Wind power plant wake flow scheduling method under wind direction monitoring

Abstract

The invention discloses a wind power plant wake flow scheduling method under wind direction monitoring, and relates to the technical field of wake flow scheduling, and the method comprises the steps: obtaining the wind speed and wind direction data and meteorological data of each fan in a wind power plant in real time through a wind direction monitoring device and a wind speed sensor; geometric parameters and operation parameters of all draught fans in the wind power plant are obtained; the wake effect model is used for calculating the wake effect between the fans in the wind power plant, and a wake effect calculation result is generated; generating a fan scheduling scheme according to the wake effect calculation result; and executing the fan scheduling scheme, controlling the power output of each fan, monitoring the power output and operation state of each fan in real time, and dynamically adjusting the fan scheduling scheme. The technical problems that in the prior art, the wind energy utilization efficiency is low, the wind power plant is unstable, and wake flow scheduling lacks adaptability are solved, and the technical effects of improving the wind energy utilization efficiency, enhancing the stability of the wind power plant and achieving intelligent scheduling are achieved.

Description

Technical Field

[0001] The invention relates to the technical field of wake scheduling, and in particular to a wind farm wake scheduling method under wind direction monitoring. Background Art

[0002] In the context of today's energy transformation, wind power generation, as a clean and renewable form of energy, has been widely used and developed around the world. However, with the continuous expansion of the scale of wind farms, some technical problems have gradually emerged. In the operation of traditional wind farms, low wind energy utilization efficiency is a common problem. Due to the layout of wind turbines in wind farms and the influence of wake effect, downstream wind turbines are often in the wake area generated by upstream wind turbines, with reduced wind speed and increased turbulence intensity, resulting in a decrease in the wind energy capture capacity of downstream wind turbines. At the same time, the existing operation strategy may not fully consider the dynamic changes in wind conditions and the interaction between wind turbines, so that wind turbines cannot always be in the best operating state, thereby limiting the effective utilization of wind energy. The stability of wind farms is also a key issue. On the one hand, the mutual influence between wind turbines in a wind farm may cause fluctuations in power output, especially under complex wind conditions. On the other hand, the lack of accurate evaluation and effective control of the wake effect may cause some wind turbines to bear excessive loads, increase the risk of equipment failure, and thus affect the stable operation of the entire wind farm.

[0003] The existing technology has technical problems such as low wind energy utilization efficiency, unstable wind farms, and lack of adaptability in wake scheduling. Summary of the invention

[0004] The present application provides a method for wind farm wake scheduling under wind direction monitoring, which is used to solve the technical problems of low wind energy utilization efficiency, unstable wind farms, and lack of adaptability in wake scheduling in the prior art.

[0005] In view of the above problems, the present application provides a wind farm wake scheduling method under wind direction monitoring, the method comprising:

[0006] By means of wind direction monitoring equipment and wind speed sensors installed in the wind farm, the wind speed and direction data of each wind turbine in the wind farm and meteorological data are obtained in real time to generate real-time wind condition information of the wind farm; the geometric parameters and operating parameters of each wind turbine in the wind farm are obtained; based on the real-time wind condition information and in combination with the geometric parameters and operating parameters of each wind turbine, the wake effect between each wind turbine in the wind farm is calculated using a wake effect model to generate a wake effect calculation result; according to the wake effect calculation result, a wind turbine scheduling plan is generated; the wind turbine scheduling plan is executed to control the power output of each wind turbine, the power output and operating status of each wind turbine are monitored in real time, and compared with the wake effect calculation result, and the wind turbine scheduling plan is dynamically adjusted.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By setting up wind direction monitoring equipment and wind speed sensors in the wind farm, the wind speed and direction data and meteorological data of each wind turbine in the wind farm are obtained in real time to generate real-time wind condition information of the wind farm; the geometric parameters and operating parameters of each wind turbine in the wind farm are obtained; based on the real-time wind condition information, combined with the geometric parameters and operating parameters of each wind turbine, the wake effect model is used to calculate the wake effect between each wind turbine in the wind farm, and the wake effect calculation result is generated; according to the wake effect calculation result, a wind turbine scheduling plan is generated; the wind turbine scheduling plan is executed to control the power output of each wind turbine, monitor the power output and operating status of each wind turbine in real time, and compare with the wake effect calculation result, and dynamically adjust the wind turbine scheduling plan. The technical effect of improving wind energy utilization efficiency, enhancing wind farm stability, and realizing intelligent scheduling is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in 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 creative work.

[0010] Figure 1 A schematic flow chart of a method for wind farm wake scheduling under wind direction monitoring provided in an embodiment of the present application;

[0011] Figure 2 A schematic diagram of a flow chart of generating wake effect calculation results in a wind farm wake scheduling method under wind direction monitoring provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] The present application provides a wind farm wake scheduling method under wind direction monitoring, which is used to solve the technical problems of low wind energy utilization efficiency, unstable wind farms, and lack of adaptability in wake scheduling in the prior art.

[0013] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] Examples, such as Figure 1 As shown, the present application provides a method for wind farm wake scheduling under wind direction monitoring, the method comprising:

[0015] Step S100: by using wind direction monitoring equipment and wind speed sensors installed in the wind farm, wind speed and wind direction data of each wind turbine in the wind farm and meteorological data are acquired in real time to generate real-time wind condition information of the wind farm.

[0016] Specifically, firstly, wind direction monitoring equipment and wind speed sensors are set up in the wind farm. These devices are distributed in different locations of the wind farm to comprehensively and accurately capture wind condition information in various areas of the wind farm.

[0017] Wind direction monitoring equipment can monitor changes in wind direction in real time. Accurate information on wind direction is crucial to the operation of wind farms, because the blades of wind turbines need to be adjusted according to wind direction to maximize the capture of wind energy. Wind speed sensors are responsible for measuring wind speed, which directly affects the power generation efficiency of wind turbines. Through these sensors, wind speed data at the locations of each wind turbine in the wind farm can be obtained in real time. In addition, meteorological data in the wind farm will also be collected. This includes humidity, temperature and atmospheric pressure, which are very important for understanding the environmental conditions of the wind farm. For example, humidity and temperature affect the density of the air, which in turn affects the availability of wind energy. Changes in atmospheric pressure will also have a certain impact on the flow of wind. Through wind direction monitoring equipment, wind speed sensors and the collection of meteorological data, real-time wind condition information of the wind farm can be generated. This information includes real-time values ​​of wind direction, wind speed and various meteorological parameters. These real-time wind condition information provides basic data for subsequent calculations and analysis, enabling a more accurate assessment of the wake effect between wind turbines in the wind farm, thereby formulating a more reasonable wind turbine scheduling plan.

[0018] Step S200: Acquire geometric parameters and operating parameters of each wind turbine in the wind farm.

[0019] Specifically, first, these parameters are collected through an interactive wind turbine history database. The wind turbine history database stores detailed information about each wind turbine, including its operating data and geometric characteristics at different time periods. For geometric parameters, this includes the blade diameter of each wind turbine. The blade diameter determines the area swept by the wind turbine blades, and a larger blade diameter can generally capture more wind energy. Hub height is also an important geometric parameter that affects the wind farm environment in which the wind turbine is located. Different hub heights may face different wind speed and wind direction conditions. Wind turbine spacing and tower height also affect the overall layout and performance of the wind farm. Reasonable wind turbine spacing can reduce wake interference between wind turbines, while tower height determines the installation location of the wind turbine and the wind resources it is exposed to. In terms of operating parameters, the power output of each wind turbine is a key indicator that directly reflects the current power generation capacity of the wind turbine. The power curve describes the change law of the output power of the wind turbine at different wind speeds. The power curve can be used to predict the power generation performance of the wind turbine under specific wind conditions. Turbulence intensity indicates the degree of turbulence of the airflow in a wind farm. Higher turbulence intensity may have an adverse effect on the structure and performance of the wind turbine. The rotation speed is the speed at which the wind turbine blades rotate, which is closely related to the wind speed and the control strategy of the wind turbine. The blade angle can adjust the wind turbine's efficiency in capturing wind energy, and by changing the blade angle, it can adapt to different wind conditions. In addition, the real-time status of the wind turbine, including operation, shutdown, maintenance and other status information, is crucial for formulating scheduling plans and ensuring the safe and stable operation of wind farms. Obtaining the geometric parameters and operating parameters of these wind turbines provides the necessary basic data for the subsequent calculation of wake effects and the generation of wind turbine scheduling plans, enabling more scientific and reasonable management and optimization of wind farms.

[0020] Step S300: Based on the real-time wind condition information, combined with the geometric parameters and operating parameters of each wind turbine, a wake effect model is used to calculate the wake effect between the wind turbines in the wind farm, and a wake effect calculation result is generated.

[0021] Specifically, first, the real-time wind information obtained previously, including wind direction, wind speed and meteorological data, is used. This information reflects the actual atmospheric environment of the current wind farm. At the same time, combined with the geometric parameters of each wind turbine, such as blade diameter, hub height, wind turbine spacing and tower height, as well as operating parameters, such as power output, power curve, turbulence intensity, speed, blade angle and real-time status of the wind turbine, these parameters together constitute the basis for calculating the wake effect. The Jensen model is used as the wake effect model. Based on certain assumptions and empirical formulas, the Jensen model can accurately estimate the wake effect between wind turbines in the wind farm. The real-time wind information and wind turbine parameters are input into the Jensen model. First, the wake diffusion range of the upstream wind turbine is calculated. The upstream wind turbine will generate a wake during operation, and its diffusion range is affected by many factors, including wind speed, wind direction, and geometric parameters of the wind turbine. Through model calculation, the area affected by the wake of the upstream wind turbine at the downstream position can be determined. Then, the attenuation prediction of the downstream wind turbine is further calculated by combining the wake diffusion coefficient and turbulence intensity. The wake diffusion coefficient reflects the diffusion speed of the wake in the air, while the turbulence intensity indicates the degree of turbulence of the airflow in the wind field. These two parameters are crucial for accurately predicting the wake impact on the downstream wind turbine. Finally, combined with the attenuation prediction of the downstream wind turbine and its power curve, the power output change of the downstream wind turbine is calculated to generate the wake effect calculation result. This result can clearly show the degree of influence of the wake interaction between the wind turbines on the wind turbine power output, providing an important basis for the subsequent generation of wind turbine scheduling plans.

[0022] Step S400: generating a wind turbine scheduling plan according to the wake effect calculation result.

[0023] Specifically, after obtaining the calculation results of the wake effect, it is necessary to generate a wind turbine dispatching plan based on this. First, analyze the mutual influence between the wind turbines in the calculation results of the wake effect, understand the degree of power attenuation caused by the upstream wind turbine to the downstream wind turbine, and the performance changes of wind turbines at different positions under the influence of the wake. Based on the calculation results of the wake effect, the power output of the upstream and downstream wind turbines is dynamically adjusted and allocated in combination with the multi-wind turbine collaborative optimization algorithm. The multi-wind turbine collaborative optimization algorithm takes into account the overall performance of the entire wind farm and the actual operating status of each wind turbine. According to the degree of wake influence, the wake influence of the upstream wind turbine on the downstream wind turbine is identified, and the power output of the upstream wind turbine is dynamically adjusted. If the wake of the upstream wind turbine has a large negative impact on the downstream wind turbine, the power output of the upstream wind turbine is appropriately reduced to reduce the intensity of the wake, thereby reducing the interference to the downstream wind turbine. At the same time, based on the real-time operating status of all wind turbines and combined with the power output feedback of the downstream wind turbine, if the actual power output of the downstream wind turbine is significantly different from the expected, it means that the current dispatching plan may need to be adjusted. The multi-wind turbine collaborative optimization algorithm is used to dynamically optimize the power output distribution of all wind turbines to ensure that the negative impact of the wake effect is minimized while meeting the overall power generation target of the wind farm. By comprehensively considering the wake effect, wind turbine operating status and multi-wind turbine collaborative optimization algorithm, a scientific and reasonable wind turbine scheduling plan is generated to improve the overall efficiency and stability of the wind farm.

[0024] Step S500: executing the wind turbine scheduling plan, controlling the power output of each wind turbine, monitoring the power output and operating status of each wind turbine in real time, and comparing them with the wake effect calculation result, and dynamically adjusting the wind turbine scheduling plan.

[0025] Specifically, once a wind turbine dispatching plan is generated, it is executed. Through the control system of the wind farm, the power output of each wind turbine is controlled according to the dispatching plan, which involves adjusting the parameters such as the blade angle and speed of the wind turbine to achieve a specific power output target. While executing the dispatching plan, the power output and operating status of each wind turbine are monitored in real time, and the actual power output value, operating parameters, and whether there is a fault of the wind turbine are continuously obtained by using sensors and monitoring equipment installed on the wind turbine. The power output and operating status of each wind turbine monitored in real time are compared with the previous wake effect calculation results. If it is found that there is a large difference between the actual power output and the expected power output, or the operating status is abnormal, the wind turbine dispatching plan needs to be dynamically adjusted. For example, if the actual power output of a wind turbine is significantly lower than expected, it may be caused by changes in the wake effect, changes in meteorological conditions, or equipment failure. At this time, it is necessary to re-evaluate the current wind condition information, wind turbine parameters, and wake effect, and adjust the dispatching plan in combination with the multi-wind turbine collaborative optimization algorithm. Dynamic adjustment can include reallocating the power output of each wind turbine, adjusting the power of upstream wind turbines to reduce the wake impact on downstream wind turbines, troubleshooting or maintenance arrangements based on the real-time operating status of wind turbines, etc. Through continuous monitoring, comparison and adjustment, it is ensured that the wind farm can maintain efficient and stable operation under various conditions, maximizing the utilization efficiency of wind energy and the benefits of power generation.

[0026] In a possible implementation, step S100 further includes:

[0027] Step S110: Real-time collection of wind speed and wind direction at multiple points through weather stations installed at different locations in the wind farm and wind direction monitoring equipment and wind speed sensors of each wind turbine.

[0028] Step S120: Collecting meteorological data in the wind farm, the meteorological data including humidity, temperature, and atmospheric pressure.

[0029] Specifically, by installing meteorological stations at different locations in the wind farm and configuring wind direction monitoring equipment and wind speed sensors on each wind turbine, real-time collection of wind speed and wind direction at multiple points in the wind farm can be achieved. Meteorological stations at different locations can cover a wider area, ensuring a comprehensive understanding of the wind conditions of the entire wind farm. Wind direction monitoring equipment can accurately capture changes in wind direction, which is crucial for wind turbines to adjust blade angles to capture wind energy to the greatest extent. Wind speed sensors continuously measure wind speeds at different locations, and the size of wind speeds directly affects the power generation efficiency of wind turbines. Through the collaborative work of these devices, wind speed and wind direction data at multiple locations in the wind farm can be obtained in real time, providing accurate basic information for subsequent wake effect calculations and wind turbine scheduling.

[0030] Further collect meteorological data within the wind farm, including humidity, temperature and atmospheric pressure. Changes in humidity will affect the density and conductivity of the air, which may in turn affect the operation and power generation efficiency of the wind turbine. The temperature will not only change the density of the air, but also affect the heat dissipation and equipment performance of the wind turbine. Changes in atmospheric pressure may also have a certain impact on the flow of wind. These meteorological data can help to more comprehensively understand the environmental conditions of the wind farm, and provide important references for accurately evaluating the wake effect and formulating reasonable wind turbine scheduling plans. By collecting and analyzing these meteorological data, we can better adapt to different meteorological conditions and improve the overall operating efficiency and stability of the wind farm.

[0031] In a possible implementation, step S200 further includes:

[0032] Step S210: Interact with the wind turbine history database to obtain the geometric parameters and operating parameters of each wind turbine, wherein the geometric parameters include the blade diameter, hub height, wind turbine spacing, and tower height of each wind turbine, and the operating parameters include the power output, power curve, turbulence intensity, rotation speed, blade angle, and real-time status of each wind turbine.

[0033] Specifically, by interacting with the wind turbine historical database, the geometric parameters and operating parameters of each wind turbine are fully obtained. For geometric parameters, the blade diameter determines the area swept by the wind turbine blades. A larger blade diameter can usually capture more wind energy at the same wind speed. The hub height affects the wind farm location of the wind turbine. Hubs of different heights will face different wind speed and wind direction conditions. Reasonable setting of wind turbine spacing is crucial. Appropriate spacing can reduce wake interference between wind turbines and improve the wind energy utilization efficiency of the entire wind farm. The tower height determines the installation height of the wind turbine, which will also affect the wind farm environment and wind turbine performance.

[0034] In terms of operating parameters, power output directly reflects the current power generation capacity of the wind turbine. The power curve describes the change law of the output power of the wind turbine at different wind speeds. By analyzing the power curve, the power generation performance of the wind turbine under specific wind conditions can be better predicted. Turbulence intensity indicates the degree of turbulence of the airflow in the wind farm. Higher turbulence intensity may have an adverse effect on the structural stability and performance of the wind turbine. The speed is the speed at which the wind turbine blades rotate, which is closely related to the wind speed and the control strategy of the wind turbine. The adjustment of the blade angle can change the efficiency of the wind turbine in capturing wind energy. Adjusting the blade angle according to different wind conditions can optimize the performance of the wind turbine. The real-time status of the wind turbine includes information such as operation, shutdown, and maintenance. Understanding these states is crucial to formulating a reasonable scheduling plan and ensuring the safe and stable operation of the wind farm. By obtaining these detailed geometric parameters and operating parameters, an accurate data basis can be provided for subsequent wake effect calculations and wind turbine scheduling, thereby achieving efficient management and optimization of wind farms.

[0035] In a possible implementation, step S300 further includes:

[0036] Step S310: performing data cleaning on the real-time wind condition information.

[0037] Step S320: standardizing the geometric parameters and operating parameters of each wind turbine.

[0038] Specifically, the real-time wind information is cleaned. Due to various factors, the real-time wind information collected may contain outliers, noise, and erroneous data. The purpose of data cleaning is to remove these bad data to ensure that the wind information used for subsequent calculations is accurate and reliable. By using filtering algorithms, wind speed, wind direction data, and meteorological data that are significantly deviated from the normal range are identified and removed. For example, if a wind speed sensor fails, resulting in abnormally high or low measurements, the data cleaning process can identify it and remove it from the data set, which can prevent erroneous data from misleading the wake effect calculation and improve the accuracy of the calculation results.

[0039] The geometric parameters and operating parameters of each wind turbine are standardized. Parameters from different sources have different dimensions and scales, which will bring difficulties to subsequent calculations and analysis. Standardization can unify these parameters to the same scale for easy comparison and calculation. For geometric parameters, such as blade diameter, hub height, wind turbine spacing and tower height, unified units are used to represent them and normalized to make the geometric parameters of different wind turbines comparable. For operating parameters, such as power output, turbulence intensity, speed, etc., they are converted into appropriate ranges through standardization methods. In this way, when using the wake effect model for calculation, the influence of each parameter is considered more accurately, the accuracy and reliability of the calculation are improved, and the standardization can also facilitate the application of different algorithms and models, making the entire wind farm wake scheduling process more efficient and scientific.

[0040] In one possible implementation, Figure 2 As shown, step S300 also includes:

[0041] Step S330: using the real-time wind condition information, combined with the geometric parameters and operating parameters of each wind turbine, inputting the wake effect model, calculating the wake diffusion range of the upstream wind turbine, and determining the impact area at the downstream position.

[0042] Step S340: by using the influence area at the downstream position, combining the wake diffusion coefficient and the turbulence intensity, inputting the wake effect model, and calculating the attenuation prediction of the downstream wind turbine.

[0043] Step S350: In combination with the attenuation prediction of the downstream wind turbine, the power curve of the downstream wind turbine is used to calculate the power output change of the downstream wind turbine to generate the wake effect calculation result.

[0044] Specifically, real-time wind information includes wind direction, wind speed, and various meteorological data, which reflect the current atmospheric environment state of the wind farm. The geometric parameters of each wind turbine, such as blade diameter, hub height, wind turbine spacing, and tower height, as well as operating parameters such as power output, turbulence intensity, speed, blade angle, and real-time status of the wind turbine, together constitute the specific characteristics of the wind turbine. These data are input into the Jensen model, which is a model widely used in the calculation of the wake effect of wind farms. It is based on specific assumptions and empirical formulas and can accurately estimate the wake effect between wind turbines. Through the calculation of the model, the wake diffusion range of the upstream wind turbine can be determined. The upstream wind turbine will generate wake during operation, and its diffusion range is affected by many factors, including wind speed, wind direction, geometric parameters of the wind turbine, and atmospheric conditions. The model will comprehensively consider these factors and calculate the diffusion of the wake in space. Once the wake diffusion range is determined, the impact area at the downstream position can be further determined. If the downstream wind turbine is located in the wake influence area of ​​the upstream wind turbine, it will be affected by the upstream wind turbine wake, resulting in changes in its performance. Determining the influence area at the downstream location provides an important basis for subsequent evaluation of the impact of the downstream wind turbine and formulation of a reasonable wind turbine scheduling plan.

[0045] After the influence area at the downstream position is known, this area indicates the range to which the downstream wind turbine is affected by the wake of the upstream wind turbine. At this time, the two important parameters of wake diffusion coefficient and turbulence intensity are combined and input into the wake effect model together with the information of the influence area. The wake diffusion coefficient reflects the diffusion speed of the wake in the air. Different atmospheric conditions and wind turbine operating conditions will cause changes in the wake diffusion coefficient. If the diffusion coefficient is large, it means that the wake diffuses faster and the impact on the downstream wind turbine may be relatively small; on the contrary, if the diffusion coefficient is small, the wake diffuses slowly, and the impact on the downstream wind turbine may be more persistent and intense. Turbulence intensity indicates the degree of turbulence of the airflow in the wind field. Higher turbulence intensity will make the wind flow more unstable, increase the complexity and uncertainty of the wake, and make the impact on the downstream wind turbine more difficult to predict. At the same time, turbulence intensity will also affect the diffusion and attenuation speed of the wake. By inputting these parameters into the wake effect model, the model can calculate the attenuation prediction of the downstream wind turbines based on factors such as the current wind conditions, wake diffusion, and turbulence intensity. This attenuation prediction includes the possible power attenuation degree, wind speed changes, and changes in other performance indicators of the downstream wind turbines, which provides an important reference for the subsequent formulation of reasonable wind turbine scheduling plans, so that appropriate measures can be taken to reduce the adverse effects of wake on downstream wind turbines and improve the overall operating efficiency and stability of wind farms.

[0046] According to the attenuation prediction of the downstream wind turbine calculated in the previous steps, this includes the evaluation of the impact of factors such as wind speed changes and turbulence intensity changes that may be caused by the upstream wind turbine wake on the performance of the downstream wind turbine. Then, the power curve of the downstream wind turbine is introduced. The power curve describes the output power characteristics of the wind turbine at different wind speeds. Combined with the current actual situation of the downstream wind turbine and the power curve, it is more accurate to judge how the power output of the downstream wind turbine will change under specific attenuation prediction conditions. For example, if the attenuation prediction shows that the downstream wind turbine is affected by the wake, resulting in a decrease in wind speed, by querying the power curve, it is determined how much the power output of the downstream wind turbine is expected to decrease at this reduced wind speed. Finally, by comprehensively considering the attenuation prediction and the analysis results of the power curve, the power output change of the downstream wind turbine is calculated. This change value reflects the specific degree of influence of the upstream wind turbine wake on the power output of the downstream wind turbine. The generated wake effect calculation results provide key data support for the subsequent formulation of wind turbine scheduling plans, enabling the wind farm to reasonably adjust the power output of each wind turbine according to the size of the wake effect to improve the power generation efficiency and stability of the entire wind farm.

[0047] In a possible implementation, step S400 further includes:

[0048] Step S410: Based on the wake effect calculation result, combined with the multi-wind turbine collaborative optimization algorithm, the power output of the upstream and downstream wind turbines is dynamically adjusted and allocated to generate a wind turbine scheduling plan.

[0049] Specifically, based on the calculation results of the wake effect calculated previously, the mutual influence of the wakes between the wind turbines in the wind farm is understood, including the power attenuation degree of the upstream wind turbine on the downstream wind turbine. These results provide an important basis for formulating a reasonable scheduling plan and can clarify the direction and focus that need to be adjusted. The multi-wind turbine collaborative optimization algorithm is introduced. Here, the genetic algorithm is used. The genetic algorithm is an optimization algorithm that simulates the biological evolution process. It simulates natural selection, crossover and mutation operations to find the optimal solution in the search space. In the context of the wind farm, the genetic algorithm uses the power output of each wind turbine in the wind farm as an individual gene, and through continuous iterative evolution, it finds the power output combination that can optimize the performance of the entire wind farm. The genetic algorithm will dynamically adjust and allocate the power output of the upstream and downstream wind turbines according to the calculation results of the wake effect and the set optimization goals. For example, if the calculation results of the wake effect show that the upstream wind turbine has a greater impact on the downstream wind turbine, the genetic algorithm will reduce the power output of the upstream wind turbine and appropriately increase the power output of the downstream wind turbine to reduce the negative impact of the wake and improve the power generation efficiency of the entire wind farm. Through continuous iteration and optimization, the genetic algorithm eventually generates a wind turbine scheduling plan that takes into account the wake interactions between wind turbines and the overall performance goals of the wind farm, and can achieve efficient operation of the wind farm and reasonable allocation of power output.

[0050] In a possible implementation, step S410 further includes:

[0051] Step S411: According to the wake effect calculation result, the wake influence of the upstream wind turbine on the downstream wind turbine is identified, and the power output of the upstream wind turbine is dynamically adjusted.

[0052] Step S412: Based on the real-time operating status of all wind turbines and combined with the power output feedback of downstream wind turbines, the multi-wind turbine collaborative optimization algorithm is used to dynamically optimize the power output distribution of all wind turbines to generate a wind turbine scheduling plan.

[0053] Specifically, in the wake dispatch of wind farms under wind direction monitoring, according to the calculation results of the wake effect, the wake influence of the upstream wind turbine on the downstream wind turbine can be clearly understood. The calculation results of the wake effect include information such as the degree of wind speed attenuation and the change of turbulence intensity. This information can accurately reflect the degree of interference of the wake generated by the upstream wind turbine on the operation of the downstream wind turbine. Once this wake influence is determined, it is necessary to dynamically adjust the power output of the upstream wind turbine, because the power output of the upstream wind turbine is directly related to the intensity of the wake generated by it. If the power output of the upstream wind turbine is too high, its wake will have too much impact on the downstream wind turbine, thereby reducing the power generation efficiency of the downstream wind turbine. On the contrary, if the power output of the upstream wind turbine is appropriately reduced, the intensity of the wake can be reduced and the interference with the downstream wind turbine can be reduced. In actual operation, by analyzing the calculation results of the wake effect, a suitable power adjustment range is determined. This range may vary according to factors such as different wind farm layouts, wind turbine models, and real-time wind conditions. At the same time, the total power generation target of the entire wind farm must be taken into account. The overall power generation of the wind farm cannot be significantly reduced due to the adjustment of the power output of the upstream wind turbine.

[0054] The real-time operating status of all wind turbines is obtained, which includes many key parameters of each wind turbine, such as the current speed, blade angle, actual power output, equipment health and other operation-related information. These real-time operating status data can reflect the current working status of each wind turbine. At the same time, combined with the power output feedback of the downstream wind turbine, the power output feedback of the downstream wind turbine is an important indicator, which directly reflects the degree of influence of the upstream wind turbine wake on it. If the power output of the downstream wind turbine is lower than expected, it means that the wake of the upstream wind turbine has a greater impact, and the power output distribution of the entire wind farm needs to be adjusted. Next, the multi-wind turbine collaborative optimization algorithm is used. The genetic algorithm is used here. The genetic algorithm regards the power output of all wind turbines as a set of genes and finds the optimal power output combination by simulating the natural evolution process. In each iteration, the algorithm will evaluate the advantages and disadvantages of different power output combinations according to the set fitness function. The fitness function will comprehensively consider multiple factors, such as the total power output of the wind farm, the power balance between each wind turbine, and the influence of the wake effect. Based on these factors, the algorithm will score different power output combinations, and then generate new power output combinations through operations such as selection, crossover and mutation, and repeat this process until the optimal or near-optimal power output allocation scheme is found. In this process, the algorithm will dynamically adjust the power output allocation based on the real-time operating status of all wind turbines and the power output feedback of downstream wind turbines. For example, if some wind turbines are in good operating condition, but the power output of downstream wind turbines is insufficient due to the effect of wake, the algorithm will appropriately reduce the power output of these well-running wind turbines and allocate more wind energy to downstream wind turbines to improve the power generation efficiency of the entire wind farm. Finally, through the continuous optimization and adjustment of the genetic algorithm, a wind turbine scheduling plan is generated. This plan can reasonably allocate the power output of each wind turbine according to the real-time situation of the wind farm, minimize the negative impact of the wake effect, and improve the overall performance and power generation efficiency of the wind farm.

[0055] In a possible implementation, step S500 further includes:

[0056] Step S510: Obtain comparison results to determine the difference between the real-time power and the expected power of each wind turbine.

[0057] Step S520: Based on the difference result, the scheduling plan is updated in real time to dynamically adjust the power output of the upstream wind turbine and the downstream wind turbine.

[0058] Specifically, first, in order to obtain the comparison results, it is necessary to obtain the real-time power and expected power data of each wind turbine at the same time. The real-time power data is collected by the power monitoring equipment installed on the wind turbine. These devices can record the power generated by the wind turbine in real time during actual operation and transmit the data to the central control system. The expected power is pre-set based on the previous wake effect calculation results, wind turbine scheduling scheme and various parameters of the wind farm. It is the power output that the wind turbine should theoretically achieve under given wind conditions, wind turbine geometric parameters and operating parameters. After obtaining these two sets of data, the real-time power of each wind turbine is compared with the expected power one by one. The comparison process needs to take into account the influence of various factors, such as changes in wind speed and wind direction at different locations in the wind farm, fluctuations in wind turbine equipment performance, dynamic changes in wake effects, etc. Through precise calculation and analysis, the difference between the real-time power and expected power of each wind turbine is determined. For each wind turbine, this difference result may be positive, negative or zero. If the real-time power is greater than the expected power, it means that the current wind conditions are more favorable to the wind turbine, or the wind turbine's operating status exceeds expectations; if the real-time power is less than the expected power, it is due to strong wake interference, lower-than-expected wind speed, wind turbine equipment failure or other factors; and when the real-time power is equal to the expected power, it means that the actual operation of the wind turbine is consistent with expectations. By determining the difference between the real-time power and the expected power of each wind turbine, the actual operating status of each wind turbine can be clearly understood, and accurate data basis can be provided for subsequent scheduling plan adjustments, so that timely measures can be taken to optimize the operation of the wind farm and improve power generation efficiency and stability.

[0059] After obtaining the difference between the real-time power and the expected power of each wind turbine, the scheduling plan is updated in real time based on this and the power output of the upstream and downstream wind turbines is dynamically adjusted. First, carefully analyze the difference results. If it is found that the real-time power of some wind turbines is significantly lower than the expected power, it is because the wake of the upstream wind turbine is too large, or the wind conditions have changed, causing the wind turbine to fail to fully utilize the wind energy. At this time, it is necessary to re-evaluate the wake distribution in the wind farm and the wind farm environment of each wind turbine. For the upstream wind turbine, according to the difference results and wake analysis, its power output will be appropriately reduced. This is because excessive power output may cause the wake intensity to be too large, causing serious interference to the downstream wind turbine. By reducing the power output of the upstream wind turbine, the wake effect can be reduced, so that the downstream wind turbine can obtain more wind energy. For example, if it is found that the downstream wind turbines in a certain area are generally underpowered according to the difference results, and the wake diffusion range of the upstream wind turbines in this area is large, then the power of the upstream wind turbine can be appropriately reduced, such as adjusting the blade angle or reducing the speed, so as to reduce the influence of the wake. For the downstream wind turbine, based on the difference results and the overall wind farm conditions, its power output will be appropriately increased. If the power of the downstream wind turbine is low due to the influence of the upstream wake, the power output can be improved by optimizing its operating parameters while ensuring the safety and stable operation of its equipment. For example, according to the real-time wind conditions and wake conditions, adjust the blade angle of the downstream wind turbine to better capture wind energy, or increase the speed within a suitable range to increase power output. In the process of updating the scheduling plan in real time, it is necessary to continuously monitor and evaluate the power output changes of each wind turbine and the overall operating status of the wind farm. By dynamically adjusting the power output of the upstream and downstream wind turbines, the wind farm can better adapt to the changes in wind conditions and the influence of the wake effect, thereby improving the power generation efficiency and stability of the entire wind farm. At the same time, it is also necessary to take into account the equipment limitations and safe operation requirements of the wind turbine to ensure that the power output is adjusted within a reasonable range to avoid damage to the wind turbine equipment.

[0060] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0061] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0062] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A wind farm wake dispatching method under wind direction monitoring, characterized in that: include: By installing wind direction monitoring equipment and wind speed sensors in the wind farm, the wind speed and direction data of each wind turbine in the wind farm and meteorological data are obtained in real time to generate real-time wind condition information of the wind farm; Obtain the geometric parameters and operating parameters of each wind turbine in the wind farm; Based on the real-time wind condition information, combined with the geometric parameters and operating parameters of each wind turbine, a wake effect model is used to calculate the wake effect between each wind turbine in the wind farm, and a wake effect calculation result is generated; generating a wind turbine dispatching plan according to the wake effect calculation result; The wind turbine scheduling plan is executed to control the power output of each wind turbine, monitor the power output and operating status of each wind turbine in real time, compare them with the wake effect calculation results, and dynamically adjust the wind turbine scheduling plan.

2. The method according to claim 1, characterized in that The real-time acquisition of wind speed and wind direction data and meteorological data of each wind turbine in the wind farm includes: The wind speed and direction at multiple points are collected in real time through the weather stations installed at different locations in the wind farm and the wind direction monitoring equipment and wind speed sensors of each wind turbine; Meteorological data in the wind farm are collected, wherein the meteorological data include humidity, temperature, and atmospheric pressure.

3. The method according to claim 1, characterized in that The step of obtaining geometric parameters and operating parameters of each wind turbine in the wind farm further includes: An interactive wind turbine history database is used to obtain geometric parameters and operating parameters of each wind turbine, wherein the geometric parameters include blade diameter, hub height, wind turbine spacing, and tower height of each wind turbine, and the operating parameters include power output, power curve, turbulence intensity, rotation speed, blade angle, and real-time status of each wind turbine.

4. The method according to claim 3, characterized in that Based on the real-time wind condition information, combined with the geometric parameters and operating parameters of each wind turbine, before using the wake effect model for calculation, the following steps are also included: Performing data cleaning on the real-time wind condition information; The geometric parameters and operating parameters of each fan are standardized.

5. The method according to claim 4, characterized in that Based on the real-time wind condition information, combined with the geometric parameters and operating parameters of each wind turbine, a wake effect model is used to calculate the wake effect between each wind turbine in the wind farm, and generating the wake effect calculation result also includes: Using the real-time wind condition information, combined with the geometric parameters and operating parameters of each wind turbine, inputting the wake effect model, calculating the wake diffusion range of the upstream wind turbine, and determining the impact area at the downstream position; By combining the influence area at the downstream position with the wake diffusion coefficient and the turbulence intensity, the wake effect model is input to calculate the attenuation prediction of the downstream wind turbine; In combination with the attenuation prediction of the downstream fan, the power curve of the downstream fan is used to calculate the power output change of the downstream fan to generate the wake effect calculation result.

6. The method according to claim 5, characterized in that Generating a wind turbine dispatching plan according to the wake effect calculation result also includes: Based on the calculation results of the wake effect, combined with the multi-wind turbine collaborative optimization algorithm, the power output of the upstream and downstream wind turbines is dynamically adjusted and allocated to generate a wind turbine scheduling plan.

7. The method according to claim 6, characterized in that Based on the wake effect calculation result, combined with the multi-wind turbine collaborative optimization algorithm, the power output of the upstream and downstream wind turbines is dynamically adjusted and allocated to generate a wind turbine scheduling plan. The method also includes: According to the wake effect calculation result, identifying the wake effect of the upstream wind turbine on the downstream wind turbine, and dynamically adjusting the power output of the upstream wind turbine; Based on the real-time operating status of all wind turbines and combined with the power output feedback of downstream wind turbines, the multi-wind turbine collaborative optimization algorithm is used to dynamically optimize the power output distribution of all wind turbines and generate a wind turbine scheduling plan.

8. The method according to claim 7, characterized in that The power output and operating status of each wind turbine are monitored in real time, and compared with the wake effect calculation result, and the wind turbine scheduling plan is dynamically adjusted. The method further includes: Obtain comparison results to determine the difference between the real-time power and the expected power of each wind turbine; Based on the difference results, the scheduling plan is updated in real time to dynamically adjust the power output of the upstream wind turbines and the downstream wind turbines.

Images