Dynamic evaluation method for micro-siting of wind power plant based on multi-source data fusion

Abstract

The invention discloses a multi-source data fusion wind power plant micro-siting dynamic evaluation method, relates to the technical field of wind power plant siting, and solves the problem that a mainstream method still depends on single anemometer tower data or static GIS analysis during wind power plant siting in the prior art. The method comprises the following steps: firstly, acquiring wind measurement data of multiple sources, unifying the wind measurement data of different sampling frequencies into a set time window, and realizing spatial scale alignment through an interpolation method; then obtaining a wind energy score according to the annual average wind speed and the main wind direction frequency, obtaining a suitability score according to the distance to the residential area or the main road, obtaining an environmental impact factor according to the noise and the ecological protection area, and constructing a target function based on the wind energy score, the suitability score and the environmental impact factor; and finally, combining a genetic algorithm and a real-time optimization model of a wake flow interference model, and dynamically adjusting the evaluation tendency according to the evaluation score of the fan layout inversion site, so that the evaluation result is more comprehensive, scientific and reasonable.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind farm site selection, in particular to a wind farm micro-site selection dynamic evaluation method based on multi-source data fusion. BACKGROUND

[0002] With the rapid development of the wind power industry, the precision of micro-site selection has become a key factor affecting the power generation efficiency and economy of wind farms. In complex terrain environments, subtle differences in meteorological conditions such as wind speed and direction can have a significant impact on the performance of wind turbines. Precise micro-site selection can ensure that wind turbines are placed in areas with the most abundant and stable wind energy resources, maximizing power generation efficiency. For example, in mountainous wind farms, proper site selection can effectively utilize the terrain's acceleration effect, significantly improving the annual power generation of wind turbines. Conversely, if the site selection is not proper, wind turbines may face problems such as insufficient wind speed or excessive turbulence, resulting in low power generation efficiency and increasing the risk of equipment wear and failure, reducing the economic benefits of wind farms. Therefore, the precision of micro-site selection is crucial for the long-term stable operation and economic benefits of wind farms, and is the foundation for the sustainable development of the wind power industry.

[0003] However, the current mainstream method of wind farm micro-site selection still relies on single wind tower data or static geographic information system (GIS) analysis. Although wind towers can provide relatively accurate meteorological data such as wind speed and direction within a certain area, their coverage is limited and they cannot fully reflect the wind field distribution under complex terrain. Moreover, the construction cost of wind towers is high and the construction period is long, so they can only measure at a limited number of points, resulting in insufficient data representation. Static GIS analysis can perform preliminary site selection evaluation based on geographic information such as terrain and topography, but it ignores the dynamic characteristics of wind fields and cannot reflect the spatio-temporal changes of meteorological elements such as wind speed and direction in real time. This method based on a single data source or static analysis cannot meet the high requirements of wind farm micro-site selection for precision, and it is urgent to introduce more advanced technologies and methods to improve the scientificity and accuracy of site selection.

[0004] Therefore, there is a need for a wind farm micro-site selection dynamic evaluation method based on multi-source data fusion. SUMMARY

[0005] In view of the problem in the prior art that the mainstream method of wind farm site selection still relies on single wind tower data or static GIS analysis, the present application provides a wind farm micro-site selection dynamic evaluation method based on multi-source data fusion, which can evaluate multi-source data fusion, significantly reduce wind resource evaluation errors, and combine genetic algorithm, real-time optimization model of wake interference model in the process of solving site selection objective function, and according to the simulation calculation of wind turbine layout, the evaluation score of the selected site is inversed, the evaluation tendency is dynamically adjusted, and the evaluation result is more comprehensive, scientific and reasonable. The specific technical scheme is as follows:

[0006] A multi-source data fusion wind farm micro-siting dynamic evaluation method, comprising the following steps:

[0007] Obtaining wind data from multiple sources, and unifying wind data of different sampling frequencies to a set time window, and realizing spatial scale alignment through interpolation method;

[0008] According to the average annual wind speed and the main wind direction frequency, the wind energy score is obtained, the suitability score is obtained according to the distance to residential area or main road, the environmental impact factor is obtained according to noise and ecological protection area, and the objective function is constructed based on the wind energy score, the suitability score and the environmental impact factor;

[0009] The coordinates of the wind turbine position are encoded and processed, and the objective function is solved, and the optimal site selection strategy and the corresponding wind energy score, suitability score and environmental impact factor under the optimal site selection strategy are obtained, and the corresponding wind energy score, suitability score and environmental impact factor under the optimal site selection strategy are taken as the evaluation result.

[0010] Preferably, the wind data from multiple sources at least includes horizontal wind speed, vertical wind speed, wind direction and inflow angle parameters at different heights from wind tower, radar and virtual wind tower.

[0011] Preferably, the wind energy score is calculated by the following formula:

[0012] The wind energy score = wind speed weight × wind speed value + terrain weight × slope acceleration factor - ecological weight × protection area attenuation coefficient;

[0013] Wherein, the wind speed value is the average value of the wind data from multiple sources, the protection area attenuation coefficient is obtained by a value less than one set in advance according to the type of ecological sensitive area, and the slope acceleration factor is calculated by the following formula:

[0014] Slope acceleration factor = 1 + k tan (θ);

[0015] In the formula, θ is the slope, and k is the terrain coefficient.

[0016] Preferably, the suitability score is calculated by the following formula:

[0017] C 适宜 = α · D 居民区 + β · D 主干道 + γ · D 电网

[0018] Wherein, C 适宜is the adaptability scoring index, α, β, and γ are the corresponding location weights, and D is the path cost index of the target location. Different subscripts represent the path costs from different types of areas to the target location, and the value is the shortest path from the target location to different types of areas multiplied by the unit path cost.

[0019] Preferably, the environmental impact factor is calculated by the following formula:

[0020] L eq =L w +10lg(Q / 4πr 2 )-A 大气 -A 地面

[0021] Among them, L w is the sound power level, Q is the sound source directivity factor, A is the attenuation coefficient, and r is the noise propagation radius.

[0022] Preferably, the objective function is as follows:

[0023] F=w1·S v +w2·C 适宜 -w3·L eq

[0024] Among them, w1, w2, w3 are the corresponding weights of each indicator, S v Rating for wind energy, C 适宜 is the suitability score, L eq Environmental impact factors.

[0025] Preferably, the objective function is as follows:

[0026] F=w1·S v +w2·C 适宜 -w3·(L eq +E 生态 )

[0027] Among them, w1, w2, w3 are the corresponding weights of each indicator, S v Rating for wind energy, C 适宜 is the suitability score, L eq is the environmental impact factor, E 生态 It is an ecological environment impact indicator, and the value determination process is as follows:

[0028] S1: Identify ecologically sensitive areas, including migratory bird corridors and wetland conservation areas, and generate a designated no-construction buffer zone;

[0029] S2: Assign a value of 0 to the prohibited construction area and 1 to other areas, and convert the buffer zone into a binary raster layer;

[0030] S3: spatial overlay calculation of the layer with the wind energy resource score layer, to obtain a comprehensive evaluation index E considering both wind energy potential and avoiding ecological sensitive areas 生态 .

[0031] Preferably, in the process of solving the objective function, the wake model is added, based on the wake model, the wind turbine of the wind farm site selection is dynamically spaced optimized, according to the wake superposition effect, the initial spacing of onshore layout and the initial spacing of offshore layout are set, and the genetic algorithm is iteratively adjusted until the wake loss is less than the set threshold.

[0032] A computer readable storage medium, the computer readable storage medium comprises a stored program, wherein the program runs to control the device where the computer readable storage medium executes the multi-source data fusion wind farm micro-siting dynamic evaluation method as described above.

[0033] A processor for running a program, wherein the program runs to execute the multi-source data fusion wind farm micro-siting dynamic evaluation method as described above.

[0034] Compared with the prior art, the beneficial effects of the present application are:

[0035] The present application firstly acquires wind measurement data from multiple sources, and unifies wind measurement data of different sampling frequencies to a set time window, and realizes spatial scale alignment through interpolation method; then acquires wind energy score according to annual average wind speed and main wind direction frequency, acquires suitability score according to the distance to residential area or main road, acquires environmental impact factor according to noise and ecological protection area, and constructs an objective function based on wind energy score, suitability score and environmental impact factor. Finally, the real-time optimization model of genetic algorithm and wake interference model is combined, and the evaluation score of the selected site is inversely calculated according to the simulation calculation of wind turbine layout, the evaluation tendency is dynamically adjusted, so that the evaluation result is more comprehensive, scientific and reasonable. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the drawings needed in the specific embodiments or prior art description will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0037] Figure 1 The flow chart of the method of the present application. DETAILED DESCRIPTION

[0038] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts should fall within the scope of the present application.

[0039] It should be understood that the terms "comprising" and "including" as used in the specification and the appended claims indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0040] It should also be understood that the terms used in the present application specification are only for the purpose of describing particular embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0041] It should be further understood that the term "and / or" as used in the present application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0042] In one embodiment of the application, a wind farm micro-siting dynamic evaluation method for multi-source data fusion is provided, as shown in Figure 1 The method comprises the following steps:

[0043] Wind data from multiple sources is obtained, and wind data with different sampling frequencies is unified to a set time window, and spatial scale alignment is achieved by interpolation method;

[0044] Wind energy score is obtained according to annual average wind speed and main wind direction frequency, suitability score is obtained according to distance to residential area or main road, environmental impact factor is obtained according to noise and ecological protection area, and a target function is constructed based on wind energy score, suitability score and environmental impact factor;

[0045] The wind turbine position coordinates are encoded and processed, and the target function is solved to obtain the optimal siting strategy and the corresponding wind energy score, suitability score and environmental impact factor under the optimal siting strategy, and the corresponding wind energy score, suitability score and environmental impact factor under the optimal siting strategy are taken as the evaluation result.

[0046] Each step will be described in detail as follows:

[0047] 1. Classification and fusion of multi-source wind data

[0048] 1.1 Multiple wind measurement schemes and data source classification: Wind measurement schemes such as wind towers, radars, and virtual wind towers are classified according to accuracy, cost (radar > wind tower > virtual), and application scope (e.g., complex terrain prefers wind radar data). A data complementary mechanism is constructed. Wind towers are suitable for long-term monitoring and high-precision demand scenarios. Radars are suitable for complex terrain or short-term supplementary measurement scenarios. Virtual wind towers are suitable for rapid evaluation during the early planning or data loss period.

[0049] According to the data that can be collected by different wind measurement schemes, the data sources are preliminarily classified, including horizontal wind speed, vertical wind speed, wind direction, and inflow angle parameters at different heights. Specifically, the corresponding parameters of each wind measurement scheme are as follows:

[0050] For wind towers:

[0051] Wind speed: Data including instantaneous wind speed (sampling per second), 10-minute average wind speed, and maximum wind speed (3-second sampling maximum value) are measured.

[0052] Wind direction: Instantaneous wind direction data is collected through a wind vane, and wind direction is represented by 16 azimuths or angles.

[0053] Meteorological parameters: Temperature (sampling every 10 seconds), atmospheric pressure (sampling every 10 seconds), and relative humidity (sampling every 10 seconds) data are collected.

[0054] Standard deviation: Wind speed fluctuation data within 10 minutes are calculated.

[0055] Vertical wind shear: It is calculated from sensor data at different height layers.

[0056] Application scenarios: Flat terrain areas require long-term stable monitoring, but are limited by the land occupation of the guyed tower and the adaptability to extreme weather.

[0057] For radar wind measurement, wind field information is retrieved by actively emitting radar waves, and the main parameters are:

[0058] Wind speed and direction: Horizontal and vertical wind speed and direction data at multiple height layers are measured based on the Doppler effect.

[0059] Vertical airflow: Acoustic radar can detect turbulence and ascending / descending airflow.

[0060] Meteorological parameters: Temperature, humidity, and pressure sensors are integrated into the device to collect meteorological parameters.

[0061] Anti-interference capability: Acoustic radar has the ability to reduce the influence of environmental noise.

[0062] Inflow angle: Inflow angle data at each point in the wind field is measured.

[0063] For virtual wind tower, it generates wind resource data based on numerical simulation and multi-source data fusion, the main output parameters include:

[0064] Wind speed and direction: 10-minute time series data is generated by atmospheric model, including average wind speed, 3-second gust.

[0065] Vertical wind shear: calculate the wind speed profile change at 50m-150m height.

[0066] Turbulence intensity: calculated based on wind speed standard deviation data.

[0067] Long-term representative data: combined with historical meteorological data to generate complete annual wind resource assessment results.

[0068] The above data classification and comparison are as follows:

[0069]

[0070]

[0071] 1.2 Dynamic data integration: Kriging interpolation and spatial overlay analysis are used to integrate multi-source wind measurement data and geographic information (terrain slope, ecological sensitive area data, etc.), to generate wind energy resource thermal map.

[0072] Kriging is a regression algorithm for spatial modeling and prediction (interpolation) of random processes / random fields based on covariance functions. In a specific random process, such as intrinsic stationary process, Kriging can give the optimal linear unbiased estimate, so it is also called spatial optimal unbiased estimator in geostatistics. The data integration process includes:

[0073] Data cleaning and calibration: outlier rejection, time alignment and sensor error correction of original data of wind towers, radars and virtual wind towers. For example, laser radar data needs to be filtered by low-pass filter to eliminate rain and fog interference noise, and virtual wind data needs to be cross-verified with historical meteorological satellite to calibrate model bias.

[0074] Temporal and spatial resolution unification: unify the data of different sampling frequencies (wind tower sampling every second, radar updating every minute, virtual wind tower outputting every 10 minutes) to 10-minute time window, and realize spatial scale alignment through Kriging interpolation (spatial grid such as 100m x 100m).

[0075] Parameter optimization and spatial modeling of Kriging interpolation: Based on the spatial and temporal correlation of wind data, calculate the semi-variogram γ(h,τ) of spatial lag distance (h) and time lag (τ), and select the spherical model or exponential model to fit the spatial autocorrelation of wind speed. For example, in mountainous terrain, the semi-variogram needs to consider the nonlinear change caused by the terrain acceleration effect. Calculate the weight λ of each wind measurement point through the Kriging equation i , to ensure the unbiasedness and minimum variance of the interpolation results. For complex terrain, introduce terrain slope and roughness length as covariates to optimize the interpolation accuracy.

[0076] where the process of optimizing the interpolation accuracy is as follows: First, standardize the wind speed, slope, and roughness data to eliminate dimensional differences. Then, through cross-variogram analysis, quantify the spatial correlation between the main variable wind speed and the covariates slope and roughness. If the covariates are significantly correlated with the wind speed, construct a co-Kriging equation set containing the covariates to solve the weights of each variable. For complex terrain, further consider the acceleration effect of terrain slope on wind speed and the attenuation effect of surface roughness on wind speed, and make nonlinear correction and spatial weighting on the covariate weights. Finally, evaluate the model accuracy through cross-validation, and use optimization methods such as genetic algorithm to optimize the covariate weights to minimize the prediction error. The whole process significantly improves the spatial heterogeneity capture ability and prediction accuracy of wind speed interpolation by integrating geographic information covariates.

[0077] Geographical information spatial superposition and heat map generation: Convert digital elevation model (DEM), ecological sensitive areas (such as migratory bird migration channels, permanent basic farmland), and policy constraint areas (such as military radar prohibited construction areas) into vector layers, and quantify their impact factors (such as wind acceleration effect increases by 0.3 m / s for every 1° increase in slope; 3 km buffer zone is set in ecological protection area to prohibit construction). Use GIS tools (such as ArcGIS spatial analysis module) to perform weighted superposition of wind energy interpolation results and geographical layers. For example, use the raster calculator to implement the following formula:

[0078] The wind energy interpolation results first include the spatial distribution of wind speed and direction generated by the interpolation method, which can intuitively show the spatial variation of wind energy resources and provide important basis for wind farm site selection and wind turbine arrangement; secondly, the interpolation results also include a series of statistical indicators such as average wind speed, maximum wind speed, and wind speed standard deviation, which are used to quantify the richness and stability of wind energy resources; in addition, in order to provide more comprehensive decision support, uncertainty analysis is also carried out on the interpolation results, including error range and confidence interval.

[0079] Finally, generate multi-dimensional heat maps (superimpose interpolation results and geographical information such as terrain, ecological sensitive areas, etc.) containing wind energy intensity, development suitability, and risk level.

[0080] 2. Dynamic evaluation model construction and optimization

[0081] 2.1 Establish key indicator system: including wind energy score (annual average wind speed, main wind direction frequency), suitability score (distance to residential area / main road), environmental impact factor (noise, ecological protection zone avoidance) three types of indicators, the weight is determined by Critic weighting method.

[0082] CRITIC method is an objective weight assignment method proposed by Diakoulaki, and its basic idea is to determine the objective weight of the index based on two basic concepts. One is the contrast intensity, which represents the size of the value difference of each evaluation scheme of the same index, which is expressed in the form of standard deviation, that is, the size of the standardized difference shows the size of the value difference of each scheme in the same index, and the larger the standard deviation, the larger the value difference of each scheme. Two is the conflict between evaluation indexes, which is based on the correlation between indexes. If two indexes have strong positive correlation, it means that the conflict between two indexes is low.

[0083] Based on the above technology, the model system established includes:

[0084] 2.1.1 Wind energy score module

[0085] Integrate multi-source data of wind measurement tower, radar and virtual wind measurement tower, annual average wind speed is calculated by average, main wind direction frequency is based on wind direction rose diagram statistics, and historical meteorological data is combined to verify long-term representativeness, among which the weight of main wind direction frequency is determined by entropy method to ensure that the proportion of dominant wind direction is higher than that of secondary wind direction.

[0086] There are two calculation methods for wind energy score:

[0087] One:

[0088] Wind energy score = wind speed weight × wind speed value + terrain weight × slope acceleration factor - ecological weight × protection zone attenuation coefficient The second method is to use normalization to map wind speed to the interval value of 0-1, and the formula is:

[0089] S v =(V 设计 -V 阈值 ) / (V 实际 -V 阈值 )

[0090] Where S v is the wind energy score index. V 设计 is the rated wind speed, V 阈值 is the cut-in wind speed, and V 实际 is the actual wind speed. Among them, the cut-in wind speed is the minimum wind speed for wind turbine to start power generation, which is determined by technical manual, wind speed probability distribution or economic model.

[0091] 2.1.2 Suitability Scoring Module

[0092] Using GIS spatial analysis technology, we established buffer zones for residential areas, main roads, and power grid access points (residential areas ≥ 500m, main roads ≥ 300m), and used the network analysis method to calculate the shortest path cost. The formula is:

[0093] C 适宜 =α·D 居民区 +β·D 主干道 +γ·D 电网

[0094] Among them, C 适宜 is the adaptability scoring index, α, β, γ are the corresponding location weights, and D is the path cost index of the target location.

[0095] Constraints are updated in real time based on policy changes in the site selection location (such as newly drawn ecological red lines), and spatial conflict detection is achieved through raster overlay.

[0096] Constraints (constraint scope) include:

[0097] Policies and regulations: such as ecological protection red lines, nature reserves, water source protection areas, basic farmland, forestry land and other statutory prohibited construction areas;

[0098] Environmentally sensitive areas: bird migration corridors, wetlands, geological parks, scenic spots and other areas that need to be avoided or restricted in development;

[0099] Engineering safety: terrain slopes exceeding 30° (prone to construction risks), earthquake fault zones, and areas prone to floods, etc.

[0100] Infrastructure: military restricted areas, airport clear areas, high-voltage corridors, oil and gas pipeline safety distances, etc.

[0101] Social impact category: 500-meter buffer zone in residential areas (noise control), cultural heritage protection areas, etc.

[0102] These conditions are clearly defined through policy documents, planning layers or technical specifications, and directly determine the feasibility boundaries of the site selection.

[0103] The specific implementation of spatial conflict detection through raster overlay is as follows:

[0104] 1. Data collection and updating: Regularly obtain the latest policy documents (such as ecological red line adjustment announcements) and geographic information data (such as the "three zones and three lines" layer of national land space planning);

[0105] 2. Rasterization: Convert vector data (e.g., ecological red line boundaries) into raster format, unify resolution (e.g., 30m x 30m), and assign constraint properties (e.g., mark ecological red line areas as "1" and non-constrained areas as "0");

[0106] 3. Overlay analysis: Overlay the wind energy resource score raster and constraint condition raster in the GIS platform, and identify conflict areas through Boolean operations (e.g., "AND" operation);

[0107] 4. Conflict marking: Mark the raster that simultaneously satisfies high wind energy resource score (e.g., Sv > 0.8) and constraint condition "1", and generate a conflict hotspot map;

[0108] 5. Dynamic update: When policies change (e.g., new ecological red lines are added), re-execute the above process to update the constraint range in real time.

[0109] 2.1.3 Environmental Impact Factor Module

[0110] Construct a noise propagation model to calculate the equivalent sound level index L eq of wind turbine noise in residential areas, with the formula:

[0111] L eq = L w +10lg(Q / 4πr 2 )-A 大气 -A 地面

[0112] where L w is the sound power level, Q is the sound source directivity factor (usually 4-8), A is the attenuation coefficient, and r is the noise propagation radius.

[0113] Through spatial overlay analysis, set a 3km no-build buffer zone in areas such as migratory bird corridors and wetland protection zones, and introduce binary constraints (set the protection zone weight to 0) in the evaluation model to obtain the ecological environmental impact index E 生态 .

[0114] 2.2 Real-time optimization of algorithm: Optimize wind turbine layout based on real number coding genetic algorithm, dynamically adjust row / column spacing combined with wake interference model, and reduce wake loss. The method specifically includes:

[0115] 2.2.1 Algorithm design

[0116] Encode the wind turbine position coordinates (X, Y) as a real number vector, with individuals represented as (x1, y1), (x2, y2),..., (x n , y n ). Integrate wind energy score, suitability score, and environmental impact score to obtain fitness function F, with the objective function as:

[0117] F = w1 · S v + w2 · C 适宜 - w3 · (L eq + E 生态 )

[0118] The weights w1, w2, w3 are the corresponding weights of each index determined by the Critic method.

[0119] The ecological environment impact index E 生态 The acquisition process is as follows: first, identify the ecological sensitive areas such as the migration channel of migratory birds and the wetland protection area and generate a 3km no-construction buffer zone, then convert the buffer zone into a binary raster layer (assign a value of 0 to the no-construction zone and a value of 1 to other areas), and finally perform spatial overlay calculation on the layer and the wind energy resource score layer to obtain the comprehensive evaluation index Eecological which takes into account both the wind energy potential and the avoidance of ecological sensitive areas.

[0120] In the suitability function of micro-siting of a wind farm, the changes of each evaluation index will directly affect the priority and feasibility of the site selection. The increase of wind energy score (such as the increase of annual average wind speed or the stabilization of main wind direction frequency) will significantly increase the power generation efficiency, but if the wind speed is too high (such as exceeding the destructive threshold) or the wind direction is too dispersed, a trade-off between power generation benefit and equipment safety, land utilization rate will be needed. The decrease of suitability score (such as the shortening of the distance to residential areas or main roads) will intensify the risk of noise complaints, forcing layout adjustment or increasing noise reduction measures; and the increase of power grid access distance will directly increase the transmission cost, which may need to sacrifice wind energy advantage for economy. The deterioration of environmental impact score (such as noise exceeding the standard or insufficient avoidance of ecological protection areas) not only may trigger policy restrictions, but also will increase the cost of ecological compensation, and even lead to the rejection of the project. In addition, the dynamic adjustment of weight distribution (such as policy strengthening the weight of ecological protection) will change the balance of multiple objectives, for example, in the ecological sensitive area, the area with low wind speed but small disturbance is preferred instead of simply pursuing maximum wind energy. Overall, the changes of each index will reshape the site selection decision through a compound effect, and need to be dynamically optimized among power generation benefit, economic cost and environmental compatibility, ultimately affecting the feasibility and sustainability of the wind farm, and providing a reference evaluation result for micro-siting of the wind farm.

[0121] 2.2.2 Tail flow interference model fusion

[0122] The wake effect refers to the formation of a wake zone with reduced wind speed downstream of a wind turbine while the wind turbine extracts energy from the wind. If there is a wind turbine downstream in the wake zone, the input wind speed of the downstream wind turbine is lower than that of the upstream wind turbine. The wake effect causes uneven wind speed distribution in the wind farm, affecting the operating conditions of each wind turbine in the wind farm, and further affecting the operating conditions and output of the wind farm; and is affected by factors such as wind farm topology, rotor diameter, thrust coefficient, wind speed and wind direction.

[0123] The wake model is modified, assuming that the wake is linear diffusion, and the speed loss is only related to the axial distance, and the wake speed loss u formula is:

[0124]

[0125] Wherein, U0 is the upstream flow wind speed, D is the diameter of the wind turbine, k is the wake expansion coefficient, x is the projection distance of the downstream wind turbine and the upstream wind turbine in the wind direction, C T The thrust coefficient.

[0126] Based on the wake model, the wind turbine of the wind farm site selection is dynamically spaced and optimized, according to the wake superposition effect, the initial spacing of the land layout is 3D*5D, and the sea is expanded to 3D*7D due to slow turbulence recovery, and the wake loss is adjusted by genetic algorithm iteration until <8%. The layout result of the optimized wind turbine spacing is inversed to the wind energy, environmental suitability and other data of the site selection place to verify the influence degree of the layout scheme on the site selection scheme, dynamically adjust the evaluation tendency according to the result, and finally obtain the evaluation result.

[0127] In summary, the multi-source data fusion evaluation of the present application can significantly reduce the wind resource evaluation error and the annual power generation prediction error, and the present application combines the real-time optimization model of the genetic algorithm and the wake interference model, and inverses the evaluation score of the site selection place according to the simulation calculation wind turbine layout, dynamically adjusts the evaluation tendency, so that the evaluation result is more comprehensive, scientific and reasonable.

[0128] Those skilled in the art can realize that the units of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both, and the components of the examples have been described in the above description in general terms in order to clearly illustrate the interchangeability of hardware and software. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0129] In the embodiments provided in the present application, it should be understood that the division of units is only a logical functional division, and when actually implemented, there can be another division manner, for example, a plurality of units can be combined into one unit, one unit can be split into a plurality of units, or some features can be ignored, etc.

[0130] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware or software functional unit.

[0131] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0132] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should be covered in the scope of the claims and the specification of the present application.

Claims

1. A dynamic evaluation method for wind farm micro-site selection based on multi-source data fusion, characterized by: The following steps are involved: Acquire wind measurement data from multiple sources, unify the wind measurement data with different sampling frequencies into a set time window, and achieve spatial scale alignment through interpolation; The wind energy score is obtained based on the average annual wind speed and the frequency of the main wind direction. The suitability score is obtained based on the distance to residential areas or main roads. The environmental impact factor is obtained based on the noise and ecological protection areas. The objective function is constructed based on the wind energy score, suitability score and environmental impact factor. The wind turbine location coordinates are encoded and the objective function is solved to obtain the optimal siting strategy and the corresponding wind energy score, suitability score and environmental impact factor under the optimal siting strategy. The wind energy score, suitability score and environmental impact factor under the optimal siting strategy are used as the evaluation results.

2. The method for dynamic evaluation of wind farm micro-site selection based on multi-source data fusion according to claim 1, characterized in that: The wind measurement data from multiple sources at least include horizontal wind speed, vertical wind speed, wind direction, and inflow angle parameters at different heights from a wind tower, a radar, and a virtual wind tower.

3. The method for dynamic evaluation of wind farm micro-site selection based on multi-source data fusion according to claim 1, characterized in that: The wind energy score is calculated by the following formula: Wind energy score = wind speed weight × wind speed value + terrain weight × slope acceleration factor - ecological weight × protected area attenuation coefficient; The wind speed value is the average of wind measurement data from multiple sources. The attenuation coefficient of the protected area is obtained by setting a value less than one in advance according to the type of ecologically sensitive area. The slope acceleration factor is calculated using the following formula: Slope acceleration factor = 1 + k·tan(θ); Where θ is the slope and k is the terrain coefficient.

4. The method for dynamic evaluation of wind farm micro-site selection based on multi-source data fusion according to claim 1, characterized in that: The suitability score is calculated using the following formula: C 适宜 =α·D 居民区 +β·D 主干道 +γ·D 电网 Among them, C 适宜 is the adaptability scoring index, α, β, and γ are the corresponding location weights, and D is the path cost index of the target location. Different subscripts represent the path costs from different types of areas to the target location, and the value is the shortest path from the target location to different types of areas multiplied by the unit path cost.

5. The method for dynamic evaluation of wind farm micro-site selection based on multi-source data fusion according to claim 1, characterized in that: The environmental impact factor is calculated by the following formula: L eq =L w +10lg(Q / 4πr 2 )-A 大气 -A 地面 Among them, L w is the sound power level, Q is the sound source directivity factor, A is the attenuation coefficient, and r is the noise propagation radius.

6. The method for dynamic evaluation of wind farm micro-site selection based on multi-source data fusion according to claim 1, characterized in that: The objective function is as follows: F=w1·S v +w2·C 适宜 -w3·L eq Among them, w1, w2, w3 are the corresponding weights of each indicator, S v Rating for wind energy, C 适宜 is the suitability score, L eq Environmental impact factors.

7. The method for dynamic evaluation of wind farm micro-site selection based on multi-source data fusion according to claim 1, characterized in that: The objective function is as follows: F=w1·S v +w2·C 适宜 -w3·(L eq +E 生态 ) Among them, w1, w2, w3 are the corresponding weights of each indicator, S v Rating for wind energy, C 适宜 is the suitability score, L eq is the environmental impact factor, E 生态 It is an ecological environment impact indicator, and the value determination process is as follows: S1: Identify ecologically sensitive areas, including migratory bird corridors and wetland conservation areas, and generate a designated no-construction buffer zone; S2: Assign a value of 0 to the prohibited construction area and 1 to other areas, and convert the buffer zone into a binary raster layer; S3: Perform spatial overlay calculation on this layer and the wind energy resource scoring layer to obtain a comprehensive evaluation index E that considers both wind energy potential and avoids ecologically sensitive areas. 生态 .

8. The method for dynamic evaluation of wind farm micro-site selection based on multi-source data fusion according to claim 1, characterized in that: In the process of solving the objective function, a wake model is added. Based on the wake model, the dynamic spacing of wind turbines in the wind farm site is optimized. According to the wake superposition effect, the initial spacing of the onshore layout and the initial spacing of the offshore layout are set, and the genetic algorithm is used to iteratively adjust until the wake loss is less than the set threshold.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the wind farm micro-site selection dynamic evaluation method based on multi-source data fusion according to any one of claims 1 to 8.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the wind farm micro-site selection dynamic evaluation method based on multi-source data fusion according to any one of claims 1 to 8.

Images