Distributed wind power site selection and optimization method, system, equipment and medium

Abstract

The invention discloses a distributed wind power site selection and optimization method, system and device and a medium, and the method comprises the steps: obtaining wind resource data of a candidate wind power plant region, and building a multi-factor physical model; constructing a multi-factor wind field site selection model, and calculating optimal solutions of total power generation power maximization and total power generation cost minimization; and determining an optimal site selection scheme by combining the model optimal solution, wind resource distribution and topographic conditions. By improving the reserved suboptimal solution of the NSGA2 algorithm and dynamically adjusting the crossover and mutation probability, the population diversity is effectively maintained, the global search ability is enhanced, and a decision maker is supported to select the optimal layout; wind resource characteristics are comprehensively quantified through a multi-factor physical model, and the physical accuracy of site selection analysis is improved; through model hypothesis, the model complexity is reduced on the premise of ensuring the reliability, and the calculation efficiency is improved; the balance between economical efficiency and power generation efficiency is realized by taking minimization of power generation cost and maximization of power generation power as targets through a multi-factor wind field site selection model.

Description

Technical Field

[0001] The present invention relates to the technical field of wind farm site selection and optimization, and in particular to a distributed wind farm site selection and optimization method, system, equipment and medium. Background Art

[0002] In recent years, distributed wind power site selection and multi-objective optimization technology have become research hotspots in the field of new energy planning. The optimization of wind farm site selection and layout requires not only comprehensive consideration of wind resource distribution, terrain conditions and meteorological environment, but also finding a balance between power generation efficiency and cost. In addition, the wake effect, as an important influencing factor in the layout of wind farms, will significantly reduce the power generation of downstream wind turbines, affecting the economy and operating life of the entire wind farm. How to reduce the negative impact of the wake effect on power generation efficiency and further improve the overall power generation efficiency of the wind farm is a difficulty in current research.

[0003] Traditional methods primarily employ qualitative methods such as the Analytic Hierarchy Process (AHP) or fuzzy comprehensive evaluation, combined with geographic information systems (GIS) for initial site screening. However, these methods employ a single optimization dimension and rely on expert experience. With breakthroughs in multi-objective evolutionary algorithms, the non-dominated sorting genetic algorithm (NSGA2) has been introduced into the field of wind farm optimization due to its Pareto frontier construction capabilities. This algorithm can simultaneously optimize objectives such as power generation efficiency, construction costs, and environmental impact. Existing research has achieved preliminary quantitative site selection analysis by coupling wake effect models, terrain correction factors, and economic constraints, and has attempted to integrate vertical wind speed distribution models, such as power-law models, with atmospheric thermodynamic parameters. However, existing technologies are still insufficient in modeling the coupling mechanisms of complex meteorological parameters, and the traditional NSGA2 algorithm is prone to falling into local optimality during solution, resulting in a decrease in the diversity of the solution set.

[0004] Current decentralized wind power site selection methods exist. The traditional multi-factor wind farm site selection model oversimplifies the coupling relationship between wind resource parameters, resulting in large errors in power generation potential assessment. The traditional NSGA2 algorithm suffers from population diversity degradation under dynamic constraint scenarios, resulting in uneven distribution of the Pareto frontier. The existing site selection model lacks a spatial correlation model for constructing the coordinated layout of wind farm groups and transmission costs, resulting in large deviations in transmission loss calculations. In contrast, the present invention achieves precise coupling calculations by integrating multi-factor physical models, and combines the retained suboptimal solution of the improved NSGA2 algorithm with the crossover probability adaptive adjustment mechanism, thereby improving the coverage of the Pareto solution set and enhancing economic constraints. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a distributed wind power site selection and optimization method and system to solve the following problems: the existing distributed wind power site selection optimization method relies on subjective experience judgment, resulting in insufficient model objectivity, the traditional NSGA2 algorithm is prone to premature convergence, and the meteorological parameter coupling modeling is imperfect; and how to achieve efficient collaborative optimization of minimizing power generation costs and maximizing power generation power.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a distributed wind power site selection and optimization method, including: obtaining wind resource data of a candidate wind farm area, establishing a multi-factor physical model based on the characteristics of the wind resource data; constructing a multi-factor wind farm site selection model, calculating the optimal solution for maximizing total power generation and minimizing total power generation cost; and determining the optimal site selection plan based on the model's optimal solution, wind resource distribution, and terrain conditions.

[0009] As a preferred solution of the distributed wind power site selection and optimization method described in the present invention, the obtaining of wind resource data of the candidate wind farm area includes collecting historical wind speed, air pressure and temperature data of the candidate area through meteorological monitoring equipment and verifying the reliability of the data.

[0010] As a preferred solution of the distributed wind power site selection and optimization method described in the present invention, the multi-factor physical model includes a wind speed logarithmic model, an air pressure density model, a linear temperature gradient model and a power output model.

[0011] As a preferred solution of the distributed wind power site selection and optimization method described in the present invention, the method includes: establishing a multi-factor physical model includes establishing a multi-factor physical model based on wind resource data characteristics through model assumptions; establishing a wind speed logarithmic model through a logarithmic wind speed profile formula based on the logarithmic relationship between wind speed and altitude in the troposphere; establishing a pressure density model by deducing the relationship between surface air pressure and altitude; estimating the temperature at different altitudes based on the temperature gradient and surface temperature, and establishing a linear temperature gradient model; and establishing a power output model based on the power coefficient curve of the wind turbine.

[0012] As a preferred solution of the distributed wind power site selection and optimization method described in the present invention, the following comprises: the model assumptions include assuming that the spatiotemporal statistical characteristics of wind speed and wind direction are stable, the surface roughness is uniform and stable, the technical parameters of the wind turbine are fixed, and the meteorological data are reliable and available.

[0013] As a preferred solution of the distributed wind power site selection and optimization method described in the present invention, the method includes: constructing a multi-factor wind farm site selection model includes constructing a multi-factor wind farm site selection model with the total power generation power and power generation cost of the wind farm as the objective function.

[0014] As a preferred solution of the distributed wind power site selection and optimization method described in the present invention, the following comprises: the calculation of the optimal solution for maximizing the total generated power and minimizing the total generated power cost comprises using an improved NSGA2 algorithm to calculate the multi-factor wind farm site selection model to obtain a frontier solution for maximizing the total generated power and minimizing the total generated power cost; the improved NSGA2 algorithm comprises retaining suboptimal solutions and dynamically adjusting crossover and mutation probabilities.

[0015] In a second aspect, the present invention provides a distributed wind power site selection and optimization system, comprising: a data processing module, a target optimization module, and a site determination module; the data processing module is used to obtain wind resource data of a candidate wind farm area and establish a multi-factor physical model based on the characteristics of the wind resource data; the target optimization module is used to construct a multi-factor wind farm site selection model and calculate the optimal solution for maximizing total power generation and minimizing total power generation cost; the site determination module is used to determine the optimal site selection plan based on the model optimal solution, wind resource distribution, and terrain conditions.

[0016] In a third aspect, the present invention provides an electronic device, comprising:

[0017] memory and processor;

[0018] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the distributed wind power site selection and optimization method are implemented.

[0019] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the distributed wind power site selection and optimization method.

[0020] Compared with the existing technology, the present invention has the following beneficial effects: the present invention effectively maintains population diversity and enhances global search capabilities by improving the NSGA2 algorithm to retain suboptimal solutions and dynamically adjust crossover and mutation probabilities. The improved algorithm can generate more evenly distributed Pareto frontier solutions, provide richer multi-objective trade-off solutions, and support decision makers in selecting the optimal layout based on wind resource distribution and terrain conditions; by integrating wind speed logarithmic models, air pressure density models, linear temperature gradient models and power output models, the wind resource characteristics are comprehensively quantified, and the physical accuracy of site selection analysis is improved; through model assumptions, the model complexity is reduced and the computational efficiency is improved while ensuring reliability; through a multi-factor wind farm site selection model with the goal of minimizing power generation costs and maximizing power generation power, a balance between economy and power generation efficiency is achieved; through precise site selection and layout optimization, the present invention reduces the impact of wake effects, maximizes power generation per unit area, promotes the efficient use of clean energy, and accelerates the realization of the "carbon neutrality" goal. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 The figure is a schematic diagram of the overall process of a distributed wind power site selection and optimization method according to an embodiment of the present invention.

[0023] Figure 2 The figure is a schematic diagram of the overall process of a distributed wind power site selection and optimization system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0025] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a distributed wind power site selection and optimization method, comprising:

[0026] S1: Obtain wind resource data for the candidate wind farm area and establish a multi-factor physical model based on the characteristics of the wind resource data;

[0027] S2: Construct a multi-factor wind farm site selection model to calculate the optimal solution for maximizing total power generation and minimizing total power generation cost;

[0028] S3: Determine the best site selection plan based on the model optimization solution, wind resource distribution and terrain conditions.

[0029] It should be noted that with the rapid growth of global energy demand and the rapid development of clean energy technology, wind energy as an important renewable energy source has received more and more attention. The construction of wind farms can not only effectively reduce greenhouse gas emissions, but also reduce dependence on fossil energy and promote the realization of "carbon peak" and "carbon neutrality" goals. However, the site selection and optimal layout of wind farms are key issues affecting the efficiency of wind energy development; therefore, the site selection and optimization of wind farms are very important for wind energy development.

[0030] Therefore, in response to the above-mentioned wind farm site selection and optimization problems, through steps S1-S3, a multi-factor physical model is established to achieve accurate coupling calculation of air density-power output; a multi-factor wind farm site selection model is constructed to achieve efficient coordination of power generation cost and power generation; and the optimal site selection plan is determined to achieve accurate site selection and layout optimization of wind farms.

[0031] Example 2, reference Figure 1 , which is an embodiment of the present invention, provides a distributed wind power site selection and optimization method based on the above embodiment.

[0032] In an embodiment of the present application, obtaining wind resource data of a candidate wind farm area in step S1 includes collecting historical wind speed, air pressure, and temperature data of the candidate area through meteorological monitoring equipment, and verifying the reliability of the data.

[0033] In an optional embodiment, the wind resource data of the wind farm area obtained in step S1 can also be monitored at multiple height levels by deploying wind towers. Professional wind towers are installed in candidate areas, and the towers are equipped with multiple sets of anemometers, wind vanes, temperature sensors, and barometers, which are respectively set at different heights. Vertical wind profile data are obtained through continuous monitoring, and the height-wind speed relationship is verified in combination with a logarithmic wind speed model. Data reliability is guaranteed by cross-checking redundant sensors and spatial interpolation of adjacent tower data.

[0034] In another optional embodiment, the wind resource data of the wind farm area obtained in step S1 can also be obtained by coupling the mesoscale data meteorological model with satellite remote sensing inversion, using the WRF model to perform high-resolution simulation of the candidate area, and generating a time series 3D wind resource data set through the CALIPSO satellite's lidar vertical wind field data.

[0035] In the embodiment of the present application, establishing the multi-factor physical model in step S1 includes the following steps A1-A5:

[0036] A1: Establish a multi-factor physical model based on wind resource data characteristics through model assumptions;

[0037] A2: Based on the logarithmic relationship between wind speed and height in the troposphere, a logarithmic wind speed model is established using the logarithmic wind speed profile formula;

[0038] A3: Develop a pressure-density model based on the relationship between surface air pressure and altitude.

[0039] A4: Estimate the temperature at different heights based on the temperature gradient and surface temperature, and establish a linear temperature gradient model;

[0040] A5: Based on the power coefficient curve of the wind turbine, establish a power output model.

[0041] It should be noted that the multi-factor physical model includes a wind speed logarithmic model, an air pressure density model, a linear temperature gradient model, and a power output model; the model assumptions include the assumption that the spatiotemporal statistical characteristics of wind speed and direction are stable, the surface roughness is uniform and stable, the technical parameters of wind turbines are fixed, and meteorological data are reliable and available.

[0042] Specifically, in step A1, the model assumes that the statistical characteristics of wind speed and direction in the site selection area are stable in space and time, which means that the wind speed distribution and wind direction frequency in the site selection area will not change drastically. The potential power generation capacity of the wind farm can be estimated based on historical meteorological data or wind energy resource assessment reports.

[0043] The model assumes that the surface roughness of the site area is uniform and stable throughout the area. This assumption simplifies the impact of topography on wind speed distribution and allows the wind speed distribution of the wind farm to be estimated using a uniform surface roughness value;

[0044] The model assumes that the technical parameters of the wind turbines used are fixed and does not consider changes in these parameters, including but not limited to cut-in wind speed, rated wind speed, and cut-out wind speed. By fixing these parameters, the model can estimate the power output of the wind farm based on wind speed.

[0045] The model assumes that reliable meteorological data are available, including but not limited to wind speed, temperature, air pressure, etc. These data are key data for wind farm site selection and power generation potential assessment.

[0046] In step A2, the logarithmic wind speed model is a model that describes the change of wind speed with height. The expression of the logarithmic wind speed model is expressed as:

[0047] V=V ref ×(ln(h / n0) / ln(h ref / n0))

[0048] Where V represents the wind speed at height h, V ref represents the wind speed at the reference height, h represents the measurement height, n0 represents the surface roughness, h ref Indicates the reference altitude;

[0049] Natural logarithm (ln(h / n0) / ln(h ref / n0)) describes the logarithmic ratio of wind speed to height;

[0050] In step A3, the pressure-density model is a model used to calculate the change of air density with altitude. The expression of the pressure-density model is expressed as:

[0051]

[0052] Where ρ represents the air density at height h, ρ ref represents the air density at the reference height, M represents the average molar mass of air molecules, g represents the acceleration due to gravity, R represents the gas constant, and T represents the temperature at the height h;

[0053] Exponential function describes the decay rate as a function of altitude;

[0054] In step A4, the linear temperature gradient model is a simplified atmospheric temperature distribution model. The expression of the linear temperature gradient model is expressed as:

[0055] T=T ref +L×(hh ref )

[0056] Among them, T ref represents the temperature at the reference plane, L represents the temperature gradient, that is, the rate of temperature change corresponding to a unit height change;

[0057] In step A5, the power output model is used to estimate the power output model of the wind turbine at different wind speeds. The expression of the power output model is expressed as:

[0058] P=0.5×ρ×A×Cp×V 3

[0059] Where P represents the power output of the wind turbine at a height of h, A represents the blade area of the wind turbine, and C p It represents the power coefficient, that is, the efficiency of converting wind energy into mechanical energy;

[0060] In the embodiment of the present application, constructing the multi-factor wind farm site selection model in step S2 includes constructing the multi-factor wind farm site selection model with the total generated power and generation cost of the wind farm as objective functions.

[0061] Specifically, the total power generation of the wind farm is expressed as:

[0062]

[0063] Among them, Total_Power represents the total power generated by the wind farm, n_ws represents the number of wind farms, Power_ws t represents the power generation of the t-th wind farm;

[0064] Power_ws of wind farm t t , expressed as:

[0065]

[0066] Among them, n_type represents the number of wind turbine models in the wind farm, n_wt represents the number of wind turbines of a certain type, and P_mean l represents the average output power of the l-th type wind turbine;

[0067] Among them, P_mean l It is calculated by the power output model;

[0068] The total power generation cost consists of the construction cost of the wind farm and the power transmission cost. The construction cost of the wind farm, Cost_ws, is expressed as:

[0069]

[0070] Among them, Cost l represents the construction cost of the l-th type wind turbine;

[0071] The power transmission cost Cost_power is related to the distance between wind farms. The distance between the wind energy distribution location and the use location is optimized to the distance between wind farms. The power transmission cost is expressed as:

[0072]

[0073] Where c represents the transmission cost per kilowatt per kilometer, dis t,t0 represents the distance between wind farm No. t and wind farm No. t0;

[0074] Total power generation cost Total_Cost, expressed as:

[0075] Total_Cost=Cost_ws+Cost_power

[0076] The overall optimization goal of the multi-objective model is to minimize the total power generation cost Total_Cost and maximize the total power generation power Total_Power of the wind farm. The constraints include the number of wind farms n_ws, the number of wind turbine types n_type in the wind farm, and the number of wind turbines of a certain type n_wt, all of which are natural numbers, and the total power generation cost Total_Cost of the wind farm cannot exceed the budget Budget.

[0077] Therefore, the mathematical representation of the multi-factor wind farm site selection model is:

[0078]

[0079] The model achieves the best economic benefits by optimizing the selection of wind farms and the number and type of wind turbines. By reasonably adjusting the location selection of wind farms, the number and type of wind turbines, the goals of reducing the total power generation cost and maximizing the total power generation capacity of the wind farm can be achieved.

[0080] In the embodiment of the present application, calculating the optimal solution for maximizing the total generated power and minimizing the total generated cost in step S2 includes using the improved NSGA2 algorithm to calculate the multi-objective optimization model to obtain the frontier solution for maximizing the total generated power and minimizing the total generated cost.

[0081] The improved NSGA2 algorithm includes retaining suboptimal solutions and dynamically adjusting crossover and mutation probabilities.

[0082] Specifically, when using the NSGA2 algorithm to calculate the multi-factor wind farm site selection model, it is necessary to define the total power generation cost and total power generation as fitness functions to evaluate the fitness of each solution. An iterative search is performed according to the basic steps of NSGA2, which includes initializing the population, non-dominated sorting, crowding distance calculation, selection operations, and genetic operations.

[0083] In each iteration, the individuals in the population are sorted by non-dominated sorting to ensure that excellent solutions can be retained;

[0084] Maintaining the diversity of the population by calculating the crowding distance to ensure that the solutions on the Pareto front can be evenly distributed;

[0085] The selection operation is used to select individuals for the next generation of population, and methods such as tournament selection are usually used for selection;

[0086] Finally, crossover and mutation operations are performed to generate new individuals and add them to the next generation population;

[0087] Through multiple iterative searches, NSGA2 generates a series of non-dominated solutions, representing different trade-offs between total generation cost and total generation power. These solutions constitute the Pareto frontier, providing decision makers with a variety of choices and trade-off opportunities. Based on specific decision-making requirements, the most suitable solution is selected from these solutions as the final wind farm site selection plan.

[0088] When solving the multi-factor wind farm site selection model, the NSGA2 algorithm may face the problem of premature convergence. To solve this problem, an improvement measure is proposed to target the retention strategy of NSGA2;

[0089] In the improved algorithm, the elite retention process no longer directly selects the top N p The optimal individuals are used as the new generation population, and a mixed strategy is adopted. The specific steps are B1-B2:

[0090] B1: From N p Select a part of individuals from ×μ individuals;

[0091] B2: Randomly select the remaining individuals from the suboptimal frontier.

[0092] By randomly selecting individuals on the suboptimal frontier, more diversity is introduced, which improves the exploration ability of the population and helps avoid the problem of premature convergence;

[0093] The improved NSGA2 algorithm can better maintain the diversity of the population when solving the multi-factor wind farm site selection model, thereby improving the algorithm's global search capability. By balancing the ratio of elite individuals and suboptimal solution individuals, the algorithm can better explore the solution space and find a more optimal solution set.

[0094] In an optional implementation, if the number of individuals on the suboptimal frontier is insufficient, a backtracking mechanism is triggered to re-add individuals from the previous generation population that did not converge;

[0095] In another optional embodiment, the crossover operation adopts simulated binary crossover, and the mutation operation adopts polynomial mutation, which is expressed as:

[0096] x new =0.5·[(1+β)·x1+(1-β)·x2]

[0097]

[0098] Among them, x mut represents the gene value of the individual after mutation, x represents the gene value of the original individual, and x max 、x min Represent the upper and lower limits of the gene value, β is the distribution index, To change the asynchronous length;

[0099] When the population diversity index is lower than the threshold of 0.5, the mutation probability is forced to increase to 0.4.

[0100] Example 3, reference Figure 2 The above is a schematic diagram of a distributed wind power site selection and optimization method. It should be noted that the technical solution of this distributed wind power site selection and optimization system and the technical solution of the distributed wind power site selection and optimization method described above are based on the same concept. For details not described in detail in the technical solution of the distributed wind power site selection and optimization system in this embodiment, please refer to the description of the technical solution of the distributed wind power site selection and optimization method described above.

[0101] This embodiment also provides a distributed wind power site selection and optimization system, including: a data processing module, a target optimization module, and a site selection determination module.

[0102] Among them, the data processing module is used to obtain wind resource data in the candidate wind farm area and establish a multi-factor physical model based on the characteristics of wind resource data; the target optimization module is used to construct a multi-factor wind farm site selection model and calculate the optimal solution for maximizing total power generation and minimizing total power generation cost; the site selection determination module is used to determine the optimal site selection plan based on the model's optimal solution, wind resource distribution, and terrain conditions.

[0103] This embodiment also provides an electronic device suitable for distributed wind power site selection and optimization, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the distributed wind power site selection and optimization method proposed in the above embodiment.

[0104] This embodiment further provides a storage medium having a computer program stored thereon. When the program is executed by a processor, the method for implementing the distributed wind power site selection and optimization proposed in the above embodiment is implemented.

[0105] The storage medium proposed in this embodiment and the method for implementing distributed wind power site selection and optimization proposed in the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0106] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general hardware, and of course can also be implemented by hardware. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0107] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A distributed wind power site selection and optimization method, characterized in that: include: Obtain wind resource data for candidate wind farm areas and establish a multi-factor physical model based on the characteristics of wind resource data; Construct a multi-factor wind farm site selection model to calculate the optimal solution for maximizing total power generation and minimizing total power generation costs; The optimal site selection plan is determined by combining the model optimization solution, wind resource distribution and terrain conditions.

2. The distributed wind power site selection and optimization method according to claim 1, characterized in that: The obtaining of wind resource data of the candidate wind farm area includes collecting historical wind speed, air pressure and temperature data of the candidate area through meteorological monitoring equipment and verifying the reliability of the data.

3. The distributed wind power site selection and optimization method according to claim 2, characterized in that: The multi-factor physical model includes a wind speed logarithmic model, an air pressure density model, a linear temperature gradient model and a power output model.

4. The distributed wind power site selection and optimization method according to claim 3, characterized in that: The establishing of the multi-factor physical model includes establishing the multi-factor physical model based on wind resource data characteristics through model assumptions; Based on the logarithmic relationship between wind speed and height in the troposphere, a logarithmic wind speed model is established using the logarithmic wind speed profile formula; The pressure-density model is established based on the relationship between surface air pressure and altitude. According to the temperature gradient and surface temperature, the temperature at different heights is estimated and a linear temperature gradient model is established; Based on the power coefficient curve of the wind turbine, a power output model is established.

5. The distributed wind power site selection and optimization method according to claim 4, characterized in that: The model assumptions include that the spatiotemporal statistical characteristics of wind speed and direction are stable, the surface roughness is uniform and stable, the technical parameters of wind turbines are fixed, and meteorological data are reliable and available.

6. The distributed wind power site selection and optimization method according to claim 5, characterized in that: The constructing of the multi-factor wind farm site selection model includes constructing the multi-factor wind farm site selection model with the total generated power and the generation cost of the wind farm as the objective function.

7. The distributed wind power site selection and optimization method according to claim 6, characterized in that: The calculation of the optimal solution for maximizing the total generated power and minimizing the total generated cost includes using an improved NSGA2 algorithm to calculate a multi-factor wind farm site selection model to obtain a frontier solution for maximizing the total generated power and minimizing the total generated cost; The improved NSGA2 algorithm includes retaining suboptimal solutions and dynamically adjusting crossover and mutation probabilities.

8. A distributed wind power site selection and optimization system, applying the method according to any one of claims 1 to 7, characterized in that: include: Data processing module, target optimization module, site selection module; The data processing module is used to obtain wind resource data of the candidate wind farm area and establish a multi-factor physical model based on the characteristics of the wind resource data; The target optimization module is used to construct a multi-factor wind farm site selection model and calculate the optimal solution for maximizing total power generation and minimizing total power generation cost; The site selection determination module is used to determine the best site selection plan by combining the model optimization solution, wind resource distribution and terrain conditions.

9. An electronic device comprising: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the distributed wind power site selection and optimization method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the distributed wind power site selection and optimization method according to any one of claims 1 to 7.

Images