Method and device for predicting generated power of wind power plant, electronic equipment and storage medium

Abstract

The invention discloses a wind power plant generation power prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: determining each to-be-predicted wind motor corresponding to a target wind power plant, and determining a historical generation power curve corresponding to each to-be-predicted wind motor; obtaining wind power prediction data corresponding to each to-be-predicted wind turbine, and determining to-be-corrected single machine prediction power of each to-be-predicted wind turbine according to the wind power prediction data and the historical generation power curve; determining power correction information corresponding to each to-be-predicted wind turbine, correcting the to-be-corrected single-machine prediction power according to the power correction information, and determining the single-machine prediction power of each to-be-predicted wind turbine; and determining a short-term generation power prediction result corresponding to the target wind power plant based on the prediction power of each single machine. By determining the single-machine prediction power corresponding to the single wind motor, the short-term power generation power prediction result corresponding to the wind power plant is determined according to the single-machine prediction power, so that the accuracy of power prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to a method, device, electronic equipment and storage medium for predicting the power generation of a wind farm. Background Art

[0002] As the process of building a new power system with new energy as the main body continues to accelerate, the proportion of new energy in my country's power supply has also increased significantly. The output of new energy such as wind power is affected by changes in meteorological conditions and has great randomness and volatility. With the increasing proportion of wind power in my country's power supply structure and the accelerated advancement of power market reform, higher and higher requirements are put forward for wind farm power generation prediction. The insufficient accuracy of wind power prediction not only causes the power station to be subject to the grid assessment and cause corresponding economic losses, but also seriously affects the safety and stability of the grid operation.

[0003] However, the main existing power forecasting scheme is to use wind farms as the basic analysis unit, use model analysis methods, use numerical weather forecasts, historical power observation data, and historical meteorological observation data as model input data, and combine statistics and algorithms to obtain ultra-short-term power forecasts corresponding to wind farms. However, the accuracy of power forecasts cannot be guaranteed. Summary of the invention

[0004] The present invention provides a method, device, electronic device and storage medium for predicting the power generation of a wind farm. The method determines the single-machine predicted power corresponding to a single wind turbine and corrects the single-machine predicted power according to power correction information corresponding to the single wind turbine. Finally, the short-term power generation prediction result corresponding to the wind farm is determined according to the predicted power of each single machine, thereby improving the accuracy of power prediction and being able to perform power prediction with a single wind turbine set as the prediction unit.

[0005] According to one aspect of the present invention, a method for predicting power generation of a wind farm is provided, comprising:

[0006] Determine each wind turbine to be predicted corresponding to the target wind farm, and determine a historical power generation curve corresponding to each wind turbine to be predicted;

[0007] Acquire wind power forecast data corresponding to each wind turbine to be forecasted, and determine the single-machine forecast power to be corrected of each wind turbine to be forecasted according to the wind power forecast data and the historical power generation curve;

[0008] Determine power correction information corresponding to each wind turbine to be predicted, correct the predicted power of the single unit to be corrected according to the power correction information, and determine the predicted power of the single unit of each wind turbine to be predicted;

[0009] A short-term power generation prediction result corresponding to the target wind farm is determined based on the predicted power of each single machine.

[0010] According to another aspect of the present invention, there is provided a device for predicting power generation of a wind farm, comprising:

[0011] A power curve determination module, used to determine each wind turbine to be predicted corresponding to the target wind farm, and determine a historical power generation curve corresponding to each wind turbine to be predicted;

[0012] A power prediction module, used for acquiring wind power prediction data corresponding to each wind turbine to be predicted, and determining the single-machine prediction power to be corrected of each wind turbine to be predicted according to the wind power prediction data and the historical power generation curve;

[0013] A power correction module, used to determine power correction information corresponding to each wind turbine to be predicted, correct the predicted power of the single unit to be corrected according to the power correction information, and determine the predicted power of the single unit of each wind turbine to be predicted;

[0014] The prediction result determination module is used to determine the short-term power generation prediction result corresponding to the target wind farm based on the predicted power of each single machine.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[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 so that the at least one processor can execute the method for predicting the generated power of a wind farm described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting the wind farm power generation power described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention is to determine each wind turbine to be predicted corresponding to the target wind farm, and determine the historical power generation curve corresponding to each wind turbine to be predicted, and then obtain the wind power prediction data corresponding to each wind turbine to be predicted, determine the corrected single-machine predicted power of each wind turbine to be predicted according to the wind power prediction data and the historical power generation curve, determine the power correction information corresponding to each wind turbine to be predicted, correct the corrected single-machine predicted power according to the power correction information, determine the single-machine predicted power of each wind turbine to be predicted, and finally determine the short-term power generation prediction result corresponding to the target wind farm based on each single-machine predicted power. Based on the above technical solution, by determining the single-machine predicted power corresponding to a single wind turbine, and correcting the single-machine predicted power according to the power correction information corresponding to the single wind turbine, and finally determining the short-term power generation prediction result corresponding to the wind farm according to each single-machine predicted power, the accuracy of power prediction is improved, and power prediction can be performed with a single wind turbine as the prediction unit.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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.

[0023] Figure 1 It is a schematic diagram of a flow chart of a method for predicting wind farm power generation provided by an embodiment of the present invention;

[0024] Figure 2 This is a wind speed and direction analysis diagram of a wind farm provided by an embodiment of the present invention;

[0025] Figure 3 is a flow chart of a method for predicting wind farm power generation provided by an embodiment of the present invention;

[0026] Figure 4 It is a structural block diagram of a device for predicting wind farm power generation provided by an embodiment of the present invention;

[0027] Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1 This is a flow chart of a method for predicting wind farm power generation provided by an embodiment of the present invention. This embodiment can be applied to determine the predicted power of each wind turbine in a wind farm, and then determine the short-term power generation prediction result corresponding to the wind farm based on the predicted power of each wind turbine. This method can be executed by a wind farm power generation prediction device, which can be implemented in the form of hardware and / or software. The wind farm power generation prediction device can be configured in an electronic device, which can be a server or a terminal device. Figure 1 As shown, the method includes:

[0032] S110 , determining each wind turbine to be predicted corresponding to the target wind farm, and determining a historical power generation curve corresponding to each wind turbine to be predicted.

[0033] The target wind farm may be a wind farm that needs short-term power forecasting. The wind turbines to be forecasted may be understood as wind turbines installed in the target wind farm. The historical power generation curve may be a power generation curve generated by each wind turbine during its historical operation.

[0034] Specifically, it can be through obtaining the electronic map of the wind farm positions of the target wind farm, and determining the wind turbines to be predicted in the target wind farm according to the electronic map of the wind farm positions. For example, the user can select the wind turbines to be predicted according to the electronic map of the wind farm positions, such as taking the wind turbines without faults as the wind turbines to be predicted. After determining the wind turbines to be predicted, the historical power generation curve corresponding to each wind turbine to be predicted is determined. For each wind turbine to be predicted, the power generation data of the wind turbine in the past period of time is collected to form a historical power generation curve. It should be noted that the historical power generation curve shows the past power generation performance of the wind turbine under different wind speeds, wind directions and other meteorological conditions, and the historical data includes multiple seasons, different weather conditions and possible operating failures, so as to more comprehensively reflect the performance characteristics of the wind turbine.

[0035] S120, obtaining wind power prediction data corresponding to each wind turbine to be predicted, and determining the single-machine prediction power to be corrected of each wind turbine to be predicted according to the wind power prediction data and the historical power generation curve.

[0036] The wind power forecast data can be understood as data used to determine the single-machine forecast power of the wind turbine to be currently forecasted, and can include meteorological data such as wind speed forecast, wind direction forecast, temperature forecast, etc. that may affect the power generation efficiency of the wind turbine. The single-machine forecast power to be corrected can be understood as the forecast power value of the wind turbine to be currently forecasted obtained by preliminary calculation.

[0037] Specifically, it can be to collect wind power forecast data corresponding to each wind turbine to be predicted. The wind power forecast data can include the wind speed forecast value, wind direction forecast value, temperature forecast value, etc. for a period of time in the future, such as the wind speed forecast value, wind direction forecast value, temperature forecast value, etc. in the next 15 minutes, and then a forecast model can be established based on the historical power generation curve and wind power forecast data. For example, the forecast model can be a statistical model, such as linear regression, multivariate regression, etc., or a model based on machine learning resume, such as neural network, random forest, etc., and then the wind power forecast data is input into the forecast model to predict the power generation of each wind turbine to be predicted. The forecast result is the predicted power of the single machine to be corrected, which indicates the power generation that the wind turbine may generate in the future under the given wind power forecast conditions.

[0038] On the basis of the above technical solution, the method of determining the to-be-revised single-unit forecast power of each wind turbine to be predicted according to the wind power forecast data and the historical power generation curve includes: obtaining the numerical weather forecast and wind tower collection data corresponding to the target wind farm, and collecting the measured wind speed and measured wind direction corresponding to the current wind turbine to be predicted; using the numerical weather forecast as the background field data, and determining the to-be-revised single-unit forecast power corresponding to the current wind turbine to be predicted based on the measured wind speed, the measured wind direction and the wind tower collection data.

[0039] Among them, numerical weather forecast can be understood as a method of predicting meteorological data in a certain period of time in the future by numerical calculations performed by large computers based on mathematical models and modern meteorological theories. For example, it can be used to determine the predicted values ​​of meteorological parameters such as wind speed, wind direction, temperature, and humidity of the target wind farm in the future through numerical weather forecast. The data collected by the wind tower can be data collected by the wind tower set up in the target wind farm. The measured wind speed and measured wind direction can be understood as data collected by sensors set up on the wind turbine to be predicted.

[0040] Specifically, the wind speed, wind direction, temperature and other meteorological parameters can be measured in real time by installing a wind tower in or around the wind farm. In order to ensure the accuracy of the predicted power of a single unit to be corrected, the wind speed and wind direction data of the wind turbine to be predicted can be obtained by using an anemometer installed on the wind turbine to obtain real-time wind speed and wind direction data. Then, the numerical weather forecast is used as the background field data, and the measured wind speed and wind direction data of each wind turbine are used to replace the field information in the wind tower data as input information. The other wind tower data variables remain unchanged, and the above information is input into the pre-established prediction model to obtain the predicted power of a single unit to be corrected corresponding to the wind turbine to be predicted. It should be noted that those skilled in the art can use existing technologies to establish the required prediction model according to needs, and the specific establishment scheme of the prediction model will not be repeated here.

[0041] S130, determining power correction information corresponding to each wind turbine to be predicted, correcting the single-machine predicted power to be corrected according to the power correction information, and determining the single-machine predicted power of each wind turbine to be predicted.

[0042] The power correction information may be information used to correct the predicted power. For example, the power correction information may be used to perform numerical correction on the predicted power of the single machine to be corrected, or the power correction information may be used to perform phase correction on the predicted power of the single machine to be corrected.

[0043] Specifically, it can be to obtain the power generation influencing factors corresponding to each wind turbine to be predicted, for example, it can be the status data of the wind turbine, such as blade angle, generator temperature, gearbox status, etc. These data can be obtained in real time through the data acquisition and monitoring control system of the wind turbine group, and it can also be to obtain meteorological data and geographical location data corresponding to the target wind farm, such as wind speed, wind direction, temperature, humidity, air pressure and other meteorological data, and then, after obtaining the power generation influencing factors, the power correction information corresponding to each wind turbine to be predicted can be calculated according to the current meteorological forecast data and wind turbine status data, and then the calculated power correction information is applied to the predicted power of the single machine to be corrected, and the predicted power is corrected.

[0044] On the basis of the above technical solution, the power correction information corresponding to each wind turbine to be predicted is determined, including: obtaining an electronic map of wind farm positions corresponding to the target wind farm, and determining the maximum wind speed and wind direction angle of the edge wind turbines of the target wind farm according to the wind power prediction data; and determining the power correction information based on the electronic map of wind farm positions, the maximum wind speed of the edge wind turbines and the wind direction angle of the edge wind turbines.

[0045] The wind farm position electronic map may be a map corresponding to the wind farm, and the wind farm position electronic map details the geographical location, orientation, and relative position relationship between each wind turbine in the wind farm. The maximum wind speed of the edge wind turbine may be understood as the maximum wind speed of the edge wind turbine of the current wind farm, and correspondingly, the wind direction angle of the edge wind turbine may be the angle between the wind direction of the edge wind turbine of the current wind farm and the main axis of the wind turbine.

[0046] Specifically, by combining the electronic map of wind farm locations and the wind speed and wind direction data of edge wind turbines, a more comprehensive analysis of the wind resource distribution within the wind farm can be conducted, thereby identifying the hot and cold spots of wind speed and wind direction within the wind farm, and based on the performance parameters of the wind turbines and the distribution of wind resources within the wind farm, the power generation potential of each wind turbine under different wind speeds and wind directions can be evaluated. Based on the above analysis results, corresponding power correction information can be determined for each wind turbine to be predicted. The power correction information may include a wind speed correction coefficient, a wind direction influence coefficient, etc., which are used to adjust the output results of the wind power prediction model. For example, for wind turbines located in areas with low wind speeds or unfavorable wind directions, their power prediction values ​​can be reduced; and for wind turbines located in areas with high wind speeds and stable wind directions, their power prediction values ​​can be appropriately increased.

[0047] On the basis of the above technical solution, the power correction information is determined based on the electronic map of the wind farm machine location, the maximum wind speed of the edge wind turbine and the wind direction angle of the edge wind turbine, including: determining the interval distance between the current wind turbine to be predicted and the edge wind turbine based on the electronic map of the wind farm machine location; determining the power correction information according to the maximum wind speed of the edge wind turbine, the wind direction angle of the edge wind turbine and the interval distance.

[0048] The power correction information includes the maximum wind speed amplitude and the maximum amplitude arrival time.

[0049] Specifically, the positions of the wind turbine to be predicted and the marginal wind turbine are accurately located on the electronic map of wind farm sites, and then the straight-line distance or effective wind propagation path distance between the wind turbine to be predicted and the marginal wind turbine is determined by using the position information on the map through geographic information system technology or simple plane geometry calculations. It should be noted that the wind speed will be affected by factors such as terrain and obstacles during the propagation process and will gradually decay. Based on the known maximum wind speed and interval distance of the edge wind turbines, a wind speed attenuation model (such as an exponential attenuation model, a logarithmic attenuation model, etc.) can be used to estimate the wind speed at the current wind turbine location to be predicted, and the wind direction angle of the edge wind turbine will affect the wind direction and wind speed distribution when the wind reaches the current wind turbine to be predicted. The principles of wind engineering or fluid dynamics, combined with the wind direction angle and interval distance, can be used to further correct the wind speed. Combined with the above-mentioned wind speed attenuation model and the correction of the wind direction angle, the maximum wind speed that may occur at the current wind turbine location to be predicted can be estimated, and the arrival time of the maximum wind speed can be predicted through numerical weather forecast data, historical wind speed records and wind speed prediction models, thereby obtaining the power correction information corresponding to the current wind turbine to be predicted.

[0050] For example, Figure 2 As shown in the figure, taking the wind farm as the analysis background, according to different geographical coordinates, the maximum wind speed of some units at a certain moment is predicted, and the following is obtained: Figure 2 The electronic layout map of wind farm units shown in the figure uses the real-time wind direction of numerical weather forecast. The wind vane and anemometer on a single wind turbine can be used to obtain wind speed and direction information in real time. The distance between WT01 and WT04 is S. Assuming that the wind direction is from west to east at this time, it can be determined that the wind first reaches the WT01 wind turbine. Suppose S = 10KM, wind speed V = 5m / s, and the time it takes for the wind wave to reach the unit is about 30min. The wind for a period of time can be divided into time zones. The WT01 unit detects the maximum wind speed in the time zone, and the maximum value of the WT04 unit after time shift is expected to be smaller than this value. It is expected that the wind speed climbing rate of WT04 in the time zone will be lower than the measured record of the WT01 unit in the time zone. Under the relationship between the units, the output of a single wind turbine at a certain moment can be corrected, and a model is established based on the three dimensions of NWP wind direction, wind turbine spatial distance, and wind turbine wind speed correlation to analyze the correlation between the predicted wind speed of wind turbines under different wind speed conditions. Using the wind direction from numerical weather forecasts, known wind speed of the turbines, and the spatial distance between turbines, we can infer the arrival time of the high value of the future wind speed waveform at time t in the future to make phase corrections.

[0051] S140: Determine a short-term power generation prediction result corresponding to the target wind farm based on the predicted power of each single machine.

[0052] The short-term power generation prediction result may be a wind power generation prediction value corresponding to the target wind farm.

[0053] Specifically, after obtaining the single-machine predicted power corresponding to each wind turbine, the short-term power generation prediction result corresponding to the target wind farm can be determined based on the single-machine predicted power. Exemplarily, the short-term power generation prediction result corresponding to the target wind farm based on the single-machine predicted power includes: adding the single-machine predicted power to obtain the short-term power generation prediction result corresponding to the target wind farm.

[0054] The technical solution of the embodiment of the present invention is to determine each wind turbine to be predicted corresponding to the target wind farm, and determine the historical power generation curve corresponding to each wind turbine to be predicted, and then obtain the wind power prediction data corresponding to each wind turbine to be predicted, determine the corrected single-machine predicted power of each wind turbine to be predicted according to the wind power prediction data and the historical power generation curve, determine the power correction information corresponding to each wind turbine to be predicted, correct the corrected single-machine predicted power according to the power correction information, determine the single-machine predicted power of each wind turbine to be predicted, and finally determine the short-term power generation prediction result corresponding to the target wind farm based on each single-machine predicted power. Based on the above technical solution, by determining the single-machine predicted power corresponding to a single wind turbine, and correcting the single-machine predicted power according to the power correction information corresponding to the single wind turbine, and finally determining the short-term power generation prediction result corresponding to the wind farm according to each single-machine predicted power, the accuracy of power prediction is improved, and power prediction can be performed with a single wind turbine as the prediction unit.

[0055] Embodiment 2

[0056] Figure 3 This is a flow chart of a method for predicting wind farm power generation provided by an embodiment of the present invention. Based on the above embodiment, this embodiment further refines the technical solution of determining the historical power generation curve corresponding to each wind turbine to be predicted. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or corresponding to the above embodiment are not repeated here. Figure 3 As shown, the method includes:

[0057] S210 . Acquire power generation data and power generation environment information corresponding to the wind turbine to be predicted currently within a preset data collection period based on a preset data collection step size.

[0058] Among them, the power generation environment information includes wind speed, cabin yaw angle and air density. The preset data collection step size can be a preset time interval for data collection, such as every minute, every ten minutes, etc. The selection of the step size should be determined according to the actual situation of the wind farm and the forecasting needs to ensure the accuracy and representativeness of the data. The preset data collection cycle can be understood as a time period for continuous data collection, such as one day, one week or longer. It should be noted that the selection of the cycle should be able to cover the operation of the wind farm under different weather and working conditions, so as to more comprehensively reflect the power generation performance of the wind turbine. The power generation power data can be the power generation operation data corresponding to the current wind turbine to be predicted.

[0059] Specifically, through the data acquisition and monitoring control system or other data acquisition equipment of the wind farm, the power generation data of the wind turbine to be predicted at each acquisition point is obtained according to the preset data acquisition step, and the power generation environment information such as wind speed, cabin yaw angle and air density corresponding to the power generation data is also obtained according to the preset data acquisition step. It should be noted that after the required data is collected, the collected data can be checked and processed to remove data points that do not meet the requirements, such as abnormal values ​​and missing values. For example, numerical screening is performed by setting data thresholds, using interpolation algorithms, etc., and the collected data is time-aligned according to the timestamp of the collected data, thereby ensuring that the power generation data and the power generation environment information are one-to-one in time, so as to facilitate subsequent analysis and processing.

[0060] S220. Determine the historical power generation curve corresponding to each wind turbine to be predicted based on the power generation data and the power generation environment information.

[0061] Specifically, the relationship between power generation data and power generation environment information is analyzed, especially the correlation between power generation and wind speed. It should be noted that the yaw angle of the nacelle reflects the adaptability of the wind turbine to wind direction, while the air density affects the kinetic energy of the wind and the power generation efficiency of the unit. Based on the preprocessed data, the historical power generation curve corresponding to each wind turbine to be predicted is drawn using chart tools (such as Excel, MATLAB, Python's Matplotlib, etc.). The curve chart should use time as the horizontal axis and power generation as the vertical axis, and can superimpose and display the changes in environmental information such as wind speed, nacelle yaw angle, and air density.

[0062] On the basis of the above technical solution, the historical power generation curve corresponding to each wind turbine to be predicted is determined based on the power generation data and the power generation environment information, including: obtaining a preset power calculation step and a preset data filtering rule, processing the power generation data according to the preset data filtering rule, and determining the target power generation data; determining the historical power generation curve of the currently predicted wind turbine based on the preset power calculation step, the target power generation data and the power generation environment information.

[0063] The preset data filtering rules may be pre-set data processing rules.

[0064] Specifically, to calculate the power that fits the actual power generation capacity of a single machine, the power calculation step can be adjusted to perform calculation analysis at 0.5 m / s. Taking 8 m / s wind speed as an example, the wind speed value range is (7.75, 8.25], and the power calculation data collection cycle is adjusted to collect data once using the preset data collection step, such as collecting data once every 7 seconds, and excluding the data within the limit power, 10 minutes before the fault, and 10 minutes after the start of the machine in the calculation, to ensure that the collected data can better reflect the current wind turbine operation characteristics, and consider the changes in power generation efficiency caused by external natural conditions, and make a three-dimensional data statistical analysis plan for wind speed, cabin yaw angle, and air density.

[0065] The technical solution of the embodiment of the present invention makes an overall evaluation of the wind farm power based on the wind power generation efficiency of a single wind farm unit. According to the historical power generation efficiency of a single unit, the operating efficiency of a single unit under different natural conditions is better evaluated, and the direct impact of turbulence and wind resource factors on the power generation efficiency of a single unit is more fully considered, and the overall power forecast of the wind farm is decomposed into a single-unit power forecast. Based on the above technical solution, by determining the single-unit predicted power corresponding to a single wind turbine, and correcting the single-unit predicted power according to the power correction information corresponding to the single wind turbine, finally the short-term power generation power forecast result corresponding to the wind farm is determined according to the predicted power of each single unit, thereby improving the accuracy of the power forecast, and being able to perform power forecasting with a single wind turbine unit as the forecasting unit.

[0066] Embodiment 3

[0067] Figure 4 The structure block diagram of a wind farm power prediction device provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, the device includes: a power curve determination module 410, a power prediction module 420, a power correction module 430 and a prediction result determination module 440.

[0068] The power curve determination module 410 is used to obtain each wind turbine to be predicted corresponding to the target wind farm, and determine the historical power generation curve corresponding to each wind turbine to be predicted;

[0069] The power prediction module 420 is used to obtain wind power prediction data corresponding to each wind turbine to be predicted, and determine the single-machine prediction power to be corrected of each wind turbine to be predicted according to the wind power prediction data and the historical power generation curve;

[0070] The power correction module 430 is used to determine the power correction information corresponding to each wind turbine to be predicted, and to correct the predicted power of each wind turbine to be corrected according to the power correction information to determine the predicted power of each wind turbine to be predicted;

[0071] The prediction result determination module 440 is used to determine the short-term power generation prediction result corresponding to the target wind farm based on the predicted power of each single machine.

[0072] On the basis of the above technical solution, the power curve determination module is used to obtain the power generation data and power generation environment information corresponding to the current wind turbine to be predicted within a preset data collection period based on a preset data collection step, wherein the power generation environment information includes wind speed, cabin yaw angle and air density; based on the power generation data and power generation environment information, determine the historical power generation curve corresponding to each wind turbine to be predicted.

[0073] On the basis of the above technical solution, the power curve determination module is used to obtain a preset power calculation step and a preset data filtering rule, process the power generation data according to the preset data filtering rule, and determine the target power generation data; based on the preset power calculation step, the target power generation data and the power generation environment information, determine the historical power generation curve of the currently predicted wind turbine.

[0074] On the basis of the above technical solution, the power correction module is used to obtain an electronic map of wind farm locations corresponding to the target wind farm, and determine the maximum wind speed and wind direction angle of the edge wind turbines of the target wind farm based on the wind power forecast data; and determine the power correction information based on the electronic map of wind farm locations, the maximum wind speed of the edge wind turbines and the wind direction angle of the edge wind turbines.

[0075] On the basis of the above technical solution, the power correction module is used to determine the interval distance between the current wind turbine to be predicted and the edge wind turbine based on the electronic map of the wind farm machine location; determine the power correction information according to the maximum wind speed of the edge wind turbine, the wind direction angle of the edge wind turbine and the interval distance, wherein the power correction information includes the maximum wind speed amplitude and the maximum amplitude arrival time.

[0076] On the basis of the above technical solution, the power prediction module is used to obtain the numerical weather forecast and wind tower data corresponding to the target wind farm, and to collect the measured wind speed and measured wind direction corresponding to the current wind turbine to be predicted; using the numerical weather forecast as the background field data, the single-machine predicted power to be corrected corresponding to the current wind turbine to be predicted is determined based on the measured wind speed, the measured wind direction and the wind tower data.

[0077] On the basis of the above technical solution, the prediction result determination module is used to add up the predicted powers of each single machine to obtain the short-term power generation prediction result corresponding to the target wind farm. The technical solution of the embodiment of the present invention determines each wind turbine to be predicted corresponding to the target wind farm, and determines the historical power generation curve corresponding to each wind turbine to be predicted, and then obtains the wind power prediction data corresponding to each wind turbine to be predicted, determines the corrected single-machine predicted power of each wind turbine to be predicted according to the wind power prediction data and the historical power generation curve, determines the power correction information corresponding to each wind turbine to be predicted, corrects the corrected single-machine predicted power according to the power correction information, determines the single-machine predicted power of each wind turbine to be predicted, and finally determines the short-term power generation prediction result corresponding to the target wind farm based on the predicted power of each single machine. Based on the above technical solution, by determining the single-machine predicted power corresponding to a single wind turbine, and correcting the single-machine predicted power according to the power correction information corresponding to the single wind turbine, finally the short-term power generation prediction result corresponding to the wind farm is determined according to the predicted power of each single machine, thereby improving the accuracy of power prediction, and being able to perform power prediction with a single wind turbine as the prediction unit.

[0078] The device for predicting the power generation of a wind farm provided in the embodiment of the present invention can execute the method for predicting the power generation of a wind farm provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0079] Embodiment 4

[0080] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0081] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0082] A number of components in the electronic device 10 are connected to the I / O 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 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.

[0083] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for predicting wind farm power generation.

[0084] In some embodiments, the method for predicting the power generated by a wind farm may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for predicting the power generated by a wind farm described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for predicting the power generated by a wind farm in any other appropriate manner (e.g., by means of firmware).

[0085] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0086] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0087] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0088] To provide interaction with a user, the systems and techniques described herein may 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 trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0089] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may 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.

[0090] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may 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 difficult management and weak business scalability in traditional physical hosts and VPS services.

[0091] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0092] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting wind farm power generation, characterized in that: include: Determine each wind turbine to be predicted corresponding to the target wind farm, and determine a historical power generation curve corresponding to each wind turbine to be predicted; Acquire wind power forecast data corresponding to each wind turbine to be forecasted, and determine the single-machine forecast power to be corrected of each wind turbine to be forecasted according to the wind power forecast data and the historical power generation curve; Determine power correction information corresponding to each wind turbine to be predicted, correct the predicted power of the single unit to be corrected according to the power correction information, and determine the predicted power of the single unit of each wind turbine to be predicted; A short-term power generation prediction result corresponding to the target wind farm is determined based on the predicted power of each single machine.

2. The method according to claim 1, characterized in that The determining of the historical power generation curve corresponding to each wind turbine to be predicted includes: Based on a preset data collection step length, obtaining power generation data and power generation environment information corresponding to the current wind turbine to be predicted within a preset data collection period, wherein the power generation environment information includes wind speed, nacelle yaw angle and air density; The historical power generation curve corresponding to each wind turbine to be predicted is determined based on the power generation data and the power generation environment information.

3. The method according to claim 2, characterized in that The determining, based on the power generation data and the power generation environment information, the historical power generation curve corresponding to each wind turbine to be predicted comprises: Obtaining a preset power calculation step and a preset data filtering rule, processing the power generation data according to the preset data filtering rule, and determining target power generation data; The currently predicted historical power generation curve of the wind turbine is determined based on the preset power calculation step, the target power generation data and the power generation environment information.

4. The method according to claim 1, characterized in that: The determining of power correction information corresponding to each wind turbine to be predicted includes: Acquire an electronic map of wind farm positions corresponding to the target wind farm, and determine the maximum wind speed and wind direction angle of the edge wind turbines of the target wind farm according to the wind power forecast data; The power correction information is determined based on the wind farm machine location electronic map, the maximum wind speed of the edge wind turbine and the wind direction angle of the edge wind turbine.

5. The method according to claim 4, characterized in that The determining of the power correction information based on the wind farm machine location electronic map, the maximum wind speed of the edge wind turbine and the wind direction angle of the edge wind turbine includes: Determine the interval distance between the wind turbine to be predicted and the edge wind turbine based on the wind farm machine position electronic map; The power correction information is determined according to the maximum wind speed of the edge wind turbine, the wind direction angle of the edge wind turbine and the interval distance, wherein the power correction information includes the maximum amplitude of the wind speed and the maximum amplitude arrival time.

6. The method according to claim 1, characterized in that The step of determining the single-machine predicted power to be corrected of each wind turbine to be predicted according to the wind power prediction data and the historical power generation curve comprises: Acquire numerical weather forecasts and wind tower data corresponding to the target wind farm, and collect actual wind speeds and actual wind directions corresponding to the wind turbines to be predicted; The numerical weather forecast is used as background field data, and the single-machine predicted power to be corrected corresponding to the current wind turbine to be predicted is determined based on the measured wind speed, the measured wind direction and the data collected by the wind tower.

7. The method according to claim 1, characterized in that The determining of the short-term power generation prediction result corresponding to the target wind farm based on the predicted power of each single machine includes: The predicted powers of each single machine are summed up to obtain a short-term power generation prediction result corresponding to the target wind farm.

8. A device for predicting wind farm power generation, characterized in that: include: A power curve determination module, used to determine each wind turbine to be predicted corresponding to the target wind farm, and determine a historical power generation curve corresponding to each wind turbine to be predicted; A power prediction module, used for acquiring wind power prediction data corresponding to each wind turbine to be predicted, and determining the single-machine prediction power to be corrected of each wind turbine to be predicted according to the wind power prediction data and the historical power generation curve; A power correction module, used to determine power correction information corresponding to each wind turbine to be predicted, correct the predicted power of the single unit to be corrected according to the power correction information, and determine the predicted power of the single unit of each wind turbine to be predicted; The prediction result determination module is used to determine the short-term power generation prediction result corresponding to the target wind farm based on the predicted power of each single machine.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, 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 so that the at least one processor can execute the method for predicting the generated power of a wind farm according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting the generated power of a wind farm according to any one of claims 1 to 7 when the instructions are executed.

Images