Method, device and medium for optimizing arrangement of double-population wind farm based on rule arrangement

Abstract

The present application relates to the technical field of wind farm micro-siting, and specifically provides a double-population wind farm machine arrangement optimization method based on regular arrangement, equipment and medium, comprising: obtaining attribute information of a wind farm to be optimized; randomly generating a regular shape variable and a wind turbine bottom layer coordinate based on the attribute information, establishing a first initial population based on the regular shape variable, establishing a second initial population based on the wind turbine bottom layer coordinate and obtaining a bottom layer coordinate vector; obtaining an arrangement scheme of wind turbines in the wind farm to be optimized based on the regular shape variable and the bottom layer coordinate vector; optimizing the arrangement scheme based on the first initial population, the second initial population and an optimization target; and obtaining an optimal arrangement scheme when the optimization target reaches a preset convergence condition; the present application can achieve a mathematical optimal solution of wind turbine point positions while ensuring that the overall layout conforms to the regular shape, thereby improving the comprehensive benefits of the whole life cycle of the wind farm.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind farm micro-siting, and particularly relates to a double-population wind farm machine arrangement optimization method based on regular arrangement, a device and a medium. BACKGROUND

[0002] As an important driving force for clean energy transformation, wind energy is promoting the development of wind farm construction towards large-scale and base development. As a mature technology and large-scale renewable clean energy power generation method, the development of wind power plays a key role in promoting the green and low-carbon transformation of energy structure. The layout of wind turbines has an important influence on their operating efficiency. By reasonably designing the layout of wind turbines, the mutual influence between wind turbines can be reduced, and the wind catching and operating efficiency of wind turbines can be improved. Reasonable wind turbine arrangement can maximize the use of wind energy resources and improve the overall power generation efficiency of the wind farm. This makes the importance of wind farm arrangement optimization research more prominent.

[0003] However, current wind farm layout design often relies on experience point arrangement. This method is difficult to obtain the mathematical optimal solution of the wind turbine point position, and completely random wind farm arrangement optimization lacks aesthetic appearance and is not conducive to the planning of operation and maintenance paths. In addition, too regular layout form will limit the overall optimization space. For example, in the area with large wake effect, reasonable reduction of the number of sites can improve the overall efficiency, but the regular dense arrangement of the layout cannot meet this requirement. This leads to poor comprehensive benefits of the wind farm.

[0004] Correspondingly, there is a need for a new double-population wind farm machine arrangement optimization scheme based on regular arrangement to solve the above problems. SUMMARY

[0005] In order to overcome the above defects, the present application is proposed to solve or at least partially solve the technical problems that the existing wind farm layout method is difficult to achieve the mathematical optimal solution of the wind turbine point position, and the regular dense arrangement form limits the overall optimization space, resulting in poor comprehensive benefits of the wind farm.

[0006] In a first aspect, a double-population wind farm machine arrangement optimization method based on regular arrangement is provided, and the method comprises:

[0007] obtaining attribute information of a wind farm to be optimized;

[0008] randomly generating regular shape variables and wind turbine bottom layer coordinates based on the attribute information;

[0009] establishing a first initial population based on the regular shape variables, wherein the first initial population comprises a plurality of first population individuals, and each first population individual is a group of regular shape variables;

[0010] establishing a second initial population based on the bottom coordinates of the wind turbines, wherein the second initial population comprises a plurality of second population individuals, each of which is a bottom coordinate vector of a group of wind turbines in the wind farm to be optimized;

[0011] obtaining the arrangement scheme of the wind turbines in the wind farm to be optimized based on the rule shape variable and the bottom coordinate vector;

[0012] optimizing the arrangement scheme of the wind turbines in the wind farm to be optimized based on the first initial population, the second initial population and the optimization target;

[0013] obtaining the optimal arrangement scheme of the wind turbines in the wind farm to be optimized when the optimization target reaches a preset convergence condition.

[0014] In one of the technical solutions of the method, the attribute information comprises a region range and a number of wind turbines of the wind farm to be optimized.

[0015] The random generation of the rule shape variable and the bottom coordinate of the wind turbine based on the attribute information comprises:

[0016] setting a distance between any two wind turbines in the wind farm to be optimized;

[0017] randomly generating a rule shape variable based on the region range of the wind farm to be optimized;

[0018] randomly generating a bottom coordinate of the wind turbine based on the region range of the wind farm to be optimized, the number of wind turbines and the distance between any two wind turbines in the wind farm to be optimized;

[0019] The rule shape variable comprises one of a parallelogram rule shape variable, a row arrangement rule shape variable and a ring rule shape variable, and the distance between any two wind turbines in the wind farm to be optimized is greater than n times of the diameter of a wind wheel, wherein n is a positive integer greater than 1.

[0020] In one of the technical solutions of the method, the random generation of the rule shape variable based on the region range of the wind farm to be optimized comprises:

[0021] randomly selecting a global center point coordinate based on the region range of the wind farm to be optimized;

[0022] randomly selecting a plurality of shape parameters in a plurality of preset shape parameter ranges based on a uniform probability distribution, wherein the type of the shape parameter is determined based on the shape type of the rule shape variable;

[0023] determining the regular shape variable based on the global center point coordinate and the plurality of shape parameters.

[0024] In one of the technical solutions of the method for optimizing arrangement of wind turbines in a double-population wind farm based on rules, the arrangement scheme of the wind turbines in the wind farm to be optimized is obtained based on the regular shape variable and the bottom layer coordinate vector.

[0025] The available point vector of the wind turbines in the wind farm to be optimized is obtained based on the regular shape variable, wherein the number of the available points is greater than or equal to the number of the wind turbines.

[0026] The arrangement scheme of the wind turbines in the wind farm to be optimized is obtained based on the available point vector and the bottom layer coordinate vector.

[0027] In one of the technical solutions of the method for optimizing arrangement of wind turbines in a double-population wind farm based on rules, the arrangement scheme of the wind turbines in the wind farm to be optimized is obtained based on the available point vector and the bottom layer coordinate vector.

[0028] S1, a coordinate point in the bottom layer coordinate vector is selected, the distances between the coordinate point and each available point in the available point vector are obtained, the available point closest to the coordinate point is extracted as the coordinate point of the wind turbine in the wind farm to be optimized, and the available point closest to the coordinate point is removed from the available point vector.

[0029] S2, all the coordinate points in the bottom layer coordinate vector are traversed, step S1 is repeated until the number of the coordinate points of the wind turbines in the wind farm to be optimized obtained is consistent with the number of the wind turbines, and the arrangement scheme of the wind turbines in the wind farm to be optimized is determined based on the plurality of coordinate points of the wind turbines in the wind farm to be optimized obtained.

[0030] In one of the technical solutions of the method for optimizing arrangement of wind turbines in a double-population wind farm based on rules, the preset convergence condition is that the target value of the optimization target is maximum.

[0031] The method further comprises:

[0032] S3, optimization is performed based on the first initial population to obtain an optimized regular shape variable;

[0033] S4, optimization is performed based on the second initial population to obtain an optimized bottom layer coordinate of the wind turbine;

[0034] S5, a first optimization population and a second optimization population are established based on the optimized regular shape variable and the optimized bottom layer coordinate of the wind turbine, and an optimized arrangement scheme of the wind turbine is obtained.

[0035] S6. Based on the optimized wind turbine layout scheme, obtain the corresponding optimized target. Repeat steps S3-S5 until the target value of the optimized target reaches its maximum, then end the optimization process and obtain the optimal regular shape variable, the optimal bottom coordinates of the wind turbine, and the optimal layout scheme of the wind turbine in the wind farm to be optimized.

[0036] In one technical solution of the above-mentioned rule-based dual-population wind farm layout optimization method, the optimization objective is the total output power of the wind farm to be optimized under the wind turbine layout scheme.

[0037] The method for obtaining the total output power of the wind farm to be optimized includes:

[0038] Obtain wind resource information of the wind farm to be optimized, wherein the wind resource information includes the ambient incoming wind speed of the wind farm to be optimized;

[0039] Based on the incoming wind speed of the wind farm to be optimized and the arrangement of wind turbines in the wind farm to be optimized, the total output power of the wind farm to be optimized is obtained according to the preset wind turbine wake model.

[0040] In one technical solution of the above-mentioned dual-swarm wind farm layout optimization method based on rule arrangement, the preset wind turbine wake model includes a two-dimensional analytical model of wind turbine wake and an analytical model of additional turbulence intensity of wind turbine wake.

[0041] The process of obtaining the total output power of the wind farm to be optimized based on the ambient inflow wind speed and the arrangement of wind turbines in the wind farm, according to a preset wake model, includes:

[0042] The wake turbulence intensity of each wind turbine in the arrangement scheme is obtained based on the analytical model of the additional turbulence intensity of the wind turbine wake.

[0043] The inflow additional turbulence intensity at multiple points on the rotor of each wind turbine is obtained based on the wake turbulence intensity of each wind turbine.

[0044] Based on the two-dimensional analytical model of the wind turbine wake and the inflow additional turbulence intensity at multiple points on the rotor of each wind turbine, the inflow velocity loss at multiple points on the rotor of each wind turbine is obtained.

[0045] Based on the inflow velocity deficit at multiple points on the rotor of each wind turbine and the ambient incoming wind speed, the wind speed in front of the hub of each wind turbine is obtained.

[0046] Based on the wind speed in front of the hub of each wind turbine and the preset power curve of each wind turbine, the output power of each wind turbine is obtained.

[0047] Based on the output power of each wind turbine, the total output power of the wind farm to be optimized is obtained.

[0048] In a second aspect, an electronic device is provided, comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program, which, when executed by the at least one processor, implements the method described in any of the above-described technical solutions of the rule-based dual-cluster wind farm layout optimization method.

[0049] In a third aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored, the program codes being adapted to be loaded and run by a processor to perform the method described in any of the above-described technical solutions of the rule-based dual-swarm wind farm deployment optimization method.

[0050] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects:

[0051] In implementing the dual-swarm wind farm layout optimization method based on rule arrangement provided by this invention, the following steps are taken: First, the attribute information of the wind farm to be optimized is obtained. Second, shape variables and bottom-level coordinates of the wind turbines are randomly generated based on the attribute information. Third, a first initial population is established based on the shape variables, and a second initial population is established based on the bottom-level coordinates of the wind turbines, obtaining the bottom-level coordinate vector. Fourth, the layout scheme of the wind turbines in the wind farm to be optimized is obtained based on the shape variables and the bottom-level coordinate vector. Fifth, the layout scheme is optimized based on the first initial population, the second initial population, and the optimization objective. Sixth, the optimal layout scheme is obtained when the optimization objective reaches a preset convergence condition. Through this optimization method, this invention can achieve the mathematically optimal solution for the wind turbine locations while ensuring that the overall layout conforms to the shape rules, thereby improving the comprehensive benefits of the wind farm throughout its entire life cycle. Attached Figure Description

[0052] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Wherein:

[0053] Figure 1 This is a schematic flowchart of the main steps of a rule-based dual-swarm wind farm wind turbine deployment optimization method according to an embodiment of the present invention;

[0054] Figure 2This is a schematic diagram of the main steps in generating shape variables based on attribute information according to an embodiment of the present invention.

[0055] Figure 3 This is a schematic diagram of the main steps of generating shape variables based on the random generation rules of the area range of the wind farm to be optimized, according to an embodiment of the present invention.

[0056] Figure 4 This is a flowchart illustrating the main steps of obtaining the layout scheme of wind turbines in a wind farm to be optimized based on available point vectors and underlying coordinate vectors according to an embodiment of the present invention.

[0057] Figure 5 This is a schematic diagram of the main steps for optimizing the layout of wind turbines in a wind farm according to an embodiment of the present invention.

[0058] Figure 6 This is a wind rose diagram according to an embodiment of the present invention;

[0059] Figure 7 These are the unit power curve and thrust coefficient curve according to an embodiment of the present invention;

[0060] Figure 8 The location of the original wind turbine generators in the wind farm to be optimized is according to an embodiment of the present invention;

[0061] Figure 9 This is an evolution curve of the optimization process of a rule-based dual-population wind farm wind turbine deployment optimization method according to an embodiment of the present invention.

[0062] Figure 10 This is a schematic diagram of generating wind turbine locations in a wind farm to be optimized based on the mapping of randomly arranged bottom-layer coordinate points with upper-layer parallelogram regular available points according to an embodiment of the present invention.

[0063] Figure 11 This refers to the optimal layout scheme of wind turbine locations in a wind farm according to an embodiment of the present invention.

[0064] Figure 12 This is a schematic diagram of the main structure of an electronic device according to an embodiment of the present invention.

[0065] Figure label:

[0066] 121: Memory; 122: Processor. Detailed Implementation

[0067] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0068] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and may also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Computer-readable storage media include any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0069] See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a rule-based dual-cluster wind farm wind turbine deployment optimization method according to an embodiment of the present invention. Figure 1 As shown, the method for optimizing the deployment of dual-species wind farms based on rule-based arrangement in this embodiment of the invention mainly includes the following steps S101 to S105.

[0070] Step S101: Obtain the attribute information of the wind farm to be optimized.

[0071] In this embodiment, the attribute information includes the area of ​​the wind farm to be optimized and the number of wind turbines. ;

[0072] In one implementation, a suitable wind turbine model can be selected based on the area of ​​the wind farm to be optimized, the number of wind turbines, and the installed capacity requirements.

[0073] Step S102: Randomly generate shape variables of rules based on attribute information, and establish a first initial population based on the shape variables of rules. The first initial population includes multiple individuals of the first population, and each individual of the first population is a shape variable of a set of rules. The available locations of wind farm units with corresponding unique and determined rule arrangement can be generated based on a specific point selection program.

[0074] In this embodiment, real number encoding is used to randomly generate regular shape variables. A first initial population is established based on the regular shape variables. The first initial population contains multiple first population individuals. Each first population individual is a set of regular shape variables. Each set of regular shape variables corresponds to a regular arrangement of available wind farm turbine locations. Real number encoding refers to representing each gene value of the first population individual with a floating-point number within a certain range.

[0075] In one implementation, the shape variables for each set of rules comprise row vectors of 10 variables, for example... .

[0076] Meanwhile, in this embodiment, constraints on the coordinates of the wind turbines are pre-set. These constraints include the area of ​​the wind farm to be optimized and the distance between any two wind turbines in the wind farm to be optimized.

[0077] See appendix Figure 2 , Figure 2 This is a schematic diagram illustrating the main steps of generating shape variables based on attribute information according to an embodiment of the present invention. Figure 2 As shown, the shape variables that are randomly generated based on attribute information include:

[0078] Step S201: Set the distance between any two wind turbines in the wind farm to be optimized;

[0079] Among them, the distance between any two wind turbines in the wind farm to be optimized Larger than the diameter of the wind turbine n times, , n It is a positive integer greater than 1;

[0080] Optionally, the distance between any two wind turbines in the wind farm to be optimized. Greater than four times the diameter of the wind turbine rotor. It should be noted that this embodiment optimizes the distance between any two wind turbines in the wind farm. The statement that the distance is greater than four times the rotor diameter is merely an example of one implementation method and is not a limitation of this embodiment. In practical applications, the embodiment of this invention addresses the distance between any two wind turbines in the wind farm to be optimized. It can be set according to actual needs.

[0081] Step S202: Randomly generate regular shape variables based on the area of ​​the wind farm to be optimized;

[0082] In one implementation, the shape variable for randomly generating a regular arrangement is: The generation method of each parameter should be determined according to the rule form of the available locations of wind turbine units in the wind farm to be optimized. The shape variables of the rule include one of the following: parallelogram rule shape variables, row arrangement rule shape variables, and ring rule shape variables.

[0083] Optionally, if the available locations of the wind turbine generators in the wind farm to be optimized are in the form of a parallelogram rule, the shape variable of the parallelogram rule... The parameters are: global center point coordinates. The included angle of a parallelogram θ Overall rotation angle γ Parallelogram side length a Parallelogram column side length b Inline gradient coefficient and inline gradient coefficient If the wind turbine locations of the wind farm to be optimized are arranged in a row arrangement, then the shape variable of the row arrangement rule is... The parameters are: global center point coordinates. Inline starting point ratio r Angle of rotation of parallel lines θ Minimum line spacing Minimum spacing within a line Line spacing gradient coefficient and inline spacing gradient coefficient If the wind turbine locations in the wind farm to be optimized are represented by a ring-shaped rule, then the shape variable of the ring-shaped rule... The parameters are: global center point coordinates. Ring spacing starting point ratio r , Angle of the starting point ray inside the ring θ Minimum spacing between rings Minimum spacing within the ring Ring spacing gradient coefficient and the gradient coefficient of the inner ring spacing It should be noted that the shape variables of the rules, including the shape variables of parallelogram rules, row arrangement rules, and ring rules, are only one example of implementation and do not constitute a limitation on the implementation of the present invention. In practical applications, the actual type of shape variable can be generated according to actual needs.

[0084] See appendix Figure 3 , Figure 3 This is a schematic flowchart illustrating the main steps of generating shape variables based on a random rule for the area range of a wind farm to be optimized, according to an embodiment of the present invention. Figure 3 As shown, the shape variables based on the random generation rules of the area range of the wind farm to be optimized include:

[0085] Step S301: Based on the area of ​​the wind farm to be optimized, randomly select the coordinates of the global center point.

[0086] Within the closed polygonal area of ​​the wind farm to be optimized, a point coordinate is randomly selected as the global center point coordinate of the regularly arranged layout. ;

[0087] Step S302: Based on a uniform probability distribution, randomly select multiple shape parameters from a range of preset shape parameters, wherein the type of the shape parameter is determined based on the shape type of the regular shape variable.

[0088] Optionally, when the shape variable of the rule is the shape variable of a parallelogram rule, the included angle of the parallelogram is randomly selected within the range of [0°, 360°]. θ and overall rotation angle γ Based on the distance between any two wind turbines in the wind farm to be optimized A certain multiple range Randomly select the row side length of the parallelogram a and the side length of the parallelogram b Randomly select the inter-row gradient coefficient within the range [0,1). and Two parameters, with inline gradient coefficients randomly selected within the range [0,1). and Two parameters;

[0089] When the shape variable of the rule is the same as the shape variable of the row arrangement rule, the proportion of the starting point in the row is randomly selected within the range [0,1). r Randomly select the rotation angle of the parallel line within the range of [0°, 360°). θ ,exist Randomly select the minimum spacing between rows within the range and minimum inline spacing Two parameters, with line spacing gradient coefficients randomly selected within the range [0,1). and Two parameters, with the inline spacing gradient coefficient randomly selected within the range [0,1). and Two parameters;

[0090] When the shape variable of the rule is a ring-shaped rule, the starting point ratio of the ring spacing is randomly selected within the range [0,1). r The ray angle of the starting point inside the ring is randomly selected within the range of [0°, 360°). θ ,exist Randomly select the minimum spacing between rings within the range and minimum spacing within the ring Two parameters, with the ring spacing gradient coefficient randomly selected within the range [0,1). and Two parameters, with the ring spacing gradient coefficient randomly selected within the range [0,1). and Two parameters.

[0091] Step S303: Determine the shape variables of the rule based on the global center point coordinates and multiple shape parameters.

[0092] Optionally, when the shape variable of the rule is a parallelogram rule, it is based on the coordinates of the global center point. The included angle of a parallelogram θ Overall rotation angle γ Parallelogram side length a , Parallelogram column side length b, inter-row gradient coefficient and inline gradient coefficient Obtain the shape variable of the parallelogram. When the shape variable of the rule is the same as the shape variable of the row arrangement rule, it is based on the global center point coordinates. Inline starting point ratio r Angle of rotation of parallel lines θ Minimum line spacing Minimum spacing within a line Line spacing gradient coefficient Inline spacing gradient coefficient Obtain the shape variable of the row arrangement rule When the shape variable of the rule is a ring-shaped rule, it is based on the global center point coordinates. Ring spacing starting point ratio r , Angle of the starting point ray inside the ring θ Minimum spacing between rings Minimum spacing within the ring Ring spacing gradient coefficient And the gradient coefficient of the inner spacing and the gradient coefficient of the inner spacing Obtain the shape variable of the ring rule .

[0093] In this embodiment, the method further includes:

[0094] Based on the number of wind turbine units, using the generated shape variables of the rule arrangement, and based on a specific point selection procedure, according to the rule form of the available points of the wind turbine units in the wind farm to be optimized, a unique and definite available point location for the wind turbine units in the wind farm to be optimized is generated within the area of ​​the wind farm to be optimized. The number of available points is greater than or equal to the number of wind turbine units.

[0095] Optionally, if the available locations of wind turbine generators in the wind farm to be optimized are obtained based on the shape variable of the parallelogram rule, the method includes:

[0096] Based on global center point coordinates and overall rotation angle γ Using the horizontal line of the area of ​​the wind farm to be optimized as a reference, the first straight line is obtained; based on the coordinates of the global center point... Angle with parallelogram θ Using the first straight line as a reference, obtain the second straight line;

[0097] Obtain the first distance between the two points where the first straight line intersects the boundary of the wind farm to be optimized; based on the first distance and the distance between any two wind turbines in the wind farm to be optimized, determine the maximum number of first gradient points; based on the maximum number of first gradient points and the inter-row gradient coefficient... The minimum spacing between the preset first gradient points is used to determine the distance between the first gradient points and the coordinates of the first gradient points on the second straight line; based on the distance between the first gradient points and the coordinates of the first gradient points on the second straight line, multiple first parallel lines parallel to the first straight line are generated.

[0098] Obtain the second distance between the two points where the second straight line intersects the boundary of the wind farm to be optimized; based on the second distance and the distance between any two wind turbines in the wind farm to be optimized, determine the maximum number of second gradient points; based on the maximum number of second gradient points and the in-row gradient coefficient... The minimum spacing between the preset second gradient points is used to determine the distance between the second gradient points and the coordinates of the second gradient points on the first straight line; based on the distance between the second gradient points and the coordinates of the second gradient points on the first straight line, multiple second parallel lines parallel to the second straight line are generated.

[0099] Multiple intersection points are obtained based on multiple first parallel lines and multiple second parallel lines. The intersection points are available locations of wind turbine generators in the wind farm to be optimized, which conform to the parallelogram rule.

[0100] Optionally, if the available locations of wind turbine generators in the wind farm to be optimized are selected according to the row arrangement rules, the methods for obtaining the available locations include:

[0101] Based on global center point coordinates and parallel line rotation angle θ Using the horizontal line of the area of ​​the wind farm to be optimized as a reference, obtain the straight line that intersects the area of ​​the wind farm to be optimized, and the length of the line segment between the two points where the straight line intersects the area of ​​the wind farm to be optimized.

[0102] Get the coordinates of the global center point For all straight lines, obtain the length of the line segment between the two points where each line intersects the boundary of the wind farm to be optimized, and select the longest line segment; based on the longest line segment and the minimum spacing between rows... Obtain the maximum number of parallel line segments within the area of ​​the wind farm to be optimized; based on the minimum inter-row spacing The maximum number of parallel line segments and the line spacing gradient coefficient To obtain the inter-row gradient interval between parallel line segments; based on the intersecting line segments and the inter-row gradient interval, to generate multiple parallel line segments that are parallel to the intersecting line segments;

[0103] Starting from one end of all parallel line segments, based on the ratio r of the inline starting point and the length of all parallel line segments, obtain multiple inline starting points on all parallel line segments; where all parallel line segments include intersecting line segments and multiple parallel line segments parallel to the intersecting line segments;

[0104] Based on the lengths of all parallel line segments and the minimum inline spacing Obtain the maximum number of gradient points on each parallel line segment; based on the minimum inline spacing. The maximum number of gradient points on each parallel line segment and the inline spacing gradient coefficient. The in-row gradient interval of each parallel line segment is obtained; based on the in-row gradient interval of each parallel line segment, multiple gradient points are obtained on both sides of the starting point of each parallel line segment, and the coordinates of multiple gradient points are obtained. Among them, the gradient points are the available points of the wind turbine generators in the wind farm to be optimized according to the row arrangement rules.

[0105] Optionally, if the available locations of wind turbine generators in the wind farm to be optimized are selected according to the ring rule, the methods for obtaining the available locations include:

[0106] Get global center point coordinates The line segments connecting each vertex of the boundary of the wind farm to be optimized, and the length of each line segment; the starting point of the ring spacing for each line segment is determined based on the length of each line segment and the ratio r of the starting point of the ring spacing.

[0107] Get global center point coordinates The shortest distance to the boundary of the wind farm to be optimized; based on the shortest distance, the length of each connecting line segment, and the minimum spacing between rings. Determine the minimum spacing between the first gradient points on each connecting line segment and the maximum number of the first gradient points; based on the ring spacing gradient coefficient. The minimum spacing between the first gradient points on each connecting line segment and the maximum number of first gradient points are used to determine the inter-ring gradient interval on each connecting line segment. Based on the inter-ring gradient interval on each connecting line segment, multiple first gradient points on each connecting line segment are obtained on both sides of the starting point of the ring spacing on each connecting line segment. Based on the multiple first gradient points on each connecting line segment, multiple rings similar to the boundary shape of the wind farm to be optimized are obtained.

[0108] Based on global center point coordinates and the angle of the starting point ray inside the ring θ Using the horizontal line of the area of ​​the wind farm to be optimized as a reference, ray rays are obtained;

[0109] Obtain the circumference of each ring based on the minimum spacing within the ring. Given the circumference of each ring, determine the maximum number of second gradient points on each ring; based on the maximum number of second gradient points on each ring and the minimum spacing within the rings... Inner ring spacing gradient coefficient The gradation interval within each ring is determined. Based on the gradation interval within each ring, multiple second gradation points are obtained on both sides of the starting point within each ring, and the coordinates of the multiple second gradation points are obtained. The second gradation points are the available locations of the wind farm units in the ring-shaped regular pattern.

[0110] Step S103: Randomly generate the bottom coordinates of the wind turbine units based on the attribute information, and establish a second initial population based on the bottom coordinates of the wind turbine units. The second initial population includes multiple individuals of the second population, and each individual of the second population is a set of bottom coordinate vectors of the wind turbine units in the wind farm to be optimized. The bottom coordinate vectors can be converted into the wind farm unit layout scheme under the regular arrangement in the first initial population based on a specific point mapping program.

[0111] In this embodiment, the bottom coordinates of the wind turbines are randomly generated based on the area of ​​the wind farm to be optimized, the number of wind turbines, and the distance between any two wind turbines in the wind farm to be optimized.

[0112] Specifically, based on the determined number of wind turbine units Randomly generate a bottom-level coordinate position vector equal to the number of turbine units within the area of ​​the wind farm to be optimized. Repeat this process until the distance between any two wind turbines is... Larger than the diameter of the wind turbine n times.

[0113] In one implementation, real-number encoding is used to generate completely random bottom-level coordinates, taking into account the constraints of the area of ​​the wind farm to be optimized and the distance between any two wind turbines.

[0114] Step S104: Based on the shape variables of the rules and the underlying coordinate vector, obtain the layout scheme of wind turbines in the wind farm to be optimized;

[0115] In this embodiment, the available locations of wind turbine units in the wind farm to be optimized are determined by the available locations of wind turbine units obtained based on the shape variables of the rules, wherein the number of available locations is greater than or equal to the number of wind turbine units.

[0116] Based on the available point vectors and the underlying coordinate vectors, the arrangement scheme of wind turbines in the wind farm to be optimized is obtained.

[0117] See appendix Figure 4 , Figure 4 This is a schematic flowchart illustrating the main steps of obtaining the layout scheme of wind turbines in a wind farm to be optimized based on available point vectors and underlying coordinate vectors, according to an embodiment of the present invention. Figure 4 As shown, based on the available point vectors and the underlying coordinate vectors, the arrangement scheme of wind turbines in the wind farm to be optimized includes:

[0118] Step S401: Select a coordinate point in the bottom coordinate vector, obtain the distance between the coordinate point and each available point in the available point vector, extract the available point closest to the coordinate point as the coordinate point of the wind turbine in the wind farm to be optimized, and remove the available point closest to the coordinate point from the available point vector.

[0119] Step S402: Traverse all coordinate points in the bottom coordinate vector and repeat step S401 until the number of coordinate points of wind turbines in the wind farm to be optimized is consistent with the number of wind turbines. Based on the obtained coordinate points of wind turbines in multiple wind farms to be optimized, determine the layout scheme of wind turbines in the wind farm to be optimized.

[0120] In one implementation, the first optimized population contains The first type of individual, namely A regular arrangement of shape variables Each shape variable can be used to generate a unique vector of available points for the wind farm turbines to be optimized through a point-sampling program. The second optimized population contains The second group of individuals, namely The bottom coordinate vector of each wind turbine ,in, ;

[0121] Traverse the underlying coordinate vector First, select the coordinate points in the underlying coordinate vector. Find the coordinates of this point and the available point vector. The distance to each available point in the data is extracted relative to the coordinates. The nearest available point Coordinates of wind turbines in the wind farm to be optimized And remove points that are in the available point vectors and have coordinates. The nearest available point That is, the point is retrieved without replacement;

[0122] Repeat the previous step, that is, for the k-th coordinate point Extract the coordinates of the point The nearest available point , serving as the coordinate points of the wind turbines in the wind farm to be optimized And remove from the available point vector of the unit That is, the point is retrieved without replacement;

[0123] Iterate through all coordinate points in the underlying coordinate vector, repeating the above steps until the number of coordinate points of wind turbines in the wind farm to be optimized is equal to the number of wind turbines. Consistent, forming vectors Based on the coordinates of the wind turbines in the multiple wind farms to be optimized, the layout scheme of the wind turbines in the wind farms to be optimized is determined.

[0124] Step S105: Based on the first initial population, the second initial population and the optimization objective, optimize the layout scheme of wind turbine units in the wind farm to be optimized; when the optimization objective reaches the preset convergence condition, obtain the optimal layout scheme of wind turbine units in the wind farm to be optimized.

[0125] In this embodiment, the preset convergence condition is that the target value of the optimization objective is maximized;

[0126] See appendix Figure 5 , Figure 5 This is a schematic flowchart illustrating the main steps of optimizing the layout of wind turbines in a wind farm according to an embodiment of the present invention. Figure 5 As shown, the methods for optimizing the layout of wind turbines in a wind farm include:

[0127] Step S501: Optimize based on the first initial population to obtain the shape variable of the optimized rule;

[0128] Step S502: Optimize based on the second initial population to obtain the optimized bottom coordinates of the wind turbine.

[0129] Step S503: Based on the optimized shape variables of the rules and the optimized bottom coordinates of the wind turbines, establish the first optimized population and the second optimized population, and obtain the optimized layout scheme of the wind turbines;

[0130] Step S504: Based on the optimized wind turbine layout scheme, obtain the corresponding optimized target. Repeat steps S501-S503 until the target value of the optimized target reaches its maximum, then end the optimization process and obtain the optimal regular shape variable, the optimal bottom coordinates of the wind turbine, and the optimal layout scheme of the wind turbine in the wind farm to be optimized.

[0131] In one implementation, a genetic algorithm is used as the optimization algorithm to optimize the layout of wind turbines in the wind farm to be optimized. The genetic algorithm can be the NSGA-II algorithm.

[0132] In one implementation, the shape variable of the rule can be obtained by cross-mutation based on the constraints of the wind turbine coordinates.

[0133] In one implementation, the method for optimizing the initial population can be as follows: setting an optimization target value, using an optimization algorithm-based wind turbine deployment optimization process, and combining other frameworks to calculate the optimization target, iteratively obtaining a series of wind turbine deployment schemes in the wind farm to be optimized that meet the requirements and have globally optimal or best optimization target values. The specific optimization process for the initial population is as follows:

[0134] (1) Population initialization. Randomly generate optimization variables (if a regular arrangement is adopted, it includes two types of optimization variables: random bottom coordinates of wind turbine units and regular shape variables; if multiple turbine models are mixed, a turbine model vector needs to be added) to form an initial population containing N individuals. Each individual is a definite arrangement scheme containing N turbine coordinates. The optimization variables are encoded with real numbers, and the turbine coordinates are randomly generated within the optimization constraints. If the turbine coordinates do not fully meet the constraints, the individual is regenerated (randomly generating optimization variables) until they are met (or, if the available points of the generated rule do not fully meet the optimization constraints, or the number of points is less than the required number of turbine units, the individual is regenerated until they are met).

[0135] (2) Crossover Mutation. This invention employs a simulated binary crossover method for crossover operations and performs mutation operations by adding Gaussian random numbers to the optimized variables (if a regular arrangement is used, crossover mutation is performed on the shape variables). During the mutation operation, there is a probability of adding random numbers of two scales, large and small, to the variables. The Gaussian standard deviation of the large-scale mutation is set to... The Gaussian standard deviation of small-scale variation is set as And set the mutation probability respectively. and .

[0136] (3) Merge parent and offspring. Merge the parent population with the offspring population generated by crossover variation to form a population of 2N individuals.

[0137] (4) Fast non-dominated sorting and crowding calculation. Calculate the optimization objective value for each individual in the merged population. Based on the optimization objective value, identify non-dominated individuals in the parent-offspring merged population to classify them into ranks. Within the same rank, sort individuals from smallest to largest according to a single objective value to obtain their sequence numbers. i Then calculate the crowding level of individuals. .

[0138] (5) Selecting the dominant population. From the merged parent-offspring population, select N individuals using the obtained ranking. If increasing a certain ranking exceeds the population size, then use an elite strategy to randomly select two individuals from that ranking. , Select the most crowded individuals until the required number of individuals are obtained.

[0139] (6) Convergence judgment. Return to (2) and repeat the steps until the number of iterations meets the requirements to obtain a converged solution set. At this time, the converged solution set is the optimized population.

[0140] In this embodiment, the optimization objective is the total output power of the wind farm to be optimized under the wind turbine layout scheme;

[0141] Methods for obtaining the total output power of the wind farm to be optimized include:

[0142] Obtain wind resource information for the wind farm to be optimized, including the ambient incoming wind speed of the wind farm to be optimized;

[0143] Based on the incoming wind speed of the wind farm to be optimized and the arrangement of wind turbines in the wind farm to be optimized, the total output power of the wind farm to be optimized is obtained according to the preset wake model of the wind turbines.

[0144] In this embodiment, the preset wind turbine wake model includes a two-dimensional analytical model of the wind turbine wake and an analytical model of the additional turbulence intensity of the wind turbine wake.

[0145] Based on the incoming wind speed of the wind farm to be optimized and the arrangement of wind turbines in the wind farm, the total output power of the wind farm to be optimized is obtained according to the preset wake model, including:

[0146] The wake turbulence intensity of each wind turbine in the arrangement scheme is obtained based on the analytical model of the additional turbulence intensity of the wind turbine wake.

[0147] The inflow additional turbulence intensity at multiple points on the rotor of each wind turbine is obtained based on the wake turbulence intensity of each wind turbine.

[0148] The inflow velocity deficit at multiple points on the wind turbine rotor is obtained based on the two-dimensional analytical model of the wind turbine wake and the inflow additional turbulence intensity at multiple points on the wind turbine rotor.

[0149] Based on the inflow velocity deficit and ambient wind speed at multiple points on the rotor of each wind turbine, the wind speed in front of the hub of each wind turbine is obtained.

[0150] The output power of each wind turbine is obtained based on the wind speed in front of the hub and the preset power curve of each wind turbine.

[0151] Based on the output power of each wind turbine, the total output power of the wind farm to be optimized is obtained.

[0152] In one implementation, the method for obtaining the total output power of the wind farm to be optimized includes:

[0153] The wake turbulence intensity of each wind turbine in the layout scheme can be calculated. The wake turbulence intensity of the wind turbine can be obtained from the analytical model of the additional turbulence intensity of the wind turbine wake in the following formulas (1)-(6):

[0154] (1)

[0155] in, This is the thrust coefficient; The intensity of atmospheric turbulence; D The diameter of the wind turbine rotor; r This is the lateral distance along the wind turbine axis; The standard deviation is the same as that of the Gaussian curve in the speed loss model; z This refers to the vertical height.

[0156] Flow direction function The maximum additional turbulence intensity of the wake cross section at each flow direction:

[0157] (2)

[0158] in, ; ; Correction values ​​are taken into account for the near-wake region.

[0159] Formula (1) expansion function for:

[0160] (3)

[0161] in, and The value can be:

[0162] (4)

[0163] (5)

[0164] For vertical correction functions:

[0165] (6)

[0166] For each wind turbine in the wind farm, based on the wake turbulence intensity at multiple points on the rotor of the current wind turbine, the inflow additional turbulence intensity at multiple points on the rotor of the current wind turbine is obtained:

[0167] (7)

[0168] in, For the current number i Taiwan wind turbine rotor top point Additional inflow turbulence intensity at the point; For the first j Taiwanese unit in i Taiwan wind turbine rotor top point The turbulence intensity in the wake direction at that location; It is a binary variable if and only if the current number is... i The Taiwanese unit is in the first j Downstream of the Taiwanese unit In other cases ; N The number of wind turbines in the wind farm needs to be optimized.

[0169] The average velocity deficit of the wind turbine is obtained based on the two-dimensional analytical model of the wind turbine wake and the inflow additional turbulence intensity at multiple points on the rotor of each wind turbine:

[0170] (8)

[0171] in, This is the thrust coefficient; The actual expansion rate of the wake boundary; The radius of the wind turbine; The standard deviation of the velocity deficit spanwise distribution is taken as half the wake width and is also used as the wake radius. This refers to the wake width.

[0172] Based on the average velocity loss of upstream wind turbines at multiple points on the rotor of the current wind turbine, the inflow velocity loss at multiple points on the rotor of the current wind turbine is obtained:

[0173] (9)

[0174] in, For the current number i Taiwan wind turbine rotor top point The inflow rate at the location is at a loss; For the first j Taiwanese unit in i Taiwan wind turbine rotor top point Average speed loss at the location; It is a binary variable if and only if the current number is... i The Taiwanese unit is in the first j Downstream of the Taiwanese unit In other cases ; N The number of wind turbines in the wind farm needs to be optimized.

[0175] Based on the inflow velocity deficit at multiple points on the wind turbine rotor, the average value is taken to obtain the wind speed in front of the wind turbine hub under preset wind conditions:

[0176] (10)

[0177] in, For the current number i Wind speed in front of the turbine hub of the typhoon generator; For the incoming airflow velocity;

[0178] At wind speed The wind direction angle is Under the given wind conditions, obtain the wind speed in front of the hub and the power curve of the current wind turbine, and obtain the output power of the current wind turbine under the above wind conditions; wherein, the wind turbine power curve includes the correspondence between the wind speed in front of the hub and the output power of the wind turbine.

[0179] Based on the output power under the above wind conditions, obtain the total output power of the wind farm to be optimized under the current layout:

[0180] (11)

[0181] in, The total output power of the wind farm to be optimized under the current layout scheme; The wind speed is The wind direction is Wind conditions; For the unit i In wind conditions Output power at the following levels; For wind conditions Frequency of occurrence; Number of wind directions; The number of wind speed segments taken for a single wind direction; N This refers to the number of generating units.

[0182] In one application scenario according to an embodiment of the present invention, the region vertex of the wind farm to be optimized can be: , , as well as The coordinate unit is meters (m), the unit model is Vestas-V80, and the number of units is... The image of a wind rose is as follows Figure 6 As shown, the unit power curve and thrust coefficient curve are as follows: Figure 7 As shown, the original turbine locations of the wind farm to be optimized are as follows: Figure 8 As shown, the available locations of the wind farm turbines to be optimized follow a parallelogram pattern. It should be noted that the area range of the wind farm to be optimized, the coordinates of the area vertices, the available locations of the turbines, the turbine models, and the number of turbines are only illustrative examples. In practical applications, these can be set as needed.

[0183] The basic parameters of the wind farm to be optimized are shown in Table 1.

[0184] Table 1 Wind Farm Parameters

[0185]

[0186] Select wind conditions with multiple wind directions and speeds; refer to the appendix for the probability values ​​for each wind direction and speed. Figure 6 . Figure 6 This is a wind rose diagram according to an embodiment of the present invention, with appended... Figure 6 The central angle of the polar coordinate bar chart represents the wind direction angle, and the height of the bar chart represents the wind frequency. Figure 7 This is a power curve and thrust coefficient curve of the wind turbine according to an embodiment of the present invention. The vertical axis represents the thrust coefficient, the horizontal axis represents the power (kW), and the vertical axis represents the wind speed (m / s). The optimization constraints are the area of ​​the wind farm to be optimized and the distance between any two wind turbines. It must be greater than 4 times the rotor diameter D This application scenario uses flat terrain and does not consider the impact of complex terrain. The evolution curve of the optimization process during deployment optimization is shown in the attached figure. Figure 9 As shown, Figure 9This is an evolution curve of the optimization process of a rule-based dual-population wind farm wind turbine layout optimization method according to an embodiment of the present invention. The horizontal axis represents the number of optimization iterations, and the vertical axis represents the maximum annual power generation (Annual Power / MWh) of the entire wind farm under different layout schemes. It can be seen from... Figure 9 As can be seen, with the increase of the number of iterations, the maximum annual power generation of the entire site gradually increases and eventually converges. It should be noted that the distance between any two wind turbines... It must be greater than 4 times the rotor diameter D The selection of flat terrain is an illustrative example of this application scenario, and can be selected as needed in practice.

[0187] Figure 8 The original wind turbine locations of the wind farm to be optimized are, according to an embodiment of the present invention. Figure 10 This is a schematic diagram of generating wind turbine locations in a wind farm to be optimized based on the mapping of randomly arranged bottom-layer coordinate points with upper-layer parallelogram regular available points according to an embodiment of the present invention. Figure 11 This refers to the optimal layout of wind turbine locations in a wind farm according to an embodiment of the present invention. (The location can be determined from...) Figure 9 and Figure 11 As can be seen, the optimal turbine locations in the wind farm exhibit a clear parallelogram-like regularity. Furthermore, since the number of usable locations in the upper parallelogram-like regularity is greater than or equal to the number of randomly selected lower-level coordinate locations, the final layout of the wind farm to be optimized exhibits a characteristic of having gaps within the farm. Under this optimal layout scheme, the annual power generation corresponding to the wind turbine locations in the wind farm to be optimized is 268,688.43 MWh. Compared to... Figure 8 The original wind turbine locations in the wind farm to be optimized correspond to an annual power generation of 261,616.18 MWh. The optimized parallelogram regular arrangement with gaps has an annual power generation increase of about 2.703%. It can ensure that the wind turbine locations in the wind farm to be optimized are arranged in a parallelogram regular pattern, while approximating the actual optimal random wind farm layout to the greatest extent, and significantly improving the power generation of the wind farm throughout its entire life cycle.

[0188] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders. These adjusted solutions are equivalent to the technical solutions described in the present invention and therefore will also fall within the protection scope of the present invention.

[0189] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0190] Another aspect of the present invention provides a computer-readable storage medium.

[0191] In one embodiment of the computer-readable storage medium according to the present invention, the computer-readable storage medium may be configured to store a program that executes the rule-based dual-cluster wind farm deployment optimization method of the above-described method embodiments. This program may be loaded and run by a processor to implement the rule-based dual-cluster wind farm deployment optimization method. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium may be a storage device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0192] Another aspect of the present invention provides an electronic device.

[0193] In one embodiment of an electronic device according to the present invention, the electronic device may include at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program, which, when executed by the at least one processor, implements the methods described in any of the above embodiments. See Appendix Figure 12 , Figure 12 The image exemplarily illustrates a communication connection between a memory 121 and a processor 122 via a bus.

[0194] In some embodiments of the present invention, the electronic device described in the present invention may be, but is not limited to, mobile phones, tablet computers, desktop computers, laptop computers, handheld computers, notebook computers, in-vehicle devices, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), augmented reality (AR) / virtual reality (VR) devices, etc., and the embodiments of the present invention do not limit this.

[0195] The technical solution of the present invention has been described above with reference to one embodiment shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions resulting from such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for optimizing wind turbine deployment in a dual-population wind farm based on regular arrangement, characterized in that, include: Obtain the attribute information of the wind farm to be optimized; Based on the attribute information, a randomized rule is generated for shape variables and the underlying coordinates of the wind turbine. A first initial population is established based on the shape variables of the rules, wherein the first initial population includes multiple first population individuals, and each first population individual is a set of shape variables of the rules. A second initial population is established based on the bottom coordinates of the wind turbine generators. The second initial population includes multiple second population individuals, each of which is a set of bottom coordinate vectors of the wind turbine generators in the wind farm to be optimized. Based on the shape variables of the rules and the underlying coordinate vector, the arrangement scheme of wind turbines in the wind farm to be optimized is obtained. Based on the first initial population, the second initial population, and the optimization objective, the arrangement scheme of wind turbines in the wind farm to be optimized is optimized. Once the optimization objective reaches the preset convergence condition, the optimal arrangement of wind turbines in the wind farm to be optimized is obtained. The attribute information includes the number of wind turbine units, and obtaining the arrangement scheme of wind turbine units in the wind farm to be optimized includes: Based on the shape variable of the rule, the available point vector of the wind turbine in the wind farm to be optimized is obtained, and the number of available points is greater than or equal to the number of wind turbines. Based on the available point vector and the underlying coordinate vector, the layout scheme of wind turbines in the wind farm to be optimized is obtained through the following steps; S1. Select a coordinate point in the underlying coordinate vector, obtain the distance between the coordinate point and each available point in the available point vector, extract the available point closest to the coordinate point as the coordinate point of the wind turbine in the wind farm to be optimized, and remove the available point closest to the coordinate point from the available point vector. S2. Traverse all coordinate points in the underlying coordinate vector and repeat step S1 until the number of coordinate points of the wind turbines in the wind farm to be optimized is consistent with the number of wind turbines. Based on the obtained coordinate points of the wind turbines in the wind farm to be optimized, determine the layout scheme of the wind turbines in the wind farm to be optimized.

2. The method for optimizing wind turbine deployment in a dual-species wind farm based on rule-based arrangement as described in claim 1, characterized in that, The attribute information includes the area range of the wind farm to be optimized; The shape variable and wind turbine bottom-level coordinates, which are randomly generated based on the attribute information, include: Set the distance between any two wind turbines in the wind farm to be optimized; Shape variables are randomly generated based on the area range of the wind farm to be optimized, according to a set rule. Based on the area of ​​the wind farm to be optimized, the number of wind turbines, and the distance between any two wind turbines in the wind farm to be optimized, the bottom coordinates of the wind turbines are randomly generated. The shape variables of the rules include one of the following: parallelogram rule shape variables, row arrangement rule shape variables, and ring rule shape variables. The distance between any two wind turbines in the wind farm to be optimized is greater than the rotor diameter. times, It is a positive integer greater than 1.

3. The method for optimizing wind turbine deployment in a dual-species wind farm based on rule-based arrangement according to claim 2, characterized in that, The shape variables based on the random generation rules for the regional extent of the wind farm to be optimized include: Based on the area of ​​the wind farm to be optimized, the coordinates of the global center point are randomly selected. Based on a uniform probability distribution, multiple shape parameters are randomly selected from a range of preset shape parameters, wherein the type of the shape parameter is determined based on the shape type of the shape variable of the rule; The shape variable of the rule is determined based on the global center point coordinates and the multiple shape parameters.

4. The method for optimizing wind turbine deployment in a dual-species wind farm based on rule-based arrangement according to claim 1, characterized in that, The preset convergence condition is that the target value of the optimization objective is maximized; The method further includes: S3. Optimize the first initial population as a benchmark to obtain the shape variable of the optimized rule; S4. Optimize based on the second initial population to obtain the optimized bottom coordinates of the wind turbine; S5. Based on the shape variables of the optimized rules and the bottom coordinates of the optimized wind turbine, establish a first optimized population and a second optimized population, and obtain the optimized wind turbine layout scheme. S6. Based on the optimized wind turbine layout scheme, obtain the corresponding optimized target. Repeat steps S3-S5 until the target value of the optimized target reaches its maximum, then end the optimization process and obtain the optimal regular shape variable, the optimal bottom coordinates of the wind turbine, and the optimal layout scheme of the wind turbine in the wind farm to be optimized.

5. The method for optimizing the deployment of wind turbines in a dual-species wind farm based on rule-based arrangement according to claim 4, characterized in that, The optimization objective is the total output power of the wind farm to be optimized under the wind turbine layout scheme. The method for obtaining the total output power of the wind farm to be optimized includes: Obtain wind resource information of the wind farm to be optimized, wherein the wind resource information includes the ambient incoming wind speed of the wind farm to be optimized; Based on the incoming wind speed of the wind farm to be optimized and the arrangement of wind turbines in the wind farm to be optimized, the total output power of the wind farm to be optimized is obtained according to the preset wind turbine wake model.

6. The method for optimizing the deployment of wind turbines in a dual-species wind farm based on regular arrangement as described in claim 5, characterized in that, The preset wind turbine wake model includes a two-dimensional analytical model of the wind turbine wake and an analytical model of the additional turbulence intensity of the wind turbine wake. The process of obtaining the total output power of the wind farm to be optimized based on the ambient inflow wind speed and the arrangement of wind turbines in the wind farm, according to a preset wake model, includes: The wake turbulence intensity of each wind turbine in the arrangement scheme is obtained based on the analytical model of the additional turbulence intensity of the wind turbine wake. The inflow additional turbulence intensity at multiple points on the rotor of each wind turbine is obtained based on the wake turbulence intensity of each wind turbine. Based on the two-dimensional analytical model of the wind turbine wake and the inflow additional turbulence intensity at multiple points on the rotor of each wind turbine, the inflow velocity loss at multiple points on the rotor of each wind turbine is obtained. Based on the inflow velocity deficit at multiple points on the rotor of each wind turbine and the ambient incoming wind speed, the wind speed in front of the hub of each wind turbine is obtained. Based on the wind speed in front of the hub of each wind turbine and the preset power curve of each wind turbine, the output power of each wind turbine is obtained. Based on the output power of each wind turbine, the total output power of the wind farm to be optimized is obtained.

7. An electronic device, characterized in that, include: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores a computer program, which, when executed by the at least one processor, implements the rule-based dual-cluster wind farm layout optimization method according to any one of claims 1 to 6.

8. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the rule-based dual-swarm wind farm layout optimization method as described in any one of claims 1 to 6.

Images