Wind farm machine arrangement optimization method and device based on row arrangement rule, and medium

Abstract

The present application relates to the technical field of wind farm micro-siting, and specifically provides a wind farm wind turbine arrangement optimization method, device and medium based on row arrangement rules, comprising: obtaining attribute information of a wind farm to be optimized; randomly generating shape variables of row arrangement rules based on the attribute information and establishing an initial population; obtaining an arrangement scheme of wind turbines based on global center point coordinates, in-row starting point proportions and parallel line rotation angles in the shape variables; optimizing the arrangement scheme based on the initial population and optimization objectives; and obtaining an optimal arrangement scheme when a preset convergence condition is reached; the present application uses global center point coordinates, in-row starting point proportions and parallel line rotation angles and other parameters of row arrangement rules to determine the arrangement scheme of wind turbines, has higher degrees of freedom, realizes a mathematical optimal solution of wind turbine point positions, significantly improves the power generation capacity of the wind farm, and does not need to perform traversal calculation, thereby improving the wind turbine arrangement efficiency and 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 wind farm machine arrangement optimization method based on row arrangement rules, a device and a medium. BACKGROUND

[0002] With the increasing demand for clean energy worldwide, wind power, as one of the important renewable energy sources, has attracted widespread attention in its development and utilization. The construction scale of wind farms is expanding, and the optimization demand for wind turbine arrangement is increasingly urgent; 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] The current layout of the wind farm is often based on the parallelogram rule to arrange the machine, and often uses the traversal calculation method, which requires a lot of time and computing resources, resulting in low efficiency and difficulty in meeting the needs of rapid response and real-time optimization; at the same time, the parallelogram arrangement lacks flexibility in layout, which may result in the wind energy resources in some areas not being fully utilized, and the optimal layout of the wind turbine point cannot be achieved, thereby resulting in low power generation.

[0004] Correspondingly, there is a need in the art for a new wind farm machine arrangement optimization scheme based on row arrangement rules 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 arrangement method obtained by traversal calculation is low in efficiency, it is difficult to obtain the real mathematical optimal solution of the wind turbine point, and the comprehensive benefit of the wind farm is poor.

[0006] In a first aspect, a wind farm machine arrangement optimization method based on row arrangement rules is provided, the method comprising:

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

[0008] randomly generating shape variables of row arrangement rules based on the attribute information;

[0009] establishing an initial population based on the shape variables of the row arrangement rules, wherein the initial population includes a plurality of individuals, each individual is a group of shape variables of row arrangement rules, and the shape variables of the row arrangement rules include global center point coordinates, in-row starting point proportions, and parallel line rotation angles;

[0010] obtaining an arrangement scheme of wind turbines in the wind farm to be optimized based on the global center point coordinates, the in-row starting point proportions, and the parallel line rotation angles;

[0011] Based on the initial population and the preset optimization objective, the arrangement scheme of wind turbine units in the wind farm to be optimized is optimized;

[0012] Once the preset optimization objective reaches the preset convergence condition, the optimal arrangement scheme of wind turbines in the wind farm to be optimized is obtained.

[0013] In one technical solution of the wind farm deployment optimization method based on row arrangement rules, the attribute information includes the area range of the wind farm to be optimized; the shape variables of the row arrangement rules also include minimum inter-row spacing, minimum intra-row spacing, row spacing gradient coefficient, and intra-row spacing gradient coefficient.

[0014] The shape variables for randomly generating row arrangement rules based on the aforementioned attribute information include:

[0015] Set 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 n times the diameter of the wind turbine, where n is a positive integer greater than 1;

[0016] Based on the area of ​​the wind farm to be optimized, the coordinates of the global center point are randomly selected.

[0017] Based on a uniform probability distribution and the distance between any two wind turbines in the wind farm to be optimized, the starting point ratio within a row is randomly selected within a preset ratio range, the parallel line rotation angle is randomly selected within a preset angle range, the minimum spacing between rows and the minimum spacing within a row are randomly selected within a preset spacing range, and the row spacing gradient coefficient and the row spacing gradient coefficient are randomly selected within a preset coefficient range.

[0018] The shape variables of the row arrangement rule are obtained based on the global center point coordinates, the ratio of the starting point in the row, the rotation angle of the parallel line, the minimum spacing between rows, the minimum spacing within a row, the gradient coefficient of the row spacing, and the gradient coefficient of the spacing within a row.

[0019] In one technical solution of the wind farm turbine deployment optimization method based on row arrangement rules, the attribute information also includes the number of wind turbine units in the wind farm to be optimized.

[0020] The method for obtaining the wind turbine layout scheme in the wind farm to be optimized includes:

[0021] Based on the global center point coordinates and the parallel line rotation angle, and taking the horizontal line of the area of ​​the wind farm to be optimized as a reference, the straight line intersecting 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 are obtained.

[0022] On both sides of the intersecting line segment, obtain multiple parallel line segments parallel to the intersecting line segment within the area of ​​the wind farm to be optimized, as well as the lengths of the multiple parallel line segments;

[0023] Starting from one end of all parallel line segments, based on the ratio of inline starting points and the length of all parallel line segments, multiple inline starting points are obtained on all parallel line segments; wherein, all parallel line segments include the intersecting line segments and multiple parallel line segments parallel to the intersecting line segments;

[0024] Multiple gradient points are obtained on both sides of the multiple starting points in the row, wherein the gradient points are the coordinate points of the wind turbines in the wind farm to be optimized;

[0025] The layout scheme of the wind turbines in the wind farm to be optimized is obtained based on the coordinate points of multiple wind turbines in the wind farm to be optimized.

[0026] In one technical solution of the wind farm deployment optimization method based on row arrangement rules, the step of obtaining multiple parallel line segments parallel to the intersecting line segment within the area of ​​the wind farm to be optimized on both sides of the intersecting line segment, and the lengths of the multiple parallel line segments, includes:

[0027] Obtain all straight lines passing through the coordinates of the global center point, obtain the length of the line segment between the two points where all the straight lines intersect the boundary of the wind farm to be optimized, and select the longest line segment;

[0028] Based on the longest line segment and the minimum inter-row spacing, the maximum number of parallel line segments within the area of ​​the wind farm to be optimized is obtained.

[0029] Based on the minimum inter-line spacing, the maximum number of parallel line segments, and the inter-line spacing gradient coefficient, the inter-line gradient interval between the parallel line segments is obtained;

[0030] Based on the intersecting line segments and the inter-row gradient interval, a plurality of parallel line segments parallel to the intersecting line segments are generated.

[0031] In one technical solution of the wind farm turbine deployment optimization method based on row arrangement rules, obtaining multiple transition points on both sides of the multiple starting points within the multiple rows includes:

[0032] Based on the lengths of all parallel line segments and the minimum spacing within the row, the maximum number of gradient points on each parallel line segment is obtained.

[0033] Based on the minimum inline spacing, the maximum number of gradient points on each parallel line segment, and the inline spacing gradient coefficient, the inline gradient interval of each parallel line segment is obtained.

[0034] Based on the inline 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 the multiple gradient points are obtained.

[0035] In one technical solution of the wind farm deployment optimization method based on row arrangement rules, the preset convergence condition is that the target value of the preset optimization objective is maximized;

[0036] The method further includes:

[0037] Based on the initial population, optimization is performed to obtain the shape variable of the optimized row arrangement rule;

[0038] An optimized population is established based on the shape variables of the optimized row arrangement rules, and an optimized wind turbine layout scheme is obtained.

[0039] The optimization process ends when the target value of the preset optimization objective reaches its maximum, thus obtaining the shape variable of the optimal row arrangement rule and the optimal layout scheme of the wind turbine units in the wind farm to be optimized.

[0040] In one technical solution of the wind farm layout optimization method based on the above row arrangement rule, the preset optimization target is the total output power of the wind farm to be optimized under the wind turbine layout scheme;

[0041] The method for obtaining the total output power of the wind farm to be optimized includes:

[0042] 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;

[0043] Based on the incoming wind speed and layout scheme of 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.

[0044] In one technical solution of the wind farm layout optimization method based on row arrangement rules, 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.

[0045] The process of obtaining the total output power of the wind farm to be optimized based on the incoming wind speed and layout scheme of the wind farm to be optimized, according to a preset wake model, includes:

[0046] 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.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] Based on the output power of each wind turbine, the total output power of the wind farm to be optimized is obtained.

[0052] 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 wind farm layout optimization method based on row arrangement rules.

[0053] In a third aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, 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 wind farm deployment optimization method based on row arrangement rules.

[0054] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects:

[0055] In implementing the wind farm turbine layout optimization method based on row arrangement rules provided by this invention, the following steps are taken: 1) Obtain the attribute information of the wind farm to be optimized; 2) Randomly generate shape variables for row arrangement rules based on the attribute information and establish an initial population based on the shape variables; 3) Obtain the layout scheme of wind turbines in the wind farm to be optimized based on the global center point coordinates, the proportion of starting points within rows, and the rotation angle of parallel lines in the shape variables; 4) Optimize the layout scheme based on the initial population and a preset optimization objective; 5) Obtain the optimal layout scheme of wind turbines in the wind farm to be optimized after the optimization objective reaches a preset convergence condition. This invention utilizes parameters such as the global center point coordinates, the proportion of starting points within rows, and the rotation angle of parallel lines in the row arrangement rules to determine the layout scheme of wind turbines, resulting in higher degrees of freedom and achieving the mathematically optimal solution for wind turbine locations, thus significantly increasing the power generation of the wind farm; 6) No traversal calculations are required, improving turbine layout efficiency and thereby enhancing the comprehensive benefits of the wind farm throughout its entire life cycle. Attached Figure Description

[0056] 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:

[0057] Figure 1 This is a schematic flowchart of the main steps of a wind farm turbine deployment optimization method based on row arrangement rules according to an embodiment of the present invention;

[0058] Figure 2 This is a flowchart illustrating the main steps of generating a shape variable with a row arrangement rule based on attribute information according to an embodiment of the present invention.

[0059] Figure 3 This is a schematic diagram of the main steps of the wind turbine layout scheme in a wind farm to be optimized according to an embodiment of the present invention.

[0060] Figure 4 This is a schematic flowchart of the main steps of a method for obtaining multiple parallel line segments according to an embodiment of the present invention;

[0061] Figure 5 This is a schematic flowchart of the main steps of a method for obtaining multiple gradient points according to an embodiment of the present invention;

[0062] Figure 6 This is a wind rose diagram according to an embodiment of the present invention;

[0063] Figure 7 These are the unit power curve and thrust coefficient curve according to an embodiment of the present invention;

[0064] 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;

[0065] Figure 9 This is a schematic diagram of the wind turbine locations in a wind farm to be optimized under the optimal layout scheme based on row arrangement rules according to an embodiment of the present invention.

[0066] Figure 10 This is a schematic diagram of the main structure of an electronic device according to an embodiment of the present invention.

[0067] Figure label:

[0068] 101: Memory; 102: Processor. Detailed Implementation

[0069] 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.

[0070] 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.

[0071] See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a wind farm turbine deployment optimization method based on row arrangement rules according to an embodiment of the present invention. Figure 1 As shown, the wind farm layout optimization based on row arrangement rules in this embodiment of the invention mainly includes the following steps S101 to S103.

[0072] Step S101: Obtain the attribute information of the wind farm to be optimized.

[0073] In this embodiment, the attribute information includes the area of ​​the wind farm to be optimized and the number of wind turbines. ;

[0074] 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.

[0075] Step S102: Randomly generate shape variables based on the row arrangement rules according to the attribute information; establish an initial population based on the shape variables based on the row arrangement rules.

[0076] In this embodiment, pre-set constraints on the wind turbine coordinates 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. Larger than the diameter of the wind turbine D of n times, , nIt is a positive integer greater than 1;

[0077] 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.

[0078] 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, shape variables of row arrangement rules are randomly generated to establish the initial population of the genetic algorithm. The initial population includes multiple individuals, each of which is a set of shape variables of row arrangement rules. Based on a specific point selection procedure, the shape variables of row arrangement rules can generate a unique arrangement scheme of wind turbines in the wind farm to be optimized.

[0079] In one implementation, real-number encoding is used to randomly generate shape variables with a row arrangement rule to establish an initial population. The initial population contains multiple individuals, each of which is a row vector containing 10 variables. Each set of row arrangement rules corresponds to a wind farm turbine layout scheme; real number encoding refers to representing each gene value of each individual using floating-point numbers within a certain range.

[0080] In this embodiment, the shape variable of the row arrangement rule includes the coordinates of the global center point. 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 .

[0081] In this embodiment, refer to the appendix. Figure 2 , Figure 2 This is a schematic diagram illustrating the main steps of generating a shape variable with random row arrangement rules based on attribute information according to an embodiment of the present invention. Figure 2 As shown, the shape variables for randomly generating row arrangement rules based on attribute information include:

[0082] Step S201: Based on the area of ​​the wind farm to be optimized, randomly select the coordinates of the global center point;

[0083] Within the closed polygonal boundary of the area of ​​the wind farm to be optimized, a point coordinate is randomly selected as the global center point coordinate of the row-arranged wind turbine layout. .

[0084] 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 starting point ratio within the row within a preset ratio range, randomly select the parallel line rotation angle within a preset angle range, randomly select the minimum spacing between rows and the minimum spacing within rows within a preset spacing range, and randomly select the row spacing gradient coefficient and the row spacing gradient coefficient within a preset coefficient range.

[0085] Specifically, the proportion of the starting point within 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;

[0086] Step S203: Obtain the shape variables of the row arrangement rules based on the global center point coordinates, the ratio of the starting point in the row, the rotation angle of the parallel line, the minimum spacing between rows, the minimum spacing in the row, the gradient coefficient of the row spacing, and the gradient coefficient of the spacing in the row.

[0087] Specifically, based on the coordinates of the global center point 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 Obtain the shape variable of the row arrangement rule .

[0088] Step S103: Obtain the layout scheme of wind turbines in the wind farm to be optimized based on the global center point coordinates, the ratio of the starting point in the row, and the rotation angle of the parallel line.

[0089] In this embodiment, refer to the appendix. Figure 3 , Figure 3 This is a schematic flowchart illustrating the main steps of an optimized wind turbine layout scheme in a wind farm according to an embodiment of the present invention. Figure 3As shown, the methods for obtaining the wind turbine layout scheme in the wind farm to be optimized include:

[0090] Step S301: Based on the global center point coordinates and the parallel line rotation angle, using the horizontal line of the area of ​​the wind farm to be optimized as the reference, obtain the straight line that intersects with 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 with the area of ​​the wind farm to be optimized.

[0091] Specifically, using the coordinates of the global center point Centered on the horizontal line of the area of ​​the wind farm to be optimized, draw a line with an angle parallel to the horizontal line. θ The straight line intersects the closed polygon boundary of the area to be optimized, at two points respectively. A 1 , B 1 , forming intersecting line segments And determine the intersecting line segments. length .

[0092] Step S302: Obtain multiple parallel line segments parallel to the intersecting line segment and their lengths within the area of ​​the wind farm to be optimized on both sides of the intersecting line segment;

[0093] Specifically, based on intersecting line segments By taking multiple parallel lines to both sides, we obtain parallel line segments within the closed polygon of the area of ​​the wind farm to be optimized, and determine the lengths of the multiple parallel line segments. Create a set of parallel line segments with a gradient. ,in, To optimize the total number of parallel line segments within the wind farm, each parallel line segment... For a row .

[0094] See appendix Figure 4 , Figure 4 This is a schematic flowchart illustrating the main steps of a method for obtaining multiple parallel line segments according to an embodiment of the present invention. Figure 4 As shown, within the area of ​​the wind farm to be optimized, parallel line segments parallel to the intersecting line segment are obtained on both sides of the intersecting line segment, and the lengths of the parallel line segments include:

[0095] Step S401: Obtain all straight lines passing through the coordinates of the global center point, obtain the length of the line segment between the two points where all straight lines intersect the boundary of the wind farm to be optimized, and select the longest line segment;

[0096] Specifically, based on the coordinates of the global center point Get all lines passing through the coordinates of the global center point. At this point, all straight lines intersect the boundary of the wind farm to be optimized; obtain the length of the line segment between the two points where each line intersects the boundary of the wind farm to be optimized, select the longest line segment, and determine the length of the longest line segment as... .

[0097] Step S402: 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;

[0098] Specifically, based on the length of the longest line segment and minimum line spacing The maximum number of parallel line segments within the area of ​​the wind farm to be optimized is determined to be [number missing]. ,in It is the largest integer not exceeding z.

[0099] Step S403: Based on the minimum inter-line spacing, the maximum number of parallel line segments, and the line spacing gradient coefficient, obtain the inter-line gradient interval between parallel line segments; specifically, consider a Gaussian distribution function with a mean of 0. Take out uniformly within the range of [-1,1] Number Then, it can be obtained from the Gaussian distribution function. Not less than Gradient interval set ,in and This is the line spacing gradient coefficient. This represents the maximum number of parallel line segments within the area of ​​the wind farm to be optimized.

[0100] Step S404: Based on the intersecting line segments and the inter-row gradient interval, generate multiple parallel line segments that are parallel to the intersecting line segments.

[0101] Specifically, within the area of ​​the wind farm to be optimized, a straight line is drawn... Centered on a set of gradually varying intervals based on a Gaussian distribution, points are taken to both sides, i.e., respectively at... Remove from both sides A few points with interlacing lines;

[0102] judge

[0103] If each transition point is within the wind farm area, remove points outside the area and retain the set of all parallel line segments passing through the transition points. .

[0104] Step S303: Starting from one end of all parallel line segments, based on the ratio of the inline starting point and the length of all parallel line segments, obtain multiple inline starting points on all parallel line segments; wherein, all parallel line segments include intersecting line segments and multiple parallel line segments parallel to the intersecting line segments;

[0105] Specifically, from parallel line segments starting point A i Departure, based on the proportion of the starting point within the row. r At a distance from the starting point A i for Take a point at the location This serves as the starting point within the line; similarly, this process is repeated on other lines to obtain the starting point within all lines.

[0106] Step S304: Obtain multiple gradient points on both sides of multiple inline starting points, where the gradient points are the coordinate points of the wind turbines in the wind farm to be optimized;

[0107] Specifically, from the line R i Inline start point Starting from the beginning of the row, using the gradual point selection method... Take out rows from both sides R i The set of all gradient points ,in, For action The total number of gradient points on the row; similarly, repeat this process on other rows to obtain the gradient points of all rows. The gradient points are the coordinate points of the wind turbines in the wind farm to be optimized.

[0108] See appendix Figure 5 , Figure 5 This is a schematic flowchart illustrating the main steps of a method for obtaining multiple gradient points according to an embodiment of the present invention. Figure 5 As shown, obtaining multiple gradient points on both sides of multiple inline starting points includes:

[0109] Step S501: Based on the length of all parallel line segments and the minimum spacing within the row, obtain the maximum number of gradient points on each parallel line segment;

[0110] Specifically, based on the current row (segment) ) length Minimum spacing within a line Determine the current row (line segment) The maximum number of gradient points is ,in It is the largest integer not exceeding z.

[0111] Step S502: Based on the minimum inline spacing, the maximum number of gradient points on each parallel line segment, and the inline spacing gradient coefficient, obtain the inline gradient interval for each parallel line segment.

[0112] Specifically, consider the Gaussian distribution function with a mean of 0. Take out uniformly within the range of [-1,1] Number Then, based on the Gaussian distribution function, in the current row (line segment) )get Not less than Gradient interval set ,in and This is the inline spacing gradient coefficient.

[0113] Step S503: Based on the inline gradient interval of each parallel line segment, obtain multiple gradient points on both sides of the starting point of each parallel line segment, and obtain the coordinates of the multiple gradient points.

[0114] Specifically, in the current row (segment) On, with Centered on the line segment, and based on the gradually varying interval set of the Gaussian distribution for each line segment, points are taken to both sides, i.e., at points... Remove from both sides One point;

[0115] judge Are the gradient points located in the current row (line segment)? Within the specified range, remove segments that extend beyond the current row (line segment). For points within a certain range, retain the set of coordinates of multiple gradient points, consisting of all gradient points. .

[0116] Step S305: Obtain the layout scheme of wind turbines in the wind farm to be optimized based on the coordinate points of the wind turbines in multiple wind farms to be optimized.

[0117] Specifically, the coordinates of multiple transition points in all rows are merged into a set of coordinate points. As the shape variable of the current row layout rule The corresponding unique and definite wind farm turbine layout scheme.

[0118] Step S104: Based on the initial population and the preset optimization objective, optimize the layout scheme of wind turbine units in the wind farm to be optimized; when the preset optimization objective reaches the preset convergence condition, obtain the optimal layout scheme of wind turbine units in the wind farm to be optimized.

[0119] In this embodiment, the preset convergence condition is that the target value of the preset optimization objective is maximized;

[0120] Methods for optimizing the layout of wind turbines in a wind farm include:

[0121] The shape variable of the optimized row arrangement rule is obtained by optimizing the initial population.

[0122] An optimized population is established based on the shape variables of the optimized row arrangement rules, and the optimized wind turbine layout scheme is obtained.

[0123] The optimization process ends when the target value of the preset optimization objective reaches its maximum, thus obtaining the shape variable of the optimal row arrangement rule and the optimal layout scheme of the wind turbine units in the wind farm to be optimized.

[0124] 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.

[0125] In one implementation, the shape variable of the row arrangement rule can be obtained by cross-mutation based on the constraints of the wind turbine coordinates to obtain a new shape variable of the row arrangement rule.

[0126] 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 preset 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 better or optimal optimization target values. The specific optimization process for the initial population is as follows:

[0127] (1) Population initialization. Randomly generate optimization variables (including shape variables of the row arrangement rules) to form an initial population containing N individuals. Each individual is a definite arrangement scheme containing N unit coordinates. The optimization variables are encoded with real numbers, and the unit coordinates are randomly generated within the optimization constraints. If the available points of the generated row arrangement rules do not fully satisfy the optimization constraints, or the number of points is less than the required number of units, the individual is regenerated until the constraints are satisfied.

[0128] (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 row arrangement rule 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 to the variables, with the Gaussian standard deviation of the large-scale mutation set to... The Gaussian standard deviation of small-scale variation is set as And set the mutation probability respectively. and .

[0129] (3) Merge parent and offspring. Merge the parent population with the offspring population generated by crossover variation to form a population of 2N individuals.

[0130] (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. .

[0131] (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.

[0132] (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.

[0133] In this embodiment, the preset optimization target is the total output power of the wind farm to be optimized under the wind turbine layout scheme;

[0134] Methods for obtaining the total output power of the wind farm to be optimized include:

[0135] Obtain wind resource information for the wind farm to be optimized, including the ambient incoming wind speed of the wind farm to be optimized;

[0136] 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.

[0137] 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.

[0138] 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:

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] Based on the output power of each wind turbine, the total output power of the wind farm to be optimized is obtained.

[0145] In one implementation, the method for obtaining the total output power of the wind farm to be optimized includes:

[0146] 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):

[0147] (1)

[0148] 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 of the Gaussian curve is the same as that of the speed loss model; z is the vertical height.

[0149] Flow direction function The maximum additional turbulence intensity of the wake cross section at each flow direction:

[0150] (2)

[0151] in, ; ; Correction values ​​are taken into account for the near-wake region.

[0152] Formula (1) expansion function for:

[0153] (3)

[0154] in, and The possible values ​​are:

[0155] (4)

[0156] (5)

[0157] For vertical correction functions:

[0158] (6)

[0159] 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:

[0160] (7)

[0161] 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.

[0162] 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:

[0163] (8)

[0164] 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.

[0165] 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:

[0166] (9)

[0167] 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.

[0168] 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:

[0169] (10)

[0170] in, For the current number i Wind speed in front of the turbine hub of the typhoon generator; For the incoming airflow velocity;

[0171] At a wind speed of 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.

[0172] 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:

[0173] (11)

[0174] 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.

[0175] 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 are arranged in a row-based pattern. It should be noted that the area range of the wind farm to be optimized, the coordinates of the area's 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.

[0176] The basic parameters of the wind farm to be optimized are shown in Table 1.

[0177] Table 1 Wind Farm Parameters

[0178]

[0179] 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 diameter of the wind turbine. D This application scenario uses flat terrain and does not consider the impact of complex terrain. It should be noted that the distance between any two wind turbines... It must be greater than 4 times the diameter of the wind turbine. D The selection of flat terrain is an illustrative example of this application scenario, and can be selected as needed in practice.

[0180] Figure 8The original wind turbine locations of the wind farm to be optimized are, according to an embodiment of the present invention. Figure 9 This is a schematic diagram of the wind turbine locations in a wind farm to be optimized under an optimal layout scheme based on row arrangement rules, according to an embodiment of the present invention. (The diagram can be viewed from...) Figure 9 As can be seen, the optimal locations of wind turbines in the wind farm exhibit a clear row-arrangement pattern. Under this optimal arrangement, the annual power generation corresponding to the wind turbine locations in the wind farm to be optimized is 269331.59 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 arrangement based on row arrangement rules has an annual power generation increase of approximately 2.949%. It can significantly improve the power generation of the wind farm throughout its entire life cycle while ensuring that the wind turbine locations in the wind farm to be optimized are arranged in a row arrangement rule.

[0181] 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.

[0182] 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.

[0183] Another aspect of the present invention provides a computer-readable storage medium.

[0184] 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 wind farm turbine deployment optimization method based on row arrangement rules described in the above-described method embodiments. This program may be loaded and run by a processor to implement the wind farm turbine deployment optimization method based on row arrangement rules. 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.

[0185] Another aspect of the present invention provides an electronic device.

[0186] 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 10 , Figure 10 The example shows a memory 101 and a processor 102 connected via a bus communication connection.

[0187] 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.

[0188] 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 wind farm turbine deployment optimization method based on row arrangement rules, characterized in that, include: Obtain the attribute information of the wind farm to be optimized; Based on the attribute information, a shape variable for randomly generating row arrangement rules is generated; An initial population is established based on the shape variables of the row arrangement rules, wherein the initial population includes multiple individuals, each individual being a set of shape variables of the row arrangement rules, the shape variables of the row arrangement rules including global center point coordinates, the proportion of the starting point in the row, and the rotation angle of the parallel line; Based on the global center point coordinates, the ratio of the starting point in the row, and the rotation angle of the parallel line, the arrangement scheme of the wind turbines in the wind farm to be optimized is obtained. Based on the initial population and the preset optimization objective, the arrangement scheme of wind turbine units in the wind farm to be optimized is optimized; Once the preset 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 area of ​​the wind farm to be optimized and the number of wind turbines in the wind farm to be optimized; The method for obtaining the wind turbine layout scheme in the wind farm to be optimized includes: Based on the global center point coordinates and the parallel line rotation angle, and taking the horizontal line of the area of ​​the wind farm to be optimized as a reference, the straight line intersecting 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 are obtained. On both sides of the intersecting line segment, obtain multiple parallel line segments parallel to the intersecting line segment within the area of ​​the wind farm to be optimized, as well as the lengths of the multiple parallel line segments; Starting from one end of all parallel line segments, based on the ratio of the inline starting points and the length of all parallel line segments, multiple inline starting points are obtained on all parallel line segments; wherein, all parallel line segments include the intersecting line segments and multiple parallel line segments parallel to the intersecting line segments; Multiple gradient points are obtained on both sides of the multiple starting points in the row, wherein the gradient points are the coordinate points of the wind turbines in the wind farm to be optimized; The layout scheme of the wind turbines in the wind farm to be optimized is obtained based on the coordinate points of multiple wind turbines in the wind farm to be optimized.

2. The wind farm deployment optimization method based on row arrangement rules according to claim 1, characterized in that, The shape variables of the row arrangement rules also include the minimum spacing between rows, the minimum spacing within rows, the row spacing gradient coefficient, and the within-row spacing gradient coefficient; The shape variables for randomly generating row arrangement rules based on the aforementioned attribute information include: Set 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 n times the diameter of the wind turbine, and m is a positive integer greater than 1; 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 and the distance between any two wind turbines in the wind farm to be optimized, the starting point ratio within a row is randomly selected within a preset ratio range, the parallel line rotation angle is randomly selected within a preset angle range, the minimum spacing between rows and the minimum spacing within a row are randomly selected within a preset spacing range, and the row spacing gradient coefficient and the row spacing gradient coefficient are randomly selected within a preset coefficient range. The shape variables of the row arrangement rule are obtained based on the global center point coordinates, the ratio of the starting point in the row, the rotation angle of the parallel line, the minimum spacing between rows, the minimum spacing within a row, the gradient coefficient of the row spacing, and the gradient coefficient of the spacing within a row.

3. The wind farm turbine deployment optimization method based on row arrangement rules according to claim 2, characterized in that, The method of obtaining multiple parallel line segments parallel to the intersecting line segment within the area of ​​the wind farm to be optimized on both sides of the intersecting line segment, and the lengths of the multiple parallel line segments, includes: Obtain all straight lines passing through the coordinates of the global center point, obtain the length of the line segment between the two points where all the straight lines intersect the boundary of the wind farm to be optimized, and select the longest line segment; Based on the longest line segment and the minimum inter-row spacing, the maximum number of parallel line segments within the area of ​​the wind farm to be optimized is obtained. Based on the minimum inter-line spacing, the maximum number of parallel line segments, and the inter-line spacing gradient coefficient, the inter-line gradient interval between the parallel line segments is obtained; Based on the intersecting line segments and the inter-row gradient interval, a plurality of parallel line segments parallel to the intersecting line segments are generated.

4. The wind farm deployment optimization method based on row arrangement rules according to claim 2, characterized in that, The step of obtaining multiple gradient points on both sides of the multiple inline starting points includes: Based on the lengths of all parallel line segments and the minimum spacing within the row, the maximum number of gradient points on each parallel line segment is obtained. Based on the minimum inline spacing, the maximum number of gradient points on each parallel line segment, and the inline spacing gradient coefficient, the inline gradient interval of each parallel line segment is obtained. Based on the inline 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 the multiple gradient points are obtained.

5. The wind farm turbine deployment optimization method based on row arrangement rules according to claim 1, characterized in that, The preset convergence condition is that the target value of the preset optimization objective is maximized; The method further includes: Based on the initial population, optimization is performed to obtain the shape variable of the optimized row arrangement rule; An optimized population is established based on the shape variables of the optimized row arrangement rules, and an optimized wind turbine layout scheme is obtained. The optimization process ends when the target value of the preset optimization objective reaches its maximum, thus obtaining the shape variable of the optimal row arrangement rule and the optimal layout scheme of the wind turbine units in the wind farm to be optimized.

6. The wind farm deployment optimization method based on row arrangement rules according to claim 5, characterized in that, The preset optimization target 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 and layout scheme of 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.

7. The wind farm deployment optimization method based on row arrangement rules according to claim 6, 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 incoming wind speed and layout scheme of the wind farm to be optimized, 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.

8. 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 wind farm layout optimization method based on row arrangement rules as described in any one of claims 1 to 7.

9. 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 wind farm layout optimization method based on row arrangement rules as described in any one of claims 1 to 7.

Images