Multi-type wind turbine generator mixed layout optimization method for high and cold zone wind power plant

Abstract

The invention relates to the technical field of wind power plant layout optimization, in particular to an alpine region wind power plant-oriented multi-type wind turbine generator hybrid layout optimization method, which comprises the following steps of: establishing at least one design variable of an alpine region wind power plant optimization model, and establishing at least one constraint condition of the alpine region wind power plant optimization model; establishing a target function of the high and cold zone wind power plant optimization model; and based on the at least one design variable, the at least one constraint condition and the target function, adopting an improved genetic strategy to carry out global optimization to obtain an initial optimization result, and based on the initial optimization result, adopting a sequence least square planning strategy to carry out position optimization to obtain a final multi-type wind turbine generator hybrid layout optimization result of the wind power plant. Therefore, the problems that in the related technology, a single optimization algorithm is difficult to consider the global search capability and the local optimization effect, and only the position variable is considered, so that the actual requirement of high and cold region wind power plant planning cannot be met are solved.

Description

Technical Field

[0001] This application relates to the field of wind farm layout optimization technology, and in particular to a method for optimizing the mixed layout of multiple types of wind turbine units for wind farms in high-altitude and cold regions. Background Technology

[0002] Currently, conventional wind farm layout optimization mainly focuses on large wind turbines, typically using the same type of turbines. With a fixed number of turbines, optimization is only done on their location, and the spacing between turbines is generally no less than five times the rotor diameter. Any two turbines are usually located in the far wake region. In special scenarios such as research stations in high-altitude and frigid regions, extreme climate, geological conditions, and construction constraints limit the selection of small wind turbines with rated power below 100kW. These turbines need to be densely arranged within limited space. To fully utilize the wind energy resources in this confined space, a mixed layout strategy of different turbine models is required.

[0003] In related technologies, conventional wind farm layout optimization uses far wake modeling methods such as the Jensen model and the Gaussian model, and often employs single optimization algorithms such as genetic algorithms and particle swarm optimization, with the optimization variable usually being only the location of the wind turbine.

[0004] However, in related technologies, a single optimization algorithm is difficult to balance global search capability and local refinement effect. In high-altitude and cold regions, two adjacent wind turbines are generally located in the near-wake region, which makes the far-wake model have limited effectiveness in dealing with complex problems such as mixed turbine types, dense layout, and joint optimization of quantity and location in wind farms in high-altitude and cold regions. It cannot meet the actual needs of wind farm planning in high-altitude and cold regions and urgently needs to be improved. Summary of the Invention

[0005] This application provides a method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions. This method addresses the problems in related technologies, such as the difficulty of a single optimization algorithm to balance global search capabilities and local optimization effects, and the inability to meet the actual needs of wind farm planning in high-altitude and cold regions due to its focus on only location variables.

[0006] The first aspect of this application provides a method for optimizing the mixed layout of multiple types of wind turbines in wind farms in high-altitude and cold regions, comprising the following steps: establishing at least one design variable for an optimization model of a wind farm in high-altitude and cold regions, and establishing at least one constraint condition for the optimization model of the wind farm in high-altitude and cold regions; establishing an objective function for the optimization model of the wind farm in high-altitude and cold regions; performing global optimization using an improved genetic strategy based on the at least one design variable, the at least one constraint condition, and the objective function to obtain initial optimization results; and performing location optimization using a sequential least squares programming strategy based on the initial optimization results to obtain the final optimization result of the mixed layout of multiple types of wind turbines in the wind farm.

[0007] Through the above-mentioned technical means, the embodiments of this application can establish the design variables, constraints and objective functions of the wind farm optimization model in high-altitude and cold regions, and combine the global optimization of the improved genetic strategy with the sequential least squares programming for location optimization, taking into account both global search capability and local optimization, to obtain the final optimization result of the mixed layout of multiple types of wind turbine units in the wind farm, thereby providing scientific and technical support for the planning of wind farms in high-altitude and cold regions.

[0008] Optionally, in one embodiment of this application, the expression of the objective function is: , in, Represents the total cost. This represents the total annual power generation of the wind farm.

[0009] Through the above-mentioned technical means, the embodiments of this application can design an objective function based on the total cost input and annual total power generation output in high-altitude and cold regions, thereby optimizing the input-output ratio, achieving a balance between economic efficiency and engineering feasibility, and providing a scientific economic evaluation basis for wind farm planning in high-altitude and cold regions.

[0010] Optionally, in one embodiment of this application, the at least one design variable includes at least one of processing quantity variables using the virtual wind turbine method, setting wind turbine existence variables, setting wind turbine type variables, and setting wind turbine location coordinate variables, and the at least one constraint includes at least one of wind farm boundary constraints, wind turbine spacing constraints, and wind turbine quantity constraints.

[0011] Through the above-mentioned technical means, the embodiments of this application can establish design variables based on the virtual wind turbine method, realize unified encoding and processing of the number, type and location variables of wind turbines, classify and process different constraints, avoid the problem of applying invalid constraints to inactive wind turbines in traditional methods, improve optimization efficiency, and provide an effective mathematical modeling framework for complex wind farm planning problems in high-altitude and cold regions.

[0012] Optionally, in one embodiment of this application, the global optimization using an improved genetic strategy includes: employing a variable type-aware encoding strategy to initialize and encode the coordinate variable, the existence variable, and the type variable respectively to obtain initial processing variables; obtaining convergence results based on tournament selection and elite retention strategies; performing differentiated crossover and mutation processing on the convergence results to obtain an initial solution; and using a combination of the objective function and the constraint violation penalty function to evaluate the fitness of the initial solution to determine the initial optimization result.

[0013] Through the above-mentioned technical means, the embodiments of this application can effectively handle the complexity of mixed integer nonlinear programming problems by using a variable type-aware encoding strategy, a differentiated crossover and mutation mechanism, and an improved fitness evaluation method designed for genetic algorithms, thereby achieving a significant improvement in algorithm performance.

[0014] Optionally, in one embodiment of this application, the step of performing location optimization based on the initial optimization result using a sequential least squares programming strategy includes: selecting an active wind turbine set based on the initial optimization result, performing dimensionality reduction processing on the location coordinate variables in the active wind turbine set; calculating the gradient of the objective function using automatic differentiation, and performing location optimization based on the gradient of the objective function using the sequential least squares programming strategy.

[0015] Through the above-mentioned technical means, the embodiments of this application can screen active units and perform dimensionality reduction processing, reduce the amount of calculation in the location optimization stage, improve the computational efficiency, accurately obtain the gradient of the objective function through automatic differentiation, provide reliable gradient information for sequential least squares programming, efficiently realize the local refinement of location variables, and thus further improve the economy and power generation performance of the layout scheme on the basis of the initial optimization.

[0016] A second aspect of this application provides a device for optimizing the mixed layout of multiple types of wind turbines in wind farms in high-altitude and cold regions, comprising: a first establishment module for establishing at least one design variable of an optimization model for a wind farm in high-altitude and cold regions, and establishing at least one constraint condition of the optimization model; a second establishment module for establishing an objective function of the optimization model; and an optimization module for performing global optimization using an improved genetic strategy based on the at least one design variable, the at least one constraint condition, and the objective function to obtain an initial optimization result, and performing location optimization using a sequential least squares programming strategy based on the initial optimization result to obtain the final optimized layout result of the mixed layout of multiple types of wind turbines in the wind farm.

[0017] Through the above-mentioned technical means, the embodiments of this application can establish the design variables, constraints and objective functions of the wind farm optimization model in high-altitude and cold regions, and combine the global optimization of the improved genetic strategy with the sequential least squares programming for location optimization, taking into account both global search capability and local optimization, to obtain the final optimization result of the mixed layout of multiple types of wind turbine units in the wind farm, thereby providing scientific and technical support for the planning of wind farms in high-altitude and cold regions.

[0018] Optionally, in one embodiment of this application, the expression of the objective function is: , in, Represents the total cost. This represents the total annual power generation of the wind farm.

[0019] Through the above-mentioned technical means, the embodiments of this application can design an objective function based on the total cost input and annual total power generation output in high-altitude and cold regions, thereby optimizing the input-output ratio, achieving a balance between economic efficiency and engineering feasibility, and providing a scientific economic evaluation basis for wind farm planning in high-altitude and cold regions.

[0020] Optionally, in one embodiment of this application, the at least one design variable includes at least one of processing quantity variables using the virtual wind turbine method, setting wind turbine existence variables, setting wind turbine type variables, and setting wind turbine location coordinate variables, and the at least one constraint includes at least one of wind farm boundary constraints, wind turbine spacing constraints, and wind turbine quantity constraints.

[0021] Through the above-mentioned technical means, the embodiments of this application can establish design variables based on the virtual wind turbine method, realize unified encoding and processing of the number, type and location variables of wind turbines, classify and process different constraints, avoid the problem of applying invalid constraints to inactive wind turbines in traditional methods, improve optimization efficiency, and provide an effective mathematical modeling framework for complex wind farm planning problems in high-altitude and cold regions.

[0022] Optionally, in one embodiment of this application, the optimization module includes: an encoding unit, configured to use a variable type-aware encoding strategy to initialize the coordinate variable, the existence variable, and the type variable respectively to obtain initial processing variables; a processing unit, configured to obtain a convergence result based on a tournament selection and elite retention strategy, and perform differential cross-mutation processing on the convergence result to obtain an initial solution; and an evaluation unit, configured to use a combination of the objective function and the constraint violation penalty function to evaluate the fitness of the initial solution and determine the initial optimization result.

[0023] Through the above-mentioned technical means, the embodiments of this application can effectively handle the complexity of mixed integer nonlinear programming problems by using a variable type-aware encoding strategy, a differentiated crossover and mutation mechanism, and an improved fitness evaluation method designed for genetic algorithms, thereby achieving a significant improvement in algorithm performance.

[0024] Optionally, in one embodiment of this application, the optimization module includes: a dimensionality reduction unit, used to filter and obtain a set of active wind turbines based on the initial optimization results, and to perform dimensionality reduction processing on the location coordinate variables in the set of active wind turbines; and a calculation unit, used to calculate the gradient of the objective function using automatic differentiation, and to perform location optimization using the sequential least squares programming strategy based on the gradient of the objective function.

[0025] Through the above-mentioned technical means, the embodiments of this application can screen active units and perform dimensionality reduction processing, reduce the amount of calculation in the location optimization stage, improve the computational efficiency, accurately obtain the gradient of the objective function through automatic differentiation, provide reliable gradient information for sequential least squares programming, efficiently realize the local refinement of location variables, and thus further improve the economy and power generation performance of the layout scheme on the basis of the initial optimization.

[0026] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the method for optimizing the hybrid layout of multiple types of wind turbines for wind farms in high-altitude and cold regions as described in the above embodiments.

[0027] A fourth aspect of this application provides a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for optimizing the hybrid layout of multiple types of wind turbines for wind farms in cold regions.

[0028] The fifth aspect of this application provides a computer program product that stores a computer program that, when executed by a processor, implements the above-described method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions.

[0029] This application's embodiments can establish design variables, constraints, and objective functions for wind farm optimization models in high-altitude and cold regions. By combining improved genetic strategies for global optimization with sequential least squares programming for location optimization, it balances global search capabilities and local optimization, yielding the final optimized layout of multi-type wind turbine units in the wind farm. This provides scientific and technical support for wind farm planning in high-altitude and cold regions. Therefore, it solves the problems in related technologies where single optimization algorithms struggle to balance global search capabilities and local optimization effects, and because they only consider location variables, they cannot meet the actual needs of wind farm planning in high-altitude and cold regions.

[0030] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0031] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart illustrating a method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions, according to an embodiment of this application. Figure 2This is a flowchart of a method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions, according to an embodiment of this application. Figure 3 This is a schematic diagram of a multi-type wind turbine hybrid layout optimization device for wind farms in high-altitude and cold regions, provided according to an embodiment of this application. Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application.

[0032] Figure label: 10-Optimization device for mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions; 100-First establishment module, 200-Second establishment module, 300-Optimization module; 401-Memory, 402-Processor, 403-Communication interface. Detailed Implementation

[0033] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0034] The following describes, with reference to the accompanying drawings, an embodiment of the present application's method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions. Addressing the problems mentioned in the background art, where single optimization algorithms struggle to balance global search capabilities and local optimization effects, and only consider location variables, thus failing to meet the practical needs of wind farm planning in high-altitude and cold regions, this application provides a method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions. This method establishes design variables, constraints, and objective functions for the optimization model of the wind farm in high-altitude and cold regions, and combines improved genetic strategies for global optimization with sequential least squares programming for location optimization, balancing global search capabilities and local optimization to obtain the final optimized result of the mixed layout of multiple types of wind turbines for the wind farm, thereby providing scientific and technical support for wind farm planning in high-altitude and cold regions. This solves the problems in the related art where single optimization algorithms struggle to balance global search capabilities and local optimization effects, and only consider location variables, leading to a failure to meet the practical needs of wind farm planning in high-altitude and cold regions.

[0035] Specifically, Figure 1 This is a flowchart illustrating a method for optimizing the mixed layout of multiple types of wind turbines in wind farms in cold regions, as provided in an embodiment of this application.

[0036] like Figure 1 As shown, the method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions includes the following steps: In step S101, at least one design variable is established for the optimization model of wind farms in high-altitude and cold regions, and at least one constraint condition is established for the optimization model of wind farms in high-altitude and cold regions.

[0037] It is understood that the design variables in the embodiments of this application can be decision parameters that can be adjusted during the wind farm layout optimization process, and the constraints can be restrictions imposed on the range of values ​​or interrelationships of the design variables based on actual scenarios such as extreme climate in high-altitude and cold regions and limited space.

[0038] In actual implementation, the embodiments of this application can establish design variables such as the number of wind turbines, type of wind turbines, and location coordinates according to the special requirements of wind farm layout in high-altitude and cold regions. In view of the special characteristics of different types of constraints in wind farms in high-altitude and cold regions, the constraints of the optimization model can be established, which may include, but are not limited to, wind farm boundary constraints, wind turbine spacing constraints, and wind turbine number constraints.

[0039] The embodiments of this application can clearly define the design variables and constraints, providing a complete and realistic mathematical problem framework for subsequent optimization algorithms, ensuring the directionality of the optimization process and the feasibility of the results, and ensuring that the optimization direction is consistent with the actual needs of high-altitude and cold regions.

[0040] Optionally, in one embodiment of this application, at least one of the following design variables includes processing quantity variables using the virtual wind turbine method, setting wind turbine existence variables, setting wind turbine type variables, and setting wind turbine location coordinate variables, and at least one of the following constraints includes wind farm boundary constraints, wind turbine spacing constraints, and wind turbine quantity constraints.

[0041] It is understood that, in the embodiments of this application, the virtual wind turbine method can handle the quantity variable by setting a fixed number of virtual wind turbines and introducing an existence binary variable to indirectly represent the actual number of wind turbines; the existence variable of the wind turbine can be a binary variable; the wind turbine type variable can be a discrete variable; the wind turbine position coordinate variable can include horizontal and vertical coordinates; the wind farm boundary constraint can be applied to all virtual wind turbines to ensure the effectiveness of the search space; the wind turbine spacing constraint can adopt an existence variable activation mechanism, which only applies to active wind turbine pairs and considers the rotor diameter differences of different types of wind turbines; the wind turbine quantity constraint can be achieved by summing the existence variables, effectively controlling the range of the number of active wind turbines.

[0042] For example, the number of wind turbines can be set in the embodiments of this application. ,type and spatial coordinates The number of wind turbines was incorporated into the design variables and optimized. It will affect the type and spatial coordinates The length and index of the variable make it difficult to express the optimization problem. Therefore, the virtual wind turbine method is used to handle the quantity variable. The unified optimization process is achieved by setting existence variables, type variables and location coordinate variables.

[0043] Specifically, the number of wind turbines in a fixed wind farm is a relatively large value. In addition to setting type and spatial location coordinate variables for each wind turbine, an existence variable is introduced to indicate whether it is active. If the existence variable is 0, meaning the wind turbine is set to inactive, it will not be considered when calculating the total wake loss of the wind farm, the total annual power generation, the violation of wind turbine spacing constraints, and the objective function; otherwise, it means the wind turbine is set to active and will be included in the relevant calculations.

[0044] This application embodiment can set a wind turbine existence variable, a wind turbine existence variable Defined as a binary variable:

[0045] , In the formula, For the first Existence variables of typhoon turbines , This represents the total number of virtual wind turbines. By setting an existence variable for wind turbines, the number of wind turbines can be indirectly controlled, effectively solving the problem of variable length and index changes caused by changes in the number.

[0046] This application embodiment can set a wind turbine type variable, and the wind turbine type variable Defined as a discrete variable, representing the first... Typhoon generator model selection: , In the formula, For the first The type variable of the typhoon generator. This represents the total number of available wind turbine types. In high-altitude and cold-weather scenarios, a mixed layout of small wind turbines with different rated power and rotor diameters is considered to fully utilize wind energy resources within limited space. The wind turbine type variable determines the corresponding technical parameters of the wind turbine, including key characteristics such as rated power, rotor diameter, and minimum spacing constraints.

[0047] This application embodiment can set wind turbine position coordinate variables, including horizontal coordinates. and vertical coordinates : , , In the formula: , The first Horizontal and vertical coordinates of a typhoon generator. and These represent the horizontal and vertical boundary ranges of the wind farm, respectively. The wind turbine location coordinates are continuous variables used to determine the specific spatial location of the wind turbines within the wind farm, directly affecting the wake interaction between wind turbines and the overall power generation of the wind farm.

[0048] Furthermore, embodiments of this application can establish constraints on the optimization model, which include three types of constraints: wind farm boundary constraints, wind turbine spacing constraints, and wind turbine quantity constraints. These constraints ensure the engineering feasibility and practical implementability of the optimization solution.

[0049] This application embodiment can establish wind farm boundary constraints based on ensuring that all wind turbine locations are within a designated area of ​​the wind farm. Wind farm boundary constraints, ensuring that all wind turbine locations are within a designated area of ​​the wind farm, can be expressed as:

[0050] In the formula, For point To a given closed curve The minimum distance function of the (wind farm boundary curve) is mathematically expressed as: , In the formula: It is a point to curve The minimum Euclidean distance Denotes the Euclidean norm, i.e. ,in yes The point on; At time, point Inside the curve; At time, point Outside the curve; At time, point In the curve Upper (boundary).

[0051] It is worth noting that the boundary constraints apply to all virtual wind turbines, including those set to be inactive. This setting effectively reduces the likelihood of virtual turbines being placed outside the feasible region, thus improving optimization efficiency.

[0052] This application embodiment can establish wind turbine spacing constraints based on ensuring a preset safe distance between any two active wind turbines. The wind turbine spacing constraints, ensuring a minimum safe distance between any two active wind turbines, can be expressed as: , In the formula, and Wind turbine and wind turbine Existence variables, Spacing constraint function: , In the formula, This is the actual distance. This is the effective distance. The formula for calculating the actual distance is: , The formula for calculating the effective distance is: , In the formula, and They represent wind turbines and The minimum spacing constraint for each corresponding wind turbine type is set to twice the rotor diameter of the wind turbine in high-altitude and cold-weather scenarios. The minimum spacing is determined based on the rotor diameter corresponding to the wind turbine type.

[0053] The spacing constraint between wind turbines is a core constraint in wind farm planning problems in high-altitude and cold regions. This constraint is invalid (automatically satisfied) when the existence variable of either of the two wind turbines is set to 0. When both wind turbines exist, the actual spatial distance between them and the effective minimum spacing are calculated, and it is determined whether the minimum spacing constraint is satisfied. The effective minimum spacing is defined as the arithmetic mean of the minimum spacings of the two wind turbines, avoiding the problems of imposing spacing constraint penalties on inactive wind turbines and applying the same spacing constraint to wind turbines of different sizes.

[0054] This application embodiment can control the range of the number of active wind turbines in a wind farm by summing existence variables, thus establishing a wind turbine quantity constraint. The wind turbine quantity constraint, which controls the range of the number of active wind turbines in a wind farm, can be expressed as: , In the formula, This represents the minimum number of active wind turbines in a wind farm. This indicates the maximum number of active wind turbines in a wind farm. This represents the summation of all existing variables, i.e., the total number of active wind turbines.

[0055] Setting a minimum number of active wind turbines is significant for accelerating optimization, avoiding the problem of slow optimization or getting stuck in local optima due to a large number of inactive wind turbines caused by an insufficient number of turbines in the early stages of optimization. In actual solution processing, the maximum number is usually set to the total number of virtual wind turbines.

[0056] The embodiments of this application can establish design variables based on the virtual wind turbine method, realize unified encoding and processing of variables such as the number, type and location of wind turbines, classify and process different constraints, avoid the problem of applying invalid constraints to inactive wind turbines in traditional methods, improve optimization efficiency, and provide an effective mathematical modeling framework for complex wind farm planning problems in high-altitude and cold regions.

[0057] In step S102, the objective function of the wind farm optimization model in high-altitude and cold regions is established.

[0058] In practical implementation, this application embodiment can study using unit electricity cost as the objective function, comprehensively considering the total cost input and annual total power generation output in high-altitude and cold-region scenarios to optimize economic benefits. Based on capital expenditures and operating expenditures in high-altitude and cold-region environments, an objective function for minimizing unit electricity cost is established, comprehensively considering capital expenditures and operating expenditures. Capital expenditures include polar fixed infrastructure costs, type-related variable costs, and economies of scale.

[0059] The embodiments of this application can establish the objective function of the optimization model of wind farms in high-altitude and cold regions, which can truly reflect the economic benefits and actual engineering needs of wind farms in high-altitude and cold regions, and provide a scientific basis for optimization decision-making.

[0060] Optionally, in one embodiment of this application, the expression for the objective function is: , in, Represents the total cost. This represents the total annual power generation of the wind farm.

[0061] It is understood that the total cost in this application embodiment may include capital expenditures and operating expenditures; the total annual power generation can be obtained through a wind resource calculation model, which takes into account the wake effect, wind resource distribution and wind turbine performance characteristics in high-altitude and cold regions.

[0062] For example, embodiments of this application can comprehensively consider the total cost input and annual total power generation output in high-altitude and cold region scenarios to optimize economic benefits. The objective function expression is: , In the formula, Represents the total cost. Let be the total annual power generation of the wind farm. This objective function optimizes the input-output ratio by minimizing the unit electricity cost.

[0063] Specifically, total annual power generation The wind resource calculation model was used to obtain the total annual power generation, which considers the wake effect, wind resource distribution, and wind turbine performance characteristics in high-altitude and cold regions. The calculation of the total annual power generation involves complex wake loss modeling and wind turbine power characteristic analysis, providing an accurate basis for power generation assessment for the objective function.

[0064] Specifically, the total cost function It includes two parts: capital expenditures and operating expenditures. , In the formula, Indicates capital expenditure, This indicates operating expenses over the product's lifecycle.

[0065] Furthermore, capital expenditures This refers to the one-time investment in project construction, which includes both variable investment and fixed investment. , In the formula, Fixed investment refers to the one-time investment required regardless of the number of wind turbines built, including the total cost of preliminary permafrost geological surveys, transportation of construction equipment, and infrastructure construction such as roads and camps.

[0066] Variable investment This refers to one-time investment costs that are strongly correlated with the number of wind turbines, such as the cost of wind turbine equipment and foundation construction costs. , In the formula, Indicates the first Number of wind turbines of different types Indicates the number of wind turbine types. Indicates the basic unit cost. Indicates the first The basic cost weighting of wind turbine-like generators Indicates the first CAPEX impact factor for different types of wind turbines This indicates the impact of scale effects.

[0067] Scale effect term The calculation formula is: , In the formula, This indicates the total number of active wind turbines. This represents the basic unit cost based on economies of scale. The CAPEX factor represents the scale effect. This is the scale effect decay parameter.

[0068] Furthermore, operating expenses This refers to the periodic expenses incurred in maintaining the daily operation of a wind farm, including maintenance costs for wind turbines in extreme environments and operating costs of anti-icing / de-icing systems. , In the formula, This represents the unit cost of basic operation and maintenance. Indicates the first OPEX impact factor for different types of wind turbines.

[0069] The objective function design fully considers the unique characteristics of wind farm construction and operation in high-altitude and cold regions. By comprehensively balancing one-time investment, operation and maintenance costs, and power generation revenue, it achieves a balance between economic efficiency and engineering feasibility, providing a scientific economic evaluation basis for wind farm planning in high-altitude and cold regions. The embodiments of this application can design an objective function based on the total cost input and annual total power generation output in high-altitude and cold regions, thereby optimizing the input-output ratio, achieving a balance between economic efficiency and engineering feasibility, and providing a scientific economic evaluation basis for wind farm planning in high-altitude and cold regions.

[0070] In step S103, based on at least one design variable, at least one constraint condition and objective function, an improved genetic strategy is used for global optimization to obtain initial optimization results. Based on the initial optimization results, a sequential least squares programming strategy is used for location optimization to obtain the final optimization results of the mixed layout of multiple types of wind turbines in the wind farm.

[0071] It is understood that the improved genetic strategy in the embodiments of this application can be used for global exploration in a complex solution space; the sequential least squares programming strategy can be an efficient local optimization algorithm used for local optimization of the initial optimization results.

[0072] In practical implementation, the embodiments of this application can use a genetic algorithm as the core to establish a complete mixed-integer nonlinear programming model, with the optimization objective being to minimize the unit electricity cost: , All design variables were processed, including wind turbine existence variables, wind turbine type variables, and wind turbine location coordinate variables, with a search space dimension of [dimensionality missing]. ( (This represents the total number of virtual wind turbines). By applying the virtual wind turbine method, the problem of variable length and index changes caused by variations in the number of wind turbines was successfully solved, achieving unified optimization of the number, type, and location of wind turbines.

[0073] The global search mechanism of the genetic algorithm, through operations such as population evolution and crossover mutation, can effectively escape local optima and explore different regions of the search space. After 600 generations of evolutionary optimization, the optimal quantity configuration, type selection, and preliminary location layout of wind turbines are determined, providing a high-quality initial solution for local fine-tuning.

[0074] The output of global optimization includes: , In the formula, To determine the number of active wind turbines, Optimal configuration for each type of wind turbine. , These are the initial position coordinates. This is the optimal configuration for existing variables.

[0075] Furthermore, based on the global optimization results, a sequential least squares programming strategy is employed to perform fine-grained location optimization for active wind turbines. This achieves significant problem dimensionality reduction. 3D search space reduced to Dimension, among which .

[0076] The objective function for local optimization is adjusted to maximize total annual power generation: , in For the first The selection of the objective function for the annual power generation of active wind turbines is based on the following considerations: the first step has determined the optimal number and type configuration of wind turbines, and the second step focuses on finding the optimal spatial layout to maximize power generation efficiency under a fixed configuration.

[0077] The sequential least squares programming strategy utilizes accurate gradient information and the Hessian matrix approximation to achieve high-precision local optimization by solving sequential quadratic programming subproblems. The convergence condition is: , In the formula, For Lagrange functions, To achieve convergence tolerance.

[0078] Furthermore, the existence and type variables determined by the global optimization remain fixed in the local optimization, while the position coordinate variables serve as the initial optimization results for the local optimization: , The set of active wind turbines determined by global optimization The constraint system for local optimization simplifies to: , The global optimization objective of maximizing unit electricity cost is mathematically equivalent to the local optimization objective of maximizing power generation: , The final output of global-local co-optimization is: , in, , These are the final position coordinates after local refinement. For the final unit cost of electricity, This represents the final total annual power generation.

[0079] Algorithm performance was evaluated using the following metrics: Convergence verification: , In the formula, For convergence criteria.

[0080] Constraint satisfaction verification: , Degree of improvement of the solution: .

[0081] The embodiments of this application can effectively solve the problem of solving mixed integer nonlinear programming problems, avoid the defect of a single algorithm being prone to getting trapped in local optima, improve the economy and reliability of the final layout scheme, and significantly improve the optimization accuracy and computational efficiency while ensuring the globality of the solution, thus realizing the efficient solution of mixed integer nonlinear programming problems in wind farms in high-altitude and cold regions.

[0082] Optionally, in one embodiment of this application, an improved genetic strategy is used for global optimization, including: using a variable type-aware encoding strategy to initialize and encode coordinate variables, existence variables, and type variables respectively to obtain initial processing variables; obtaining convergence results based on tournament selection and elite retention strategies; performing differentiated crossover and mutation processing on the convergence results to obtain an initial solution; and using a combination of objective function and constraint violation penalty function to evaluate the fitness of the initial solution to determine the initial optimization result.

[0083] It is understood that the variable type-aware encoding strategy in this application embodiment can be to adopt different encoding methods according to the type of the design variable to ensure that the encoding can accurately convey variable information; tournament selection can be to select excellent individuals by randomly selecting a portion of individuals to compete; elite retention can be to directly retain the best individuals in each generation to improve convergence efficiency; differentiated crossover and mutation can be to implement multi-point crossover and standard mutation on wind turbine coordinate variables, and selective crossover and reinforcement mutation on wind turbine existence variables and wind turbine type variables; constraint violation penalty function can be to impose penalties on individuals that violate constraints, reduce their fitness, and ensure that the optimization results meet the constraint conditions.

[0084] In practical implementation, the embodiments of this application can employ an improved genetic algorithm for global optimization, aiming to minimize the unit electricity cost, and comprehensively optimize the variables of wind turbine existence, wind turbine type, and wind turbine location coordinates. The genetic algorithm achieves efficient solutions to mixed-integer nonlinear programming problems by simulating phenomena such as gene replication, gene recombination, gene mutation, and natural selection in biological evolution.

[0085] Specifically, a variable type-aware coding strategy is adopted to initialize and encode the wind turbine coordinate variables, wind turbine existence variables, and wind turbine type variables separately. Considering the characteristics of wind farm layout optimization problems, which include both continuous and discrete variables, a unified binary coding mechanism is designed. Each wind turbine's existence and type variables are represented by one binary bit, while the location coordinate variable is represented by eight binary bits, providing 256 discretization levels.

[0086] For continuous variables In the interval Inside, use When encoding bits, the formula for calculating the quantization interval is: , The formula for converting a real number to an integer index is: , Include The chromosome structure of a typhoon turbine is represented as follows: , In the formula, the superscript indicates the number of bits, and the total chromosome length is... Bits. This encoding strategy enables a unified representation of different types of design variables, providing a consistent operation object for crossover, mutation, and other operations in genetic algorithms.

[0087] The embodiments of this application can obtain convergence results based on tournament selection and elite retention strategies, and then perform differential crossover mutation processing on the convergence results to obtain an initial solution.

[0088] Specifically, an improved tournament selection strategy is adopted, combining population shuffling and dynamic competition size mechanisms. For each position in the population, three candidate individuals are randomly selected to compete, and the individual with the best fitness is selected to enter the next generation.

[0089] When the number of unique fitness values ​​in the population is less than one-third of the total population size, increase the tournament size from 3 to 5: , In the elite retention strategy, the number of elite individuals is set to 2% of the population size, with a minimum of 1 and a maximum of 3. , At the same time, a 5% random selection probability is introduced to maintain population diversity and prevent excessive convergence.

[0090] Furthermore, a cross-strategy based on variable structure awareness is designed to implement differentiated treatment for different types of design variables.

[0091] For coordinate variables, an adaptive multi-point intersection is used, with the number of intersection points being 10% of the total number of bits. , For discrete variables, selective crossover is used, with a maximum crossover ratio of 25% of the total number of variables. , The mutation strategy employs a hierarchical mechanism, with standard mutation probabilities used for coordinate variables. Existence variables are represented by enhanced mutation probabilities: , The mutation probability of the type variable is set as follows: , The differentiation mechanism fully considers the hierarchy of importance of different variable types on system performance, achieving a balanced exploration of the algorithm across different search dimensions. The core parameters of the genetic algorithm can be set as follows: population size of 400 individuals, maximum number of generations of evolution of 600, crossover probability of 0.6, and mutation probability of 0.004, ensuring the algorithm's search efficiency and convergence quality.

[0092] The embodiments of this application can use a combination of objective function and constraint violation penalty function to evaluate the fitness of the initial solution and determine the initial optimization result.

[0093] Specifically, the fitness evaluation adopts a combination of the objective function value and the constraint violation penalty function: , In the formula, The return value of the objective function. To constrain the penalty function for violations.

[0094] The constraint violation penalty function uses an external penalty method: , In the formula, For penalty parameters, As a penalty index, For the first Constraint functions.

[0095] To address the constraint on the number of wind turbines, an exponentially enhanced penalty is employed: , The penalty mechanism effectively avoids the occurrence of low-quality solutions with too few wind turbines, ensuring the engineering feasibility of the solution during the optimization process.

[0096] The embodiments of this application can effectively handle the complexity of mixed integer nonlinear programming problems by using a variable type-aware encoding strategy, a differentiated crossover and mutation mechanism, and an improved fitness evaluation method designed for genetic algorithms, thereby achieving a significant improvement in algorithm performance.

[0097] Optionally, in one embodiment of this application, location optimization is performed using a sequential least squares programming strategy based on the initial optimization results, including: selecting an active wind turbine set based on the initial optimization results, performing dimensionality reduction on the location coordinate variables in the active wind turbine set; calculating the gradient of the objective function using automatic differentiation, and performing location optimization using a sequential least squares programming strategy based on the gradient of the objective function.

[0098] It is understood that in the embodiments of this application, the set of active wind turbines can be the actual units with an existence variable of 1 in the initial optimization results; dimensionality reduction can be the removal of location coordinate variables other than active units to reduce computational complexity; automatic differentiation can be an efficient method for calculating the gradient of a function, which can accurately obtain the partial derivative of the objective function with respect to the location coordinate variables and provide gradient information for sequential least squares programming.

[0099] For example, embodiments of this application can employ a sequential least squares programming algorithm to perform fine-grained location optimization on active wind turbines determined by a genetic algorithm. In local optimization, the optimization objective is adjusted to maximize the total annual power generation, achieving a significant reduction in problem size and a substantial improvement in computational efficiency.

[0100] The mathematical expression of the optimization problem is as follows: , In the formula, The number of active wind turbines determined for global optimization. This represents the total annual power generation of the wind farm.

[0101] Specifically, based on the initial optimization results, a set of active wind turbines is obtained, and the location coordinate variables in the active wind turbine set are subjected to dimensionality reduction processing. Based on the optimization results, the system automatically selects wind turbines with an existence variable of 1, and determines them as the set of active wind turbines. , In the formula, For the set of indexes of active wind turbines, For the first The existence variables of typhoon turbines. The type of active wind turbines remains fixed, and only the location coordinates of their wind turbines are optimized.

[0102] Local optimization achieves significant dimensionality reduction of design variables, 3D search space ( Typhoon generator , , , Dimensionality reduction of variables dimension( Taiwan active wind turbine , (coordinates), where .

[0103] The reduced-dimensional design variable vector representation is as follows: , This selective optimization strategy significantly improves optimization efficiency, enabling sequential least squares programming to achieve high-precision local optimization in a short time.

[0104] Furthermore, automatic differentiation is used to calculate the gradient of the objective function. Based on the gradient of the objective function, a sequential least squares programming algorithm is used for position optimization. The efficiency of the sequential least squares programming algorithm depends on accurate gradient information. By integrating automatic differentiation technology, the gradient of the objective function can be accurately calculated. , Automatic differentiation technology automatically calculates the derivative of composite functions using the chain rule, avoiding the truncation error of numerical differentiation and the complexity of sign differentiation. In wind farm physical models, the annual power generation function involves complex wake effect calculations, and automatic differentiation technology provides reliable technical support for gradient optimization.

[0105] Specifically, the constraint system for local optimization has been specifically simplified, focusing on the physical constraints of active wind turbines. The constraints include: Wind farm boundary constraints are used to ensure that all active wind turbine locations are within a designated area of ​​the wind farm: , Wind turbine spacing constraints are used to ensure that a minimum safe distance is met between any two active wind turbines: , The sequential least squares programming algorithm uses the interior-point method to handle constraints, incorporating them into the objective function through Lagrange multipliers. In each iteration, the algorithm simultaneously updates the design variables and the Lagrange multipliers, ensuring that constraint satisfaction and objective function optimization occur concurrently. The Lagrange function is expressed as: , In the formula, and Let be the Lagrange multiplier vectors for equality constraints and inequality constraints, respectively. and These are the equality constraint and inequality constraint functions, respectively.

[0106] The sequential least squares programming algorithm obtains the optimal solution by solving the KKT conditions: , The parameters for the sequential least squares programming algorithm can be configured as follows: maximum number of iterations 200, convergence tolerance... The parameter settings are determined based on a large number of numerical experiments, which can control the computation time while ensuring convergence quality. The sequential least squares programming algorithm usually converges within 100 iterations, and the convergence curve exhibits a typical exponential decay characteristic.

[0107] The embodiments of this application can screen active units and perform dimensionality reduction, reduce the amount of computation in the location optimization stage, improve computational efficiency, and accurately obtain the gradient of the objective function through automatic differentiation, providing reliable gradient information for sequential least squares programming, and efficiently realize local refinement of location variables, thereby further improving the economy and power generation performance of the layout scheme on the basis of initial optimization.

[0108] Specifically, it can be combined with Figure 2 As shown, a specific embodiment is used to elaborate in detail on the working principle of the multi-type wind turbine hybrid layout optimization method for wind farms in high-altitude and cold regions in this application.

[0109] like Figure 2As shown in the embodiment of this application, wind resource data and wind farm boundary conditions in high-altitude and cold regions can be input. Then, a comprehensive optimization model is constructed, which includes design variables (location, type, existence), constraints (boundary, spacing, quantity constraints), and an objective function (minimizing unit electricity cost).

[0110] Specifically, a global-local hybrid optimization is performed. Global optimization uses a genetic algorithm, first initializing and encoding the population, then evaluating convergence using a fitness test with constraints. If convergence fails, selection, crossover, and mutation operations are performed, repeating this process until convergence, at which point the global solution is output. Local optimization uses the SLSQP algorithm, receiving the global solution and fixing its existence and type, performing fine-tuning on the location variables, and then applying gradient optimization and constraint processing to output the local solution.

[0111] Furthermore, the local solutions are decoded to output the optimal optimization scheme, including the number of wind turbines, the type of wind turbines, and the location of the wind turbines.

[0112] The method for optimizing the mixed layout of multiple types of wind turbines in wind farms in high-altitude and cold regions, as proposed in this application, can establish the design variables, constraints, and objective function of the optimization model for wind farms in high-altitude and cold regions. It combines improved genetic strategy global optimization with sequential least squares programming for location optimization, taking into account both global search capability and local optimization, to obtain the final optimized result of the mixed layout of multiple types of wind turbines in the wind farm. This provides scientific and technical support for the planning of wind farms in high-altitude and cold regions. Therefore, it solves the problem in related technologies where a single optimization algorithm cannot simultaneously consider global search capability and local optimization effect, and only considers location variables, thus failing to meet the actual needs of wind farm planning in high-altitude and cold regions.

[0113] Next, referring to the accompanying drawings, a hybrid layout optimization device for multi-type wind turbine units for wind farms in high-altitude and cold regions, proposed according to an embodiment of this application, is described.

[0114] Figure 3 This is a schematic diagram of the structure of the multi-type wind turbine hybrid layout optimization device for wind farms in high-altitude and cold regions, according to an embodiment of this application.

[0115] like Figure 3 As shown, the multi-type wind turbine hybrid layout optimization device 10 for wind farms in high-altitude and cold regions includes: a first establishment module 100, a second establishment module 200, and an optimization module 300.

[0116] The first establishment module 100 is used to establish at least one design variable for the optimization model of wind farms in high-altitude and cold regions, and to establish at least one constraint condition for the optimization model of wind farms in high-altitude and cold regions.

[0117] The second module 200 is used to establish the objective function of the wind farm optimization model in high-altitude and cold regions.

[0118] The optimization module 300 is used to perform global optimization based on at least one design variable, at least one constraint, and an objective function using an improved genetic strategy to obtain initial optimization results. Based on the initial optimization results, it uses a sequential least squares programming strategy to perform location optimization, and finally obtains the optimization results of the mixed layout of multiple types of wind turbines in the wind farm.

[0119] Optionally, in one embodiment of this application, the expression for the objective function is: , in, Represents the total cost. This represents the total annual power generation of the wind farm.

[0120] Optionally, in one embodiment of this application, at least one of the following design variables includes processing quantity variables using the virtual wind turbine method, setting wind turbine existence variables, setting wind turbine type variables, and setting wind turbine location coordinate variables, and at least one of the following constraints includes wind farm boundary constraints, wind turbine spacing constraints, and wind turbine quantity constraints.

[0121] Optionally, in one embodiment of this application, the optimization module 300 includes: an encoding unit, a processing unit, and an evaluation unit.

[0122] The encoding unit is used to initialize the coordinate variables, existence variables, and type variables using a variable type-aware encoding strategy to obtain the initial processing variables.

[0123] The processing unit is used to obtain convergence results based on tournament selection and elite retention strategies, and to perform differential crossover mutation processing on the convergence results to obtain the initial solution.

[0124] The evaluation unit is used to evaluate the fitness of the initial solution by using a combination of the objective function and the constraint violation penalty function, and to determine the initial optimization result.

[0125] Optionally, in one embodiment of this application, the optimization module 300 includes a dimensionality reduction unit and a calculation unit.

[0126] The dimensionality reduction unit is used to filter out the set of active wind turbines based on the initial optimization results and perform dimensionality reduction processing on the location coordinate variables in the set of active wind turbines.

[0127] The computational unit is used to calculate the gradient of the objective function using automatic differentiation, and to perform position optimization using a sequential least squares programming strategy based on the gradient of the objective function.

[0128] It should be noted that the explanation of the above-mentioned embodiment of the method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions also applies to the device for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions in this embodiment, and will not be repeated here.

[0129] The multi-type wind turbine hybrid layout optimization device for wind farms in high-altitude and cold regions proposed in this application can establish the design variables, constraints, and objective function of the wind farm optimization model. It combines improved genetic strategy global optimization with sequential least squares programming for location optimization, taking into account both global search capability and local optimization, to obtain the final multi-type wind turbine hybrid layout optimization result for the wind farm. This provides scientific and technical support for wind farm planning in high-altitude and cold regions. Therefore, it solves the problem in related technologies where a single optimization algorithm cannot simultaneously consider global search capability and local optimization effect, and only considers location variables, thus failing to meet the actual needs of wind farm planning in high-altitude and cold regions.

[0130] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0131] When the processor 402 executes the program, it implements the method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions provided in the above embodiments.

[0132] Furthermore, electronic devices also include: Communication interface 403 is used for communication between memory 401 and processor 402.

[0133] The memory 401 is used to store computer programs that can run on the processor 402.

[0134] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0135] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0136] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0137] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0138] This embodiment also provides a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for optimizing the hybrid layout of multiple types of wind turbines for wind farms in high-altitude and cold regions.

[0139] This application also provides a computer program product storing a computer program that, when executed by a processor, implements the above-described method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions.

[0140] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0141] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0142] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0143] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0144] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0145] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0146] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0147] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for optimizing the hybrid layout of multiple types of wind turbine units in wind farms located in high-altitude and cold regions, characterized in that, Includes the following steps: Establish at least one design variable for the optimization model of wind farms in high-altitude and cold regions, and establish at least one constraint condition for the optimization model of wind farms in high-altitude and cold regions; Establish the objective function of the optimization model for the wind farm in the high-altitude cold region; Based on the at least one design variable, the at least one constraint, and the objective function, an improved genetic strategy is used for global optimization to obtain initial optimization results. Based on the initial optimization results, a sequential least squares programming strategy is used for location optimization to obtain the final optimization results of the mixed layout of multiple types of wind turbines in the wind farm.

2. The method according to claim 1, characterized in that, The expression for the objective function is: ， in, Represents the total cost. This represents the total annual power generation of the wind farm.

3. The method according to claim 1, characterized in that, The at least one design variable includes at least one of the following: using the virtual wind turbine method to handle quantity variables, setting wind turbine existence variables, setting wind turbine type variables, and setting wind turbine location coordinate variables; and the at least one constraint includes at least one of the following: wind farm boundary constraints, wind turbine spacing constraints, and wind turbine quantity constraints.

4. The method according to claim 3, characterized in that, The global optimization using the improved genetic strategy includes: A variable type-aware encoding strategy is adopted to initialize the coordinate variable, the existence variable, and the type variable respectively to obtain the initial processing variable; Based on the tournament selection and elite retention strategy, a convergence result is obtained. The convergence result is then subjected to differential crossover mutation processing to obtain an initial solution. The fitness of the initial solution is evaluated by using a combination of the objective function and the constraint violation penalty function to determine the initial optimization result.

5. The method according to claim 1, characterized in that, The step of optimizing the position using a sequential least squares programming strategy based on the initial optimization results includes: Based on the initial optimization results, an active wind turbine set is obtained, and the location coordinate variables in the active wind turbine set are subjected to dimensionality reduction processing. The gradient of the objective function is calculated using automatic differentiation, and the position is optimized based on the gradient of the objective function using the sequential least squares programming strategy.

6. A device for optimizing the hybrid layout of multiple types of wind turbine units for wind farms in high-altitude and cold regions, characterized in that, include: The first module is used to establish at least one design variable for the optimization model of wind farms in high-altitude and cold regions, and to establish at least one constraint condition for the optimization model of wind farms in high-altitude and cold regions. The second module is used to establish the objective function of the wind farm optimization model in the high-altitude cold region. The optimization module is used to perform global optimization using an improved genetic strategy based on the at least one design variable, the at least one constraint, and the objective function to obtain initial optimization results, and then to perform location optimization using a sequential least squares programming strategy based on the initial optimization results to obtain the final optimization results of the mixed layout of multiple types of wind turbines in the wind farm.

7. The apparatus according to claim 6, characterized in that, The expression for the objective function is: ， in, Represents the total cost. This represents the total annual power generation of the wind farm.

8. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for optimizing the hybrid layout of multiple types of wind turbines for wind farms in high-altitude and cold regions as described in any one of claims 1-5.

9. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions as described in any one of claims 1-5.

10. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the method for optimizing the mixed layout of multiple types of wind turbines for wind farms in high-altitude and cold regions as described in any one of claims 1-5.

Images