 3 below, and the algorithm parameters of the traditional genetic algorithm used for comparison are shown in Table 4 below.

[0139] Table 3

[0140]

[0141] Table 4

[0142]

[0143] Using the Ishihara-Qian wake model to describe the total power generation of a wind farm under a certain layout The calculation results are as follows Figures 4 to 8 As shown in the following Table 5, Table 5 shows the optimization results of different genetic algorithms under various wind conditions.

[0144] Table 5

[0145]

[0146] It can be seen from Table 5 that, compared with the traditional genetic algorithm, the improved genetic algorithm proposed in the present invention that dynamically adjusts the crossover rate and mutation rate based on the fitness difference of the population can significantly improve the disadvantage that the wind farm optimization is prone to fall into the local optimal solution, and improves the optimization ability of the algorithm in the wind farm optimization problem. After the maximum number of iterations, the objective function value is improved compared with the traditional genetic algorithm under each wind condition.

[0147] Figure 4 and Figure 5 The fitness changing trends of the traditional genetic algorithm (GA) and the improved genetic algorithm (improved GA) proposed in the present invention with the number of iterations under wind conditions 1 and 2 respectively. Under the same number of generations, the fitness optimized by the improved genetic algorithm of the embodiment of the present invention is higher than that of the traditional genetic algorithm, indicating that the ability of the algorithm to escape from the local optimal solution is significantly improved.

[0148] Figure 6and 7 Comparison of wind turbine layout after wind farm layout optimization using traditional genetic algorithm (GA) and improved genetic algorithm (improved GA) proposed in this invention. Figure 8 Schematic diagram of the wake of the fan arrangement after optimization of the two algorithms.

[0149] From the experimental example, after the wind field simulation based on the Ishihara-Qian wake model, the improved genetic algorithm adapted to the main wind direction significantly improved the optimization degree of the algorithm under the same conditions, and more importantly, the global optimization ability of the algorithm was greatly improved. Under the same number of iterations, the fitness improvement of the improved genetic algorithm under both wind conditions is higher than that of the traditional genetic algorithm; at the same time, the fitness curve of the improved genetic algorithm is more tortuous and changeable than that of the traditional algorithm, and it can often quickly find a better solution in a shorter number of iterations, significantly enhancing the global search ability, and can avoid falling into the local optimal solution and causing premature convergence to a greater extent. As the iteration proceeds, the speed of fitness growth slows down, but no matter what wind condition, the final fitness of the improved genetic algorithm is higher than that of the traditional genetic algorithm, indicating that the improved genetic algorithm proposed in the present invention has the advantages of being more efficient and more accurate than the traditional genetic algorithm.

[0150] The above embodiment describes a wind farm layout optimization method based on a Gaussian wake model and an improved genetic algorithm, which uses a higher-precision wake analysis model, the Ishihara-Qian wake model, to evaluate the power generation of a wind farm. The model can efficiently and accurately predict wind speed loss and additional turbulence intensity, and improves the mutation rate and crossover rate of the genetic algorithm according to the fitness of the population, so that these two parameters of each iteration can be dynamically adjusted according to the fitness of the population. When the fitness difference in a population is small (the population is more uniform), the corresponding crossover rate or mutation rate increases, thereby increasing the diversity of the population and avoiding falling into a local optimal solution.

[0151] The above method disclosed can be implemented by using various forms of equipment, so the present invention also discloses a wind farm layout optimization device corresponding to the above method, and specific embodiments are given below for detailed description.

[0152] like Fig. 9 As shown, one embodiment of the present invention provides a wind farm layout optimization device, comprising:

[0153] A wind farm information acquisition module 902 is used to acquire target wind farm information;

[0154] A power generation calculation module 904 is used to describe the total power generation of the wind farm based on the target wind farm information using the Ishihara-Qian wake model;

[0155] The layout optimization module 906 is used to grid the target wind farm, take the maximum total power generation of the wind farm as the optimization target, use the improved genetic algorithm to optimize the grid position of the wind farm units, and obtain the wind farm layout plan; wherein the crossover rate and mutation rate of the improved genetic algorithm are calculated according to the population fitness.

[0156] The implementation principle and technical effects of the device provided in the embodiments of the present application are the same as those of the aforementioned method embodiments. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiments.

[0157] The methods and related devices mentioned in the above embodiments are described with reference to the method flow charts and / or structural diagrams provided in the embodiments of the present application. Specifically, each process and / or block in the method flow charts and / or structural diagrams, as well as the combination of processes and / or blocks in the flow charts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the process. Figure 1 A process or multiple processes and / or structures Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or structures Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A flow or multiple flows and / or structures illustrate the steps of the functions specified in one block or multiple blocks.

[0158] The following embodiments are described by taking the method applied to a computer device as an example. It can be understood that the computer device can be any device with computing and processing functions, and can be but not limited to a server or a personal laptop computer, etc. In one embodiment, the computer device can be an application server, and the application server can be a server for running an application to be tested.

[0159] See also Fig.10, which shows a hardware block diagram of an electronic device, the electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0160] like Fig.10 As shown, the electronic device includes: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;

[0161] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 communicate with each other through the communication bus 4;

[0162] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0163] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), etc., such as at least one disk memory;

[0164] The memory stores a program, and the processor can call the program stored in the memory, wherein the program is used to: implement each processing flow of the aforementioned wind farm layout optimization solution based on the Gaussian wake model and the improved genetic algorithm.

[0165] An embodiment of the present invention also provides a readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program implements the various processing flows of the wind farm layout optimization solution based on the Gaussian wake model and the improved genetic algorithm provided in the above embodiment and / or any possible implementation method in combination with the embodiment.

[0166] The above-mentioned embodiments have described the present invention in particular detail with respect to possible scenarios, and those skilled in the art will recognize that the present invention can be practiced through other embodiments. The specific naming of components, the capitalization of terms, attributes, data structures, or any other programming or structural aspects are not mandatory or important, and the mechanisms or features of the present invention may have different names, forms, or procedures. The system may be implemented by a combination of hardware and software (as described), entirely by hardware elements, or entirely by software elements. The specific division of functions between the various system components described herein is exemplary only and not mandatory; on the contrary, the functions performed by a single system component may be performed by multiple components, or the functions performed by multiple components may be performed by a single component.

[0167] Those skilled in the art should understand that the various steps of the above disclosed method can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented with program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the embodiments of the present invention are not limited to any specific combination of hardware and software.

[0168] These computing device executable programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors, and these computing programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0169] Certain aspects of the present invention include process steps and instructions described herein in the form of algorithms. It should be noted that the process steps and instructions of the present invention can be implemented in software, firmware and / or hardware, and when implemented by software, it can be downloaded, stored on different platforms used by various operating systems and operated from the platforms.

[0170] Those skilled in the art will understand that the structures shown in the accompanying drawings are merely block diagrams of partial structures related to the scheme of the present application, and do not constitute a limitation on the terminal device to which the scheme of the present application is applied. The specific terminal device may include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

[0171] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "possible design" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0172] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A wind farm layout optimization method based on Gaussian wake model and improved genetic algorithm, characterized in that: include: Obtain target wind farm information; The Ishihara-Qian wake model is used to describe the total power generation of the wind farm based on the target wind farm information; The target wind farm is gridded, and the maximum total power generation of the wind farm is taken as the optimization goal. The improved genetic algorithm is used to optimize the grid position of the wind farm units to obtain the wind farm layout plan; Among them, the crossover rate and mutation rate of the improved genetic algorithm are calculated according to the population fitness.

2. The method according to claim 1, characterized in that The total power generation of the wind farm described by using the Ishihara-Qian wake model based on the target wind farm information includes: Convert the initial wind turbine layout of the wind farm to the main wind direction according to the given wind direction; Calculate the wind speed loss and additional turbulence generated by the upstream wind turbine of the nth wind turbine in the wind farm at the nth wind turbine according to the unit specification parameters along the wind direction; The average wind speed at the rotor plane of the nth wind turbine is calculated based on the wind speed deficit, and the average turbulence at the nth wind turbine is calculated based on the additional turbulence; The power generation of the nth wind turbine is calculated based on the average wind speed and average turbulence on the wind rotor plane, and the total power generation of the wind farm is calculated based on the power generation of each wind turbine.

3. The method according to claim 2, characterized in that Calculating the average wind speed of the wind turbine rotor plane at the nth wind turbine according to the wind speed loss includes: Considering the wind speed deficit caused by the upstream wind turbine of the nth wind turbine at the nth wind turbine, the total wind speed deficit at the nth wind turbine is calculated as follows: ， in, represents the wind speed loss caused by the mth upstream fan of the nth fan at the nth fan, Indicates the background wind speed loss, is the downwind position of the wind turbine hub center in the coordinate system, and are the coordinates of the crosswind direction and the vertical direction in the coordinate system respectively; The average wind speed at the rotor plane is calculated based on the total wind speed loss at the nth wind turbine as follows: ， in, is the effective wind speed of the wind turbine rotor surface of the nth wind turbine, is the blade swept area of ​​the nth fan, represents the integral over the wind rotor plane.

4. The method according to claim 2, characterized in that: Calculating the average turbulence at the nth fan according to the additional turbulence comprises: The turbulence superposition correction term is introduced into the additional turbulence as follows: in, The distance from any point in the yz plane to the hub center of the mth upstream fan of the nth fan is represented by , H is the height of the fan hub center, represents the y-axis coordinate of the mth upstream fan; is the secant length of the intersection area between the tail flow of the mth upstream wind turbine and wind turbine l, , wind turbine l is the wind turbine closest to the mth upstream wind turbine in the wind farm, represents the fan wake width, .

5. The method according to claim 2, characterized in that: The calculation of the power generation of the nth wind turbine based on the average wind speed and average turbulence of the wind rotor plane includes: Considering the influence of turbulence on wind speed of wind turbine according to the average turbulence degree, the power generation of the nth wind turbine is calculated according to the average wind speed of the wind rotor plane as follows: ， in, is the air density, is the blade swept area of ​​the nth fan, is the effective wind speed of the wind turbine rotor surface of the nth wind turbine, is the power generation efficiency of the nth wind turbine, is the fan power factor.

6. The method according to claim 2, characterized in that Calculating the total power generation of the wind farm according to the power generation of each wind turbine includes: The given wind farm layout is calculated based on the power generation of each wind turbine as follows: In ambient wind speed ,wind direction and turbulence The overall power generation under: in, represents the power generation of the nth wind turbine, i and j represent the wind speed condition and wind direction condition respectively, and N represents the number of wind turbines; Considering different wind direction and wind speed distribution frequencies, the total power generation of the wind farm is calculated as follows: Among them, I and J represent the total number of wind speed conditions and wind direction conditions, respectively. Indicates the frequency of wind direction and speed distribution.

7. The method according to claim 1, characterized in that The crossover rate and mutation rate of the improved genetic algorithm are calculated according to the population fitness and include: When the improved genetic algorithm is used to optimize the grid position of wind farm units, the maximum fitness and average fitness of the population at the tth iteration are calculated. The crossover rate at the tth iteration is calculated based on the maximum fitness and average fitness of the population as follows: and mutation rate : in, It represents the difference between the maximum fitness and the average fitness of the population at the tth iteration, and it represents the maximum fitness recorded during the tth iteration. , Right now , and is the sensitivity factor that characterizes the speed of probability change, is a constant.

8. A wind farm layout optimization device, characterized in that: include: A wind farm information acquisition module is used to acquire target wind farm information; A power generation calculation module is used to describe the total power generation of the wind farm based on the target wind farm information using the Ishihara-Qian wake model; The layout optimization module is used to grid the target wind farm, take the maximum total power generation of the wind farm as the optimization goal, use the improved genetic algorithm to optimize the grid position of the wind farm units, and obtain the wind farm layout plan; among which, the crossover rate and mutation rate of the improved genetic algorithm are calculated according to the population fitness.

9. An electronic device, characterized in that: The device comprises a memory storing computer executable instructions and a processor. When the computer executable instructions are executed by the processor, the device executes the wind farm layout optimization method based on the Gaussian wake model and the improved genetic algorithm as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that: A computer executable program is stored, and when the program is executed, the wind farm layout optimization method based on the Gaussian wake model and the improved genetic algorithm as described in any one of claims 1 to 7 can be implemented.

Images