Method and device for determining wind power, equipment, medium and product
By adjusting the model and using deep learning technology based on wind speed information in wind farms, the problem of high computational complexity and insufficient accuracy in wind power prediction has been solved, achieving efficient and low-cost wind power prediction and improving the grid dispatch and economic benefits of wind farms.
Patent Information
- Application Number
- CN202511690224.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-18
- Publication Date
- 2026-02-27
AI Technical Summary
Existing wind power prediction methods rely on physical models, which have high computational complexity, limited real-time performance, and high cost. They also fail to effectively reflect the wake effect of wind farms, resulting in insufficient prediction accuracy.
By determining the location, wind speed, wind direction, temperature, and humidity of the wind turbines to be predicted in the wind farm, the model is adjusted using pre-trained wind speed information. Combined with long short-term memory networks and multilayer perceptron models, the wind speed information is optimized, the wake effect is corrected, and the wind speed and wind power of each wind turbine are accurately determined.
It enables efficient and low-cost wind power prediction, improves the grid dispatching capability and equipment operating efficiency of wind farms, and enhances the economic benefits of wind farms.
Smart Images
Figure CN121584543A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of wind power, in particular to a wind power determination method, device, equipment, medium and product. BACKGROUND
[0002] As a safe and clean renewable energy, wind energy has great development potential. Precise prediction of wind power of a wind farm can effectively improve the grid scheduling capability, optimize power scheduling, improve the operation efficiency of wind power equipment and the economic benefit of the wind farm.
[0003] At present, the power prediction method of the wind farm is to obtain environmental information such as meteorological information and wind speed of the wind farm, and then combine empirical coefficients such as wind turbine power control coefficients and environmental coefficients to optimize the obtained environmental information, analyze the wind speed information of each wind turbine in the wind farm, and then determine the wind power of the wind farm. However, the method of correcting the wind speed and determining the wind power by using the empirical coefficients needs to use a physical model, the calculation complexity of the physical model is high, the real-time performance of the wind power prediction is limited, the demand for computing resources is large, and the cost of the wind power prediction is high. In addition, the scale of the wind farm is large and the terrain is complex, the wind speed and power of the downstream wind turbine are affected by the upstream wind turbine, and the empirical coefficients such as the wind turbine power control coefficients and the environmental coefficients cannot reflect the wake effect of the wind farm, so the prediction accuracy of the wind power is limited.
[0004] Therefore, how to accurately, efficiently and at low cost determine the wind speed and wind power of each wind turbine in the wind farm, and then predict the wind power of the wind farm, and improve the grid scheduling capability, optimize the power scheduling, improve the operation efficiency of the wind power equipment and the economic benefit of the wind farm, is a problem to be solved in the field of wind power technology. SUMMARY
[0005] The present application provides a wind power determination method, device, equipment, medium and product, which can evaluate the influence degree between wind turbines, accurately, efficiently and at low cost determine the wind speed and wind power of each wind turbine in the wind farm, and then predict the wind power of the wind farm, and improve the grid scheduling capability, optimize the power scheduling, improve the operation efficiency of the wind power equipment and the economic benefit of the wind farm.
[0006] According to an aspect of the present application, a wind power determination method is provided, which comprises:
[0007] determining the position information of a to-be-predicted wind turbine, the wind speed information, the wind direction information, the temperature information and the humidity information of the wind farm, wherein the to-be-predicted wind turbine comprises at least two wind turbines;
[0008] processing the wind speed information, the wind direction information, the temperature information, the humidity information and the position information of the at least two wind turbines to obtain standby wind speed information of the at least two wind turbines;
[0009] The wind speed information adjustment model is used to process the wind speed information, the wind direction information, the temperature information, the humidity information and the standby wind speed information of the at least two wind turbines, to obtain target wind speed information of the at least two wind turbines.
[0010] Based on the target wind speed information of the at least two wind turbines, the wind power of the at least two wind turbines is determined, and the wind power of the wind farm is determined according to the wind power of the at least two wind turbines.
[0011] According to another aspect of the present application, a wind power determination device is provided, which is used to implement the wind power determination method in any of the embodiments of the present application. The device comprises:
[0012] An information acquisition module is configured to determine position information of wind turbines to be predicted, wind speed information, wind direction information, temperature information and humidity information of a wind farm, wherein the wind turbines to be predicted include at least two wind turbines.
[0013] A wind speed determination module is configured to process the wind speed information, the wind direction information, the temperature information, the humidity information and the position information of the at least two wind turbines, to obtain standby wind speed information of the at least two wind turbines.
[0014] A wind speed adjustment module is configured to use a pre-trained wind speed information adjustment model to process the wind speed information, the wind direction information, the temperature information, the humidity information and the standby wind speed information of the at least two wind turbines, to obtain target wind speed information of the at least two wind turbines.
[0015] A power determination module is configured to determine wind power of the at least two wind turbines based on the target wind speed information of the at least two wind turbines, and determine wind power of the wind farm according to the wind power of the at least two wind turbines.
[0016] According to another aspect of the present application, an electronic device is provided, which comprises:
[0017] At least one processor; and a memory connected to the at least one processor in communication;
[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the wind power determination method in any of the embodiments of the present application.
[0019] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the wind power determination method in any of the embodiments of the present application when executed.
[0020] According to another aspect of the present application, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of determining wind power of any of the embodiments of the present application.
[0021] The method of determining wind power of the present application comprises: determining position information of wind turbines to be predicted, wind speed information, wind direction information, temperature information and humidity information of a wind farm, the wind turbines to be predicted comprising at least two wind turbines; processing the wind speed information, the wind direction information, the temperature information, the humidity information and the position information of the at least two wind turbines to obtain standby wind speed information of the at least two wind turbines; processing the wind speed information, the wind direction information, the temperature information, the humidity information and the standby wind speed information of the at least two wind turbines by using a pre-trained wind speed information adjustment model to obtain target wind speed information of the at least two wind turbines; determining wind power of the at least two wind turbines based on the target wind speed information of the at least two wind turbines, and determining wind power of the wind farm according to the wind power of the at least two wind turbines. According to the technical solution of the present application, the standby wind speed of each wind turbine is determined according to the wind speed information, the wind direction information, the temperature information and the humidity information of the wind farm and the position information of each wind turbine, and then the wind speed information, the wind direction information, the temperature information and the humidity information of the wind farm and the standby wind speed of each wind turbine are processed automatically, efficiently and at low cost by using the wind speed information adjustment model. In essence, the influence of the upstream wind turbine on the downstream wind turbine is analyzed in combination with the environmental information, and then the standby wind speed of each wind turbine is adjusted to obtain the target wind speed of each wind turbine, thereby improving the accuracy of the wind speed of the wind turbine, and further obtaining the wind power of each wind turbine and the wind power of the wind farm with better accuracy, thereby improving the prediction accuracy of the wind power. The problems of high calculation complexity of the physical model, limited real-time prediction of the wind power, large demand for calculation resources and high prediction cost of the wind power are solved by using the experience coefficient to correct the wind speed and determine the wind power. The problems of limited prediction accuracy of the wind power due to the large scale and complex terrain of the wind farm, the influence of the upstream wind turbine on the wind speed and power of the downstream wind turbine, and the fact that the experience coefficient such as the wind turbine power control coefficient and the environmental coefficient cannot reflect the wake effect of the wind farm are also solved.
[0022] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS
[0023] In order to more clearly illustrate the technical solutions in the present application, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creating any labor.
[0024] Figure 1 This is a flowchart illustrating a method for determining wind power provided by the present invention.
[0025] Figure 2 This is a flowchart illustrating another method for determining wind power provided by the present invention;
[0026] Figure 3 This is a schematic diagram of the structure of a wind power determination device provided by the present invention;
[0027] Figure 4 This is a schematic diagram of the structure of an electronic device provided by the present invention. Detailed Implementation
[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort should fall within the scope of protection of the present invention.
[0029] It should be noted that the terms "first," "second," "initial," "intermediate," "candidate," "alternate," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0030] The technical solutions of the present application meet the relevant provisions of national laws and regulations in data acquisition, storage, use, processing, etc. Specifically, the user information collected in the present application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with relevant national and regional laws, regulations and standards, necessary security measures are taken, public order and good customs are not violated, and appropriate operation portals are provided for users to choose authorization or refuse automated decision results; if the user chooses to refuse, the expert decision process is entered. It should be noted that in the embodiments of the present application, some industry existing solutions, components, models, etc. may be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility of the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the related content of the solution.
[0031] Figure 1 is a flowchart of a wind power determination method provided by the present application, and the present embodiment can be applied to accurately, efficiently and low-costly determine the wind speed and wind power of each wind turbine in a wind farm, and high-quality predict the wind power of the wind farm, such as predicting the wind power of a complex terrain wind farm in the future 0-6 hours. The method can be executed by a wind power determination device provided by the present application, which can be realized in the form of hardware and / or software. In a specific embodiment, the device can be integrated in an electronic device. The following embodiments will be described by taking the device integrated in an electronic device as an example, and the device can be realized in the form of hardware and / or software. Figure 1 The method specifically includes the following steps:
[0032] S101, determining the position information of the wind turbine to be predicted in the wind farm, the wind speed information, the wind direction information, the temperature information and the humidity information of the wind farm.
[0033] A wind farm, also known as a wind power plant or wind field, can be understood as a complete power generation facility that deploys several (dozens to hundreds) wind turbine generators (i.e., wind turbines, with a capacity generally between 1MW and 15MW) in the same area, along with supporting equipment such as power collection lines, substations, transmission lines, and control systems. It then converts wind energy into electrical energy through unified scheduling and centrally transmits it to the power grid. Generally, all wind turbines in a wind farm participate in wind power generation. The wind turbines to be predicted refer to all wind turbines in the wind farm, including at least two turbines. The location information of the wind turbines to be predicted can be understood as the spatial location information of each turbine in the wind farm, not simply latitude and longitude information. It is an optimized set of coordinates constrained by multiple factors such as wind resources, terrain, environmental protection, power grid, and transportation. The location information is unique for each turbine. In this invention, wind speed information is essentially wind speed / wind speed value, wind direction information is essentially wind direction angle, temperature information is essentially temperature / temperature value, and humidity information is essentially temperature / temperature value. Wind farms typically deploy one or more meteorological information monitors to detect meteorological information about the environment, such as wind speed, wind direction, temperature, humidity, and atmospheric pressure. The wind speed, wind direction, temperature, and humidity information of the wind farm in this invention can be understood as the wind speed, wind direction, temperature, and humidity measured by the meteorological information monitors. It is worth noting that if a wind farm deploys meteorological information monitors, the detection results of these monitors constitute the wind speed, wind direction, temperature, and humidity information of the wind farm. If multiple meteorological information monitors are deployed, the wind speed, wind direction, temperature, and humidity information can be determined based on the average of the detection results from multiple monitors. Furthermore, the wind speed, wind direction, temperature, and humidity information of the wind farm can also be determined based on publicly available data from public platforms; this invention does not limit this approach. The advantage of this setup is that it allows for the acquisition of comprehensive and real-time wind farm data, enabling accurate prediction of the wind power output of the wind farm.
[0034] S102. Process the wind speed information, wind direction information, temperature information, humidity information and the location information of at least two fans to obtain the backup wind speed information of at least two fans.
[0035] The wind speed information of the wind farm is the free flow wind speed of the environment where the wind farm is located, but the wind speed at the actual wind turbine is not the free flow wind speed of the environment where the wind farm is located due to the influence of geographical location, terrain and surrounding buildings. The standby wind speed information can be understood as the wind speed information of the environment where each wind turbine is located, which is analyzed in combination with the position information of each wind turbine, the wind speed information, the wind direction information, the temperature information and the humidity information of the wind farm. Specifically, the present application can determine the standby wind speed information of each wind turbine by using a wind speed analysis model, for example, inputting the wind speed information, the wind direction information, the temperature information, the humidity information and the position information of each wind turbine into the wind speed analysis model for processing, and determining the standby wind speed of each wind turbine according to the model output result. The advantage of such setting is that the wind speed received by each wind turbine is analyzed individually in combination with the spatial position of each wind turbine and the environmental information of the wind farm, so as to calculate the wind power of each wind turbine with high quality.
[0036] In one embodiment, S102 can specifically include:
[0037] 1) determining a reference wind turbine of the wind farm from at least two wind turbines based on the wind direction information and the position information of the at least two wind turbines, the reference wind turbine being the wind turbine in the wind farm that is least affected by the wake factor.
[0038] The reference wind turbine is essentially the wind turbine that first contacts the air flow in the entire wind farm, i.e., the most upstream wind turbine in the wind farm. Generally, the reference wind turbine can be considered to be unaffected by other wind turbines, and the wind speed at the reference wind turbine is equivalent to the wind speed of the wind farm. Specifically, the wind turbine that first contacts the air flow in the wind farm can be determined according to the spatial position of each wind turbine and the wind direction information of the wind farm. Generally, the number of reference wind turbines is one, but in special cases, the number of reference wind turbines can also be multiple, which is not limited by the present application.
[0039] 2) determining the wake expansion rate of the wind farm based on the wind speed information, the wind direction information, the temperature information and the humidity information.
[0040] The wake expansion rate is a dimensionless coefficient describing the speed at which the radius of the wake zone of a wind turbine increases linearly with the downstream distance, and determines the wind speed loss and the turbulence intensity increment experienced by the downstream wind turbine. For a wind farm, the wake expansion rate is related to the environmental parameters of the wind farm, including but not limited to air pressure information, wind speed information, wind direction information, temperature information, and humidity information. Specifically, the determination method of the wake expansion rate of the wind farm can be: k = f(x1, x2, x3, x4), wherein k represents the wake expansion rate of the wind farm, f(.) represents the calculation logic of the wake expansion rate, x1 represents the wind speed information of the wind farm, x2 represents the wind direction information of the wind farm, x3 represents the temperature information of the wind farm, x4 represents the humidity information of the wind farm, and x5 represents the air pressure information of the wind farm. After obtaining the air pressure information, wind speed information, wind direction information, temperature information, and humidity information of the wind farm, the wake expansion rate of the wind farm can be calculated by means of the calculation logic of the wake expansion rate.
[0041] 3) Based on the position information of the reference wind turbine and the position information of at least two wind turbines, the distance information of the reference wind turbine and the at least two wind turbines is determined, and based on the wake expansion rate, the wind speed information, and the distance information of the reference wind turbine and the at least two wind turbines, the standby wind speed information of the at least two wind turbines is determined.
[0042] It is worth noting that if wind turbine 1 is the reference wind turbine, the distance information between the reference wind turbine and wind turbine 1 is 0, and the standby wind speed of wind turbine 1 can be considered as the wind speed information of the wind farm since it is not affected by other wind turbines.
[0043] The determination method of the standby wind speed of the remaining wind turbines is the same as that of the reference wind turbine. Taking any one wind turbine as an example, the determination method of the standby wind speed information of the wind turbine is: wherein v represents the standby wind speed information of the wind turbine, v0 represents the wind speed information of the wind farm, k represents the wake expansion rate, x represents the distance information between the wind turbine and the reference wind turbine, D represents the rotor diameter of the wind turbine, and C represents the thrust coefficient of the wind turbine.
[0044] The advantage of such a setting is that the individualized wind speed of each wind turbine is determined by combining the environmental information of the wind farm and the position information of each wind turbine, so as to improve the prediction accuracy of wind power.
[0045] In order to ensure the compatibility of the data, after obtaining the standby wind speed of each wind turbine, the minimum-maximum normalization method is used to process it, and a data set matched with the wind speed information adjustment model is constructed, so that the wind speed information adjustment model optimizes the standby wind speed, obtains a wind speed with higher accuracy in the environment where the wind turbine is located, and further improves the prediction accuracy of wind power. Taking wind speed as an example, the normalization method is: norm xi -x min ) / (x max -x min ), wherein x norm represents the normalized wind speed, x i represents the wind speed before normalization, x min represents the minimum wind speed in the wind speed data, and x max represents the maximum wind speed in the wind speed data. The normalization methods of temperature, humidity, air pressure and the like are the same as that of the wind speed, and the present application does not show this. The constructed data set is [batch_size, T, N, C], which is a multi-dimensional wake flow data set, wherein batch_size represents the batch size, which is the number of samples input into the neural network at a time, generally set between 32 and 512, and the samples contain the environmental information of the wind farm and the standby wind speed of each wind turbine; T is the time step, N is the total number of wind turbines in the wind farm, and C is the number of feature channels, including wind speed, speed deficit (wind speed deficit of the wind turbine relative to the reference wind turbine), temperature, humidity, air pressure and the like. The purpose of data processing is to better connect the wind speed information adjustment model and improve the data processing speed and quality of the wind speed information adjustment model.
[0046] S103, using the pre-trained wind speed information adjustment model to process the wind speed information, wind direction information, temperature information, humidity information and standby wind speed information of at least two wind turbines, and obtain target wind speed information of the at least two wind turbines.
[0047] The pre-trained wind speed information adjustment model can be a fusion model of pre-trained LSTM (Long Short-Term Memory) and MLP (Multi-Layer Perceptron) capable of adjusting and optimizing wind speed, which can improve the prediction accuracy of wind speed by correcting the wake effect error, and thus improve the power prediction accuracy, so as to optimize the power grid dispatching and wind farm operation efficiency. Specifically, the present application adopts an innovative space-time attention network deep learning model, on the one hand, the space-time attention mechanism efficiently captures the space-time dynamic characteristics of the wake effect, and maps the wind speed field to the wind speed prediction of a single wind turbine, on the other hand, through the nonlinear modeling ability and efficient computing ability of STA-Net (Spatial-Temporal Attention Network), the problems of low-fidelity model precision deficiency and high-fidelity model high computational complexity are solved, which has high practicability, and can also reduce the cost and resource demand of the power prediction task.
[0048] The target wind speed information of the fan can be understood as the standby wind speed after the wake effect correction processing, the target wind speed reduces the influence of the upstream fan on the downstream fan as much as possible, is closer to the real wind speed of the fan, and can effectively improve the prediction accuracy of the power of a single fan.
[0049] In one embodiment, S103 can specifically include: 1) adjusting the wind speed information using the model (in fact, adjusting the time sequence feature extraction function of the wind speed information using the model), processing the wind speed information, the wind direction information, the temperature information, the humidity information and the standby wind speed information of the at least two fans to obtain the single-machine time sequence dynamic characteristics of the at least two fans. 2) performing vector splicing processing on the single-machine time sequence dynamic characteristics of the at least two fans to obtain the fan feature matrix of the wind farm. 3) adjusting the wind speed information using the model (in fact, using the spatial feature fusion function of the wind speed information adjustment model), processing the fan feature matrix to obtain the target wind speed information of the at least two fans. The purpose of such setting is to use the wind speed information adjustment model to optimize the standby wind speed of each fan in combination with the environmental information of the wind farm, to obtain a fan wind speed with better accuracy and to improve the wind power prediction accuracy.
[0050] The single-machine time sequence dynamic characteristics refer to the "power-speed-load" response law of a single wind turbine generator set on a second-minute time scale, which is non-stationary, nonlinear and hysteresis.
[0051] The present application can independently construct a long short-term memory network for each fan in a wind farm to extract single-machine time sequence dynamic characteristics. Specifically, for the i th fan, the input of the last time step t is the normalized time sequence data , wherein T is the time step, C is the number of feature channels, is a T-row C-column table or matrix, each row represents a time point, and each column represents a different measurement variable (for example, temperature, humidity, wind speed, etc.), which aims to completely describe the state change of the i th fan at the past T time points through the matrix. The update formula of the hidden state of the LSTM is: , wherein h i,t represents the hidden state of the i th fan at time step t, h i,t-1 represents the hidden state of the i th fan at time step t-1, N is the total number of fans, the present application extracts the hidden state of the last layer of all fans, and the last layer hidden state of a single fan is a vector with a length of d h , and the vectors of N fans are spliced to obtain an N-row d h column matrix (i.e., the fan feature matrix of the wind farm) . It is worth noting that d hFor the dimension of the hidden layer, a larger d h Allow the model to capture longer-term and more complex temporal dependencies, but increase the number of parameters of the model and the risk of overfitting, so the use requirements can be set and adjusted adaptively.
[0052] Further, the i-th (i=1, 2, 3,...N) fan and the spatial characteristics (relative coordinates And , the dominant wind direction and the relative azimuth angle information ) of the upstream fan are spliced. Wherein, j is the upstream fan that has a significant wake effect on fan i (for example, the K fans that have the greatest impact on fan i are dynamically screened according to the wind direction, K can be set and adjusted according to the actual number of fans in the station, which can be 10%, 20%, 30% of the total number of fans, etc. It is worth noting that if there is no upstream fan that has a significant impact under the current wind direction, the parameters involved are determined as 0). is the difference between the x-axis coordinates of fan i and fan j, is the difference between the y-axis coordinates of fan i and fan j, is the dominant wind direction, i.e. the wind direction in the current forecast or the wind direction of the wind farm detected by the weather information monitor, is the angle between the direction from fan i to fan j and the north direction, which is 1 if the dominant wind direction and the relative azimuth angle are consistent, and -1 otherwise. For all fans, a matrix , representing an N-row column matrix, is obtained. The spliced matrix is input into the MLP, and the target wind speed of each fan is obtained. It is worth noting that the wind speed information adjustment model also needs to be optimized regularly. When the error between the predicted wind speed and the actual wind speed is greater than the pre-set error value, the wind speed information adjustment model is optimized. The purpose of this setting is to ensure the wind speed prediction accuracy of the wind speed information adjustment model. Secondly, the adaptive optimization learning rate optimization algorithm can be used during model training and optimization. The wake effect error is optimized by the way of iterative updating the weight through back propagation, and the mean square error is used as the loss function. When the mean square error meets the tolerance range, the model optimization or training is determined to be completed.
[0053] S104, based on the target wind speed information of at least two fans, determine the wind power of at least two fans, and determine the wind power of the wind farm according to the wind power of at least two fans.
[0054] The wind speed of the fan and the power are in a corresponding relationship. After obtaining the target wind speed information of the fan, the wind power of the fan can be obtained by combining the corresponding relationship between the wind speed and the power of the fan. The wind power of the wind farm is the total power of the wind power of all the fans in the wind farm. Ideally, the wind power of the wind farm can be considered as the sum of the wind power of all the fans in the wind farm. However, there is a certain loss in the energy transmission process, so the wind power of the wind farm is generally less than the sum of the wind power of all the fans in the wind farm. The transmission line of the fan is long and short, so the power loss of each fan is different. The accurate wind power of the wind farm can be calculated by combining the wind power and the power loss of each fan.
[0055] Optionally, for any one fan, based on the target wind speed information of the fan, the wind power of the fan is determined, including: determining the cut-in wind speed, the rated wind speed and the cut-out wind speed of the fan; when the target wind speed information is greater than the cut-out wind speed or the target wind speed information is less than the cut-in wind speed, the wind power of the fan is determined as the first wind power; when the target wind speed information is greater than the rated wind speed and less than the cut-out wind speed, the wind power of the fan is determined as the second wind power, the second wind power is the rated power of the fan, and the second wind power is greater than the first wind power; when the target wind speed information is greater than the cut-in wind speed and less than the rated wind speed, the wind power of the fan is determined based on the air density of the wind farm, the target wind speed information, the rotor area and the power coefficient.
[0056] The cut-in wind speed is the wind speed at which the fan starts to generate electricity and is connected to the grid. The rated wind speed is the wind speed at which the fan starts to output rated power. The cut-out wind speed is the highest operating wind speed of the fan. When the cut-out wind speed is reached, the fan needs to be automatically shut down to protect the safety of the unit. Different models of fans have different cut-in wind speeds, rated wind speeds and cut-out wind speeds. The first wind power is essentially the corresponding power when the fan is not connected to the grid (the power is 0). In a specific example, the determination method of the wind power of the fan can be: wherein P(v) represents the wind power of the fan, v represents the target wind speed of the fan, v in represents the cut-in wind speed of the fan, v out represents the cut-out wind speed of the fan, v rated represents the rated wind speed of the fan, P rated represents the rated power of the fan, represents the air density, A represents the rotor area of the fan, and C p represents the power coefficient of the fan. Determining the wind power of the fan based on the air density of the wind farm, the target wind speed information, the rotor area and the power coefficient can be understood as determining the wind power of the fan based on the formula “ ”. The advantage of such setting is to provide a quantitative and specific determination method of the wind power of the fan, so as to quickly, efficiently and accurately calculate the wind power of the fan.
[0057] Optionally, determining the wind power of the wind farm according to the wind power of the at least two wind turbines comprises: determining power loss parameters of the at least two wind turbines based on position information of the at least two wind turbines; and determining the wind power of the wind farm according to the wind power of the at least two wind turbines and the power loss parameters.
[0058] The power loss parameter of the wind turbine can be understood as the loss of energy of the wind turbine in the transmission process. The determination of the power loss parameters of the at least two wind turbines based on the position information of the at least two wind turbines can be understood as the determination of the distance of the energy transmission of each wind turbine according to the position information of each wind turbine, and then the energy loss in the energy transmission of each wind turbine is analyzed. The determination of the wind power of the wind farm according to the wind power of the at least two wind turbines and the power loss parameters can be understood as the determination of the effective wind power of each wind turbine according to the wind power of each wind turbine and the power loss parameters, and then the determination of the wind power of the wind farm according to the sum of the effective wind power of each wind turbine. The advantage of such setting is to estimate the loss and obtain the actual external wind power of the wind farm, so as to provide accurate data source for subsequent grid connection and power optimization tasks.
[0059] Further, after determining the wind power of the wind farm, the application further comprises: obtaining a wind power accuracy indication table of the wind farm, and matching the wind power of the wind farm in the wind power accuracy indication table to obtain wind power accuracy information of the wind farm; determining a wind power deviation of the wind farm according to the wind power accuracy information, and controlling an information interaction interface to display the wind power of the wind farm and the wind power deviation.
[0060] The predicted wind power has a certain deviation compared with the actual wind power, which is similar to normal distribution, and the deviation of wind power in different intervals is different. The wind power accuracy indication table can be understood as indication data of error interval and error degree of each error interval. The matching of the wind power of the wind farm in the wind power accuracy indication table can obtain the wind power accuracy information of the wind farm (i.e., the power deviation degree of the wind farm, such as 0.05%, 0.08%, etc.). The wind power deviation of the wind farm (i.e., the power deviation degree, the specific deviation range) can be calculated by combining the predicted wind power value and the wind power accuracy information. The control of the information interaction interface to display the wind power of the wind farm and the wind power deviation is to facilitate the management personnel to understand the wind power generation situation of the wind farm, so as to perform subsequent electric energy processing tasks, and also to facilitate timely intervention when the wind power generation of the wind farm is abnormal, and to improve the safety of the wind farm.
[0061] The beneficial effects of the wind power determination method (i.e., the wind power prediction method) of the present application include: 1) generating a multi-dimensional wake data set containing wind turbine location, wind speed variation, and wake propagation characteristics (e.g., wake diameter, speed deficit, etc.), constructing an index system directly related to wind farm power prediction through a customized feature extraction algorithm, and improving power prediction accuracy and efficiency. Compared with the traditional method of using only meteorological data, the present application associates the wake effect with the wind turbine operating parameters (e.g., power curve, cut-out wind speed, etc.), realizing the business transformation from "meteorological prediction" to "power impact prediction". 2) Combined with the spatial attention mechanism to capture the spatial distribution characteristics of the wake, the time series attention mechanism is used to determine the dynamic dependence of wind speed variation, which has stronger non-linear modeling capability and computational efficiency than traditional physical models. 3) The prediction accuracy index can be defined and the model can be optimized through regional double rules evaluation rules to ensure that the prediction results meet the requirements of power grid dispatching, and compared with the general terrain correction, it is more suitable for wind farm operation requirements. The technical scheme of the present application can significantly improve the short-term power prediction accuracy of complex terrain wind farms, especially in the case of multiple wind turbine layouts and dynamic wind conditions. The spatial-temporal attention mechanism can effectively capture the non-linear characteristics of the wake effect, correct the prediction error of the low-fidelity model, output high-precision wind speed of a single wind turbine, and improve the power prediction results of the whole field. Through Monte Carlo sampling, the confidence interval is provided to provide a reliable basis for power grid dispatching and operation decision-making.
[0062] The technical scheme of the above embodiment determines the standby wind speed of each wind turbine according to the wind speed information, wind direction information, temperature information, and humidity information of the wind farm and the position information of each wind turbine, and then adjusts the model using the wind speed information to automatically, efficiently, and low-costly process the wind speed information, wind direction information, temperature information, and humidity information of the wind farm and the standby wind speed of each wind turbine. In essence, the wake effect of the upstream wind turbine on the downstream wind turbine is analyzed in combination with the environmental information, and then the standby wind speed of each wind turbine is adjusted to obtain the target wind speed of each wind turbine, improve the accuracy of the wind speed of the wind turbine, and further obtain the wind power of each wind turbine and the wind power of the wind farm with better accuracy, thereby improving the prediction accuracy of the wind power. The method solves the problems of high computational complexity of the physical model, limited real-time prediction of the wind power, large demand for computing resources, and high cost of predicting the wind power. It also solves the problem of large scale and complex terrain of the wind farm, where the upstream wind turbine affects the wind speed and power of the downstream wind turbine, and the empirical coefficients such as wind turbine power control coefficient and environmental coefficient cannot reflect the wake effect of the wind farm, resulting in limited prediction accuracy of the wind power.
[0063] Figure 2is a flowchart of another method for determining wind power provided by the present application, and the embodiment provides a preferred method for determining wind power of a wind farm with more complete flow details on the basis of the above-mentioned embodiment. Specifically, as shown in the figure, the method comprises the following steps. Figure 2
[0064] S201, determining position information of a to-be-predicted wind turbine in a wind farm, wind speed information, wind direction information, temperature information and humidity information of the wind farm.
[0065] The to-be-predicted wind turbine comprises at least two wind turbines.
[0066] S202, determining a reference wind turbine of the wind farm from the at least two wind turbines based on the wind direction information and the position information of the at least two wind turbines.
[0067] The reference wind turbine is the wind turbine in the wind farm that is least affected by the wake factor.
[0068] S203, determining a wake expansion rate of the wind farm based on the wind speed information, the wind direction information, the temperature information and the humidity information.
[0069] S204, determining distance information of the reference wind turbine and the at least two wind turbines based on the position information of the reference wind turbine and the position information of the at least two wind turbines, and determining standby wind speed information of the at least two wind turbines according to the wake expansion rate, the wind speed information, the distance information of the reference wind turbine and the at least two wind turbines.
[0070] S205, processing the wind speed information, the wind direction information, the temperature information, the humidity information and the standby wind speed information of the at least two wind turbines by using a wind speed information adjustment model to obtain single-machine time-series dynamic characteristics of the at least two wind turbines.
[0071] S206, performing vector splicing processing on the single-machine time-series dynamic characteristics of the at least two wind turbines to obtain a wind turbine feature matrix of the wind farm.
[0072] S207, processing the wind turbine feature matrix by using a wind speed information adjustment model to obtain target wind speed information of the at least two wind turbines.
[0073] S208, determining wind power of the at least two wind turbines based on the target wind speed information of the at least two wind turbines, and determining wind power of the wind farm according to the wind power of the at least two wind turbines.
[0074] Figure 3 is a structural diagram of a device for determining wind power provided by the present application. As shown in the figure, Figure 3 The device comprises an information acquisition module 301, a wind speed determination module 302, a wind speed adjustment module 303 and a power determination module 304.
[0075] The information acquisition module 301 is configured to determine position information of wind turbines to be predicted, wind speed information, wind direction information, temperature information and humidity information of the wind farm, wherein the wind turbines to be predicted include at least two wind turbines.
[0076] The wind speed determination module 302 is configured to process the wind speed information, the wind direction information, the temperature information, the humidity information and the position information of the at least two wind turbines to obtain standby wind speed information of the at least two wind turbines.
[0077] The wind speed adjustment module 303 is configured to process the wind speed information, the wind direction information, the temperature information, the humidity information and the standby wind speed information of the at least two wind turbines by using a pre-trained wind speed information adjustment model to obtain target wind speed information of the at least two wind turbines.
[0078] The power determination module 304 is configured to determine wind power of the at least two wind turbines based on the target wind speed information of the at least two wind turbines, and determine wind power of the wind farm according to the wind power of the at least two wind turbines.
[0079] Optionally, the wind speed determination module 302 is specifically configured to determine a reference wind turbine of the wind farm from the at least two wind turbines based on the wind direction information and the position information of the at least two wind turbines, wherein the reference wind turbine is a wind turbine of the wind farm that is least affected by a wake factor; determine a wake expansion rate of the wind farm based on the wind speed information, the wind direction information, the temperature information and the humidity information; determine distance information of the reference wind turbine and the at least two wind turbines based on the position information of the reference wind turbine and the position information of the at least two wind turbines, and determine the standby wind speed information of the at least two wind turbines according to the wake expansion rate, the wind speed information and the distance information of the reference wind turbine and the at least two wind turbines.
[0080] Optionally, the wind speed adjustment module 303 is specifically configured to process the wind speed information, the wind direction information, the temperature information, the humidity information and the standby wind speed information of the at least two wind turbines by using the wind speed information adjustment model to obtain single-machine time-series dynamic characteristics of the at least two wind turbines; perform vector splicing processing on the single-machine time-series dynamic characteristics of the at least two wind turbines to obtain a wind turbine feature matrix of the wind farm; and process the wind turbine feature matrix by using the wind speed information adjustment model to obtain the target wind speed information of the at least two wind turbines.
[0081] Optionally, for any one wind turbine, the power determination module 304 is specifically configured to: determine the cut-in wind speed, the rated wind speed and the cut-out wind speed of the wind turbine; when the target wind speed information is greater than the cut-out wind speed or the target wind speed information is less than the cut-in wind speed, determine the wind power of the wind turbine as a first wind power; when the target wind speed information is greater than the rated wind speed and less than the cut-out wind speed, determine the wind power of the wind turbine as a second wind power, wherein the second wind power is the rated power of the wind turbine, and the second wind power is greater than the first wind power; and when the target wind speed information is greater than the cut-in wind speed and less than the rated wind speed, determine the wind power of the wind turbine based on the air density of the wind farm, the target wind speed information, the rotor area and the power coefficient.
[0082] Optionally, the power determination module 304 is specifically configured to: determine the power loss parameters of the at least two wind turbines based on the position information of the at least two wind turbines; and determine the wind power of the wind farm according to the wind power of the at least two wind turbines and the power loss parameters.
[0083] Optionally, the wind power determination device further comprises a prompt module configured to: after determining the wind power of the wind farm, acquire a wind power accuracy indication table of the wind farm, and match the wind power of the wind farm in the wind power accuracy indication table to obtain wind power accuracy information of the wind farm; determine a wind power deviation of the wind farm according to the wind power accuracy information, and control an information interaction interface to display the wind power of the wind farm and the wind power deviation.
[0084] The wind power determination device provided in the embodiment can perform the wind power determination method provided in any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.
[0085] Figure 4 is a structural schematic diagram of an electronic device provided by the present application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices (such as headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.
[0086] As Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory 12, a random access memory (also referred to as a random access memory) 13, etc., which is communicatively connected to the at least one processor 11, wherein the memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory 12 or loaded from the storage unit 18 into the random access memory 13. In the random access memory 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the read-only memory 12, and the random access memory 13 are connected to each other through a bus 14. An input / output interface 15 is also connected to the bus 14.
[0087] A plurality of components in the electronic device 10 are connected to the input / output interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.
[0088] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit, a graphics processing unit, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, a digital signal processor, and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the determination method of wind power.
[0089] In some embodiments, the determination method of wind power can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the read-only memory 12 and / or the communication unit 19. When the computer program is loaded into the random access memory 13 and executed by the processor 11, one or more steps of the determination method of wind power described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the determination method of wind power by any other appropriate means (for example, by means of firmware).
[0090] The various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits, application specific standard products, chips, microprocessors, computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.
[0091] Computer programs used to implement the methods of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program
[0092] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory / flash memory, an optical fiber, a portable compact disc read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0093] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.
[0094] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), a blockchain network, and the Internet.
[0095] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of large management difficulty and weak business scalability in traditional physical hosts and virtual private servers.
[0096] In one specific embodiment, the present application further includes a computer program product comprising a computer program which, when executed by a processor, implements the method of determining wind power of any embodiment of the present application.
[0097] The computer program product, in implementation, can be written in one or more programming languages or combinations of languages to implement the operations of the present application, including object oriented programming languages and conventional procedural programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network or a wide area network, or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).
[0098] It should be understood that the various forms of flow shown above can be re-ordered, added to, or have steps deleted. For example, the steps recited in the present application can be performed in parallel, in series, or in a different order, without limitation herein, so long as the desired results of the technical solutions of the present application are achieved.
[0099] The specific embodiments discussed above do not constrain the scope of the present application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and alternatives can be made to the specific embodiments without departing from the spirit and principles of the present application. Any such modifications, equivalents, and alternatives are intended to be included within the scope of the present application.
Claims
1. A method for determining wind power output, characterized in that, include: The location information of the wind turbines to be predicted in the wind farm, the wind speed information, wind direction information, temperature information and humidity information of the wind farm are determined, wherein the wind turbines to be predicted include at least two wind turbines; The wind speed information, wind direction information, temperature information, humidity information, and the location information of the at least two fans are processed to obtain the backup wind speed information of the at least two fans; Using a pre-trained wind speed information adjustment model, the wind speed information, wind direction information, temperature information, humidity information, and backup wind speed information of at least two wind turbines are processed to obtain the target wind speed information of the at least two wind turbines; Based on the target wind speed information of the at least two wind turbines, the wind power of the at least two wind turbines is determined, and the wind power of the wind farm is determined based on the wind power of the at least two wind turbines.
2. The method according to claim 1, characterized in that, The process of processing the wind speed information, wind direction information, temperature information, humidity information, and the location information of the at least two fans to obtain the backup wind speed information of the at least two fans includes: Based on the wind direction information and the location information of the at least two wind turbines, a reference wind turbine for the wind farm is determined from the at least two wind turbines, wherein the reference wind turbine is the wind turbine in the wind farm that is least affected by wake factors. Based on the wind speed information, wind direction information, temperature information, and humidity information, the wake spread rate of the wind farm is determined; Based on the location information of the reference fan and the location information of the at least two fans, the distance information between the reference fan and the at least two fans is determined, and the backup wind speed information of the at least two fans is determined according to the wake spread rate, the wind speed information, and the distance information between the reference fan and the at least two fans.
3. The method according to claim 1, characterized in that, The step of using a pre-trained wind speed information adjustment model to process the wind speed information, wind direction information, temperature information, humidity information, and the standby wind speed information of at least two wind turbines to obtain the target wind speed information of the at least two wind turbines includes: Using the wind speed information adjustment model, the wind speed information, wind direction information, temperature information, humidity information, and standby wind speed information of the at least two wind turbines are processed to obtain the individual time-series dynamic characteristics of the at least two wind turbines; The individual time-series dynamic features of the at least two wind turbines are processed by vector concatenation to obtain the wind turbine feature matrix of the wind farm; The wind speed information adjustment model is used to process the wind turbine feature matrix to obtain the target wind speed information of the at least two wind turbines.
4. The method according to claim 1, characterized in that, For any given wind turbine, the wind power output of the wind turbine is determined based on the target wind speed information of the wind turbine, including: Determine the cut-in velocity, rated velocity, and cut-out velocity of the fan; When the target wind speed information is greater than the cut-out wind speed or the target wind speed information is less than the cut-in wind speed, the wind power of the wind turbine is determined to be the first wind power. When the target wind speed information is greater than the rated wind speed and less than the cut-out wind speed, the wind power of the wind turbine is determined to be the second wind power, wherein the second wind power is the rated power of the wind turbine and the second wind power is greater than the first wind power. When the target wind speed information is greater than the cut-in wind speed but less than the rated wind speed, the wind power of the wind turbine is determined based on the air density of the wind farm, the target wind speed information, the rotor area, and the power coefficient.
5. The method according to claim 1, characterized in that, Determining the wind power of the wind farm based on the wind power of the at least two wind turbines includes: Based on the location information of the at least two wind turbines, determine the power loss parameters of the at least two wind turbines; The wind power of the wind farm is determined based on the wind power and power loss parameters of the at least two wind turbines.
6. The method according to claim 1, characterized in that, After determining the wind power output of the wind farm, the method further includes: Obtain the wind power accuracy indication table of the wind farm, and match the wind power of the wind farm with the wind power accuracy indication table to obtain the wind power accuracy information of the wind farm. Based on the wind power accuracy information, the wind power deviation of the wind farm is determined, and the information interaction interface is controlled to display the wind power and wind power deviation of the wind farm.
7. A device for determining wind power output, characterized in that, The wind power determination device for implementing the wind power determination method according to any one of claims 1 to 6 includes: The information acquisition module is used to determine the location information of the wind turbines to be predicted in the wind farm, the wind speed information, wind direction information, temperature information and humidity information of the wind farm, wherein the wind turbines to be predicted include at least two wind turbines; The wind speed determination module is used to process the wind speed information, the wind direction information, the temperature information, the humidity information, and the position information of the at least two fans to obtain the backup wind speed information of the at least two fans. The wind speed adjustment module is used to process the wind speed information, wind direction information, temperature information, humidity information and backup wind speed information of the at least two fans using a pre-trained wind speed information adjustment model to obtain the target wind speed information of the at least two fans. The power determination module is used to determine the wind power of the at least two wind turbines based on the target wind speed information of the at least two wind turbines, and to determine the wind power of the wind farm based on the wind power of the at least two wind turbines.
8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the method for determining wind power according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining wind power as described in any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method for determining wind power as described in any one of claims 1 to 6.