Method and system for realizing wind power plant fan arrangement

Abstract

The invention discloses a method and system for realizing wind power plant fan arrangement, and the method comprises the steps: collecting actual wind power resource data, and analyzing wind energy conditions, including consideration of generating capacity, cost per kilowatt-hour and wake effect; preliminarily optimizing the fan layout by using a heuristic search method; and fan arrangement is further refined by improving a genetic algorithm, so that optimal power generation efficiency and cost control are realized. According to the embodiment of the invention, efficient production and management are realized while the wind power generation project is ensured to meet ecological requirements, so that sustainable development of the wind power generation project is promoted, and economic benefits and environmental responsibility are balanced.

Description

Technical Field

[0001] This application relates to, but is not limited to, the field of wind power generation technology, and in particular to a method and system for arranging wind turbines in a wind farm. Background Technology

[0002] In the wind power industry, wind farm site selection is crucial for achieving efficient and sustainable power generation. Traditional site selection methods focus on wind energy resource assessment and the convenience of power transmission, but often overlook the potential impact on the ecological environment. With increasing environmental awareness and the advancement of sustainable development strategies, how to minimize adverse ecological impacts while ensuring the economic viability and power generation efficiency of wind farms has become an urgent technical problem to be solved. Summary of the Invention

[0003] This application provides a method and system for realizing the layout of wind turbines in a wind farm, which can optimize the layout of wind turbines, thereby taking into account both power generation efficiency and ecological protection.

[0004] This application provides a method for arranging wind turbines in a wind farm, including:

[0005] Obtain actual wind resource data of the target wind farm and determine the wind turbine parameters of the target wind farm;

[0006] Based on the obtained wind resource data and wind turbine parameters, an objective function for the comprehensive cost per kilowatt-hour and power generation is constructed.

[0007] Based on wind resource data, wind turbine parameters, and objective functions of levelized cost of electricity (LCOE) and power generation, an initial population is generated using heuristic search. A genetic algorithm is then executed in the initial population to optimize the wind turbine layout and update the population generation by generation in order to achieve the optimal levelized cost of electricity and power generation efficiency.

[0008] The individual with the highest fitness value is selected from the updated population and used as the optimal wind turbine layout scheme for the wind farm.

[0009] Based on the optimal wind turbine layout scheme and the actual ecological conditions of the wind farm, and combined with expert knowledge, an ecological protection and restoration plan for the wind farm is generated to ensure that the construction and operation of the wind farm meet the requirements of ecological protection.

[0010] In one exemplary instance, the method further includes integrating the analysis of the wind resources, the optimized objective function, the arrangement results of the genetic algorithm, and the ecological protection and restoration scheme into a visual decision-making system to support the dynamic management and adjustment of wind farm projects.

[0011] In one exemplary instance, acquiring the actual wind resource data of the target wind farm and determining the wind turbine parameters of the target wind farm includes:

[0012] Obtain wind speed and direction data from meteorological stations and wind measurement towers near the target wind farm and assess its long-term wind energy resource distribution; draw a wind rose diagram of the region based on long-term measured wind data to determine the prevailing wind direction; and conduct statistical analysis of wind speed frequency using the Weibull distribution.

[0013] In one exemplary instance, the wind speed frequency f(v) is statistically analyzed using the Weibull distribution according to the following formula:

[0014]

[0015] Where v represents wind speed, c is the scale parameter, and k is the shape parameter.

[0016] In one exemplary instance, determining the wind turbine parameters of the target wind farm includes: determining the initial parameters of the wind turbines of the target wind farm based on the obtained wind resource data;

[0017] The initial parameters of the wind turbines in the target wind farm include: the installed capacity of the wind farm; the parameters of the wind turbines include: the hub height, blade diameter, and wind power curve.

[0018] In one exemplary instance, the objective function comprises two parts: the levelized cost of electricity (LCOE) of the wind farm and the amount of electricity generated by the wind farm, wherein,

[0019] The Levelized Cost of Electricity (LCOE) is calculated as follows: Among them, C ECC Indicates total power generation; C LCC This represents the total cost, including the initial investment cost C. I Operation and maintenance costs C OM Cost of retirement upon expiration C DR and ecological and environmental costs C ES C LCC =C I +C OM +C DR +C ES ;

[0020] Electricity E i The calculation is as follows: Where P(v) is the power at wind speed v, obtained from the wind power curve; f(v) represents the probability density function of wind speed, obtained from the Weibull distribution, etc.; y represents the ratio of the wind turbine's normal operating time to the total annual time.

[0021] In one exemplary instance, generating the initial population using heuristic search includes:

[0022] From all possible installation locations, select the location with the highest wind speed as the installation location for the first fan;

[0023] Wind speed correction is applied to the grid affected by the wake effect, and stops when the first preset threshold of the required total number of wind turbines is reached;

[0024] After completing the placement of some wind turbines, the remaining wind turbine locations are screened to generate an initial population containing high-quality chromosomes.

[0025] In one exemplary instance, the wake effect is calculated as follows:

[0026]

[0027] Where u represents the wind speed at the downstream fan; u0 represents the free wind speed upstream; a represents the axial induction factor; α represents the entrainment constant; x represents the distance from the downstream location to the fan; and r represents the radius of the wake effect downwind.

[0028] In one exemplary instance, the filtering of remaining wind turbine locations includes:

[0029] The remaining grids are sorted by wind speed value, and the grids that are below the first preset threshold are selected as candidate positions. The remaining wind turbine positions are randomly selected from these candidates to form a certain number of individuals containing high-quality chromosomes. The number of high-quality individuals is set as the second preset threshold of the initial population size.

[0030] In one exemplary instance, the optimization of wind turbine layout using a genetic algorithm includes:

[0031] Perform genetic algorithm operations on the generated initial population to iteratively generate a new population;

[0032] The fitness function value is calculated for each generation of individuals, and the population is updated generation by generation until the maximum number of generations is reached or the fitness change is less than the threshold. Optimization stops and a population is obtained, which contains several wind turbine layout schemes, and the fitness values ​​are sorted from high to low.

[0033] In one exemplary instance, the value of the fitness function is the reciprocal of the value of the objective function.

[0034] In one exemplary instance, the ecological protection and restoration scheme for generating a wind farm includes:

[0035] Based on the ecological environment of the wind farm area and the optimal wind turbine layout scheme, assess the impact of wind turbine location on the local ecosystem;

[0036] Based on expert knowledge, the system intelligently generates ecological protection and restoration plans adapted to the local ecological environment.

[0037] This application also provides a computer-readable storage medium storing computer-executable instructions, which are used to execute the method for implementing wind turbine layout in a wind farm as described in any of the above claims.

[0038] This application embodiment further provides a computer device, including a memory and a processor, wherein the memory stores the following instructions executable by the processor: steps for performing the method for implementing the wind turbine layout of a wind farm as described in any of the above claims.

[0039] This application embodiment further provides a system for realizing the arrangement of wind turbines in a wind farm, including: an acquisition module, a construction module, an optimization module, a determination module, and a generation module; wherein...

[0040] The acquisition module is used to acquire the actual wind resource data of the target wind farm and determine the wind turbine parameters of the target wind farm;

[0041] The module is used to construct an objective function for the overall cost per kilowatt-hour and power generation based on the obtained wind resource data and wind turbine parameters;

[0042] The optimization module is used to generate an initial population based on wind resource data, wind turbine parameters, and objective functions of levelized cost of electricity and power generation. It uses heuristic search to generate an initial population, and executes a genetic algorithm in the initial population to optimize the wind turbine layout and update the population generation by generation to achieve the optimal levelized cost of electricity and power generation efficiency.

[0043] The determination module is used to select the individual with the highest fitness value from the updated population as the optimal wind turbine layout scheme for the wind farm.

[0044] The generation module is used to generate ecological protection and restoration plans for wind farms based on the optimal wind turbine layout and on-site ecological conditions, combined with expert knowledge, to ensure that the construction and operation of wind farms meet ecological protection requirements.

[0045] In one exemplary instance, it further includes: an integration module for integrating the analysis of the wind resources, the optimized objective function, the arrangement results of the genetic algorithm, and the ecological protection and restoration scheme into a visualization decision-making system to support the dynamic management and adjustment of wind farm projects.

[0046] The method for wind turbine layout in wind farms provided in this application collects actual wind resource data and analyzes wind energy conditions, including considerations of power generation, cost per kilowatt-hour, and wake effect. Then, a heuristic search method is used for initial optimization of the turbine layout; an improved genetic algorithm is used to further refine the turbine layout to achieve optimal power generation efficiency and cost control. This application ensures that wind power projects meet ecological requirements while achieving efficient production and management, thereby promoting the sustainable development of wind power projects and balancing economic benefits and environmental responsibility.

[0047] Taking into account wind energy resources, economic efficiency, and ecological protection needs, the project achieved intelligent site selection and eco-friendly design for wind farms. The final result is an optimal wind turbine layout scheme that balances power generation efficiency and ecological protection.

[0048] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0049] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0050] Figure 1 This is a flowchart illustrating the method for arranging wind turbines in a wind farm, as described in this application embodiment.

[0051] Figure 2 This is a schematic diagram of the system composition for arranging wind turbines in a wind farm, as described in this application embodiment. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be arbitrarily combined with each other.

[0054] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings, which illustrate embodiments of the present application. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of this application will be more thorough and complete.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0056] It is understood that the terms "first" and "second" used in this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0057] It is understood that the term "connection" in the following embodiments should be understood as "electrical connection," "communication connection," etc., if the connected circuits, modules, units, etc., have electrical signal or data transmission with each other.

[0058] When used herein, the singular forms of “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising / including” or “having,” etc., specify the presence of the stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.

[0059] The construction and operation of wind farms can have long-term negative impacts on biodiversity and ecosystems, thereby affecting project compliance and public support. Therefore, developing new technologies and methods to more systematically consider and mitigate these impacts is crucial for the sustainable development of the industry.

[0060] To consider the impact on the ecological environment, this application integrates expert knowledge and ecological assessment data, utilizing a visualized integrated system to manage ecological restoration and protection measures, forming an intelligent ecological restoration plan. This not only provides an innovative environmental protection approach for wind farms but also demonstrates the commitment of modern wind power projects to higher environmental responsibility standards. The core of this method is the use of an improved genetic algorithm to assess and optimize long-term wind resource distribution, enhancing the optimization process of wind turbine layout. This method not only improves the energy efficiency and economy of wind farms but also significantly enhances their adaptability to the ecological environment, providing reliable support for eco-production synergy decision-making in wind farms.

[0061] Figure 1This is a flowchart illustrating the method for arranging wind turbines in a wind farm, as described in the embodiments of this application. Figure 1 As shown. It can include:

[0062] Step 100: Obtain the actual wind resource data of the target wind farm and determine the wind turbine parameters of the target wind farm.

[0063] In one exemplary instance, the wind resource data of the target wind farm may include, but is not limited to, measured wind speed data, measured wind direction data, probability distribution of wind speed, wind rose diagram, etc.

[0064] In one embodiment, wind speed and direction data can be obtained from weather stations and wind measurement towers to provide basic data for wind energy analysis and wind turbine layout.

[0065] In one embodiment, wind rose diagrams can be drawn using measured data to determine the prevailing wind direction, providing directional basis for the overall layout of wind farms and wake effect assessment.

[0066] In one embodiment, the probability distribution of wind speed can be described by the Weibull distribution or other statistical models, thereby more accurately estimating the annual average wind speed and frequency.

[0067] In one exemplary instance, step 100 may include: acquiring wind speed and direction data from meteorological stations and meteorological towers near the target wind farm and assessing its long-term wind energy resource distribution. Based on the long-term measured wind data, a wind rose diagram of the region is drawn to determine the dominant wind direction; and the wind speed frequency is statistically analyzed using the Weibull distribution. Taking the statistical analysis of wind speed frequency f(v) using the Weibull distribution to assess the long-term wind energy resource distribution as an example, as shown in formula (1):

[0068]

[0069] In formula (1), v represents wind speed, c is the scale parameter, and k is the shape parameter.

[0070] In one exemplary instance, initial parameters for the wind turbines of a target wind farm can be determined based on the obtained wind resource data, such as setting the installed capacity of the wind farm and the turbine model. This provides the necessary foundational conditions for optimizing the construction of the target model, including the turbine hub height, blade diameter, and wind power curve.

[0071] In one embodiment, the wind turbine parameters mainly refer to the physical and performance characteristics of the wind turbine equipment, which may include, but are not limited to, wind turbine hub height, wind turbine blade diameter, wind power curve representing the relationship between wind speed and wind turbine output power, and the maximum output power of the wind turbine under rated wind speed conditions, i.e., rated power.

[0072] Step 101: Based on the obtained wind resource data and wind turbine parameters, construct an objective function for the comprehensive cost per kilowatt-hour and power generation.

[0073] In one exemplary instance, step 101 establishes a wind farm levelized cost of electricity that takes into account the ecological and environmental impact in order to find the optimal layout. The objective function consists of two parts: one part is the wind farm levelized cost of electricity, and the other part is the wind farm power generation.

[0074] The objective function includes the levelized cost of electricity (LCOE) and the amount of electricity generated. The calculation of the levelized cost of electricity is shown in formula (2):

[0075]

[0076] In formula (2), C ECC Indicates total power generation; C LCC This represents the total cost, including the initial investment cost C. I Operation and maintenance costs C OM Cost of retirement upon expiration C DR and ecological and environmental costs C ES C LCC =C I +C OM +C DR +C ES .

[0077] Electricity E i The calculation is shown in formula (3):

[0078]

[0079] In formula (3), P(v) is the power at wind speed v, which is obtained from the wind power curve; f(v) represents the probability density function of wind speed, which is obtained from the Weibull distribution, etc.; y represents the ratio of the wind turbine's normal operating time to the total annual time.

[0080] Step 102: Based on wind resource data, wind turbine parameters, and objective functions of levelized cost of electricity (LCOE) and power generation, an initial population is generated using heuristic search. A genetic algorithm is then executed in the initial population to optimize the wind turbine layout and update the population generation by generation to achieve the optimal LCOE and power generation efficiency.

[0081] In one exemplary instance, generating an initial population using heuristic search may include:

[0082] From all possible installation locations, select the location with the highest wind speed as the installation location for the first fan to ensure the efficiency of the initial layout plan;

[0083] Wind speed correction is applied to the grid affected by the wake effect, and stops when the wind speed reaches the first preset threshold of the required total number of installed wind turbines, such as 30%.

[0084] After completing the placement of some wind turbines, the remaining wind turbine locations are screened to generate an initial population containing high-quality chromosomes.

[0085] In this embodiment of the application, a heuristic search method is used to add a high-quality wind turbine layout scheme (called an individual) when the genetic algorithm initializes the population, so as to converge to a high-quality solution faster and reduce the risk of getting trapped in local optima.

[0086] In one embodiment, if there are equal wind speeds, one of them is randomly selected as the installation location of the first fan.

[0087] When one wind turbine is located downwind of another, the upstream turbine generates a wake, causing a decrease in wind speed at the downstream turbine. Therefore, a wake correction is applied to the wind speed in the downwind region. The wake effect is calculated using formula (4):

[0088]

[0089] In formula (4), u represents the wind speed at the downstream fan; u0 represents the free wind speed upstream; a represents the axial induction factor, which is a coefficient related to the energy extracted by the fan from the upstream airflow, and its value is generally 0.2; α represents the entrainment constant, and its value is 0.1; x represents the distance of the downstream location from the fan; and r represents the radius of the downwind direction affected by the wake.

[0090] In one embodiment, after completing the placement of some wind turbines, for example, reaching a preset proportion of the total number of wind turbines, such as 30%, the remaining wind turbine locations are screened. Specifically, this may include: sorting the remaining grid cells by wind speed value, selecting the top 30% of grid cells as candidate locations, randomly selecting remaining wind turbine locations from these, and finally forming a certain number of individuals containing high-quality chromosomes. The number of high-quality individuals is set as a second preset threshold of 20% of the initial population size. The initial population generated in this way contains high-quality chromosomes, which helps the genetic algorithm converge to a high-quality solution more quickly and reduces the risk of getting trapped in local optima.

[0091] In one embodiment, other genetic algorithm parameters may include, for example, population size, mutation rate, maximum number of iterations, etc., and the fitness function may be set as the reciprocal of the levelized cost of electricity (LCOE).

[0092] In one exemplary instance, optimizing wind turbine layout using a genetic algorithm may include:

[0093] Genetic algorithm operations (selection, crossover, mutation) are performed on the generated initial population to iteratively generate a new population; the fitness function value is calculated for each generation of individuals, and the population is updated generation by generation until the preset maximum number of generations is reached or the fitness change is less than the threshold, at which point the optimization stops and a population is obtained, which contains several wind turbine layout schemes, with fitness values ​​sorted from high to low.

[0094] In a genetic algorithm, each generation contains a set of schemes (i.e., a set of different wind turbine arrangements), called a population. Through multiple iterations, individuals in each generation of the population are selected through fitness, crossover, and mutation to produce new individuals. Individuals with higher fitness (i.e., wind turbine arrangements with lower levelized cost of electricity) are more likely to be retained and carried over to the next generation. The ultimate goal of the genetic algorithm is to gradually optimize the wind turbine arrangement scheme through multiple generations of iteration, and finally find the scheme with the highest fitness, that is, the wind turbine layout with the lowest levelized cost of electricity, the highest power generation efficiency, and the best ecological friendliness.

[0095] In one embodiment, in the genetic algorithm, the fitness function is defined as the reciprocal of the objective function value, as shown in formula (5):

[0096]

[0097] As shown in formula (5), individuals with higher fitness indicate lower cost per kilowatt-hour. Wind turbine arrangement schemes with lower cost per kilowatt-hour are more likely to be selected for crossover and mutation in the genetic algorithm. This helps the genetic algorithm select the optimal wind turbine arrangement scheme until the preset maximum number of iterations or fitness value is reached, at which point the genetic algorithm terminates.

[0098] In one embodiment, the optimal wind turbine layout is selected through multiple iterations based on the calculated fitness, which may include:

[0099] Based on the calculated fitness, individuals with higher fitness (i.e., wind turbine layout schemes with low cost per kilowatt-hour and high power generation efficiency) are selected from the current population to enter the next generation. The selection operation is a prerequisite for crossover and mutation; only selected individuals will participate in crossover and mutation, thereby generating the next generation population.

[0100] The arrangement of wind turbines in two individuals can be partially swapped, for example, by cross-selecting certain turbine positions. This allows the offspring to inherit part of the layout from the parent while also acquiring new characteristics. The cross-selection operation follows the selection operation and relies on the highly fit parent provided by the selection operation.

[0101] For some individuals, the positions of some wind turbines are randomly changed, such as moving one turbine from its current location to another randomly selected location. Mutation typically follows crossover and is applied with low probability to newly generated individuals. The purpose of mutation is to break possible local optima by introducing new genes to increase population diversity, giving the algorithm the opportunity to explore a wider solution space.

[0102] In step 102 of this embodiment, a heuristic search method is used to add high-quality individuals when the genetic algorithm initializes the population, which helps to converge to a high-quality solution faster and reduces the risk of getting trapped in local optima.

[0103] Step 103: Select the individual with the highest fitness value from the updated population as the optimal wind turbine layout scheme for the wind farm.

[0104] In one exemplary instance, step 103 may include:

[0105] The fitness value of each individual in the updated population obtained from the final output of the genetic algorithm is calculated. The wind turbine layout schemes with the highest fitness values ​​are then selected. In this way, the optimal layout is obtained by judging the merits of the wind turbine layout schemes based on the individual fitness calculation results.

[0106] Step 104: Based on the optimal wind turbine layout scheme and the actual ecological conditions of the wind farm, and combined with expert knowledge, generate an ecological protection and restoration plan for the wind farm to ensure that the construction and operation of the wind farm meet the requirements of ecological protection.

[0107] In one exemplary instance, step 104 may include:

[0108] Based on the ecological environment of the wind farm area and the optimal wind turbine layout, assess the impact of the wind turbine location on the local ecosystem, including but not limited to the potential impact on vegetation, water resources, and wildlife habitats;

[0109] Based on expert knowledge, the system intelligently generates ecological protection and restoration plans adapted to the local environment. These plans include: protecting local flora and fauna and preventing habitat impact from wind turbine construction; ensuring that wind turbine construction and operation do not affect local water quality; and post-construction vegetation restoration to reduce soil erosion and protect the local landscape. Step 104 intelligently selects an ecological restoration and protection plan for the wind farm based on local ecological conditions and expert knowledge.

[0110] The method for wind turbine layout in wind farms provided in this application collects actual wind resource data and analyzes wind energy conditions, including considerations of power generation, cost per kilowatt-hour, and wake effect. Then, a heuristic search method is used for initial optimization of the turbine layout; an improved genetic algorithm is used to further refine the turbine layout to achieve optimal power generation efficiency and cost control. This application ensures that wind power projects meet ecological requirements while achieving efficient production and management, thereby promoting the sustainable development of wind power projects and balancing economic benefits and environmental responsibility.

[0111] In one exemplary instance, the method for implementing wind turbine layout in a wind farm provided in this application embodiment may further include:

[0112] Step 105: Integrate wind energy resource analysis, optimization objective function, genetic algorithm layout results, and ecological protection and restoration schemes into a visual decision-making system to support the dynamic management and adjustment of wind farm projects.

[0113] In one exemplary instance, such as Figure 2 As shown, the interface can display information such as wind turbine layout, wind energy resource distribution, wake effect area, estimated cost per kilowatt-hour, and ecological restoration area, forming an intuitive management tool. This application embodiment integrates all the functions implemented in the steps of this application embodiment into the system, realizing visualized operation of intelligent decision-making for ecological-production collaboration.

[0114] The decision-making system provided in this application has dynamic update and adjustment functions, and can provide new suggestions based on environmental changes or the operating status of wind farms, further optimize wind turbine layout and ecological protection strategies, realize full-process management from wind energy assessment to wind turbine layout optimization and ecological restoration plan, and ensure that wind farms achieve a balance between economic benefits and ecological responsibilities.

[0115] The method for wind turbine layout in a wind farm provided in this application mainly includes: acquiring measured wind energy data of the target field and conducting wind energy condition simulation assessment; using the assessment range as the search space; adding high-quality initial populations based on a heuristic search algorithm; using power generation and the levelized cost of electricity (LCOE) of the wind farm considering the ecological environment impact as comprehensive objective functions; optimizing the wind turbine layout of the wind farm using a genetic algorithm; and intelligently proposing a wind farm ecological environment restoration and protection scheme based on expert knowledge and establishing a visual integrated system based on the actual ecological environment conditions of the wind farm. The method for wind turbine layout in a wind farm provided in this application considers the impact of the ecological environment on the turbine layout and improves the genetic algorithm by adding high-quality individuals, thereby improving the optimization efficiency of the turbine layout and converging to a better solution. Furthermore, an intelligent protection and restoration scheme is formed based on the actual ecological environment conditions.

[0116] The method for wind turbine layout in wind farms provided in this application comprises a complete decision-making process, from collecting measured wind energy data to establishing an ecological-production collaborative decision-making system. First, by collecting actual wind resource data, the wind energy situation is analyzed, including considerations of power generation, cost per kilowatt-hour, and wake effect. Next, a heuristic search method is used for preliminary optimization of the turbine layout. Then, an improved genetic algorithm is used to further refine the turbine layout to achieve optimal power generation efficiency and cost control. Finally, the protection and restoration plan is integrated with the layout results into the ecological-production collaborative decision-making system, ensuring that wind power projects meet ecological requirements while achieving efficient production and management, thereby promoting the sustainable development of wind power projects and balancing economic benefits and environmental responsibility.

[0117] This application also provides a computer-readable storage medium storing computer-executable instructions for performing the method for implementing wind turbine layout in a wind farm as described in any of the preceding claims.

[0118] This application further provides a computer device, including a memory and a processor, wherein the memory stores the following instructions executable by the processor: steps for performing the method for implementing the wind turbine layout of a wind farm as described in any of the preceding claims.

[0119] Figure 2 This is a schematic diagram of the composition structure of the system for implementing the wind turbine layout in a wind farm, as shown in the embodiments of this application. Figure 2 As shown, it can include: an acquisition module, a construction module, an optimization module, a determination module, and a generation module; among which,

[0120] The acquisition module is used to acquire the actual wind resource data of the target wind farm and determine the wind turbine parameters of the target wind farm;

[0121] The module is used to construct an objective function for the overall cost per kilowatt-hour and power generation based on the obtained wind resource data and wind turbine parameters;

[0122] The optimization module is used to generate an initial population based on wind resource data, wind turbine parameters, and objective functions of levelized cost of electricity and power generation. It uses heuristic search to generate an initial population, and executes a genetic algorithm in the initial population to optimize the wind turbine layout and update the population generation by generation to achieve the optimal levelized cost of electricity and power generation efficiency.

[0123] The determination module is used to select the individual with the highest fitness value from the updated population as the optimal wind turbine layout scheme for the wind farm.

[0124] The generation module is used to generate ecological protection and restoration plans for wind farms based on the optimal wind turbine layout and on-site ecological conditions, combined with expert knowledge, to ensure that the construction and operation of wind farms meet ecological protection requirements.

[0125] The system for wind turbine layout in wind farms provided in this application collects actual wind resource data and analyzes wind energy conditions, including considerations of power generation, cost per kilowatt-hour, and wake effect. Then, a heuristic search method is used for initial optimization of the turbine layout; an improved genetic algorithm is used to further refine the turbine layout to achieve optimal power generation efficiency and cost control. This application ensures that wind power projects meet ecological requirements while achieving efficient production and management, thereby promoting the sustainable development of wind power projects and balancing economic benefits and environmental responsibility.

[0126] In one exemplary instance, an integration module may also be included, used to integrate the analysis of the wind resources, the optimized objective function, the arrangement results of the genetic algorithm, and the ecological protection and restoration scheme into a visual decision-making system, supporting the dynamic management and adjustment of wind farm projects. This application embodiment, through the integration module, integrates the functions of each component module of the system for realizing wind farm turbine arrangement provided in this application embodiment into the system, realizing visualized operation of ecological-production collaborative intelligent decision-making.

[0127] Although the embodiments disclosed in this application are as described above, the content described is merely for the purpose of understanding this application and is not intended to limit this application. Any person skilled in the art to which this application pertains may make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in this application; however, the scope of patent protection of this application shall still be determined by the scope defined in the appended claims.

Claims

1. A method for arranging wind turbines in a wind farm, characterized in that, include: Obtain actual wind resource data of the target wind farm and determine the wind turbine parameters of the target wind farm; Based on the obtained wind resource data and wind turbine parameters, an objective function for the comprehensive cost per kilowatt-hour and power generation is constructed. Based on wind resource data, wind turbine parameters, and objective functions of levelized cost of electricity (LCOE) and power generation, an initial population is generated using heuristic search. A genetic algorithm is then executed in the initial population to optimize the wind turbine layout and update the population generation by generation in order to achieve the optimal levelized cost of electricity and power generation efficiency. The individual with the highest fitness value is selected from the updated population and used as the optimal wind turbine layout scheme for the wind farm. Based on the optimal wind turbine layout scheme and the actual ecological conditions of the wind farm, and combined with expert knowledge, an ecological protection and restoration plan for the wind farm is generated to ensure that the construction and operation of the wind farm meet the requirements of ecological protection.

2. The method according to claim 1, further comprising: The analysis of the wind resources, the optimized objective function, the arrangement results of the genetic algorithm, and the ecological protection and restoration scheme are integrated into a visual decision-making system to support the dynamic management and adjustment of wind farm projects.

3. The method according to claim 1 or 2, wherein, The process of acquiring actual wind resource data of the target wind farm and determining the wind turbine parameters of the target wind farm includes: Obtain wind speed and direction data from meteorological stations and wind measurement towers near the target wind farm and assess its long-term wind energy resource distribution; draw a wind rose diagram of the region based on long-term measured wind data to determine the prevailing wind direction; and conduct statistical analysis of wind speed frequency using the Weibull distribution.

4. The method according to claim 3, wherein, The wind speed frequency f(v) is statistically analyzed using the Weibull distribution as described in the following formula: Where v represents wind speed, c is the scale parameter, and k is the shape parameter.

5. The method according to claim 4, wherein, The determination of the wind turbine parameters of the target wind farm includes: determining the initial parameters of the wind turbines of the target wind farm based on the obtained wind resource data; The initial parameters of the wind turbines in the target wind farm include: the installed capacity of the wind farm; the parameters of the wind turbines include: the hub height, blade diameter, and wind power curve.

6. The method according to claim 1 or 2, wherein, The objective function comprises two parts: the levelized cost of electricity (LCOE) of the wind farm and the amount of electricity generated by the wind farm. The Levelized Cost of Electricity (LCOE) is calculated as follows: Among them, C ECC Indicates total power generation; C LCC This represents the total cost, including the initial investment cost C. I Operation and maintenance costs C OM Cost of retirement upon expiration C DR and ecological and environmental costs C ES C LCC =C I +C OM +C DR +C ES ; Electricity E i The calculation is as follows: Where P(v) is the power at wind speed v, obtained from the wind power curve; f(v) represents the probability density function of wind speed, obtained from the Weibull distribution, etc.; y represents the ratio of the wind turbine's normal operating time to the total annual time.

7. The method according to claim 1 or 2, wherein, The method of generating the initial population using heuristic search includes: From all possible installation locations, select the location with the highest wind speed as the installation location for the first fan; Wind speed correction is applied to the grid affected by the wake effect, and stops when the first preset threshold of the required total number of wind turbines is reached; After completing the placement of some wind turbines, the remaining wind turbine locations are screened to generate an initial population containing high-quality chromosomes.

8. The method according to claim 7, wherein, The wake effect is calculated as follows: Where u represents the wind speed at the downstream fan; u0 represents the free wind speed upstream; a represents the axial induction factor; α represents the entrainment constant; x represents the distance from the downstream location to the fan; and r represents the radius of the wake effect downwind.

9. The method according to claim 7, wherein, The process of filtering the remaining wind turbine locations includes: The remaining grids are sorted by wind speed value, and the grids that are below the first preset threshold are selected as candidate positions. The remaining wind turbine positions are randomly selected from these candidates to form a certain number of individuals containing high-quality chromosomes. The number of high-quality individuals is set as the second preset threshold of the initial population size.

10. The method according to claim 1 or 2, wherein, The optimization of wind turbine layout using a genetic algorithm includes: Perform genetic algorithm operations on the generated initial population to iteratively generate a new population; The fitness function value is calculated for each generation of individuals, and the population is updated generation by generation until the maximum number of generations is reached or the fitness change is less than the threshold. Optimization stops and a population is obtained, which contains several wind turbine layout schemes, and the fitness values ​​are sorted from high to low.

11. The method according to claim 10, wherein, The fitness function is the reciprocal of the objective function.

12. The method according to claim 1 or 2, wherein, The ecological protection and restoration plan for the generated wind farm includes: Based on the ecological environment of the wind farm area and the optimal wind turbine layout scheme, assess the impact of wind turbine location on the local ecosystem; Based on expert knowledge, the system intelligently generates ecological protection and restoration plans adapted to the local ecological environment.

13. A computer-readable storage medium storing computer-executable instructions for performing the method for arranging wind turbines in a wind farm as described in any one of claims 1-12.

14. A computer device comprising a memory and a processor, wherein, The memory stores the following instructions that can be executed by a processor: steps for performing the method for implementing the wind turbine layout of a wind farm as described in any one of claims 1-12.

15. A system for arranging wind turbines in a wind farm, characterized in that, include: The modules are: module acquisition, module construction, module optimization, module determination, and module generation; among them, The acquisition module is used to acquire the actual wind resource data of the target wind farm and determine the wind turbine parameters of the target wind farm; The module is used to construct an objective function for the overall cost per kilowatt-hour and power generation based on the obtained wind resource data and wind turbine parameters; The optimization module is used to generate an initial population based on wind resource data, wind turbine parameters, and objective functions of levelized cost of electricity and power generation. It uses heuristic search to generate an initial population, and executes a genetic algorithm in the initial population to optimize the wind turbine layout and update the population generation by generation to achieve the optimal levelized cost of electricity and power generation efficiency. The determination module is used to select the individual with the highest fitness value from the updated population as the optimal wind turbine layout scheme for the wind farm. The generation module is used to generate ecological protection and restoration plans for wind farms based on the optimal wind turbine layout and on-site ecological conditions, combined with expert knowledge, to ensure that the construction and operation of wind farms meet ecological protection requirements.

16. The system of claim 15, further comprising: The integration module is used to integrate the analysis of the wind resources, the optimized objective function, the arrangement results of the genetic algorithm, and the ecological protection and restoration scheme into a visual decision-making system, supporting the dynamic management and adjustment of wind farm projects.

Images