A method and system for joint optimization of wind farm parallelogram-shaped cable layout

Abstract

This invention discloses a method and system for joint optimization of wind farm parallelogram-shaped wind turbine and cable layout. The method includes: obtaining the area and number of wind turbines in the wind farm; randomly generating shape variables for a parallelogram-shaped layout; establishing an initial population of shape variables using a genetic algorithm to generate a wind farm turbine layout scheme; establishing an initial population of booster station locations using a genetic algorithm based on the wind farm turbine layout scheme; using maximizing output power and minimizing cable cost as optimization objectives, generating new shape variables for a parallelogram-shaped layout and booster station coordinates to form an optimization population; performing multi-objective optimization on the wind farm turbine layout scheme and booster station location scheme based on the genetic algorithm to obtain the Pareto front of the multi-objective optimization; and finally selecting the optimal wind farm layout scheme according to requirements. This invention reduces wind farm cable costs while ensuring the total output power of the wind farm, thereby improving the overall benefits of the wind farm throughout its entire life cycle.

Description

Technical Field

[0001] This invention mainly relates to the field of wind power technology, specifically to a method and system for optimizing the joint layout of wind turbines and cables in a parallelogram-shaped pattern in wind farms. Background Technology

[0002] In the design and operation of wind farms, the arrangement of wind turbines has a significant impact on power generation efficiency. Traditional wind farm designs often employ regular geometric arrangements, such as grid-like or linear layouts, with turbine placement done manually. While this approach is easy to plan, it has revealed several shortcomings in practical applications. First, it fails to fully consider the directionality and distribution characteristics of wind resources, leading to low operating efficiency for some turbines. Second, it fails to adequately account for the power output reduction effect of wake effects between turbines, which is particularly pronounced under specific wind direction conditions.

[0003] Existing technologies either rely on simple, regular geometric shapes and employ traversal methods to find optimal wind turbine placement, which, while improving placement, is inefficient and fails to achieve full optimization, making it difficult to balance dynamic adjustments and cost control under complex wind farm conditions. Other approaches attempt to improve placement effectiveness and efficiency through optimization methods, but these typically involve random, irregular turbine locations, lacking aesthetic appeal and hindering construction, operation, and maintenance planning. These limitations provide a clear direction and technical requirements for further optimization of wind farm placement methods.

[0004] In wind farm planning, the micro-site selection of turbine locations and cable layout are typically considered independent, sequential planning steps. First, the turbine locations and substations are planned according to the parallelogram rule, followed by the design of the cable layout. However, due to the competition between turbine power generation and cable costs within a wind farm, traditional step-by-step sequential design may lead to suboptimal solutions. In such cases, a comprehensive joint planning method is needed to find a balance between turbine locations and cable layout, which is of great significance for the research and practical application of wind farm planning.

[0005] In summary, relying on experience-based site selection in the current wind farm design process makes it difficult to achieve optimal power generation. Completely random layouts lack aesthetic appeal and are detrimental to operation and maintenance path design. Simply pursuing higher power generation without fully considering the impact of wind farm cable costs fails to achieve optimal returns on investment throughout the entire lifecycle of offshore wind farms. Summary of the Invention

[0006] To address the technical problems existing in the prior art, this invention provides a method and system for optimizing the parallelogram-shaped wind farm layout and cable arrangement, while ensuring the total output power of the wind farm, reducing the cost of wind farm cables, and improving the overall benefits of the wind farm throughout its entire life cycle.

[0007] To solve the above-mentioned technical problems, the technical solution proposed by this invention is as follows:

[0008] A method for joint optimization of wind farm parallelogram-shaped wind turbine and cable layout, comprising the following steps:

[0009] Obtain the area range, turbine model and quantity, wind resource conditions, and values ​​of various parameters required for cable layout design of the wind farm to be optimized;

[0010] Based on the area of ​​the wind farm and the number of wind turbines, shape variables with parallelogram rules are randomly generated, and an initial population of shape variables with genetic algorithm is established. The initial population of coordinates contains multiple individuals, each of which is a set of shape variables with parallelogram rules. Based on the point selection program, a unique parallelogram rule wind farm turbine layout scheme can be generated.

[0011] Based on the generated wind farm turbine layout scheme, within the range that meets the optimization constraints, booster stations are randomly generated within the farm to establish an initial population of booster stations using a genetic algorithm; wherein, the initial population of booster stations contains multiple individuals, each of which represents a wind farm booster station location scheme;

[0012] Using the maximization of the first optimization objective and the minimization of the second optimization objective as optimization objectives, starting from the initial population of shape variables and the initial population of booster stations, new parallelogram-shaped shape variables and booster station coordinates are generated to form an optimization population. Based on a genetic algorithm, multi-objective optimization is performed on the wind farm turbine layout scheme and the booster station location scheme. The first optimization objective is the total output power of the wind farm under the layout scheme corresponding to each individual; the second objective is the cable cost of the wind farm under the layout scheme corresponding to each individual.

[0013] Once both the first and second optimization objectives converge, the optimization process ends, yielding the Pareto front for multi-objective optimization. Each individual on the Pareto front represents a specific wind farm turbine layout and substation location scheme, including the coordinates of each turbine and substation.

[0014] At the Pareto frontier, the optimal wind farm layout is selected based on demand.

[0015] Preferably, the specific steps for randomly generating the shape variable of a parallelogram based on the area of ​​the wind farm and the number of wind turbines are as follows:

[0016] First, set constraints on the wind turbine coordinates; these constraints include a preset wind farm area and a distance greater than [specified value] between any two wind turbines within the wind farm. That is, the diameter of the wind turbine rotor. of times, of which It is a positive integer greater than 1;

[0017] Secondly, within the closed polygonal area of ​​the wind farm region, a point coordinate is randomly selected as the global center point coordinate for the parallelogram-shaped wind turbine deployment. ;

[0018] Secondly, according to a uniform probability distribution, in Randomly select the included angle of two sides of a parallelogram within the range and the overall rotation angle of the parallelogram Based on unit spacing limitations A certain multiple range Randomly select the side length of the parallelogram and ,exist Randomly select the inter-row gradient coefficient within the range and Two parameters, in Randomly select the inline gradient coefficients within the range and Two parameters;

[0019] Finally, based on the determined number of wind turbine units, the shape variable of the generated parallelogram rule is used; according to the point selection procedure, a unique wind farm turbine unit layout scheme is generated within the wind farm area, and this process is repeated until the total number of units in the unit layout scheme meets the required number of units.

[0020] Preferably, the specific steps for generating a unique and definite wind farm turbine layout scheme within the wind farm area according to the point selection procedure are as follows:

[0021] Shape variables based on parallelogram rules And the global center point coordinates are extracted from the closed polygon area of ​​the wind farm region. ;by With the vertex as the top and the horizontal line as one edge, rotate counterclockwise. Draw a straight line that intersects the entire polygon; this line is denoted as the straight line. , and then As the vertex, with Rotate counterclockwise along one edge. Angle, then draw a straight line intersecting the entire polygon, denoted as line . ;

[0022] Using line l as a reference, from the coordinates of the global center point Starting from point m, using the gradual point selection method, select points to both sides, and then draw several parallel lines to line l through these points, intersecting the closed region. Next, using line m as the reference, again using the gradual point selection method, select points to both sides, and draw several parallel lines to line m through these points, intersecting the closed region. Record the intersection of these two sets of parallel lines as... Let ... =a , =b The union of all intersection points As the shape variable of the current parallelogram rule The corresponding unique and definite wind farm turbine layout scheme.

[0023] Preferably, using line l as a reference, the coordinates of the global center point are... Starting from this point, according to the gradual point selection method, points are selected to both sides, and then several parallel lines are drawn through these points to form line l. The specific steps are as follows:

[0024] Let the longest hypotenuse distance of the wind farm boundary be... Then it is necessary to pass through the global center point. The maximum number of intervals between the transition points along the perpendicular direction of line l, which is also the number of lines, is [number]. ,in Not exceeding The largest integer;

[0025] Consider a Gaussian distribution function with a mean of 0. ,exist Take out evenly within the range Number of - Then, it can be obtained from the Gaussian distribution function. Not less than A collection of gradient distances:

[0026] ;

[0027] in and The set represents the parallelogram row spacing gradient coefficient, and all gradient points form a set. ;

[0028] Draw a line parallel to line l through the chosen point of gradual change.

[0029] Preferably, taking line m as the reference, and similarly using the gradual point selection method, taking points to both sides, and drawing several lines parallel to line m through these points, the specific process is as follows:

[0030] Let the longest hypotenuse distance of the wind farm boundary be... Then it is necessary to pass through the global center point. Along the perpendicular direction of line m, the number of intervals between the transition points, which is also the number of lines, can be at most 100. ,in Not exceeding The largest integer;

[0031] Consider a Gaussian distribution function with a mean of 0. ,exist Take out evenly within the range Number of - Then, based on the Gaussian distribution function, we get Not less than A collection of gradient distances:

[0032] ;

[0033] in and The set represents the parallelogram row spacing gradient coefficient, and all gradient points form a set. ;

[0034] Draw a line parallel to line m through the chosen point of gradual change.

[0035] Preferably, the steps of randomly generating booster stations within the wind farm based on the generated wind farm turbine layout scheme and within the scope of optimization constraints, and establishing the initial population of booster stations using a genetic algorithm, specifically include:

[0036] First, set the location constraints for the booster station; the constraints include a preset wind farm area range and a distance greater than [value missing] from the booster station relative to any wind turbine in the wind farm. That is, n times the diameter of the wind turbine rotor, where n is a positive integer greater than 1;

[0037] Randomly select points within the wind farm area to generate the coordinate location vector of the booster station. Repeat this process to satisfy the point selection constraints of the booster station.

[0038] Preferably, the steps to terminate the optimization process and obtain the Pareto front for multi-objective optimization after both the first and second optimization objectives have converged specifically include:

[0039] According to the genetic algorithm, the location coordinates of wind turbines and substations are encoded with real numbers, and two ranges of unit coordinate mutation processes and probabilities are set respectively: the large-scale mutation process randomly selects new coordinates within 2 / 3 times the wind turbine diameter of the original coordinates, and the small-scale mutation process randomly selects new coordinates within 1 / 6 times the wind turbine diameter of the original coordinates.

[0040] At the start of the optimization, both large-scale and small-scale unit position coordinate mutation processes are used simultaneously. After the first and second optimization objectives converge for the first time, the probability of large-scale mutation is set to 0, and only the small-scale unit position coordinate mutation process is used until the first and second optimization objectives converge for the second time, at which point the optimization process ends and the Pareto front of the multi-objective optimization is obtained.

[0041] Preferably, based on the average incoming wind speed and turbulence intensity of the wind farm, and considering the wake effect, the wake model is used to calculate the output power and directional turbulence intensity of each wind turbine in the wind farm, thereby obtaining the total output power of the wind farm.

[0042] Preferably, the specific steps for obtaining the total output power of the wind farm are as follows:

[0043] For each wind turbine in the wind farm, the inflow velocity loss at multiple points on the rotor of the current wind turbine is obtained according to formula (1) based on the velocity loss of the upstream wind turbine at multiple points on the rotor of the current wind turbine:

[0044] (1)

[0045] in, The current wind turbine rotor point of the i-th unit The inflow rate at the location is at a loss; For the j-th unit, point on the rotor of the i-th unit Average speed loss at the location; is a binary variable; N is the number of wind turbines in the wind farm;

[0046] For each wind turbine in the wind farm, the inflow additional turbulence intensity at multiple points on the rotor of the current wind turbine is obtained according to formula (2) based on the additional turbulence intensity at multiple points on the rotor of the current wind turbine at multiple points on the upstream wind turbine:

[0047] (2)

[0048] in, The additional turbulence intensity in the flow direction at point (x,y,z) on the rotor of the i-th unit; The additional directional turbulence intensity of the j-th unit at the point (x,y,z) on the rotor of the i-th unit; It is a binary variable; The number of wind turbines in the wind farm;

[0049] Based on the inflow velocity deficit at multiple points on the wind turbine rotor, the average value is taken, and the wind speed in front of the wind turbine hub under the preset wind conditions is obtained according to formula (3):

[0050] (3)

[0051] in, The wind speed in front of the hub of the i-th wind turbine is currently being measured. For the incoming airflow velocity;

[0052] At wind speed The wind direction angle is Under certain wind conditions, the wind speed in front of the hub and the power curve of the wind turbine are obtained, and the output power of the wind turbine under these wind conditions is obtained; where 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.

[0053] Based on the output power corresponding to this wind condition, and according to formula (4), the total output power of the wind farm under the current wind farm layout scheme is obtained:

[0054] (4)

[0055] in, This represents the total output power of the wind farm under the current wind farm layout scheme. The wind speed is The wind direction is Wind conditions; For unit i in wind conditions Output power at the following levels; For wind conditions Frequency of occurrence; Number of wind directions; N represents the number of wind speed ranges taken under a single wind direction; N is the number of units.

[0056] Preferably, the specific steps for calculating the cable cost of the wind farm under the corresponding layout scheme for each individual include:

[0057] Based on the location of the wind farm's booster station and the coastline, the closest coastal point to the booster station is determined and used as the feeder cable node.

[0058] Based on the turbine and substation locations under the wind farm layout scheme, as well as the information on various types of cables within the farm, and coupling the feeder cable node and feeder cable model information, a total cable cost model for the wind farm is established, and the total cable cost of the wind farm is obtained by solving the problem.

[0059] (5)

[0060] in, This is the unit price of the cable. Representative point and The Euclidean distance between them It is a given safety factor.

[0061] The present invention also discloses a computer program product, comprising a computer program that, when executed by a processor, performs the steps of the method described above.

[0062] The present invention further discloses a computer-readable storage medium having a computer program stored thereon, the computer program executing the steps of the method described above when run by a processor.

[0063] The present invention also discloses a wind farm parallelogram regular layout wind turbine-cable joint optimization system, including a memory and a processor connected to each other. The memory stores a computer program, which executes the steps of the method described above when run by the processor.

[0064] Compared with the prior art, the advantages of the present invention are as follows:

[0065] This invention presents a parallelogram-shaped wind turbine and cable joint optimization method to address the shortcomings of existing wind farm turbine location design methods. These methods rely on experience to achieve mathematical optimization of turbine locations, while completely random layouts lack aesthetic appeal and hinder maintenance path design. Furthermore, they prioritize higher power generation without adequately considering cable costs. To address these issues, this invention employs a genetic algorithm to optimize the turbine layout scheme across multiple objectives: maximizing the first objective and minimizing the second. It utilizes two scales of turbine coordinate mutation processes and probabilities, employing a two-stage mutation probability setting scheme to ensure rapid and sufficient convergence of the optimization objectives. Finally, the optimized wind farm layout is determined based on the obtained Pareto front solution for the multi-objective optimization, according to actual needs. This method comprehensively considers both total wind farm output power and cable costs, reducing cable costs while maintaining total wind farm output power, thus improving the overall lifecycle benefits of the wind farm. Attached Figure Description

[0066] Figure 1 The flowchart below shows the optimization method of the present invention in an embodiment.

[0067] Figure 2 This is a schematic diagram illustrating the calculation of the wind farm feedout point in this invention.

[0068] Figure 3The following are schematic diagrams of the wind farm wind measurement tower rose diagram and the turbine power thrust system curve in this invention: (a) is the wind farm wind measurement tower rose diagram; (b) is the turbine power thrust system curve.

[0069] Figure 4 This is a diagram showing the original wind farm unit locations, the original booster station, and the connection of the collection lines in this invention.

[0070] Figure 5 This is an evolution curve of wind farm output power during the optimization process of this invention.

[0071] Figure 6 This is a structural diagram showing the optimized unit locations, substation locations, and cable route layout of the present invention. Detailed Implementation

[0072] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0073] like Figure 1 As shown in the figure, the wind farm parallelogram regular layout wind turbine-cable joint optimization method provided by the embodiment of the present invention includes the following steps:

[0074] Obtain the area range, turbine model and quantity, wind resource conditions, and values ​​of various parameters required for cable layout design of the wind farm to be optimized;

[0075] Based on the preset wind farm area and the determined number of wind turbine units, shape variables with parallelogram rules are randomly generated to establish an initial population of shape variables for a genetic algorithm. The initial population of coordinates contains multiple individuals, each of which is a set of shape variables with parallelogram rules. Based on a specific point selection procedure, a unique and determined wind farm turbine layout scheme with parallelogram rules can be generated. During the iteration process, the turbine location coordinates generated in each generation are random, but they can still meet the requirements of regular turbine layout.

[0076] Based on the wind farm turbine layout scheme generated above, within the range that meets the optimization constraints, booster stations are randomly generated within the farm to establish an initial population of booster stations using a genetic algorithm; wherein, the initial population of booster stations contains multiple individuals, each of which represents a wind farm booster station location scheme;

[0077] Using the maximization of the first optimization objective and the minimization of the second optimization objective as optimization objectives, starting from the initial population of shape variables and the initial population of booster stations, new parallelogram-shaped shape variables and booster station coordinates are generated to form an optimization population. Based on a genetic algorithm, multi-objective optimization is performed on the wind farm turbine layout scheme and booster station location scheme. While ensuring that the power generation remains unchanged, the cable cost can be significantly reduced. The first optimization objective is the total output power of the wind farm under the layout scheme corresponding to each individual; the second optimization objective is the cable cost of the wind farm under the layout scheme corresponding to each individual.

[0078] Once both the first and second optimization objectives converge, the optimization process ends, yielding the Pareto front for multi-objective optimization. Each individual on the Pareto front represents a specific wind farm turbine layout and substation location scheme, including the coordinates of each turbine and substation.

[0079] At the Pareto frontier, the optimal wind farm layout is selected based on demand.

[0080] The parallelogram-shaped wind farm layout and cable joint optimization method of the present invention reduces the investment cost of wind farm cables, closely approximates the theoretically optimal completely random unit layout, and takes into account the influence of the on-site substation, collector lines and wind farm feeder main cables. While increasing the power generation of the wind farm, it reduces the investment cost of wind farm cables, enhances the economics of the wind farm throughout its entire life cycle, and enables the wind farm to perform better.

[0081] In one specific embodiment, the step of randomly generating a parallelogram-shaped shape variable based on a preset wind farm area and a determined number of wind turbines specifically includes:

[0082] The shape variables based on the parallelogram rule specifically include... The parameters are: global center point coordinates. The included angle of a parallelogram Overall rotation angle 1. Parallelogram row side length a; 2. Parallelogram column side length b; 3. Row gradient coefficient and inline gradient coefficient ;

[0083] First, set constraints on the wind turbine coordinates; these constraints include a preset wind farm area and a distance greater than [specified value] between any two wind turbines within the wind farm. That is, the diameter of the wind turbine rotor. times, of which It is a positive integer greater than 1;

[0084] Secondly, within the closed polygonal area of ​​the wind farm region, a point coordinate is randomly selected as the global center point coordinate for the parallelogram-shaped wind turbine deployment. ;

[0085] Secondly, according to a uniform probability distribution, in Randomly select the included angle of two sides of a parallelogram within the range and the overall rotation angle of the parallelogram Based on unit spacing limitations A certain multiple range Randomly select the side length of the parallelogram and ,exist Randomly select the inter-row gradient coefficient within the range and Two parameters, in Randomly select the inline gradient coefficients within the range and Two parameters;

[0086] Finally, based on the determined number of wind turbine units, the shape variable of the generated parallelogram rule is used. According to the point selection procedure, a unique wind farm unit layout scheme is generated within the wind farm area. This process is repeated until the total number of units in the unit layout scheme meets the required number of units.

[0087] Specifically, following the point-taking procedure, a unique wind farm turbine layout scheme is generated based on the shape variable of the parallelogram rule, including:

[0088] Shape variables based on parallelogram rules And the global center point coordinates are extracted from the closed polygon area of ​​the wind farm region. .by With the vertex as the top and the horizontal line as one edge, rotate counterclockwise. Draw a straight line that intersects the entire polygon; this line is denoted as the straight line. , and then As the vertex, with Rotate counterclockwise along one edge. Angle, then draw a straight line intersecting the entire polygon, denoted as line . .

[0089] Using line l as a reference, from the coordinates of the global center point Starting from point m, using the gradual point selection method, take points to both sides, and then draw several parallel lines to line l through these points, intersecting the closed region. Next, using line m as the reference, again using the gradual point selection method, take points to both sides, and draw several parallel lines to line m through these points, intersecting the closed region. Record the intersection of these two sets of parallel lines as... Let ... =a , =b The union of all intersection points. As the shape variable of the current parallelogram rule The corresponding unique and definite wind farm turbine layout scheme.

[0090] Specifically, taking line l as the reference, from the coordinates of the global center point... Starting from this point, according to the gradual point selection method, the steps of selecting points to both sides and then drawing several parallel lines to line l through these points specifically include:

[0091] Let the longest hypotenuse distance of the wind farm boundary be... Then it is necessary to pass through the global center point. The maximum number of intervals between the transition points along the perpendicular direction of line l, which is also the number of lines, is [number]. ,in Not exceeding The largest integer;

[0092] Consider a Gaussian distribution function with a mean of 0. ,exist Take out evenly within the range Number of - Then, it can be obtained from the Gaussian distribution function. Not less than Gradual distance collection ,in and The set represents the parallelogram row spacing gradient coefficient, and all gradient points form a set. ;

[0093] Draw a line parallel to line l through the chosen point of gradual change.

[0094] Specifically, taking line m as the reference, and following the same gradual point selection method, taking points to both sides, and drawing several parallel lines through these points, the steps include:

[0095] Let the longest hypotenuse distance of the wind farm boundary be... Then it is necessary to pass through the global center point. Along the perpendicular direction of line m, the number of intervals between the transition points, which is also the number of lines, can be at most 100. ,in Not exceeding The largest integer;

[0096] Consider a Gaussian distribution function with a mean of 0. ,exist Take out evenly within the range Number of - Then, it can be obtained from the Gaussian distribution function. Not less than Gradual distance collection ,in and The set represents the parallelogram row spacing gradient coefficient, and all gradient points form a set. ;

[0097] Draw a line parallel to line m through the chosen point of gradual change.

[0098] In one specific embodiment, based on the wind farm turbine layout scheme generated above, the steps of randomly generating booster stations within the farm within the scope of optimization constraints and establishing the initial population of booster stations using a genetic algorithm specifically include:

[0099] First, set the location constraints for the booster station; the constraints include a preset wind farm area range and a distance greater than [value missing] from the booster station relative to any wind turbine in the wind farm. That is, n times the diameter of the wind turbine rotor, where n is a positive integer greater than 1;

[0100] Within the wind farm area, randomly selected points are used to generate the coordinate location vector of the booster station. Repeat this process to satisfy the point selection constraints of the booster station.

[0101] In one specific embodiment, the steps to terminate the optimization process and obtain the Pareto front for multi-objective optimization after both the first and second optimization objectives have converged specifically include:

[0102] According to the genetic algorithm, the location coordinates of wind turbines and substations are encoded with real numbers, and two ranges of unit coordinate mutation processes and probabilities are set respectively: the large-scale mutation process randomly selects new coordinates within 2 / 3 times the wind turbine diameter of the original coordinates, and the small-scale mutation process randomly selects new coordinates within 1 / 6 times the wind turbine diameter of the original coordinates.

[0103] During the optimization process, a two-stage mutation probability setting scheme is adopted, which enables the population to have both global and local search capabilities in the early stage of optimization, and only retain a certain local search capability in the later stage of optimization. That is, at the beginning of optimization, both large-scale and small-scale unit position coordinate mutation processes are used simultaneously. When the first optimization objective and the second optimization objective have both converged for the first time, the large-scale mutation probability is set to 0, and only the small-scale unit position coordinate mutation process is used until the first optimization objective and the second optimization objective have both converged for the second time, at which point the optimization process ends and the Pareto front of the multi-objective optimization is obtained.

[0104] In one specific embodiment, calculating the total output power of the wind farm under the layout scheme corresponding to each individual wind turbine includes: based on the average incoming wind speed and turbulence intensity of the wind farm, considering the wake effect, using a wake model to calculate the output power and directional turbulence intensity of each wind turbine in the wind farm, and obtaining the total output power of the wind farm. The specific steps are as follows:

[0105] For each wind turbine in a wind farm, based on the velocity loss at multiple points on the rotor of the current wind turbine from the upstream wind turbine, the inflow velocity loss at multiple points on the rotor of the current wind turbine is obtained using the following formula:

[0106] (1)

[0107] in, The current wind turbine rotor point of the i-th unit The inflow rate at the location is at a loss; For the j-th unit, point on the rotor of the i-th unit Average speed loss at the location; It is a binary variable, which is defined if and only if the current i-th unit is downstream of the j-th unit. =1, in other cases =0; N is the number of wind turbines in the wind farm;

[0108] For each wind turbine in a wind farm, based on the additional directional turbulence intensity at multiple points on the rotor of the current wind turbine from the upstream wind turbine, and according to the method described in the following formula, the inflow additional directional turbulence intensity at multiple points on the rotor of the current wind turbine is obtained:

[0109] (2)

[0110] in, The additional turbulence intensity in the flow direction at point (x,y,z) on the rotor of the i-th unit; The additional directional turbulence intensity of the j-th unit at the point (x,y,z) on the rotor of the i-th unit; It is a binary variable, which is defined if and only if the current i-th unit is downstream of the j-th unit. =1, in other cases ; The number of wind turbines in the wind farm;

[0111] Based on the inflow velocity deficit at multiple points on the wind turbine rotor, the average value is taken, and the wind speed in front of the wind turbine hub under preset wind conditions is obtained according to the method described below:

[0112] (3)

[0113] in, The wind speed in front of the hub of the i-th wind turbine is currently being measured. For the incoming airflow velocity;

[0114] At a wind speed of The wind direction angle is Under certain wind conditions, the wind speed in front of the hub and the power curve of the wind turbine are obtained, and the output power of the wind turbine under these wind conditions is obtained; where 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.

[0115] Based on the output power under this wind condition, and according to the method described in the following formula, obtain the total output power of the wind farm under the current wind farm layout scheme:

[0116] (4)

[0117] in, This represents the total output power of the wind farm under the current wind farm layout scheme. The wind speed is The wind direction is Wind conditions; For unit i in wind conditions Output power at the following levels; For wind conditions Frequency of occurrence; Number of wind directions; N represents the number of wind speed ranges taken under a single wind direction; N is the number of units.

[0118] In one specific embodiment, the total cost of the wind farm collector line, considering the total feeder cable under the layout scheme corresponding to each individual, is calculated, specifically including:

[0119] Based on the location of the wind farm's booster station and the coastline, the closest coastal point to the booster station is determined and used as the feeder cable node.

[0120] Based on the turbine and substation locations under the wind farm layout scheme, as well as the information on various types of cables within the farm, and coupling the feeder cable node and feeder cable model information, a total cable cost model for the wind farm is established, and the total cable cost of the wind farm is obtained by solving the problem.

[0121] (5)

[0122] in, This is the unit price of the cable. Representative point and The Euclidean distance between them It is a given safety factor.

[0123] Specifically, based on the turbine locations and substation locations under the wind farm layout scheme, as well as the information on various types of cables within the farm, and coupling the feeder cable node and feeder cable model information, the steps to establish a total cable cost model for the wind farm and solve for the total cable cost of the wind farm include:

[0124] binary variable The definition is as follows, where Indicates cable type:

[0125] (6)

[0126] Despite Several types of cables are available, but each cable selection is mutually exclusive. Only one type of cable can be used for laying on the same route. The constraints are as follows:

[0127] (7)

[0128] The formula for calculating cable cost is as follows:

[0129] (8)

[0130] in, This is the unit price of the cable. Representative point and The Euclidean distance between them It is a given safety factor.

[0131] To meet the design requirements of the collection system for radial wind farms, the cable routing should satisfy the following constraints:

[0132] (9)

[0133] (10)

[0134] (11)

[0135] (12)

[0136] (13)

[0137] (14)

[0138] (15)

[0139] (16)

[0140] (17)

[0141] (18)

[0142] (19)

[0143] Formula (9) ensures that each node has only one cable for energy output. Formula (10) ensures that at least one cable is connected to the booster station. Formula (11) prevents the same cable segment from being connected end-to-end to the same node. Formula (12) ensures that there is no energy output after the feeder point. Formula (13) ensures that there is a route from the booster station to the feeder point. Formula (14) ensures that there is no route from the generator unit to the feeder point. Formula (15) ensures that cable type 4 is used from the booster station to the feeder point. Formula (16) prevents energy loops between any two nodes. Formula (17) avoids any two cable segments crossing and stores crossed cable pairs. Formula (18) represents the power balance of each node, where is a continuous non-negative variable. Formula (19) ensures that the power flow on each cable is less than the cable capacity.

[0144] The above cable mathematical model can be solved using the mixed integer linear programming method (MILP) to obtain the total cable cost and cable layout under the wind farm unit layout and substation location scheme.

[0145] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0146] like Figure 1 As shown, the wind farm parallelogram regular layout and cable joint optimization method in this embodiment of the invention mainly includes the following steps (1)-(6):

[0147] (1) Obtain the area range, turbine model and quantity, wind resources, and values ​​of various parameters required for cable layout design of the wind farm to be optimized.

[0148] In one implementation, a suitable wind turbine model can be selected based on the scope of the wind farm to be constructed and the required installed capacity.

[0149] For example, the regional vertex of a wind farm can be... , , as well as The coordinate unit is meters (m), the unit model is Vestas-V80, and the number of units is... Wind rose diagrams and unit power and thrust coefficient curves are as follows: Figure 3 As shown, the original turbine locations of the wind farm are as follows: Figure 4 As shown. Within the wind farm, the unit prices of various types of cables are as follows: , , , Where t1-t3 are the cables within the site, and t4 is the main feeder cable. The current carrying capacity (maximum number of units that can be connected) of each type of cable is as follows: , , , .

[0150] (2) Based on the preset wind farm area and the determined number of wind turbine units, randomly generate parallelogram regular shape variables and establish the initial population of shape variables of the genetic algorithm; wherein, the initial population of coordinates contains multiple individuals, each of which is a set of parallelogram regular shape variables, and can generate a unique parallelogram regular wind farm turbine unit layout scheme based on a specific point selection program.

[0151] In one implementation, real-number encoding is used to randomly generate parallelogram-like shape variables to establish an initial population. The initial population contains multiple individuals, each of which is a row vector containing 10 variables (i.e., ...). Each of these corresponds to a wind farm turbine layout scheme. Real number encoding refers to representing each gene value of an individual using a floating-point number within a certain range.

[0152] The shape variables of this parallelogram regularity specifically include... The parameters are: global center point coordinates. The included angle of a parallelogram Overall rotation angle Parallelogram side length Parallelogram column side length Inline gradient coefficient and inline gradient coefficient .

[0153] The initial generation method is as follows: First, the coordinate constraints of the wind turbine units are set to be a closed polygon enclosed by the vertices of the wind farm area, and the distance between any two wind turbine units is greater than... That is, four times the diameter of the wind turbine rotor; secondly, within the closed polygonal area of ​​the wind farm region, a point coordinate is randomly selected as the global center point coordinate for the regular wind turbine deployment. Finally, according to a uniform probability distribution, in Randomly select the included angle of two sides of a parallelogram within the range and the overall rotation angle of the parallelogram Based on unit spacing limitations A certain multiple range Randomly select the side length of the parallelogram and ,exist Randomly select the inter-row gradient coefficient within the range and Two parameters, in Randomly select the inline gradient coefficients within the range and Two parameters.

[0154] (3) Based on the wind farm unit layout scheme generated above, random substations are generated within the range that meet the optimization constraints, and an initial population of substations for the genetic algorithm is established; wherein, the initial population of substations contains multiple individuals, each of which is a wind farm substation location scheme.

[0155] In one implementation, real number encoding is used, taking into account the constraints of wind farm range and wind turbine spacing, to generate completely random coordinates of the in-farm booster station.

[0156] (4) Taking the target value of maximizing the first optimization objective and minimizing the target value of the second optimization objective as optimization objectives, starting from the initial population of shape variables and the initial population of booster stations, new parallelogram regular shape variables and booster station coordinates are generated to form an optimization population. Based on the genetic algorithm, the multi-objective optimization of the wind farm unit layout and booster station location scheme is carried out.

[0157] In this embodiment, the optimization objective can be the total output power of the wind farm under the layout scheme corresponding to each individual and the total cost of the collection line considering the feeder cable.

[0158] In one implementation, the genetic algorithm can be the NSGA-II algorithm.

[0159] In one implementation, the shape variables of the parallelogram rule, the underlying random coordinates, and the coordinates of the booster station in the field can be obtained by cross-mutation based on the optimization constraints in step (2).

[0160] (5) When the first and second optimization objectives converge, the optimization process ends and the Pareto front of the multi-objective optimization is obtained. Each individual on the Pareto front is a specific wind farm unit layout and substation location scheme, including the coordinates of each unit and the substation.

[0161] (6) On the Pareto front, the optimal wind farm layout can be selected according to the needs.

[0162] In this embodiment, the specific layout scheme of the wind farm can be determined by a specific point-sampling procedure based on the shape variable of the parallelogram rule with the optimal optimization objective value. Furthermore, based on the location of the booster station within the wind farm corresponding to the shape variable of the optimal parallelogram rule (each with the same index within the population), and the information of various types of cables, a total cable cost model for the wind farm is established to calculate the optimal cable layout of the wind farm.

[0163] Based on the above steps (1)-(6), this invention can apply a genetic algorithm to the initial population established based on optimization constraints, using the goal of maximizing the target value of the first optimization objective and minimizing the target value of the second optimization objective as optimization objectives. Simultaneously, it performs multi-objective optimization on the parallelogram-shaped variable population and the substation population within the field. It also uses two scales of unit coordinate mutation processes and probabilities, and through a "two-stage" mutation probability setting scheme, ensures that the optimization objective value can converge quickly and sufficiently. Finally, based on the obtained multi-objective optimization Pareto front solution, it can determine the wind farm layout and cable path optimization scheme according to actual needs. Through the above method, this invention comprehensively considers the total output power of the wind farm and the total cable cost including the feeder cable. While ensuring the randomness of the wind farm unit locations, it satisfies the regular characteristics of the unit locations, thereby reducing the total cable cost of the wind farm while ensuring the total output power of the wind farm, and improving the comprehensive benefits of the wind farm throughout its entire life cycle.

[0164] In one specific embodiment, in step (4), based on the average incoming wind speed and turbulence intensity of the wind farm, and considering the wake effect, the wake model is used to calculate the output power and directional turbulence intensity of each wind turbine in the wind farm, thereby obtaining the total output power of the wind farm. The steps specifically include:

[0165] (4.1) For each wind turbine in the wind farm, based on the velocity loss of the upstream wind turbine at multiple points on the rotor of the current wind turbine, and according to the method described in the following formula, obtain the inflow velocity loss at multiple points on the rotor of the current wind turbine:

[0166] (20)

[0167] in, The inflow velocity deficit is at point (x,y,z) on the rotor of the i-th unit. The average speed loss of the j-th unit at the point (x,y,z) on the rotor of the i-th unit; It is a binary variable, which is defined if and only if the current i-th unit is downstream of the j-th unit. In other cases =0; N is the number of wind turbines in the wind farm.

[0168] In this embodiment, the average speed loss of the wind turbine can be obtained from the two-dimensional analytical model of the wind turbine wake in the following formula (21):

[0169] (twenty one)

[0170] in, This is the thrust coefficient; R is the actual expansion rate of the wake boundary; R is the rotor radius; r is the radial distance between a point (x,y,z) on the rotor surface and the rotor center.

[0171] (4.2) For each wind turbine in the wind farm, based on the additional turbulent intensity in the upstream wind turbine at multiple points on the rotor of the current wind turbine, and according to the method described in the following formula, obtain the inflow additional turbulent intensity in the inflow direction at multiple points on the rotor of the current wind turbine:

[0172] (twenty two)

[0173] in, The additional turbulence intensity in the flow direction at point (x,y,z) on the rotor of the i-th unit; The additional directional turbulence intensity of the j-th unit at the point (x,y,z) on the rotor of the i-th unit; It is a binary variable, which is defined if and only if the current i-th unit is downstream of the j-th unit. =1, in other cases ; This represents the number of wind turbines in the wind farm.

[0174] In this embodiment, 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 (23)-(27):

[0175] (twenty three)

[0176] in, The standard deviation of the Gaussian curve is the same as that of the speed loss model; z is the vertical height.

[0177] Flow direction function The maximum additional turbulence intensity of the wake cross section at each flow direction:

[0178] (twenty four)

[0179] in, Correction values ​​are taken into account for the near-wake region.

[0180] Formula (25) expansion function for:

[0181] (25)

[0182] in, and The value can be:

[0183] (26)

[0184] (27)

[0185] For vertical correction functions:

[0186] (28)

[0187] (4.3) Based on the inflow velocity deficit at multiple points on the wind turbine rotor, take the average value and obtain the wind speed in front of the wind turbine hub under the preset wind conditions according to the method described in the following formula:

[0188] (29)

[0189] in, The wind speed in front of the hub of the i-th wind turbine is currently being measured. For the incoming airflow velocity;

[0190] At wind speed The wind direction angle is Under certain wind conditions, the wind speed in front of the hub and the power curve of the wind turbine are obtained, and the output power of the wind turbine under these wind conditions is obtained. The power curve of the wind turbine includes the correspondence between the wind speed in front of the hub and the output power of the wind turbine.

[0191] Based on the output power under this wind condition, and according to the method described in the following formula, obtain the total output power of the wind farm under the current wind farm layout scheme:

[0192] (30)

[0193] in, This represents the total output power of the wind farm under the current wind farm layout scheme. The wind speed is The wind direction is Wind conditions; For unit i in wind conditions Output power at the following levels; For wind conditions Frequency of occurrence; Number of wind directions; N represents the number of wind speed ranges taken under a single wind direction; N is the number of units.

[0194] In one specific embodiment, step (4), determining the optimal total power generation and total cable cost for the wind farm layout corresponding to the optimized individual, specifically includes:

[0195] At the vertex of the wind farm area boundary is , , as well as Within a polygonal area (coordinates in meters), 40 Vestas-V80 wind turbines will be installed. The original turbine locations for the wind farm are as follows: Figure 4 As shown in Table 1, the basic parameters of the wind farm are shown in Table 1, and the power and thrust curves of the wind turbine generators are shown in Table 2. Figure 3 As shown in (b), the evolution curve of the optimization process is as follows: Figure 5 As shown.

[0196] Table 1 Wind Farm Parameters

[0197]

[0198] Select wind conditions with multiple wind directions and speeds; refer to the probability values ​​for each wind direction and speed. Figure 2 . Figure 2 This is a wind rose diagram according to one embodiment of the present invention. Figure 2 The central angle of the polar coordinate histogram represents the wind direction angle, and the height of the histogram represents the wind frequency. The optimization constraints are that the wind farm area and the safe distance between any two wind turbines must be greater than four times the rotor diameter. In this example, flat terrain is selected, and the influence of complex terrain is not considered. The joint optimization of wind farm turbine deployment and cable paths is performed using steps (1) to (6) in the aforementioned method embodiment, as follows: Figure 5 The figure shows the maximum output power of each wind farm layout scheme within the population during each iteration of the optimization process. It can be seen that the optimization population eventually converges. Therefore... Figure 6 The embodiment of the present invention shows an optimal turbine location on the Pareto front of a wind farm. Figure 4 This refers to the original turbine locations of a wind farm according to an embodiment of the present invention. Figure 6It can be seen that the optimal locations of wind farm units exhibit a clear parallelogram-like regular arrangement. The annual power generation corresponding to this optimal unit location is significantly higher than... Figure 4 The optimized parallelogram-shaped arrangement with gaps increases the annual power generation of the wind farm by approximately 3.695% compared to the original turbine locations. Simultaneously, considering the total cable cost of the feeder cable, it is reduced by approximately 6.172% compared to the original cable layout. Therefore, this invention can significantly improve the power generation of the wind farm throughout its entire lifecycle and reduce the total cable cost considering the feeder cable while ensuring a parallelogram-shaped arrangement of the turbine locations.

[0199] This invention presents a parallelogram-shaped wind turbine and cable joint optimization method to address the shortcomings of existing wind farm turbine location design methods. These methods rely on experience to achieve mathematical optimization of turbine locations, while completely random layouts lack aesthetic appeal and hinder maintenance path design. Furthermore, they prioritize higher power generation without adequately considering cable costs. To address these issues, this invention employs a genetic algorithm to optimize the turbine layout scheme across multiple objectives: maximizing the first objective and minimizing the second. It utilizes two scales of turbine coordinate mutation processes and probabilities, employing a two-stage mutation probability setting scheme to ensure rapid and sufficient convergence of the optimization objectives. Finally, the optimized wind farm layout is determined based on the obtained Pareto front solution for the multi-objective optimization, according to actual needs. This method comprehensively considers both total wind farm output power and cable costs, reducing cable costs while maintaining total wind farm output power, thus improving the overall lifecycle benefits of the wind farm.

[0200] Glossary

[0201] Wind farm micro-site selection: The planning and design process within the wind farm planning area, including the location of wind turbine units and the layout of power collection lines;

[0202] Pareto front: A set of solutions obtained through multi-objective optimization that can dominate all solutions outside the Pareto front, but do not dominate each other;

[0203] Speed ​​loss: The attenuation of the wind speed behind the wind turbine rotor relative to the free flow at infinity in front of the rotor;

[0204] Additional directional turbulence intensity: The increase in directional turbulence intensity behind the wind turbine rotor relative to the ambient turbulence intensity at infinity in front of the rotor;

[0205] Real number encoding: All elements in the variable are real numbers; WT: Wind turbine generator set; OSS: Offshore substation; MILP: Mixed integer linear programming method; NSGA-II: Non-dominated sorting genetic algorithm with elitist strategy; CIC: Cable installation cost.

[0206] This invention also discloses a computer program product, comprising a computer program that, when run by a processor, performs the steps of the method described above. This invention further discloses a computer-readable storage medium storing a computer program that, when run by a processor, performs the steps of the method described above. This invention also discloses a wind farm parallelogram-shaped cable deployment optimization system, comprising an interconnected memory and a processor, wherein the memory stores a computer program that, when run by a processor, performs the steps of the method described above. The products, media, and systems of this invention, corresponding to the methods described above, also possess the advantages described above.

[0207] The present invention can implement all or part of the processes in the methods of the above embodiments, or it can be implemented by hardware related to computer program instructions. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above method embodiments. 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 includes: any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. The memory is used to store computer programs and / or modules. The processor implements various functions by running or executing the computer programs and / or modules stored in the memory, and by calling data stored in the memory. The memory may include high-speed random access memory, as well as non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart media cards (SMC), secure digital (SD) cards, flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0208] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should be considered within the scope of protection of the present invention.

Claims

1. A joint optimization method for wind farm parallelogram-shaped regular wind turbine and cable layout, characterized in that, Including the following steps: Obtain the area range, turbine model and quantity, wind resource conditions, and values ​​of various parameters required for cable layout design of the wind farm to be optimized; Based on the area of ​​the wind farm and the number of wind turbines, shape variables with parallelogram rules are randomly generated, and an initial population of shape variables with genetic algorithm is established. The initial population of coordinates contains multiple individuals, each of which is a set of shape variables with parallelogram rules. Based on the point selection program, a unique parallelogram rule wind farm turbine layout scheme can be generated. Based on the generated wind farm turbine layout scheme, within the range that meets the optimization constraints, booster stations are randomly generated within the farm to establish an initial population of booster stations using a genetic algorithm; wherein, the initial population of booster stations contains multiple individuals, each of which represents a wind farm booster station location scheme; Using the maximization of the first optimization objective and the minimization of the second optimization objective as optimization objectives, starting from the initial population of shape variables and the initial population of booster stations, new parallelogram-shaped shape variables and booster station coordinates are generated to form an optimization population. Based on a genetic algorithm, multi-objective optimization is performed on the wind farm turbine layout scheme and the booster station location scheme. The first optimization objective is the total output power of the wind farm under the layout scheme corresponding to each individual; the second objective is the cable cost of the wind farm under the layout scheme corresponding to each individual. Once both the first and second optimization objectives converge, the optimization process ends, yielding the Pareto front for multi-objective optimization. Each individual on the Pareto front represents a specific wind farm turbine layout and substation location scheme, including the coordinates of each turbine and substation. At the Pareto frontier, the optimal wind farm layout is selected based on demand.

2. The wind farm parallelogram-shaped regular wind turbine and cable joint optimization method according to claim 1, characterized in that, The specific steps for randomly generating a parallelogram-shaped shape variable based on the geographical area and number of wind turbines in the wind farm are as follows: First, set constraints on the wind turbine coordinates; these constraints include a preset wind farm area and a distance greater than [specified value] between any two wind turbines within the wind farm. That is, the diameter of the wind turbine rotor. of times, of which It is a positive integer greater than 1; Secondly, within the closed polygonal area of ​​the wind farm region, a point coordinate is randomly selected as the global center point coordinate for the parallelogram-shaped wind turbine deployment. ; Secondly, according to a uniform probability distribution, in Randomly select the included angle of two sides of a parallelogram within the range and the overall rotation angle of the parallelogram Based on unit spacing limitations A certain multiple range Randomly select the side length of the parallelogram and ,exist Randomly select the inter-row gradient coefficient within the range and Two parameters, in Randomly select the inline gradient coefficients within the range and Two parameters; Finally, based on the determined number of wind turbine units, the shape variable of the generated parallelogram rule is used; according to the point selection procedure, a unique wind farm turbine unit layout scheme is generated within the wind farm area, and this process is repeated until the total number of units in the unit layout scheme meets the required number of units.

3. The wind farm parallelogram-shaped regular wind turbine and cable joint optimization method according to claim 2, characterized in that, The specific steps for generating a unique wind farm turbine layout scheme within the wind farm area according to the point selection procedure are as follows: Shape variables based on parallelogram rules And the global center point coordinates are extracted from the closed polygon area of ​​the wind farm region. ;by With the vertex as the top and the horizontal line as one edge, rotate counterclockwise. Draw a straight line that intersects the entire polygon, and denote it as line 1#. Then... Using line 1# as the vertex, rotate counterclockwise. Find the angle, then draw a straight line that intersects the entire polygon, denoted as line m#; Using line 1# as the reference, from the global center point coordinates Starting from point m, take points to both sides using the gradual point selection method, and then draw several parallel lines to line 1# through the points, intersecting the closed area; then, using line m# as the reference, take points to both sides using the same gradual point selection method, and draw several parallel lines to line m# through the points, intersecting the closed area. Let the intersection of these two sets of parallel lines be denoted as . Let ... =asinθ, =bsinθ; the union of all intersection points As the shape variable of the current parallelogram rule The corresponding unique and definite wind farm turbine layout scheme.

4. The wind farm parallelogram-shaped regular wind turbine and cable joint optimization method according to claim 3, characterized in that, Using line 1# as the reference, from the global center point coordinates Starting from this point, according to the gradual point selection method, points are selected to both sides, and then several parallel lines are drawn through these points to form line #1. The specific steps are as follows: Let the longest hypotenuse distance of the wind farm boundary be... Then it is necessary to pass through the global center point. Along the perpendicular direction of line 1#, draw the intervals between the transition points, which is the number of lines. The maximum number of intervals is [number missing]. ,in Not exceeding The largest integer; Consider a Gaussian distribution function with a mean of 0. ,exist Take out evenly within the range Number of - Then, it can be obtained from the Gaussian distribution function. Not less than A collection of gradient distances: ； in and The set represents the parallelogram row spacing gradient coefficient, and all gradient points form a set. ; Draw a line parallel to line l# through the chosen point of gradual change.

5. The wind farm parallelogram-shaped regular wind turbine and cable joint optimization method according to claim 3, characterized in that, Using line m# as a reference, and following the same gradual point selection method, points are selected to both sides, and the specific process of drawing several parallel lines to line m# through these points is as follows: Let the longest hypotenuse distance of the wind farm boundary be... Then it is necessary to pass through the global center point. Along the perpendicular direction of line m#, the number of intervals between the transition points, which is also the number of lines, can be at most 100. ,in Not exceeding The largest integer; Consider a Gaussian distribution function with a mean of 0. ,exist Take out evenly within the range Number of - Then, based on the Gaussian distribution function, we get Not less than A collection of gradient distances: ； in and The set represents the parallelogram row spacing gradient coefficient, and all gradient points form a set. ; Draw a line parallel to line m# through the chosen point of gradual change.

6. The wind farm parallelogram-shaped regular wind turbine and cable joint optimization method according to any one of claims 1-5, characterized in that, Based on the generated wind farm turbine layout scheme, within the scope of optimization constraints, random generation of booster stations within the farm, and the steps to establish the initial population of booster stations using a genetic algorithm specifically include: First, set the location constraints for the booster station; the constraints include a preset wind farm area range and a distance greater than [value missing] from the booster station relative to any wind turbine in the wind farm. That is, n times the diameter of the wind turbine rotor, where n is a positive integer greater than 1; Randomly select points within the wind farm area to generate the coordinate location vector of the booster station. Repeat this process to satisfy the point selection constraints of the booster station.

7. The wind farm parallelogram-shaped regular wind turbine and cable joint optimization method according to any one of claims 1-5, characterized in that, Once both the first and second optimization objectives have converged, the optimization process ends, and the specific steps to obtain the Pareto front for multi-objective optimization include: According to the genetic algorithm, the location coordinates of wind turbines and substations are encoded with real numbers, and two ranges of unit coordinate mutation processes and probabilities are set respectively: the large-scale mutation process randomly selects new coordinates within 2 / 3 times the wind turbine diameter of the original coordinates, and the small-scale mutation process randomly selects new coordinates within 1 / 6 times the wind turbine diameter of the original coordinates. At the start of the optimization, both large-scale and small-scale unit position coordinate mutation processes are used simultaneously. After the first and second optimization objectives converge for the first time, the probability of large-scale mutation is set to 0, and only the small-scale unit position coordinate mutation process is used until the first and second optimization objectives converge for the second time, at which point the optimization process ends and the Pareto front of the multi-objective optimization is obtained.

8. The wind farm parallelogram-shaped regular wind turbine and cable joint optimization method according to any one of claims 1-5, characterized in that, Based on the average incoming wind speed and turbulence intensity of the wind farm, and considering the wake effect, the wake model is used to calculate the output power and directional turbulence intensity of each wind turbine in the wind farm, and the total output power of the wind farm is obtained.

9. The wind farm parallelogram-shaped regular wind turbine and cable joint optimization method according to claim 8, characterized in that, The specific steps to obtain the total output power of a wind farm are as follows: For each wind turbine in the wind farm, the inflow velocity loss at multiple points on the rotor of the current wind turbine is obtained according to formula (1) based on the velocity loss of the upstream wind turbine at multiple points on the rotor of the current wind turbine: （1） in, The current wind turbine rotor point of the i-th unit The inflow rate at the location is at a loss; For the j-th unit, point on the rotor of the i-th unit Average speed loss at the location; is a binary variable; N is the number of wind turbines in the wind farm; For each wind turbine in the wind farm, the inflow additional turbulence intensity at multiple points on the rotor of the current wind turbine is obtained according to formula (2) based on the additional turbulence intensity at multiple points on the rotor of the current wind turbine at multiple points on the upstream wind turbine: （2） in, The additional turbulence intensity in the flow direction at point (x,y,z) on the rotor of the i-th unit; The additional directional turbulence intensity of the j-th unit at the point (x,y,z) on the rotor of the i-th unit; It is a binary variable; The number of wind turbines in the wind farm; Based on the inflow velocity deficit at multiple points on the wind turbine rotor, the average value is taken, and the wind speed in front of the wind turbine hub under the preset wind conditions is obtained according to formula (3): （3） in, The wind speed in front of the hub of the i-th wind turbine is currently being measured. For the incoming airflow velocity; At a wind speed of The wind direction angle is Under certain wind conditions, the wind speed in front of the hub and the power curve of the wind turbine are obtained, and the output power of the wind turbine under these wind conditions is obtained; where 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. Based on the output power corresponding to this wind condition, and according to formula (4), the total output power of the wind farm under the current wind farm layout scheme is obtained: （4） in, This represents the total output power of the wind farm under the current wind farm layout scheme. The wind speed is The wind direction is Wind conditions; For unit i in wind conditions Output power at the following levels; For wind conditions Frequency of occurrence; Number of wind directions; N represents the number of wind speed ranges taken under a single wind direction. T This refers to the number of generating units.

10. The wind farm parallelogram-shaped regular wind turbine and cable joint optimization method according to any one of claims 1-5, characterized in that, The specific steps for calculating the cable cost of a wind farm under the corresponding layout scheme for each individual wind farm include: Based on the location of the wind farm's booster station and the coastline, the closest coastal point to the booster station is determined and used as the feeder cable node. Based on the turbine and substation locations under the wind farm layout scheme, as well as the information on various types of cables within the farm, and coupling the feeder cable node and feeder cable model information, a total cable cost model for the wind farm is established, and the total cable cost of the wind farm is obtained by solving the problem. (5) in, This is the unit price of the cable. Representative point and The Euclidean distance between them It is a given safety factor.

11. A computer program product, comprising a computer program, characterized in that, The computer program is executed by a processor to perform the steps of the method as described in any one of claims 1-10.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when run by a processor, performs the steps of the method as described in any one of claims 1-10.

13. A wind farm parallelogram-shaped regular wind turbine-cable joint optimization system, comprising an interconnected memory and a processor, wherein the memory stores a computer program, characterized in that, The computer program, when run by a processor, performs the steps of the method as described in any one of claims 1-10.

Images