Method, device, equipment, medium and program product for predicting power of fan

Abstract

The application discloses a wind turbine power prediction method, device, equipment, medium and program product, and designs a new energy field. The method comprises the following steps: acquiring first icing prediction data and wind speed data of a wind turbine operation area in a historical time period, historical power generation data of a wind turbine in the wind turbine operation area in the historical time period, determining a correction parameter based on the first icing prediction data, the wind speed data and the historical power generation data, acquiring second icing prediction data of the wind turbine operation area in a future time period; correcting the second icing prediction data based on the correction parameter to obtain an icing sequence, adjusting wind power generation of the wind turbine in the future time period based on the correction parameter and the icing sequence to obtain power generation prediction data. The accuracy of the icing condition prediction of the wind turbine operation area is improved, the operation condition and the output power condition of the wind turbine under the icing condition are accurately understood, and the operation and maintenance efficiency of the wind turbine is improved.

Description

Technical Field

[0001] This application relates to the field of new energy, and in particular to a method, apparatus, equipment, medium, and program product for predicting wind turbine power. Background Technology

[0002] Wind power generation is a major power generation technology in the new energy field. The blades of a wind turbine rotate under the action of wind, converting the kinetic energy of the wind into electrical energy, thus realizing wind power generation. In low temperature and high humidity environments, the blades of wind turbines are very likely to freeze, causing power loss in the generator output.

[0003] In related technologies, the speed of ice accumulation and melting of wind turbines under different environments is studied, and the occurrence of icing on wind turbine blades is predicted.

[0004] However, the relevant technologies cannot predict the actual output power of wind turbines when blade icing occurs, resulting in low operating and maintenance efficiency of wind turbines. Summary of the Invention

[0005] This application provides a method, apparatus, device, medium, and program product for predicting wind turbine power, which can predict the power generation of wind turbines when icing occurs in a wind farm. The technical solution is as follows:

[0006] On the one hand, a method for predicting wind turbine power is provided, the method comprising:

[0007] Acquire first icing forecast data and wind speed data for the wind turbine operating area within a historical time period; and acquire historical power generation data of the wind turbine generators in the wind turbine operating area within the historical time period, wherein the first icing forecast data is data obtained by predicting icing for the historical time period.

[0008] Based on the first icing forecast data, the wind speed data, and the historical power generation data, correction parameters are determined, which are used to adjust the predicted power generation data of the wind turbine.

[0009] Obtain second icing forecast data for the wind turbine operating area in the future time period;

[0010] The second icing forecast data is corrected based on the correction parameters to obtain the icing sequence of the wind turbine operating area in the future time period. The icing sequence is used to indicate the icing situation of the wind turbine operating area at different time points in the future time period.

[0011] Based on the correction parameters and the icing sequence, the wind power generation of the wind turbine is adjusted for the future time period to obtain power generation prediction data.

[0012] On the other hand, a wind turbine power prediction device is provided, the device comprising:

[0013] The acquisition module acquires first icing forecast data and wind speed data of the wind turbine operating area within a historical time period; and acquires historical power generation data of the wind turbine generators in the wind turbine operating area within the historical time period, wherein the first icing forecast data is data obtained by predicting icing during the historical time period.

[0014] The determination module determines correction parameters based on the first icing forecast data, the wind speed data, and the historical power generation data. The correction parameters are used to adjust the predicted power generation data of the wind turbine.

[0015] The acquisition module acquires second icing forecast data for the wind turbine operating area within a future time period;

[0016] The correction module corrects the second icing forecast data based on the correction parameters to obtain the icing sequence of the wind turbine operating area in the future time period. The icing sequence is used to indicate the icing situation of the wind turbine operating area at different time points in the future time period.

[0017] The adjustment module adjusts the wind power generation of the wind turbine in the future time period based on the correction parameters and the icing sequence to obtain power generation prediction data.

[0018] On the other hand, a computer device is provided, the computer device including a processor and a memory, the memory storing at least one instruction, at least one program, code set or instruction set, the at least one instruction, the at least one program, the code set or instruction set being loaded and executed by the processor to implement the wind turbine power prediction method as described in any of the embodiments of this application above.

[0019] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction, at least one program, code set, or instruction set is stored therein, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the wind turbine power prediction method as described in any of the embodiments of this application above.

[0020] On the other hand, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the wind turbine power prediction method described in any of the above embodiments.

[0021] The beneficial effects of the technical solutions provided in this application include at least the following:

[0022] By acquiring the first icing forecast data, wind speed data, and historical power generation data of the wind turbine operating area within a historical time period, correction parameters are obtained based on these data. These correction parameters can adjust the predicted power generation for future time periods, yielding the actual power output of the wind turbine under icing conditions. This provides an accurate understanding of the wind turbine's operating status and output power, improving the efficiency of wind turbine operation and maintenance. Furthermore, by correcting the icing forecast data for future time periods based on these parameters, an icing sequence for the wind turbine operating area in the future time period is obtained, further improving the accuracy of icing predictions for the wind turbine operating area. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of an implementation environment provided by an exemplary embodiment of this application;

[0025] Figure 2 This is a flowchart of a wind turbine power prediction method provided in an exemplary embodiment of this application;

[0026] Figure 3 This is a flowchart of a method for obtaining correction parameters provided in an exemplary embodiment of this application;

[0027] Figure 4 This is a flowchart of a method for obtaining an icing sequence provided in an exemplary embodiment of this application;

[0028] Figure 5 This is a schematic diagram of an icing sequence provided in an exemplary embodiment of this application;

[0029] Figure 6This is an exemplary embodiment provided by this application based on Figure 5 A schematic diagram illustrating the determination of icing intervals based on the icing sequence;

[0030] Figure 7 This is a structural block diagram of a wind turbine power prediction device provided in an exemplary embodiment of this application;

[0031] Figure 8 This is a structural block diagram of a wind turbine power prediction device provided in another exemplary embodiment of this application;

[0032] Figure 9 This is a structural block diagram of a computer device provided in an exemplary embodiment of this application. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0034] First, a brief introduction to the terms used in the embodiments of this application:

[0035] The Weather Research and Forecasting Model (WRF) is a numerical weather prediction model, hailed as a next-generation mesoscale weather prediction model. The WRF model is a unified mesoscale weather prediction model.

[0036] The WRF model system, with its portability, ease of maintenance, scalability, high efficiency, and convenience, has become a tool for improving the accuracy of forecasts for important weather features from cloud scales to various synoptic scales. Based on meteorological models within the WRF model, it is possible to forecast future icing conditions in different regions.

[0037] Wind power generation refers to the process of converting the kinetic energy of wind into electrical energy. It is one of the main technologies for new energy power generation. Wind energy is a clean and pollution-free renewable energy source. The advantages of wind power generation lie in its environmental friendliness and sustainability. Moreover, wind energy reserves are enormous and can effectively address the environmental impacts of global warming. Therefore, it is receiving increasing attention from countries around the world.

[0038] Wind turbines installed in wind farms convert the kinetic energy of the wind into mechanical kinetic energy, and then into electrical kinetic energy. In this process, the wind drives the blades of the wind turbine to rotate, and the speed increaser increases the rotation speed to generate electricity.

[0039] However, in low-temperature and high-humidity environments, the blades of wind turbines will freeze, which will lead to power loss. The actual output power will be lower than the theoretical output power, and in severe cases, it may even cause the blades to break, resulting in serious economic losses and safety hazards.

[0040] A wind farm, or the area where wind turbines operate, requires icing forecasting. This allows us to obtain information on the icing conditions in the wind turbine operating area for a future period, thereby improving the operation and maintenance efficiency of wind turbines and ensuring the safety of equipment and personnel in the wind farm.

[0041] The relevant technologies mainly include methods for simulating the speed of ice accumulation and the speed of ice melting. Based on empirical theories of ice accumulation from physical processes such as freezing rain, cloud icing, and wet snow icing, the speed of ice accumulation can be simulated: according to variables such as the cross-sectional area of ​​the object relative to the direction of motion of colliding particles, the velocity vector of the particles, and the liquid water content in the air, the speed of ice accumulation is simulated according to a preset formula; the rate of ice melting is obtained based on calculations such as the sensible heat between the air and the melting layer and the heat lost by ice evaporation.

[0042] However, the impact of icing on the wind turbine's output power when icing occurs in the operating area is not directly explained, making it impossible to predict the wind turbine's output power based on icing forecasts.

[0043] In this embodiment, the icing conditions in the wind turbine operating area are forecasted for a future time period using the meteorological model in the WRF mode, thus obtaining future icing forecast data. Similarly, by acquiring historical icing forecast data and historical power generation data of the wind turbine operating area over a historical period, and analyzing the above data, the difference between the actual output power and the theoretical output power of the wind turbine under different icing conditions can be obtained, leading to correction parameters.

[0044] When icing occurs in the wind turbine operating area in the future, the future icing forecast data can be corrected based on correction parameters to obtain a more accurate icing situation; the theoretical wind power generation of the wind turbine in the future period can be adjusted based on correction coefficients to obtain accurate power generation prediction data.

[0045] Secondly, the implementation environment involved in the embodiments of this application will be described, for illustrative purposes only. Please refer to [the relevant documentation]. Figure 1 It illustrates a schematic diagram of an implementation environment provided by an exemplary embodiment of this application, such as... Figure 1 As shown, the implementation environment includes a terminal 100, a server 120, and a wind turbine 130. The terminal 100 and the server 120 are connected through a communication network 110, and the wind turbine 130 and the terminal 100 are connected through a data cable or other lines.

[0046] The wind turbine 130 is located in the wind turbine operating area and sends its own historical power generation data to the terminal 100. The historical power generation data refers to the power generation data output by the wind turbine 130 within a historical time period.

[0047] Terminal 100 is equipped with an application that provides icing forecasting functionality. This application predicts icing conditions in the wind turbine operating area over a historical period, generates first icing forecast data, and stores this data in terminal 100. After obtaining actual operating data of the wind turbine generators 130 within the operating area, terminal 100 sends the first icing forecast data and the actual data to server 120. The actual data includes wind speed data and historical power generation data of the wind turbine generators 130 within the operating area over a historical period.

[0048] After receiving the first icing forecast data, wind speed data, and historical power generation data, server 120 calculates the theoretical power generation data of wind turbine 130 within the historical time period based on the wind speed data. The theoretical power generation data refers to the ideal power generation of wind turbine 130 calculated based on the wind speed data when no icing occurs in the wind turbine operating area during the historical time period.

[0049] Server 120 contains a model capable of predicting the power generation of wind turbine 130 under icing conditions. Theoretical power generation data, historical power generation data, and the first icing forecast data are input into the power prediction model, and correction parameters are output. These correction parameters are used to correct the theoretical power generation data to obtain the power data of wind turbine 130 under icing conditions, i.e., the power prediction data.

[0050] The terminal 100 includes at least one of the following: smartphone, tablet computer, portable laptop, desktop computer, smart speaker, smart wearable device, smart voice interaction device, smart home appliance, etc.

[0051] It is worth noting that the aforementioned communication network 110 can be implemented as a wired network or a wireless network, and the communication network 110 can be implemented as any one of a local area network, a metropolitan area network, or a wide area network. This application embodiment does not limit this.

[0052] It is worth noting that the aforementioned server 120 can be implemented as a cloud server in the cloud. Cloud technology refers to a hosting technology that unifies hardware, software, and network resources within a wide area network (WAN) or local area network (LAN) to achieve data computation, storage, processing, and sharing. Cloud technology is a general term encompassing network technology, information technology, integration technology, management platform technology, and application technology applied to the cloud computing business model. It can form resource pools, available on demand, and offers flexibility and convenience. Cloud computing technology will become a crucial support. Backend services of technical network systems require substantial computing and storage resources, such as video websites, image websites, and many portal websites. With the rapid development and application of the internet industry, every item may have its own identification mark in the future, requiring transmission to a backend system for logical processing. Data at different levels will be processed separately, and various industry data will require robust system support, which can only be achieved through cloud computing.

[0053] In some embodiments, the server 120 can also be implemented as a node in a blockchain system. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and cryptographic algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer.

[0054] Based on the above-described terminology and application scenarios, the wind turbine power prediction method provided in this application embodiment will be explained, using the example of a terminal executing the method. For illustrative purposes, please refer to [reference needed]. Figure 2 The diagram illustrates a flowchart of a wind turbine power prediction method provided in an exemplary embodiment of this application, the method comprising the following steps:

[0055] Step 210: Obtain the first icing forecast data and wind speed data of the wind turbine operating area within the historical time period; and obtain the historical power generation data of the wind turbine generators in the wind turbine operating area within the historical time period.

[0056] Optionally, the first icing forecast data and wind speed data mentioned above can be obtained based on the meteorological model in the WRF model.

[0057] The first icing forecast data is obtained by predicting icing over historical time periods. It represents the possible time points and ice mass data within those historical periods. The ice mass data represents the mass of the ice formed when icing occurs. Each wind turbine operating area corresponds to its own first icing forecast data.

[0058] Optionally, the first icing forecast data is obtained by predicting icing over a historical period from 0:00 AM to 12:00 AM on December 1st.

[0059] The possible times for icing are 6:00, 10:00, and 18:00, which means that icing may occur in the wind turbine operating area at 6:00 am, 10:00 am, and 18:00 pm on December 1st, respectively.

[0060] Optionally, the icing quality data corresponding to the above time points includes the following:

[0061] (1) Icing occurred at 6:00 AM on December 1st. The total icing mass in the fan operating area was 70 grams, and the icing intensity was: weak icing.

[0062] (2) Icing occurred at 10:00 AM on December 1st. The total icing mass in the fan operating area was 150 grams, and the icing intensity was: moderate icing.

[0063] (3) Icing occurred at 18:00 on December 1st. The total icing mass in the fan operating area was 10 grams, and the icing intensity was: weak icing.

[0064] The greater the icing mass, the greater the corresponding icing strength. Icing strength is divided into the following levels, from low to high:

[0065] 1. Weak freezing: Freezing mass data is 0-100 grams;

[0066] 2. Moderate freezing: The weight of the frozen material is 100-200 grams;

[0067] 3. Strong freezing: The weight of the frozen substance is 200-300 grams;

[0068] 4. Extremely strong freezing: The weight of the frozen substance is 300-400 grams.

[0069] The wind turbine operating area refers to the region used for wind power generation, within which at least one wind turbine exists. The wind turbine is the main entity executing the wind power generation process; its blades rotate under the influence of wind, converting wind energy into electrical energy, and thus outputting corresponding power. Wind speed is a crucial factor affecting the output power of a wind turbine; the higher the wind speed, the greater the power output.

[0070] Wind speed data is used to represent the speed of wind propagation within the operating area of ​​a wind turbine over a historical period. Wind speed data is constantly changing.

[0071] The historical time period refers to a certain period in the past. The first icing forecast data of the wind turbine operating area within the historical time period includes, but is not limited to, the following: (1) the time points in the wind turbine operating area where icing may occur; (2) the duration of each icing time point when icing occurs; and (3) the total icing mass data when icing occurs.

[0072] Historical power generation data of wind turbines in the wind turbine operating area refers to the actual power output data of wind turbines at different points in time or time periods.

[0073] Optionally, the historical time period refers to the previous winter (e.g., from 0:00:00 on December 1, 2021 to 24:00:00 on February 25, 2022). There are 5 wind turbine operating areas, corresponding to the first icing forecast data and wind speed data of the 5 areas respectively. In these wind turbine operating areas, the historical power generation data of the wind turbine is represented by a power curve with time on the horizontal axis and power on the vertical axis.

[0074] In some embodiments, the first icing forecast data and wind speed data can be obtained in addition to the WRF mode, and other types of data can also be used. This embodiment does not limit this to any particular type of data.

[0075] It is worth noting that there is at least one wind turbine operating area, and the division of the wind turbine operating area can be arbitrary; each wind turbine operating area has corresponding first icing forecast data and wind speed data, corresponding to the historical power generation data of all wind turbines in each wind turbine operating area in the same historical time period; the form of the historical power generation data can be arbitrary, and this embodiment does not limit it.

[0076] It is worth noting that the icing quality data includes, but is not limited to, the total icing quality and the icing intensity. The icing intensity can be divided in any way, and the correspondence between the total icing quality and the icing intensity can be arbitrary. This embodiment does not limit this.

[0077] Step 220: Determine correction parameters based on the first icing forecast data, wind speed data, and historical power generation data.

[0078] The correction parameters are used to adjust the predicted power generation data of the wind turbines.

[0079] Wind speed data can be used to predict the power output of wind turbines, resulting in predicted power output data. However, the predicted power output data will be lost when icing occurs in the wind turbine operating area, resulting in a difference between the predicted power output data and the actual power output data.

[0080] In other words, the correction parameters are used to adjust the predicted power generation data of wind turbines so that the adjusted power generation data is the same as the historical power generation data.

[0081] The correction parameters include extended time and derating rate. Extended time refers to the time during which the icing and melting processes occur in the wind turbine operating area, while derating rate is used to indicate the decrease in wind power generation under icing conditions.

[0082] The initial icing forecast data includes time points within historical periods where icing may occur. However, these time points only indicate the presence of icing at a specific moment and do not include the time spent on the icing and melting processes; that is, they do not include extended periods. In reality, extended periods can also impact wind turbines within the operating area, reducing their output power.

[0083] The derating rate represents the proportion of the actual power output of a wind turbine to the predicted power output due to icing conditions. The predicted power output refers to the theoretical power output of a wind turbine under conditions where icing does not occur.

[0084] In some embodiments, the correction parameters include, but are not limited to, time extension and derating rate; this embodiment does not limit these parameters.

[0085] Step 230: Obtain the second icing forecast data for the wind turbine operating area in the future time period.

[0086] The second icing forecast data has the same format as the first icing forecast data. It refers to data obtained by predicting icing over a future time period, used to indicate the time points and icing quality at which icing may occur within a certain future time period. Each wind turbine operating area corresponds to its own second icing forecast data.

[0087] Optionally, the future time period refers to the next day, the number of wind turbine operating areas is 1, and the second icing forecast data corresponds to 1 area.

[0088] In some embodiments, the duration of the future time period can be arbitrary, and this embodiment does not limit it.

[0089] Step 240: Correct the second icing forecast data based on the correction parameters to obtain the icing sequence of the wind turbine operating area in the future time period.

[0090] The second icing forecast data also includes time points in the future time period where icing may occur. These time points indicate that icing will occur at least at any point in the future time period, without including extended time.

[0091] Based on the extended time in the correction parameters, the second icing forecast data is corrected to obtain the icing sequence, which is used to indicate the icing situation at different time points in the future operating area of ​​the wind turbine.

[0092] Optionally, the second icing forecast data corresponds to the icing situation in the wind turbine operating area on the next day (e.g., December 30), from 0:00 AM to 12:00 PM on December 30, a total of 24 hours.

[0093] Optionally, the second icing forecast data indicates that icing will occur at the following times: 8:00 AM, 12:00 PM, and 4:00 PM, for a total of 3 times; the corresponding extension times are: 1 hour before and 1 hour after, 0.5 hours before and 1 hour after, and 1 hour before and 1 hour after.

[0094] The corrected freezing sequence is as follows: freezing occurs from 7:00 to 9:00 AM, freezing occurs from 11:30 AM to 12:30 PM, freezing occurs from 3:00 PM to 5:00 PM, and freezing does not occur in other time periods.

[0095] In some embodiments, the duration of the future time period corresponding to the second icing forecast data can be arbitrary, and the starting point of the future time period can be arbitrary; in the second icing forecast data, the time point at which icing may occur can be arbitrary, and the extension time corresponding to the time point can also be arbitrary, and this embodiment does not limit this.

[0096] Step 250: Adjust the wind power generation of the wind turbine in the future time period based on the correction parameters and icing sequence to obtain the power generation prediction data.

[0097] The weather model in WRF mode can predict wind speed data for a future time period, obtain future wind speed data, and analyze the future wind speed data to calculate the wind power generation of the wind turbine in the future time period, i.e., the future wind power generation.

[0098] When icing occurs in the wind turbine operating area in the future, the blades of the wind turbine will freeze, affecting the output power and reducing the future wind power generation. In this case, it is necessary to adjust the future wind power generation based on the correction parameters.

[0099] Based on the icing sequence obtained after adjusting the second icing forecast data, the wind power generation adjustment range of the wind turbines is determined. The wind power generation adjustment range refers to the time interval during which the wind power generation of the wind turbines needs to be adjusted in the future. In other words, it is the time interval during which icing occurs.

[0100] The correction parameters include the extension time and derating rate. Based on the derating rate in the correction parameters, the wind power generation within the wind power generation adjustment range is adjusted to obtain the power generation prediction data.

[0101] The product of the derating rate and the future wind power generation capacity is the predicted power generation capacity.

[0102] Optionally, the wind power generation adjustment range includes: (1) 7:00 to 9:00 a.m.; (2) 11:30 a.m. to 12:30 p.m.; (3) 3:00 p.m. to 5:00 p.m.

[0103] The derating rates corresponding to the above adjustment intervals are 90%, 75%, and 88%, respectively. Within the time intervals corresponding to the above adjustment intervals, the future wind power generation capacity is 1500KW, 1000KW, and 1200KW, respectively.

[0104] After adjusting the aforementioned future wind power generation capacity based on the derating rate, the resulting power generation forecasts are as follows:

[0105] (1) From 7:00 AM to 9:00 AM: 90% * 1500KW = 1350KW;

[0106] (2) 11:30 AM to 12:30 PM: 75% * 1000KW = 750KW;

[0107] (3) From 3:00 PM to 5:00 PM: 88% * 1200KW = 1056KW.

[0108] In some embodiments, the future wind power generation is adjusted based on the derating rate to obtain power generation prediction data, including but not limited to the method described above, which is obtained by multiplying the derating rate by the future wind power generation. This embodiment does not limit this method.

[0109] It is worth noting that the wind power generation adjustment range can be any time period, the method of determining the wind power generation adjustment range based on the icing sequence can be arbitrary, and the corresponding derating rate in different power generation adjustment ranges can be arbitrary; the derating rate can be in the form of decimal, percentage, fraction, etc., and this embodiment does not limit it.

[0110] In summary, the method provided in this application obtains first icing forecast data, wind speed data, and historical power generation data of the wind turbine operating area within a historical time period. Based on the first icing forecast data, wind speed data, and historical power generation data, correction parameters are obtained. Based on the correction parameters, the predicted power generation in the future time period is corrected to obtain the actual power generation data that the wind turbine can output under icing conditions. This accurately understands the operating status and output power of the wind turbine, improving the operation and maintenance efficiency of the wind turbine. Furthermore, by correcting the icing forecast data in the future time period based on the correction parameters, the icing sequence of the wind turbine operating area in the future time period is obtained, improving the accuracy of predicting the icing conditions in the wind turbine operating area.

[0111] The method provided in this embodiment determines the wind power generation adjustment range of the wind turbine based on the icing sequence, and adjusts the wind power generation within the adjustment range based on the derating rate in the correction parameters to obtain power generation prediction data. This improves the accuracy of the power prediction data and can improve the operation and maintenance efficiency of the wind turbine.

[0112] Figure 3 This application illustrates a flowchart of a method for obtaining correction parameters according to an exemplary embodiment. The correction parameters are determined based on first icing forecast data, wind speed data, and historical power generation data. Figure 3 As shown, the method includes:

[0113] Step 310: Based on wind speed data, obtain historical power generation prediction data.

[0114] Historical power generation forecast data refers to the power generation data of wind turbines predicted within a historical time period.

[0115] Wind speed data is an important factor affecting the power generation data of wind turbines. By inputting the wind speed data into the preset power prediction formula, the corresponding theoretical power generation data, that is, the historical power generation prediction data, can be obtained.

[0116] It is worth noting that the historical power generation prediction data refers to the power that the wind turbine blades can output when blown by the wind under normal conditions, that is, when there is no icing in the wind turbine operating area. There is an error between the historical power generation prediction data and the actual data. The preset power prediction formula can be arbitrary, and this embodiment does not limit it.

[0117] In some embodiments, the historical power generation prediction data based on wind speed data does not need to be calculated by a formula, and the historical power generation prediction data can also be obtained based on other data. This embodiment does not limit this.

[0118] Step 320: Determine the extension time based on historical power generation forecast data, historical power generation data, and the first icing forecast data.

[0119] Among them, the historical power generation prediction data is calculated based on wind speed data within a historical time period, and is the predicted power data of the wind turbine under the condition that no icing occurs in the wind turbine operating area during the historical time period; the historical power generation data is obtained after correcting the historical power generation prediction data, and is the actual power data of the wind turbine under the condition that icing occurs in the wind turbine operating area during the historical time period.

[0120] Optionally, historical power generation forecast data, historical power generation data, and first icing forecast data are input into a preset power prediction model to output the extended time.

[0121] Because icing occurred in the wind turbine operating area, the output power of the wind turbine was damaged. There was an error between the historical power generation prediction data and the historical power generation data. The extended time was used to determine the correction range.

[0122] Optionally, the historical time period refers to the past winter. The first icing forecast data, historical power generation prediction data and historical power generation data corresponding to the past winter for each wind turbine operating area are input into the preset power prediction model, which can output an extended time with high accuracy.

[0123] In some embodiments, wind speed data, first icing forecast data, and historical power generation data within a historical time period can be input into a preset power prediction model to output an extended time.

[0124] Step 330: Based on the first icing forecast data, determine the total duration of icing in the wind turbine operating area within the historical time period.

[0125] Optionally, the historical time period refers to the past winter. Icing prediction is performed on the past winter to obtain the first icing forecast data corresponding to each wind turbine operating area. The first icing forecast data includes the following: the time points of icing and icing quality data of the past winter.

[0126] Based on the first icing forecast data, for each wind turbine operating area, the duration of icing in that operating area during the historical time period is added together to obtain the total icing duration for each wind turbine operating area.

[0127] Optionally, there are two fan operating areas: a first fan operating area and a second fan operating area; the total duration of icing in the first fan operating area is 5 hours, and the total duration of icing in the second fan operating area is 8 hours.

[0128] In some embodiments, in addition to directly determining the total duration based on the first icing forecast data, the total duration can also be obtained by directly inputting the first icing forecast data into a preset model and outputting the total icing duration. This embodiment does not limit this method.

[0129] Step 340: Determine the derating rate based on the relationship between the total duration and the preset duration threshold.

[0130] The preset duration threshold is used to determine whether the reduction rate needs to be determined based on the first icing forecast data within the historical time period. The preset duration threshold can be any unit or any value.

[0131] The relationship between the total duration and the preset duration threshold includes, but is not limited to, the following two cases:

[0132] (1) If the total duration is less than the preset duration threshold, the derating rate is determined to be the preset default value;

[0133] Optionally, the preset duration threshold is 20 hours, and the total duration is 5 hours. If the total duration of freezing is less than the preset duration threshold, the derating rate will be the preset default value.

[0134] (2) If the total duration is greater than the preset duration threshold, the derating rate is determined based on the ratio of historical power generation data and historical power generation prediction data.

[0135] Optionally, the preset duration threshold is 20 hours, and the total duration is 25 hours. If the total duration of icing is greater than the preset duration threshold, the derating rate is determined based on the ratio of historical power generation data to historical power generation prediction data.

[0136] Optionally, there are two wind turbine operating areas: a first wind turbine operating area and a second wind turbine operating area. If the total duration of icing in the first wind turbine operating area is 5 hours, which is less than a preset duration threshold, then the derating rate of the first wind turbine operating area is the preset default value. If the total duration of icing in the second wind turbine operating area is 25 hours, which is greater than the preset duration threshold, then the derating rate of the second wind turbine operating area is the ratio of historical power generation data to historical power generation prediction data.

[0137] In some embodiments, when the total duration of icing in a wind turbine operating area exceeds a preset duration threshold, the wind speed data, first icing forecast data, and historical power generation data of the wind turbine operating area in the historical time period can be directly input into a preset power prediction model to output the optimal derating rate for the wind turbine operating area.

[0138] By following the steps above, the derating rate and extension time of each wind turbine operating area in the historical time period are obtained and saved. This data can be used to correct the icing prediction data for the future time period, and thus obtain the predicted power generation data of the wind turbine in the wind turbine operating area under the condition of icing in the future time period.

[0139] In some embodiments, after obtaining the derating rate and extension time of each wind turbine operating area in a historical time period through a preset power prediction model, the derating rate data and extension time are saved to the preset power prediction model. Icing forecast data for future time periods can be input into the preset power prediction model, and the power generation prediction data of the wind turbine in the wind turbine operating area under icing conditions in the future time period can be output.

[0140] In summary, the method provided in this application obtains first icing forecast data, wind speed data, and historical power generation data for each wind turbine operating area within a historical time period. Based on these parameters, it obtains highly accurate correction parameters for each wind turbine operating area, including time extension and derating rate. This method can predict the power generation data of wind turbines in each operating area under icing conditions in the future time period, thereby improving the accuracy of power prediction and the efficiency of wind turbine operation and maintenance.

[0141] The method provided in this embodiment obtains the predicted output power of the wind turbine based on wind speed data within a historical time period. It analyzes the predicted and actual output power of the wind turbine based on the first icing forecast data to obtain an extended time with high accuracy. The icing forecast data for future time periods can be corrected based on the extended time to improve the accuracy of the icing forecast data and further obtain more accurate power generation prediction data for future time periods.

[0142] The method provided in this embodiment obtains the total icing duration of each wind turbine operating area based on the first icing forecast data within a historical time period, determines the calculation method of the derating rate based on the relationship between the total duration and the preset duration threshold, and directly uses the preset default value for wind turbine operating areas with a shorter total icing duration, which can improve the effect of obtaining the derating rate.

[0143] Figure 4 The flowchart illustrates a method for obtaining an icing sequence according to an embodiment of this application. The method involves correcting icing forecast data based on correction parameters to obtain the corresponding icing sequence, and includes the following steps:

[0144] Step 410: Based on the second icing forecast data, determine the icing time points in the wind turbine operating area within the future time period.

[0145] The second icing forecast data is used to forecast the icing situation in the wind turbine operating area in the future time period. Each wind turbine operating area corresponds to its own second icing forecast data, which includes the icing time points in the wind turbine operating area in the future time period.

[0146] Optionally, the starting point of the future time period is 8:00 AM on the following day (e.g., December 30th), and the duration is 24 hours, i.e., from 8:00 AM on December 30th to 8:00 AM on December 31st. The second icing forecast data for each wind turbine operating area corresponds to the icing situation forecast within the above time period.

[0147] Optionally, there exists a wind turbine operating area, and the corresponding second icing forecast data indicates that icing will occur at the following times: 10:00 AM on December 30, 1:00 PM on December 30, and 4:00 AM on December 31, for a total of 3 time points.

[0148] It is worth noting that the starting point and duration of the future time period can be arbitrary, the number of wind turbine operating areas can be arbitrary, and the time points in the second icing forecast data where icing may occur can be arbitrary. This embodiment does not limit this.

[0149] Step 420: Correct the icing time point based on the extended time to obtain the icing sequence of the wind turbine operating area in the future time period.

[0150] Optionally, the extension times corresponding to the above freezing time points are as follows:

[0151] (1) Ice formation occurred at 10:00 AM on December 30: The time extension is 1 hour before and 1 hour after.

[0152] (2) Ice formation occurred at 13:00 on December 30: The time was extended by 1 hour before and 1 hour after.

[0153] (3) Ice formation occurred at 4:00 AM on December 31: The extension time is 0.5 hours before and after.

[0154] Indicative, such as Figure 5 As shown, Figure 5 This is a schematic diagram of an icing sequence.

[0155] The corrected freezing sequence 500 contains three freezing time points, while freezing does not occur at the other time points.

[0156] (1) The first time point 501 indicates that icing occurred between 9:00 AM and 11:00 AM on December 30th;

[0157] (2) The second time point 502 indicates that icing occurred between 12:00 noon and 14:00 on December 30;

[0158] (3) The third time point 503 indicates that icing occurred between 3:30 am and 4:30 am on December 31.

[0159] Step 430: Based on the time interval between freezing time points in the freezing sequence, determine at least one freezing interval, wherein at least one freezing interval meets the requirement of continuous freezing time.

[0160] After the icing sequence is obtained by correcting the second icing forecast data based on the extended time, the icing interval is determined by the time interval between the icing time points in the icing sequence based on the preset continuous non-icing duration.

[0161] Among them, meeting the continuous time requirement means that the continuous duration during which no ice formation occurs in the wind turbine operating area is less than the preset continuous non-icing duration.

[0162] Optionally, the preset continuous non-icing time is 3 hours. The continuous non-icing time is used to determine the icing interval. If there is a time interval of less than 3 hours between two adjacent icing points, then the area between these two icing points is set as icing, and the icing interval is determined.

[0163] Indicative, such as Figure 6 As shown, Figure 6 It is based on Figure 5 A schematic diagram showing how the freezing sequence determines the freezing interval.

[0164] There are three freezing time points in freezing sequence 500: first time point 501, second time point 502, and third time point 503. The freezing duration corresponding to the first time point 501 is 2 hours, the freezing duration corresponding to the second time point 502 is 2 hours, and the freezing duration corresponding to the third time point 503 is 1 hour.

[0165] Among them, the continuous non-icing time between the icing duration corresponding to the first time point 501 and the icing duration corresponding to the second time point 502 is 1 hour: from 11:00 am to 12:00 pm on December 30th. If this time interval is less than the preset continuous non-icing time, then this time period is set as the icing situation.

[0166] The first icing interval 610 is defined as: 9:00 AM to 2:00 PM on December 30th. The icing time period corresponding to the third time point 503 can also be used as the second icing interval 620.

[0167] It is worth noting that, based on the time interval between freezing time points in the freezing sequence, at least one freezing interval is determined. In addition to the method of continuous non-freezing time mentioned above, other methods can also be used, and this embodiment does not limit this method.

[0168] Step 440: Smooth the icing sequence to obtain a smoothed and updated icing sequence.

[0169] The icing sequence contains at least one icing interval, which is used to represent the icing situation in the wind turbine operating area. By smoothing the icing sequence, a more accurate and coherent icing sequence is obtained, which more intuitively shows the icing situation in the wind turbine operating area in the future time period.

[0170] In summary, the method provided in this application, by obtaining second icing forecast data for a future time period and correcting the second icing forecast data based on a known extended time, obtains an icing sequence, which can improve the accuracy of icing forecasts and improve the operation and maintenance efficiency of wind turbines in the wind turbine operating area.

[0171] The method provided in this embodiment determines at least one icing interval that meets the continuous icing time requirement by preset a continuous non-icing time and based on the continuous non-icing time and the time interval between icing time points in the icing sequence, so that the icing situation in the wind turbine operating area represented by the icing sequence is more accurate.

[0172] The method provided in this embodiment obtains a smoothed and updated, more coherent icing sequence by smoothing the icing sequence, thereby making the icing situation in the wind turbine operating area more accurate.

[0173] Figure 7 This is a structural block diagram of a wind turbine power prediction device provided in an exemplary embodiment of this application, as shown below. Figure 7 As shown, the device includes:

[0174] The acquisition module 710 is used to acquire first icing forecast data and wind speed data of the wind turbine operating area within a historical time period; and to acquire historical power generation data of the wind turbine generator in the wind turbine operating area within the historical time period, wherein the first icing forecast data is data obtained by icing prediction of the historical time period.

[0175] The determining module 720 is used to determine correction parameters based on the first icing forecast data, the wind speed data, and the historical power generation data. The correction parameters are used to adjust the predicted power generation data of the wind turbine.

[0176] The acquisition module 710 is also used to acquire second icing forecast data for the wind turbine operating area in the future time period;

[0177] The correction module 730 is used to correct the second icing forecast data based on the correction parameters to obtain the icing sequence of the wind turbine operating area in the future time period. The icing sequence is used to indicate the icing situation of the wind turbine operating area at different time points in the future time period.

[0178] The adjustment module 750 is used to adjust the wind power generation of the wind turbine in the future time period based on the correction parameters and the icing sequence, so as to obtain the power generation prediction data.

[0179] In an optional embodiment, such as Figure 8 As shown, the correction parameters include extended time and derating rate. The extended time refers to the time taken for the icing and melting processes to occur in the wind turbine operating area, and the derating rate is used to represent the decrease in wind power generation of the wind turbine under icing conditions.

[0180] The correction module 730 further includes:

[0181] The power acquisition unit 731 is used to obtain historical power generation prediction data based on the wind speed data, wherein the historical power generation prediction data refers to the power generation data of the wind turbine predicted within the historical time period.

[0182] The determining unit 732 is used to determine the extended time based on the historical power generation prediction data, the historical power generation data, and the first icing forecast data;

[0183] The determining unit 732 is further configured to determine, based on the first icing forecast data, the total duration of icing in the wind turbine operating area within the historical time period;

[0184] The determining unit 732 is further configured to determine the derating rate based on the relationship between the total duration and the preset duration threshold.

[0185] In an optional embodiment, the determining unit 732 is further configured to determine the derating rate as a preset default value in response to the total duration being less than the preset duration threshold; and to determine the derating rate based on the ratio of the historical power generation data and the historical power generation prediction data in response to the total duration being greater than the preset duration threshold.

[0186] In an optional embodiment, the correction module 730 is further configured to determine, based on the second icing forecast data, the icing time point in the future time period in which the wind turbine operating area will ic up; and to correct the icing time point based on the extended time to obtain the icing sequence in the future time period in the wind turbine operating area.

[0187] In an optional embodiment, the correction module 730 is further configured to determine at least one icing interval based on the time interval between the icing time points in the icing sequence, wherein the at least one icing interval meets the continuous icing time requirement.

[0188] In an optional embodiment, the adjustment module 750 is further configured to determine the wind power generation adjustment range of the wind turbine based on the icing sequence, wherein the wind power generation adjustment range refers to the time interval during which the wind power generation of the wind turbine needs to be adjusted within the future time period; and adjust the wind power generation within the wind power generation adjustment range based on the derating rate to obtain the power generation prediction data.

[0189] In an optional embodiment, after the correction module 730, the device further includes:

[0190] The smoothing module 740 is used to smooth the icing sequence to obtain the updated smoothed icing sequence.

[0191] In summary, the wind turbine power prediction device provided in this application acquires first icing forecast data, wind speed data, and historical power generation data of the wind turbine operating area within a historical time period. Based on the first icing forecast data, wind speed data, and historical power generation data, correction parameters are obtained. These correction parameters can correct the predicted power generation in the future time period, obtaining the actual power generation data that the wind turbine can output under icing conditions. This provides an accurate understanding of the wind turbine's operating status and output power, improving the efficiency of wind turbine operation and maintenance. Furthermore, by correcting the icing forecast data for the future time period based on the correction parameters, an icing sequence for the wind turbine operating area in the future time period is obtained, improving the accuracy of predicting the icing conditions in the wind turbine operating area.

[0192] It should be noted that the wind turbine power prediction device provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the wind turbine power prediction device and the wind turbine power prediction method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0193] Figure 9This illustration shows a structural block diagram of a computer device 900 provided in an exemplary embodiment of this application. The computer device 900 may be a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The computer device 900 may also be referred to as user equipment, portable terminal, laptop terminal, desktop terminal, or other names.

[0194] Typically, computer device 900 includes a processor 901 and a memory 902.

[0195] Processor 901 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 901 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 901 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 901 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 901 may also include an AI processor for handling computational operations related to machine learning.

[0196] The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 902 are used to store at least one instruction, which is executed by the processor 901 to implement the wind turbine power prediction method provided in the method embodiments of this application.

[0197] In some embodiments, the computer device 900 also includes other components, as those skilled in the art will understand. Figure 9 The structure shown does not constitute a limitation on terminal 900, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0198] Optionally, the computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), solid-state drives (SSDs), or optical discs, etc. The random access memory may include resistive random access memory (ReRAM) and dynamic random access memory (DRAM). The sequence numbers of the embodiments in this application are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0199] This application also provides a computer device, which includes a processor and a memory. The memory stores at least one instruction, at least one program, a code set, or an instruction set. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the wind turbine power prediction method as described in any of the above embodiments of this application.

[0200] This application also provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the wind turbine power prediction method as described in any of the above embodiments of this application.

[0201] This application also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform any of the wind turbine power prediction methods described in the above embodiments.

[0202] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0203] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for predicting wind turbine power, characterized in that, The method includes: The system acquires first icing forecast data and wind speed data for the wind turbine operating area within a historical time period; and acquires historical power generation data of the wind turbine generators in the wind turbine operating area within the historical time period. The first icing forecast data is data obtained by predicting icing for the historical time period. The first icing forecast data is used to represent the time points and icing quality data where icing may occur within the historical time period. Based on the first icing forecast data, the wind speed data, and the historical power generation data, correction parameters are determined. These correction parameters are used to adjust the predicted power generation data of the wind turbine. The correction parameters include extended time and derating rate. The extended time refers to the time elapsed during the icing and melting process in the wind turbine operating area, and the derating rate represents the decrease in wind power generation under icing conditions. Specifically, based on the wind speed data, historical power generation prediction data is obtained, which refers to the predicted power generation data of the wind turbine within the historical time period. Based on the historical power generation prediction data, the historical power generation data, and the first icing forecast data, the extended time is determined. Based on the first icing forecast data, the total duration of icing in the wind turbine operating area within the historical time period is determined. If the total duration is less than a preset duration threshold, the derating rate is determined to be a preset default value. If the total duration is greater than the preset duration threshold, the derating rate is determined based on the ratio of the historical power generation data to the historical power generation prediction data. Obtain second icing forecast data for the wind turbine operating area in the future time period; The second icing forecast data is corrected based on the correction parameters to obtain the icing sequence of the wind turbine operating area in the future time period. The icing sequence is used to indicate the icing situation of the wind turbine operating area at different time points in the future time period. The icing sequence is formed by extending and correcting the icing time points in the second icing forecast data forward and backward. Based on the correction parameters and the icing sequence, the wind power generation of the wind turbine is adjusted for the future time period to obtain power generation prediction data.

2. The method according to claim 1, characterized in that, The step of correcting the second icing forecast data based on the correction parameters to obtain the icing sequence of the wind turbine operating area in the future time period includes: Based on the second icing forecast data, the icing time points in the future time period where the wind turbine operating area will ic up are determined. The icing time point is corrected based on the extended time to obtain the icing sequence of the wind turbine operating area in the future time period.

3. The method according to claim 2, characterized in that, The method further includes: Based on the time interval between the freezing time points in the freezing sequence, at least one freezing interval is determined, and the at least one freezing interval meets the requirement of continuous freezing time.

4. The method according to claim 1, characterized in that, The adjustment of the wind power generation of the wind turbine in the future time period based on the correction parameters and the icing sequence to obtain power generation prediction data includes: Based on the icing sequence, the wind power generation adjustment range of the wind turbine is determined. The wind power generation adjustment range refers to the time interval during which the wind power generation of the wind turbine needs to be adjusted within the future time period. Based on the derating rate, the wind power generation within the wind power generation adjustment range is adjusted to obtain the predicted power generation data.

5. The method according to claim 1, characterized in that, After correcting the second icing forecast data based on the correction parameters to obtain the icing sequence of the wind turbine operating area in the future time period, the method further includes: The icing sequence is smoothed to obtain the smoothed updated icing sequence.

6. A device for predicting wind turbine power, characterized in that, The device includes: The acquisition module acquires first icing forecast data and wind speed data of the wind turbine operating area within a historical time period; and acquires historical power generation data of the wind turbine generator in the wind turbine operating area within the historical time period. The first icing forecast data is data obtained by predicting icing in the historical time period. The first icing forecast data is used to represent the time points and icing quality data where icing may occur within the historical time period. The determination module determines correction parameters based on the first icing forecast data, the wind speed data, and the historical power generation data. These correction parameters adjust the predicted power generation data of the wind turbine. The correction parameters include extended time and derating rate. The extended time refers to the time elapsed during the icing and melting processes in the wind turbine operating area, and the derating rate represents the decrease in wind power generation under icing conditions. Specifically, based on the wind speed data, historical power generation prediction data is obtained, which refers to the predicted power generation data of the wind turbine within the historical time period. Based on the historical power generation prediction data, the historical power generation data, and the first icing forecast data, the extended time is determined. Based on the first icing forecast data, the total duration of icing in the wind turbine operating area within the historical time period is determined. If the total duration is less than a preset duration threshold, the derating rate is determined to be a preset default value. If the total duration is greater than the preset duration threshold, the derating rate is determined based on the ratio of the historical power generation data to the historical power generation prediction data. The acquisition module acquires second icing forecast data for the wind turbine operating area within a future time period; The correction module corrects the second icing forecast data based on the correction parameters to obtain the icing sequence of the wind turbine operating area in the future time period. The icing sequence is used to indicate the icing situation of the wind turbine operating area at different time points in the future time period. The icing sequence is formed by extending and correcting the icing time points in the second icing forecast data forward and backward. The adjustment module adjusts the wind power generation of the wind turbine in the future time period based on the correction parameters and the icing sequence to obtain power generation prediction data.

7. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one program, which is loaded and executed by the processor to implement the wind turbine power prediction method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The storage medium stores at least one program, which is loaded and executed by a processor to implement the wind turbine power prediction method as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the wind turbine power prediction method as described in any one of claims 1 to 5.

Images