Parallelogram rule-based wind power plant layout optimization method and device, and medium

Abstract

The invention relates to the technical field of wind power plant micro-siting, and particularly provides a parallelogram rule-based wind power plant layout optimization method and device and a medium, and the method comprises the steps: obtaining the attribute information of a to-be-optimized wind power plant; randomly generating a shape variable of a parallelogram rule based on the attribute information, and establishing an initial population based on the shape variable; based on the global center point coordinate, the parallelogram included angle and the overall rotation angle in the shape variables, obtaining an arrangement scheme of the wind turbine generators in the to-be-optimized wind power plant; optimizing the arrangement scheme based on the initial population and the optimization target; when the optimization target reaches a preset convergence condition, obtaining an optimal arrangement scheme; according to the method, the arrangement scheme of the wind turbine generators is set by using the global center point coordinate, the parallelogram included angle, the overall rotation angle and other parameters of the parallelogram rule, traversal calculation is not needed, calculation resources are saved, the generator arrangement efficiency is improved, the mathematical optimal solution of the generator set point location is achieved, and the comprehensive benefits of the whole life cycle of a wind power plant are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of micro-siting of wind farms, and particularly to an optimization method, device and medium for wind turbine layout in a wind farm based on the parallelogram rule. Background Art

[0002] As a relatively mature and large-scale renewable clean energy power generation method, the development of wind power generation plays a key role in promoting the green and low-carbon transformation of the energy structure; the layout of wind turbines has an important impact on their operating efficiency. By reasonably designing the layout of wind turbines, the mutual influence between wind turbines can be reduced, and the wind capture and operating efficiency of wind turbines can be improved.

[0003] Currently, the layout of wind farms often arranges wind turbines based on the parallelogram rule. However, the traditional method of arranging wind turbines based on the parallelogram rule often adopts a traversal calculation method, that is, tries all possible wind turbine layout schemes and then selects the optimal one from them. Although this method can theoretically find the optimal solution, in actual operation, due to the large scale of wind farms and the large number of wind turbine positions, the time and computing resources required for traversal calculation are very large, resulting in low efficiency and being difficult to promote in actual applications. Moreover, traversal calculation cannot ensure obtaining the true mathematical optimal solution of wind turbine positions, resulting in poor comprehensive benefits of wind farms.

[0004] Correspondingly, there is a need in the art for a new optimization scheme for wind turbine layout in a wind farm based on the parallelogram rule to solve the above problems. Summary of the Invention

[0005] In order to overcome the above defects, the present invention is proposed to solve or at least partially solve the technical problems that the existing wind farm has low efficiency in obtaining the wind turbine layout method based on the parallelogram rule through traversal calculation, and it is difficult to obtain the true mathematical optimal solution of wind turbine positions, resulting in poor comprehensive benefits of the wind farm.

[0006] In a first aspect, an optimization method for wind turbine layout in a wind farm based on the parallelogram rule is provided, and the method includes: Obtain the attribute information of the wind farm to be optimized; Randomly generate shape variables of the parallelogram rule based on the attribute information; Establish an initial population based on the shape variables of the parallelogram rule, where the initial population includes multiple individuals, each individual is a set of shape variables of the parallelogram rule, and the shape variables of the parallelogram rule include the global center point coordinates, the parallelogram included angle, and the overall rotation angle; Obtain the layout scheme of wind turbines in the wind farm to be optimized based on the global center point coordinates, the parallelogram included angle, and the overall rotation angle; Optimize the layout plan of the wind turbines in the wind farm to be optimized based on the initial population and the preset optimization objective; After the preset optimization objective reaches the preset convergence condition, obtain the optimal layout plan of the wind turbines in the wind farm to be optimized.

[0007] In a technical solution of the above wind farm layout optimization method based on the parallelogram rule, the attribute information includes the regional scope of the wind farm to be optimized; the shape variables of the parallelogram rule also include the side length of the parallelogram row, the side length of the parallelogram column, the row spacing gradient coefficient, and the in-row spacing gradient coefficient; Randomly generating the shape variables of the parallelogram rule based on the attribute information includes: Set the distance between any two wind turbines in the wind farm to be optimized, where the distance between any two wind turbines in the wind farm to be optimized is greater than n times the rotor diameter, and n is a positive integer greater than 1; Randomly select the global center point coordinates based on the regional scope of the wind farm to be optimized; Based on the uniform probability distribution and the distance between any two wind turbines in the wind farm to be optimized, randomly select the parallelogram included angle and the overall rotation angle within a preset angle range, randomly select the side length of the parallelogram row and the side length of the parallelogram column within a preset side length range, and randomly select the row spacing gradient coefficient and the in-row spacing gradient coefficient within a preset coefficient range; Obtain the shape variables of the parallelogram rule based on the global center point coordinates, the parallelogram included angle, the overall rotation angle, the side length of the parallelogram row, the side length of the parallelogram column, the row spacing gradient coefficient, and the in-row spacing gradient coefficient.

[0008] In a technical solution of the above wind farm layout optimization method based on the parallelogram rule, the attribute information further includes the number of wind turbines in the wind farm to be optimized; The method for obtaining the layout plan of the wind turbines in the wind farm to be optimized includes: Based on the global center point coordinates and the overall rotation angle, obtain the first straight line with the horizontal line of the regional scope of the wind farm to be optimized as the reference; Based on the global center point coordinates and the parallelogram included angle, obtain the second straight line with the first straight line as the reference; Obtain multiple first gradient points on both sides of the global center point coordinates on the second straight line, and obtain multiple first parallel lines parallel to the first straight line based on the multiple first gradient points; Obtain a plurality of second gradient points on both sides of the global center point coordinates on the first straight line, and obtain a plurality of second parallel lines parallel to the second straight line based on the plurality of second gradient points; Obtain a plurality of intersection points based on the plurality of first parallel lines and the plurality of second parallel lines, wherein the intersection points are the coordinate points of the wind turbines in the wind farm to be optimized; Obtain the layout scheme of the wind turbines in the wind farm to be optimized based on the coordinate points of the wind turbines in the wind farm to be optimized.

[0009] In a technical solution of the above wind farm layout optimization method based on the parallelogram rule, the obtaining a plurality of first gradient points on both sides of the global center point coordinates on the second straight line and obtaining a plurality of first parallel lines parallel to the first straight line based on the plurality of first gradient points includes: Obtain the first distance between two intersection points of the first straight line and the boundary of the wind farm to be optimized; Determine the maximum number of the first gradient points based on the first distance and the distance between any two wind turbines in the wind farm to be optimized; Determine the distance between the first gradient points and the coordinate points of the first gradient points on the second straight line based on the maximum number of the first gradient points, the row spacing gradient coefficient and the row side length of the parallelogram; Generate a plurality of first parallel lines parallel to the first straight line based on the distance between the first gradient points and the coordinate points of the first gradient points on the second straight line.

[0010] In a technical solution of the above wind farm layout optimization method based on the parallelogram rule, the obtaining a plurality of second gradient points on both sides of the global center point coordinates on the first straight line and obtaining a plurality of second parallel lines parallel to the second straight line based on the plurality of second gradient points includes: Obtain the second distance between two intersection points of the second straight line and the boundary of the wind farm to be optimized; Determine the maximum number of the second gradient points based on the second distance and the distance between any two wind turbines in the wind farm to be optimized; Determine the distance between the second gradient points and the coordinate points of the second gradient points on the first straight line based on the maximum number of the second gradient points, the in-row spacing gradient coefficient and the column side length of the parallelogram; Generate a plurality of second parallel lines parallel to the second straight line based on the distance between the second gradient points and the coordinate points of the second gradient points on the first straight line.

[0011] In a technical solution of the above wind farm layout optimization method based on the parallelogram rule, the preset convergence condition is that the target value of the preset optimization target is the largest; The method further includes: Optimizing based on the initial population to obtain the shape variables of the optimized parallelogram rule; Establishing an optimized population based on the shape variables of the optimized parallelogram rule and obtaining the layout scheme of the optimized wind turbine units; Until the target value of the preset optimization target reaches the maximum, end the optimization process, and obtain the optimal shape variables of the parallelogram rule and the optimal layout scheme of the wind turbine units in the wind farm to be optimized.

[0012] In a technical solution of the above wind farm layout optimization method based on the parallelogram rule, the preset optimization target is the total output power of the wind farm to be optimized under the layout scheme of the wind turbine units; The method for obtaining the total output power of the wind farm to be optimized includes: Obtaining the wind resource information of the wind farm to be optimized, wherein the wind resource information includes the environmental incoming flow wind speed of the wind farm to be optimized; Based on the environmental incoming flow wind speed and the layout scheme of the wind farm to be optimized, obtain the total output power of the wind farm to be optimized according to the preset wind turbine wake model.

[0013] In a technical solution of the above wind farm layout optimization method based on the parallelogram rule, 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 obtaining of the total output power of the wind farm to be optimized based on the environmental incoming flow wind speed and the layout scheme of the wind farm to be optimized according to the preset wake model includes: Obtaining the wake flow direction turbulence intensity of each wind turbine unit in the layout scheme based on the analytical model of the additional turbulence intensity of the wind turbine wake; Obtaining the additional incoming flow direction turbulence intensity at multiple points on the wind wheel of each wind turbine unit based on the wake flow direction turbulence intensity of each wind turbine unit; Obtaining the incoming flow velocity deficit at multiple points on the wind wheel of each wind turbine unit based on the two-dimensional analytical model of the wind turbine wake and the additional incoming flow direction turbulence intensity at multiple points on the wind wheel of each wind turbine unit; Obtaining the wind speed in front of the hub of each wind turbine unit based on the incoming flow velocity deficit at multiple points on the wind wheel of each wind turbine unit and the environmental incoming flow wind speed; Obtaining the output power of each wind turbine unit based on the wind speed in front of the hub of each wind turbine unit and the preset power curve of each wind turbine unit; Obtaining the total output power of the wind farm to be optimized based on the output power of each wind turbine unit.

[0014] In a second aspect, an electronic device is provided, which includes at least one processor; and a memory communicatively connected to the at least one processor; wherein, a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method described in any one of the technical solutions of the above technical solution of the wind farm layout optimization method based on the parallelogram rule is implemented.

[0015] In a third aspect, a computer-readable storage medium is provided, which stores multiple program codes, and the program codes are adapted to be loaded and run by a processor to execute the method described in any one of the technical solutions of the above technical solution of the wind farm layout optimization method based on the parallelogram rule.

[0016] One or more of the above technical solutions of the present invention have at least one or more of the following beneficial effects: In implementing the technical solution of the wind farm layout optimization method based on the parallelogram rule provided by the present invention, attribute information of the wind farm to be optimized is obtained; shape variables of the parallelogram rule are randomly generated based on the attribute information and an initial population is established based on the shape variables; an arrangement plan of wind turbines in the wind farm to be optimized is obtained based on the global center point coordinates, parallelogram angle and overall rotation angle in the shape variables; the arrangement plan is optimized based on the initial population and a preset optimization target; when the preset optimization target reaches the preset convergence condition, an optimal arrangement plan of wind turbines in the wind farm to be optimized is obtained; the present invention uses parameters such as the global center point coordinates, parallelogram angle and overall rotation angle of the parallelogram rule to set the arrangement plan of wind turbines, without the need for traversal calculation, which reduces the calculation time required, saves calculation resources, improves the layout efficiency, realizes the mathematical optimal solution of the positions of wind turbines, and thus improves the comprehensive benefits of the entire life cycle of the wind farm. Description of the Drawings

[0017] Referring to the drawings, the disclosure of the present invention will become more understandable. It is easy for those skilled in the art to understand that: these drawings are only for the purpose of illustration and are not intended to limit the protection scope of the present invention. Among them: Figure 1 is a schematic flowchart of the main steps of the wind farm layout optimization method based on the parallelogram rule according to an embodiment of the present invention; Figure 2 is a schematic flowchart of the main steps of randomly generating shape variables of the parallelogram rule based on attribute information according to an embodiment of the present invention; Figure 3 is a schematic flowchart of the main steps of the arrangement plan of wind turbines in the wind farm to be optimized according to an embodiment of the present invention; Figure 4Schematic diagram of the main steps of a method for obtaining a plurality of first parallel lines according to an embodiment of the present invention; Figure 5 Schematic diagram of the main steps of a method for obtaining a plurality of second parallel lines according to an embodiment of the present invention; Figure 6 Wind rose diagram according to an embodiment of the present invention; Figure 7 Unit power curve and thrust coefficient curve according to an embodiment of the present invention; Figure 8 Original wind turbine positions of the wind farm to be optimized according to an embodiment of the present invention; Figure 9 Schematic diagram of the positions of wind turbines in the wind farm to be optimized under the optimal layout scheme based on the parallelogram rule according to an embodiment of the present invention; Figure 10 Schematic diagram of the main structure of an electronic device according to an embodiment of the present invention.

[0018] Reference signs: 101: Memory; 102: Processor. Detailed implementation manners

[0019] The following describes some embodiments of the present invention with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principle of the present invention and are not intended to limit the protection scope of the present invention.

[0020] In the description of the present invention, "module" and "processor" may include hardware, software, or a combination of both. A module may include a hardware circuit, various suitable sensors, communication ports, a memory, and may also include a software part, such as program code, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, in hardware, or in a combination of both. The computer-readable storage medium includes any suitable medium for storing program code, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and the like. The term "A and / or B" represents all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a meaning similar to "A and / or B" and may include only A, only B, or A and B. The singular terms "a" and "this" may also include the plural form.

[0021] Refer to the attached Figure 1 , Figure 1It is a schematic diagram of the main step flow of the wind farm layout optimization method based on the parallelogram rule according to an embodiment of the present invention. As Figure 1 shown, the wind farm layout optimization method based on the parallelogram rule in the embodiment of the present invention mainly includes the following steps S101 to S104.

[0022] Step S101: Obtain the attribute information of the wind farm to be optimized.

[0023] In this embodiment, the attribute information includes the regional scope of the wind farm to be optimized and the number of wind turbines. ; In one implementation manner, a suitable wind turbine model can be selected according to the regional scope, the number of wind turbines, and the installed capacity requirements of the wind farm to be optimized.

[0024] Step S102: Randomly generate the shape variables of the parallelogram rule based on the attribute information; establish an initial population based on the shape variables of the parallelogram rule.

[0025] In this embodiment, the constraint conditions of the wind turbine coordinates are preset, and the constraint conditions include the regional scope of the wind farm to be optimized and the distance between any two wind turbines in the wind farm to be optimized. Among them, the distance between any two wind turbines in the wind farm to be optimized is greater than the wind wheel diameter D times n of , n where is a positive integer greater than 1; Optionally, the distance between any two wind turbines in the wind farm to be optimized is greater than four times the wind wheel diameter. It should be noted that the distance between any two wind turbines in the wind farm to be optimized in this embodiment being greater than four times the wind wheel diameter is only an example of an implementation manner and is not a limitation to this embodiment. In the actual application of the implementation manner of the present invention, the distance between any two wind turbines in the wind farm to be optimized

[0026] can be set according to actual needs.

[0027] In one embodiment, real - number coding is adopted to randomly generate the shape variables of the parallelogram rule, and an initial population is established. The initial population contains multiple individuals, and each individual is a row vector containing 10 variables, that is ; each set of shape variables of the parallelogram rule corresponds to a wind farm unit layout scheme; among them, real - number coding means that each gene value of each individual is represented by a floating - point number within a certain range.

[0028] In this embodiment, the shape variables of the parallelogram rule include the global center - point coordinates , the included angle of the parallelogram θ , the overall rotation angle γ , the side length of the parallelogram in the row direction a , the side length of the parallelogram in the column direction b , the gradient coefficient of the row - to - row spacing and the gradient coefficient of the in - row spacing .

[0029] In this embodiment, referring to the appendix Figure 2 , Figure 2 is a schematic diagram of the main step flow for randomly generating the shape variables of the parallelogram rule based on attribute information according to an embodiment of the present invention. As Figure 2 shown, randomly generating the shape variables of the parallelogram rule based on attribute information includes: Step S201: Randomly select the global center - point coordinates based on the regional scope of the wind farm to be optimized; Specifically, within the closed polygon of the regional scope of the wind farm to be optimized, randomly pick out a point coordinate as the global center - point coordinates for parallelogram - rule unit layout .

[0030] Step S202: Based on the uniform probability distribution and the distance between any two wind turbines in the wind farm to be optimized, randomly select the included angle of the parallelogram and the overall rotation angle within a preset angle range, randomly select the side length of the parallelogram in the row direction and the side length of the parallelogram in the column direction within a preset side - length range, and randomly select the gradient coefficient of the row - to - row spacing and the gradient coefficient of the in - row spacing within a preset coefficient range; Specifically, according to the uniform probability distribution, randomly pick out the included angle between two sides of the parallelogram and the overall rotation angle θ of the parallelogram within the range of γ , and randomly pick out the side length of the parallelogram in the row direction and the side length b of the parallelogram in the column direction within a certain multiple range of the unit - distance limit a . Randomly pick out the gradient coefficient of the row - to - row spacing and within the range of [0, 1).Two parameters, randomly obtain the row spacing gradient coefficient within the range of [0, 1). and Two parameters.

[0031] Step S203: Obtain the shape variables of the parallelogram rule based on the global center point coordinates, parallelogram angle, overall rotation angle, parallelogram row side length, parallelogram column side length, row spacing gradient coefficient, and in-row spacing gradient coefficient.

[0032] Specifically, based on the global center point coordinates , parallelogram angle θ , overall rotation angle γ , parallelogram row side length a , parallelogram column side length b, row spacing gradient coefficient and in-row spacing gradient coefficient to obtain the shape variables of the parallelogram rule .

[0033] Step S103: Obtain the layout scheme of the wind turbines in the wind farm to be optimized based on the global center point coordinates, parallelogram angle, and overall rotation angle.

[0034] In this embodiment, refer to the appendix Figure 3 , Figure 3 is the main step flow diagram of the layout scheme of the wind turbines in the wind farm to be optimized according to an embodiment of the present invention. As Figure 3 shown, the method for obtaining the layout scheme of the wind turbines in the wind farm to be optimized includes:[[]] Step S301: Based on the global center point coordinates and overall rotation angle, take the horizontal line of the area range of the wind farm to be optimized as the benchmark to obtain the first straight line; Specifically, with the global center point coordinates as the vertex, take the horizontal line of the area range of the wind farm to be optimized as the benchmark, and rotate counterclockwise by an overall rotation angle γ angle to make a straight line intersect with the boundary of the closed polygon of the entire area range of the wind farm to be optimized to obtain the first straight line.

[0035] Step S302: Based on the global center point coordinates and parallelogram angle, take the first straight line as the benchmark to obtain the second straight line; Specifically, with the global center point coordinates as the vertex, take the first straight line as one side, rotate counterclockwise by a parallelogram angle θ angle, and then make another straight line intersect with the boundary of the closed polygon of the entire area range of the wind farm to be optimized to obtain the second straight line.

[0036] Step S303: Obtain multiple first gradient points on both sides of the global center point coordinates on the second straight line, and obtain multiple first parallel lines parallel to the first straight line based on the multiple first gradient points; Specifically, taking the first straight line as a reference and using the global center point coordinates as the center, according to the gradient point-taking method, take multiple first gradient points on the second straight line towards both sides of the global center point coordinates ; based on the multiple first gradient points, draw multiple first parallel lines parallel to the first straight line, and the multiple first parallel lines intersect with the boundary of the closed polygon of the area range of the wind farm to be optimized.

[0037] Refer to the appendix Figure 4 , Figure 4 which is a schematic main step flow diagram of the method for obtaining multiple first parallel lines according to an embodiment of the present invention. As Figure 4 shown, the method for obtaining multiple first parallel lines includes: Step S401: Obtain the first distance between two intersection points of the first straight line and the boundary of the wind farm to be optimized; Specifically, determine the first distance between two intersection points of the first straight line and the boundary of the wind farm to be optimized (the area range of the wind farm to be optimized) .

[0038] Step S402: Determine the maximum number of first gradient points based on the first distance and the distance between any two wind turbines in the wind farm to be optimized; Specifically, based on the first distance and the distance between any two wind turbines in the wind farm to be optimized , determine the number of first gradient points and the number of first parallel lines, and the maximum number is , where is the largest integer not exceeding z.

[0039] Step S403: Determine the distance between the first gradient points and the coordinate points of the first gradient points on the second straight line based on the maximum number of first gradient points, the row spacing gradient coefficient, and the side length of the parallelogram row; Specifically, considering the Gaussian distribution function with an average value of 0 , uniformly take out numbers in the range of [-1, 1] , then the distance set between the first gradient points not less than can be obtained according to the Gaussian distribution function , where and are the parallelogram row spacing gradient coefficients, corresponds to in the Gaussian distribution function x , In the corresponding Gaussian distribution function , , the set composed of all the coordinates of the first gradient points is .

[0040] Step S404: Generate a plurality of first parallel lines parallel to the first line based on the distances between the first gradient points and the coordinate points of the first gradient points on the second line.

[0041] Specifically, draw a plurality of first parallel lines passing through the first gradient points and parallel to the first line.

[0042] Step S304: Obtain a plurality of second gradient points on both sides of the global center point coordinate on the first line, and obtain a plurality of second parallel lines parallel to the second line based on the plurality of second gradient points; Specifically, taking the second line as a reference, with the global center point coordinate as the center, according to the gradient point-taking method, take a plurality of second gradient points on both sides of the global center point coordinate on the first line, and based on the plurality of second gradient points, draw a plurality of second parallel lines parallel to the second line. The plurality of second parallel lines intersect with the boundary of the closed polygon of the area range of the wind farm to be optimized.

[0043] Refer to Appendix Figure 5 , Figure 5 is a schematic flowchart of the main steps of the method for obtaining a plurality of second parallel lines according to an embodiment of the present invention. As Figure 5 shown, the method for obtaining a plurality of second parallel lines includes: Step S501: Obtain the second distance between the two intersection points of the second line and the boundary of the wind farm to be optimized; Specifically, determine the second distance between the two intersection points of the first line and the boundary of the wind farm to be optimized (the area range of the wind farm to be optimized) .

[0044] Step S502: Determine the maximum number of second gradient points based on the second distance and the distance between any two wind turbines in the wind farm to be optimized; Specifically, based on the second distance and the distance between any two wind turbines in the wind farm to be optimized , determine the number of second gradient points and the number of second parallel lines. The maximum number is , where is the largest integer not exceeding.

[0045] Step S503: Determine the distance between the second gradient points and the coordinate points of the second gradient points on the first line based on the maximum number of second gradient points, the in-line spacing gradient coefficient, and the side length of the parallelogram column; Specifically, consider a Gaussian distribution function with a mean of 0 , and uniformly extract numbers within the range of [-1, 1], then a set of distances between the second inflection points not less than can be obtained according to the Gaussian distribution function , where and are the in-row spacing gradient coefficients of the parallelogram, corresponds to in the Gaussian distribution function, x , corresponds to in the Gaussian distribution function, , and the set composed of all the coordinates of the second inflection points is .

[0046] Step S504: Generate multiple second parallel lines parallel to the second line based on the distances between the second inflection points and the coordinate points of the second inflection points on the first line.

[0047] Specifically, draw multiple second parallel lines parallel to the second line through the second inflection points.

[0048] Step S305: Obtain multiple intersection points based on the multiple first parallel lines and the multiple second parallel lines, where the intersection points are the coordinate points of the wind turbine generators in the wind farm to be optimized; Specifically, denote the intersection points of the multiple first parallel lines and the multiple second parallel lines as , and the multiple first parallel lines and the multiple second parallel lines intersect to form multiple parallelograms with the same size and shape. Denote the side length of the parallelogram on the first line as the parallelogram row side length a , denote the side length of the parallelogram on the second line as the parallelogram column side length b , the distance between two first parallel lines of the parallelogram is , and the distance between two second parallel lines of the parallelogram is .

[0049] Step S306: Obtain the layout scheme of the wind turbine generators in the wind farm to be optimized based on the coordinate points of the multiple wind turbine generators in the wind farm to be optimized.

[0050] Specifically, use the set of all intersection points as the uniquely determined wind farm unit layout scheme corresponding to the shape variable of the current parallelogram rule.

[0051] Step S104: Optimize the layout scheme of wind turbines in the wind farm to be optimized based on the initial population and the preset optimization objective; when the preset optimization objective reaches the preset convergence condition, obtain the optimal layout scheme of wind turbines in the wind farm to be optimized.

[0052] In this embodiment, the preset convergence condition is that the target value of the preset optimization objective is the largest; The method for optimizing the layout scheme of wind turbines in the wind farm to be optimized includes: Optimize based on the initial population to obtain the shape variables of the optimized parallelogram rule; Establish an optimized population based on the shape variables of the optimized parallelogram rule and obtain the optimized layout scheme of wind turbines; Until the target value of the preset optimization objective reaches the maximum, end the optimization process, and obtain the optimal shape variables of the parallelogram rule and the optimal layout scheme of wind turbines in the wind farm to be optimized.

[0053] In one implementation, the layout scheme of wind turbines in the wind farm to be optimized is optimized based on the genetic algorithm as the optimization algorithm, and the genetic algorithm can be the NSGA-II algorithm.

[0054] In one implementation, the shape variables of the parallelogram rule can be obtained through crossover and mutation based on the constraint conditions of the wind turbine coordinates to get new shape variables of the parallelogram rule.

[0055] In one implementation, the method for optimizing the initial population can be: set the optimization target value, and through the layout optimization process based on the optimization algorithm, and combine with other frameworks to calculate the preset optimization objective, and iteratively obtain a series of layout schemes of wind turbines in the wind farm to be optimized that meet the requirements and have a globally better or optimal optimization target value. The specific optimization process of the initial population is as follows: (1) Population initialization. Randomly generate optimization variables (including the shape variables of the parallelogram rule) to form an initial population containing N individuals. Each individual is a definite layout scheme, containing N unit coordinates. The optimization variables use real number coding, and the unit coordinates are randomly generated within the optimization constraints. If the available points of the generated parallelogram rule do not fully meet the optimization constraints, or the number of points is less than the required number of units, then regenerate this individual until it meets the requirements.

[0056] (2) Crossover and mutation. The present invention uses the simulated binary crossover method for the crossover operation and performs the mutation operation by adding Gaussian random numbers to the optimization variables (if the parallelogram rule layout form is adopted, crossover and mutation are performed on the shape variables). In the mutation operation, there is a probability of adding random numbers of two scales, large and small, to the variables, and the Gaussian standard deviation of the large-scale mutation is set to , the Gaussian standard deviation of the small-scale variation is set to , and the mutation probabilities are set respectively and .

[0057] (3) Combine the parent and offspring. Combine the parent population with the offspring population generated by crossover and mutation to form a population of 2N individuals in total.

[0058] (4) Fast non-dominated sorting and crowding degree calculation. Calculate the optimized objective values of each individual in the combined population. According to the optimized objective values, find the non-dominated individuals in the combined population of parents and offspring in turn to divide them into levels. In the same level, sort the individuals in ascending order according to one objective to obtain the serial number i , and then calculate the crowding degree of the individuals .

[0059] (5) Screen to obtain the dominant population. Select N individuals in the combined population of parents and offspring using the obtained levels. If adding a certain level exactly exceeds the population size, then randomly select two individuals 、 in this level using the elite strategy, and select the one with a larger crowding degree until the required number of individuals is obtained.

[0060] (6) Convergence judgment. Return to (2), repeat the steps until the number of iterations meets the requirements to obtain a convergent solution set. At this time, the convergent solution set is the optimized population.

[0061] In this embodiment, the preset optimization objective is the total output power of the wind farm to be optimized under the layout scheme of the wind turbines; The method for obtaining the total output power of the wind farm to be optimized includes: Obtain the wind resource information of the wind farm to be optimized, where the wind resource information includes the environmental incoming flow wind speed of the wind farm to be optimized; Based on the environmental incoming flow wind speed of the wind farm to be optimized and the layout scheme of the wind turbines in the wind farm to be optimized, obtain the total output power of the wind farm to be optimized according to the preset wind turbine wake model.

[0062] 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; Based on the environmental incoming flow wind speed of the wind farm to be optimized and the layout scheme of the wind turbines in the wind farm to be optimized, obtaining the total output power of the wind farm to be optimized according to the preset wake model includes: Obtain the wake flow direction turbulence intensity of each wind turbine in the layout scheme based on the analytical model of the additional turbulence intensity of the wind turbine wake; Obtain the additional incoming flow direction turbulence intensity at multiple points on the wind wheel of each wind turbine based on the wake flow direction turbulence intensity of each wind turbine; Based on the two-dimensional analytical model of the wake of a wind turbine and the additional inflow directional turbulence intensity at multiple points on the wind turbine rotor, the inflow velocity deficit at multiple points on the wind turbine rotor is obtained; Based on the inflow velocity deficit at multiple points on the wind turbine rotor and the ambient inflow 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.

[0063] In one embodiment, the method for obtaining the total output power of the wind farm to be optimized includes: Calculating the wake directional turbulence intensity of each wind turbine in the layout scheme, and the wake directional turbulence intensity of the wind turbine can be obtained from the wake additional turbulence intensity analytical model in the following formulas (1)-(6): (1) Wherein, is the thrust coefficient; is the atmospheric environmental turbulence intensity; D is the wind turbine rotor diameter; r is the lateral distance of the rotor axis; is the standard deviation of the Gaussian curve the same as the velocity deficit model; z is the vertical height.

[0064] Flow function is the maximum additional turbulence intensity of the wake cross-section at each flow direction position: (2) Wherein, ; ; is the correction value considering the near wake region.

[0065] Formula (1) spanwise function is: (3) Wherein, and take values: (4) (5) is the vertical correction function: (6) For each wind turbine in a wind farm, based on the wake flow direction turbulence intensity at multiple points on the wind turbine rotor of the upstream wind turbine of the current wind turbine, obtain the additional inflow direction turbulence intensity at multiple points on the wind turbine rotor of the current wind turbine: (7) where is the additional inflow direction turbulence intensity at point i on the rotor of the th unit; is the wake flow direction turbulence intensity at point j on the rotor of the i th unit by the th unit; is a binary variable, which is i when and only when the current j th unit is downstream of the th unit, and in other cases; N is the number of wind turbines in the wind farm to be optimized.

[0066] Obtain the average velocity deficit of the wind turbine based on the wind turbine wake two-dimensional analytical model and the additional inflow direction turbulence intensity at multiple points on the rotor of each wind turbine: (8) where is the thrust coefficient; is the actual expansion rate of the wake boundary; is the rotor radius; is the standard deviation of the spanwise distribution of the velocity deficit, taken as half of the wake width and also used as the wake radius, is the wake width.

[0067] Obtain the inflow velocity deficit at multiple points on the rotor of the current wind turbine based on the average velocity deficit at multiple points on the rotor of the upstream wind turbine of the current wind turbine: (9) where is the inflow velocity deficit at point i on the rotor of the current th unit; is the average velocity deficit at point j on the rotor of the i th unit by the th unit; is a binary variable, which is i when and only when the current j th unit is downstream of the th unit, and ; N is the number of wind turbines in the wind farm to be optimized.

[0068] According to the inflow velocity loss of multiple points on the wind turbine rotor, the average value is taken to obtain the wind speed in front of the hub of the current wind turbine under the preset wind conditions: (10) in, For the current i The wind speed in front of the hub of the typhoon turbine; is the ambient wind speed; At wind speed , wind direction angle Under the wind condition of , the wind speed in front of the hub of the current wind turbine and the power curve of the current wind turbine are obtained, and the output power of the current wind turbine under the above wind condition is obtained; wherein the power curve of the wind turbine includes the corresponding relationship between the wind speed in front of the hub and the output power of the wind turbine.

[0069] According to the corresponding output power under the above wind conditions, the total output power of the wind farm to be optimized under the current arrangement scheme is obtained: (11) in, is the total output power of the wind farm to be optimized under the current arrangement scheme; The wind speed is , wind direction is wind conditions; For the crew i In wind conditions Output power under For wind conditions Frequency of occurrence; is the number of wind directions; The number of wind speed segments taken for a single wind direction; N is the number of units.

[0070] In an application scenario according to an embodiment of the present invention, the regional vertices of the wind farm to be optimized may be , , as well as , the coordinate dimension is meter (m), the unit model is Vestas-V80 unit (Vestas-V80 unit), and the number of units is , wind rose diagram Figure 6 As shown, the unit power curve and thrust coefficient curve are as follows Figure 7 As shown in the figure, the original unit locations of the wind farm to be optimized are as follows Figure 8As shown in the figure, the rule form of the available positions of the wind turbines in the wind farm to be optimized is the parallelogram rule. It should be noted that the regional scope of the wind farm to be optimized, the coordinates of the regional vertices, the available form of the available positions of the wind turbines in the wind farm to be optimized, the turbine models, the number of turbines, etc. are only for illustrative purposes, and in actual applications, they can be set according to needs.

[0071] The basic parameters of the wind farm to be optimized are shown in Table 1; Table 1 Wind Farm Parameters

[0072] Select the wind conditions with multiple wind directions and multiple wind speeds, and the probability values for each wind direction and wind speed can be referred to in the appendix Figure 6 . Figure 6 is the wind rose diagram according to an embodiment of the present invention. In the appendix Figure 6 the central angle of the polar coordinate histogram represents the wind direction angle, and the height of the histogram represents the wind frequency. Figure 7 is the power curve and thrust coefficient curve of the wind turbine according to an embodiment of the present invention. The ordinate Thrust Coefficient is the thrust coefficient, Power is the power (kW), and the abscissa Wind Speed is the wind speed (m / s). The optimization constraint conditions are the regional scope of the wind farm to be optimized, and the distance between any two wind turbines must be greater than 4 times the wind turbine diameter D . In this application scenario, flat terrain is selected, and the influence of complex terrain is not considered. It should be noted that the distance between any two wind turbines must be greater than 4 times the wind turbine diameter D , and the selection of flat terrain are all for illustrative purposes in this application scenario, and can be selected according to needs in actual situations.

[0073] Figure 8 is the original wind turbine positions in the wind farm to be optimized according to an embodiment of the present invention, Figure 9 is the schematic diagram of the wind turbine positions in the wind farm to be optimized under the optimal layout scheme based on the parallelogram rule according to an embodiment of the present invention. It can be seen from Figure 9 that the optimal wind turbine positions in the wind farm have obvious parallelogram rule layout characteristics. The annual power generation corresponding to the wind turbine positions in the wind farm to be optimized under this optimal layout scheme is 265391.86 MWh. Compared with Figure 8 the annual power generation of 261616.18 MWh corresponding to the original wind turbine positions in the wind farm to be optimized, the optimized layout scheme based on the parallelogram rule has an annual power generation increase of about 1.443%. It can ensure that the wind turbine positions in the wind farm to be optimized are arranged in a parallelogram rule, while significantly improving the power generation of the wind farm throughout its life cycle.

[0074] It should be noted that although the above embodiments describe the steps in a specific order, those skilled in the art can understand that in order to achieve the effects of the present invention, it is not necessary to execute different steps in such an order. They can be executed simultaneously (in parallel) or in other orders, and these adjusted solutions are equivalent technical solutions to the technical solutions described in the present invention, and thus will also fall within the protection scope of the present invention.

[0075] Those skilled in the art can understand that all or part of the processes in the method of the above embodiment of the present invention can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0076] Another aspect of the present invention also provides a computer-readable storage medium.

[0077] In an embodiment of a computer-readable storage medium according to the present invention, the computer-readable storage medium can be configured to store a program for executing the wind farm layout optimization method based on the parallelogram rule of the above method embodiment. The program can be loaded and run by a processor to implement the wind farm layout optimization method based on the parallelogram rule. For the sake of convenience of description, only the parts related to the embodiments of the present invention are shown. For the specific technical details not disclosed, please refer to the method part of the embodiments of the present invention. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiments of the present invention is a non-transitory computer-readable storage medium.

[0078] Another aspect of the present invention also provides an electronic device.

[0079] In an embodiment of an electronic device according to the present invention, the electronic device can include at least one processor; and a memory communicatively connected to at least one processor; wherein, a computer program is stored in the memory, and when the computer program is executed by at least one processor, the method described in any of the above embodiments is implemented. Refer to the attached Figure 10 , Figure 10 It is exemplarily shown in the figure that the memory 101 and the processor 102 are communicatively connected through a bus.

[0080] In some embodiments of the present invention, the electronic device described in the present invention may be, but is not limited to, a mobile phone, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, a vehicle-mounted device, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), an augmented reality (AR) / virtual reality (VR) device, etc. The embodiments of the present invention are not limited thereto.

[0081] So far, the technical solution of the present invention has been described in conjunction with an embodiment shown in the accompanying drawings. However, those skilled in the art can easily understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A wind farm layout optimization method based on the parallelogram rule, characterized in that: include: Obtaining attribute information of the wind farm to be optimized; Randomly generate shape variables of a parallelogram rule based on the attribute information; Establishing an initial population based on the shape variables of the parallelogram rule, wherein the initial population includes a plurality of individuals, each of which is a set of shape variables of the parallelogram rule, and the shape variables of the parallelogram rule include global center point coordinates, parallelogram angles, and overall rotation angles; Obtaining an arrangement scheme of wind turbines in the wind farm to be optimized based on the global center point coordinates, the parallelogram angle and the overall rotation angle; Based on the initial population and the preset optimization target, optimizing the arrangement scheme of the wind turbines in the wind farm to be optimized; When the preset optimization target reaches the preset convergence condition, the optimal arrangement scheme of the wind turbines in the wind farm to be optimized is obtained.

2. The wind farm layout optimization method based on the parallelogram rule according to claim 1 is characterized in that: The attribute information includes the regional scope of the wind farm to be optimized; the shape variables of the parallelogram rule also include the parallelogram row side length, the parallelogram column side length, the row spacing gradient coefficient and the row spacing gradient coefficient; The shape variables of the parallelogram rule randomly generated based on the attribute information include: Setting the distance between any two wind turbines in the wind farm to be optimized, wherein the distance between any two wind turbines in the wind farm to be optimized is greater than times the diameter of the wind rotor and is a positive integer greater than 1; Based on the regional scope of the wind farm to be optimized, randomly selecting the coordinates of the global center point; Based on the uniform probability distribution and the distance between any two wind turbines in the wind farm to be optimized, the parallelogram angle and the overall rotation angle are randomly selected within a preset angle range, the parallelogram row side length and the parallelogram column side length are randomly selected within a preset side length range, and the row spacing gradient coefficient and the intra-row spacing gradient coefficient are randomly selected within a preset coefficient range; The shape variables of the parallelogram rule are obtained based on the global center point coordinates, the parallelogram angle, the overall rotation angle, the parallelogram row side length, the parallelogram column side length, the row spacing gradient coefficient and the intra-row spacing gradient coefficient.

3. The wind farm layout optimization method based on the parallelogram rule according to claim 2 is characterized in that: The attribute information also includes the number of wind turbines in the wind farm to be optimized; The method for obtaining the arrangement scheme of wind turbines in the wind farm to be optimized comprises: Based on the global center point coordinates and the overall rotation angle, a first straight line is obtained with the horizontal line of the regional range of the wind farm to be optimized as a reference; Based on the global center point coordinates and the parallelogram angle, taking the first straight line as a reference, obtaining a second straight line; Acquire a plurality of first gradient points on both sides of the global center point coordinates on the second straight line, and obtain a plurality of first parallel lines parallel to the first straight line based on the plurality of first gradient points; Acquire a plurality of second gradient points on both sides of the global center point coordinates on the first straight line, and obtain a plurality of second parallel lines parallel to the second straight line based on the plurality of second gradient points; Obtaining a plurality of intersection points based on a plurality of first parallel lines and a plurality of second parallel lines, wherein the intersection points are coordinate points of wind turbines in the wind farm to be optimized; An arrangement scheme of the wind turbine sets in the wind farm to be optimized is obtained based on a plurality of coordinate points of the wind turbine sets in the wind farm to be optimized.

4. The wind farm layout optimization method based on the parallelogram rule according to claim 3 is characterized in that: The acquiring a plurality of first gradient points on both sides of the global center point coordinates on the second straight line, and acquiring a plurality of first parallel lines parallel to the first straight line based on the plurality of first gradient points comprises: Acquire a first distance between two intersection points of the first straight line and the boundary of the wind farm to be optimized; Determining a maximum number of the first gradient points based on the first distance and the distance between any two wind turbines in the wind farm to be optimized; Determine the distance between the first gradient points and the coordinate points of the first gradient points on the second straight line based on the maximum number of the first gradient points, the line spacing gradient coefficient and the length of the parallelogram line side; A plurality of first parallel lines parallel to the first straight line are generated based on the distances between the first gradient points and the coordinate points of the first gradient points on the second straight line.

5. The wind farm layout optimization method based on the parallelogram rule according to claim 3 is characterized in that: The acquiring a plurality of second gradient points on both sides of the global center point coordinates on the first straight line, and acquiring a plurality of second parallel lines parallel to the second straight line based on the plurality of second gradient points comprises: Acquire a second distance between two points where the second straight line intersects the boundary of the wind farm to be optimized; Determining the maximum number of the second gradient points based on the second distance and the distance between any two wind turbines in the wind farm to be optimized; Determine the distance between the second gradient points and the coordinates of the second gradient points on the first straight line based on the maximum number of the second gradient points, the intra-row spacing gradient coefficient, and the length of the parallelogram column side; A plurality of second parallel lines parallel to the second straight line are generated based on the distances between the second gradient points and the coordinates of the second gradient points on the first straight line.

6. The wind farm layout optimization method based on the parallelogram rule according to claim 1 is characterized in that: The preset convergence condition is that the target value of the preset optimization target is maximum; The method further comprises: Optimizing based on the initial population to obtain the shape variables of the optimized parallelogram rule; Establishing an optimized population based on the shape variables of the optimized parallelogram rule, and obtaining an optimized arrangement scheme of the wind turbine generator sets; When the target value of the preset optimization target reaches the maximum, the optimization process is terminated to obtain the optimal shape variables of the parallelogram rule and the optimal arrangement scheme of the wind turbines in the wind farm to be optimized.

7. The wind farm layout optimization method based on the parallelogram rule according to claim 6 is characterized in that: The preset optimization target is the total output power of the wind farm to be optimized under the arrangement scheme of the wind turbines; The method for obtaining the total output power of the wind farm to be optimized comprises: Acquiring 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 ambient incoming wind speed and arrangement scheme of the wind farm to be optimized, the total output power of the wind farm to be optimized is obtained according to a preset wind turbine wake model.

8. The wind farm layout optimization method based on the parallelogram rule according to claim 7 is characterized in that: The preset wind turbine wake model includes a two-dimensional analytical model of the wind turbine wake and an additional turbulence intensity analytical model of the wind turbine wake; The step of obtaining the total output power of the wind farm to be optimized based on the wind speed and arrangement scheme of the wind farm to be optimized and according to a preset wake model comprises: Based on the analytical model of additional turbulence intensity of the wind turbine wake, the turbulence intensity of the wake of each wind turbine in the arrangement scheme is obtained; Based on the wake flow turbulence intensity of each wind turbine group, obtaining the additional flow turbulence intensity of the inflow at multiple points on the wind rotor of each wind turbine group; Obtaining the inflow velocity loss at multiple points on the wind rotor of each wind turbine based on the two-dimensional analytical model of the wind turbine wake and the inflow additional flow turbulence intensity at multiple points on the wind rotor of each wind turbine; Based on the inflow velocity loss at multiple points on the wind 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 set and a preset power curve of each wind turbine set, the output power of each wind turbine set is obtained; Based on the output power of each wind turbine generator set, the total output power of the wind farm to be optimized is obtained.

9. An electronic device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; Wherein, a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the wind farm layout optimization method based on the parallelogram rule described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the wind farm layout optimization method based on the parallelogram rule according to any one of claims 1 to 8.

Images