Offshore wind power prediction method and system based on high-frequency updated weather forecast

Abstract

The present disclosure relates to a method and system for predicting offshore wind power based on high-frequency updated weather forecasts, and relates to the field of renewable energy power generation technology. By acquiring information representing the actual weather conditions of an offshore wind power station, the high-frequency updated weather forecast data is corrected, and the generated power of the offshore wind power station is predicted using the corrected weather forecast data. Because the weather forecast data is corrected using information representing the actual weather conditions of the offshore wind power station, the corrected weather forecast data can be made closer to the actual weather conditions, improving the accuracy of the corrected weather forecast data. Thus, the generated power can be predicted using the more accurate weather forecast data, improving the accuracy of offshore power generation predictions and, in turn, improving the operational stability of the offshore wind power station.

Description

Technical Field

[0001] The present disclosure relates to the field of renewable energy power generation technology, and in particular to a method and system for predicting offshore wind power based on high-frequency updated weather forecasts. Background Art

[0002] An offshore wind power station is a facility that uses ocean wind energy resources to generate electricity. The principle of an offshore wind power station is to use the offshore wind to drive the windmill blades to rotate, converting the kinetic energy of the sea wind into mechanical kinetic energy, and then converting it into electrical kinetic energy to drive the generator to generate electricity.

[0003] In the operation of offshore wind power plants, it is often necessary to predict the generated power to control the plant accordingly and ensure its operational stability. High-frequency weather forecast data, typically sourced from meteorological satellites, radar, ocean buoys, and weather models, is fundamental to offshore wind power forecasting.

[0004] At present, offshore wind power prediction based on high-frequency updated meteorological forecast data usually directly applies the high-frequency updated meteorological forecast data. This application method does not take into account the deviation between the high-frequency updated meteorological forecast data and the actual situation, resulting in low accuracy of offshore wind power prediction, which may affect the operational stability of offshore wind power stations. Summary of the Invention

[0005] The purpose of the present disclosure is to provide an offshore wind power prediction method and system based on high-frequency updated weather forecasts, which improves the accuracy of offshore wind power predictions and thus improves the operational stability of offshore wind power stations.

[0006] To achieve the above-mentioned objectives, in a first aspect, the present disclosure provides an offshore wind power prediction method based on high-frequency updated weather forecasts, comprising: obtaining weather forecast data of an offshore wind power station, wherein the update frequency of the weather forecast data is higher than a preset frequency; obtaining target information for characterizing the actual weather conditions of the offshore wind power station, wherein the offshore wind power station comprises a plurality of wind turbines arranged in a target sea area, and the target information comprises a first meteorological feature and a second meteorological feature, wherein the first meteorological feature is used to characterize the vibration distribution of the plurality of wind turbines, and the second meteorological feature is used to characterize the sound distribution of the plurality of wind turbines; according to the target information, the weather forecast data is corrected to obtain corrected weather forecast data; according to the corrected weather forecast data, the power generation power of the offshore wind power station is predicted to obtain predicted power generation power.

[0007] Optionally, the offshore wind power station is provided with multiple wind turbines in the target sea area, and the acquiring of target information for characterizing the real meteorological conditions of the offshore wind power station includes: acquiring vibration information corresponding to each of the multiple wind turbines; acquiring sound information corresponding to each of the multiple wind turbines; acquiring position distribution characteristics, wherein the position distribution characteristics are used to characterize the position distribution of the multiple wind turbine generators in the target sea area; and determining the target information based on the vibration information, the sound information and the position distribution characteristics.

[0008] Optionally, determining the target information based on the vibration information, the sound information and the position distribution characteristics includes: generating multiple position distribution matrices corresponding to the multiple wind turbines based on the position distribution characteristics, wherein each position distribution matrix includes multiple first matrix elements, one first matrix element corresponds to one wind turbine, and different position distribution matrices correspond to different wind directions and different starting wind turbines; generating multiple vibration distribution matrices based on the vibration information and the multiple position distribution matrices, wherein each vibration distribution matrix includes multiple second matrix elements, and one second matrix element corresponds to the vibration information of a wind turbine; generating multiple sound distribution matrices based on the sound information and the multiple position distribution matrices, wherein each sound distribution matrix includes multiple third matrix elements, and one third matrix element corresponds to the sound information of a wind turbine; and determining the target information based on the multiple vibration distribution matrices and the multiple sound distribution matrices.

[0009] Optionally, determining the target information based on the multiple vibration distribution matrices and the multiple sound distribution matrices includes: performing dimensionality reduction processing on the multiple vibration distribution matrices respectively to obtain multiple vibration distribution matrices after dimensionality reduction; performing dimensionality reduction processing on the multiple sound distribution matrices respectively to obtain multiple sound distribution matrices after dimensionality reduction; performing deduplication processing on the multiple vibration distribution matrices after dimensionality reduction to obtain a target vibration distribution matrix; performing deduplication processing on the multiple sound distribution matrices after dimensionality reduction to obtain a target sound distribution matrix; determining the matrix characteristics of the target vibration distribution matrix as the first meteorological characteristics; determining the matrix characteristics of the target sound distribution matrix as the second meteorological characteristics; and determining the first meteorological characteristics and the second meteorological characteristics as the target information.

[0010] Optionally, the weather forecast data is corrected according to the target information to obtain corrected weather forecast data, including: predicting the vibration distribution of the multiple wind turbines according to the weather forecast data to obtain vibration distribution prediction information; predicting the sound distribution of the multiple wind turbines according to the weather forecast data to obtain sound distribution prediction information; and correcting the vibration-related data and the sound-related data in the weather forecast data according to the vibration distribution prediction information, the first meteorological feature, the sound distribution prediction information and the second meteorological feature to obtain corrected weather forecast data.

[0011] Optionally, the offshore wind power prediction method also includes: obtaining simulation data obtained in advance through simulation, the simulation data including meteorological simulation data, vibration distribution simulation information corresponding to the meteorological simulation data, and sound distribution simulation information corresponding to the meteorological simulation data; predicting the vibration distribution of the multiple wind turbines based on the meteorological forecast data to obtain vibration distribution prediction information, including: determining the vibration distribution prediction information based on the meteorological forecast data, the meteorological simulation data, and the vibration distribution simulation information corresponding to the meteorological simulation data; predicting the sound distribution of the multiple wind turbines based on the meteorological forecast data to obtain sound distribution prediction information, including: determining the sound distribution prediction information based on the meteorological forecast data, the meteorological simulation data, and the sound distribution simulation information corresponding to the meteorological simulation data.

[0012] Optionally, the vibration-related data include wind speed and wind force, and the sound-related data include wind speed, wind force and wind direction, and the vibration-related data and sound-related data in the meteorological forecast data are corrected according to the vibration distribution prediction information, the first meteorological feature, the sound distribution prediction information and the second meteorological feature to obtain corrected meteorological forecast data, including: with respect to the wind speed and wind force, correcting according to the vibration distribution prediction information, the first meteorological feature, the sound distribution prediction information and the second meteorological feature to obtain corrected wind speed and wind force; with respect to the wind direction, correcting according to the sound distribution prediction information and the second meteorological feature to obtain a corrected wind direction; and determining the corrected meteorological forecast data according to the corrected wind speed, the corrected wind force and the corrected wind direction.

[0013] Optionally, the power generation power of the offshore wind power station is predicted based on the revised weather forecast data to obtain the predicted power generation power, including: determining the prediction weight based on the update frequency of the weather forecast data; obtaining the historical power generation power and the historical weather forecast data corresponding to the historical power generation power; and predicting the power generation power of the offshore wind power station based on the prediction weight, the historical power generation power, the historical weather forecast data and the revised weather forecast data through a pre-trained power generation prediction model to obtain the predicted power generation power.

[0014] Optionally, the offshore wind power prediction method also includes: determining power generation change information based on the predicted power generation and the historical power generation; determining meteorological change information based on the historical meteorological forecast data and the revised meteorological forecast data; and adjusting the update frequency of the meteorological forecast data based on the power generation change information and the meteorological change information.

[0015] In a second aspect, the present disclosure provides an offshore wind power prediction system based on high-frequency updated weather forecasts, comprising: a vibration sensing device, the vibration sensing device being arranged on a wind turbine for collecting vibration information of the wind turbine; a sound sensing device being arranged on a wind turbine for collecting sound information of the wind turbine; and a prediction platform, being communicatively connected to the vibration sensing device and the sound sensing device respectively, for executing the offshore wind power prediction method based on high-frequency updated weather forecasts as described in the first aspect of the present disclosure.

[0016] The above technical solution obtains information representing the actual meteorological conditions of the offshore wind power station, corrects the frequently updated meteorological forecast data, and uses the corrected meteorological forecast data to predict the offshore wind power station's power generation. Because the meteorological forecast data is corrected using information representing the actual meteorological conditions of the offshore wind power station, the corrected meteorological forecast data is closer to the actual meteorological conditions, improving the accuracy of the corrected meteorological forecast data. Consequently, the more accurate meteorological forecast data can be used to predict power generation, improving the accuracy of offshore power generation predictions and, in turn, enhancing the operational stability of the offshore wind power station.

[0017] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following detailed description, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0019] Figure 1The present invention is a structural block diagram of an offshore wind power prediction system based on high-frequency updated weather forecasts according to an exemplary embodiment.

[0020] Figure 2 The present invention is a flowchart of a method for predicting offshore wind power based on high-frequency updated weather forecasts according to an exemplary embodiment.

[0021] Figure 3 The figure is a schematic diagram showing the location distribution of a wind turbine according to an exemplary embodiment.

[0022] Figure 4 The present invention is a block diagram of an offshore wind power prediction device based on high-frequency updated weather forecasts according to an exemplary embodiment.

[0023] Figure 5 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0024] The following describes the specific embodiments of the present disclosure in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure and are not intended to limit the present disclosure.

[0025] An offshore wind power station is a facility that uses ocean wind energy resources to generate electricity. The principle of an offshore wind power station is to use the offshore wind to drive the windmill blades to rotate, converting the kinetic energy of the sea wind into mechanical kinetic energy, and then converting it into electrical kinetic energy to drive the generator to generate electricity.

[0026] In the operation of offshore wind power plants, it is often necessary to predict the generated power to control the plant accordingly and ensure its operational stability. High-frequency weather forecast data, typically sourced from meteorological satellites, radar, ocean buoys, and weather models, is fundamental to offshore wind power forecasting.

[0027] At present, offshore wind power prediction based on high-frequency updated meteorological forecast data usually directly applies the high-frequency updated meteorological forecast data. This application method does not take into account the deviation between the high-frequency updated meteorological forecast data and the actual situation, resulting in low accuracy of offshore wind power prediction, which may affect the operational stability of offshore wind power stations.

[0028] Based on this, the embodiment of the present disclosure provides a technical solution to obtain information used to characterize the actual meteorological conditions of offshore wind power stations, correct the meteorological forecast data based on high-frequency updates, and use the corrected meteorological forecast data to predict the power generation of offshore wind power stations.

[0029] Since the weather forecast data is corrected using information representing the actual weather conditions of the offshore wind power station, the corrected weather forecast data can be made closer to the actual weather conditions, thereby improving the accuracy of the corrected weather forecast data. Therefore, the power generation capacity can be predicted using more accurate weather forecast data, thereby improving the accuracy of offshore power generation predictions and further improving the operational stability of the offshore wind power station.

[0030] Figure 1 FIG. 1 is a structural block diagram of an offshore wind power prediction system based on high-frequency updated weather forecasts according to an exemplary embodiment. Figure 1 As shown, the system includes: a vibration sensing device, a sound sensing device and a prediction platform. The prediction platform is respectively connected to the vibration sensing device and the sound sensing device.

[0031] In some embodiments, the communication method of the prediction platform, vibration sensing equipment and sound sensing equipment can adopt a communication method adapted to the marine communication environment to improve communication stability.

[0032] In some embodiments, an offshore wind power station may include multiple wind turbines, which may be distributed in the same power generation area (sea area). Vibration sensing devices and sound sensing devices may be installed on each of the multiple wind turbines.

[0033] The vibration sensing device may be a vibration sensor array composed of multiple vibration sensors to achieve more comprehensive vibration information collection. The vibration sensing device can collect vibration information such as vibration frequency, vibration amplitude, and vibration intensity.

[0034] The sound sensing device may be a microphone array composed of multiple microphones to achieve more comprehensive sound information collection. The sound sensing device can collect sound information such as sound frequency and sound decibels.

[0035] As you can understand, offshore wind turbines rely on wind power to generate electricity. As wind passes through the wind turbine, its sound and vibration can reflect the wind conditions. Therefore, vibration and sound information can serve as the data basis for determining information reflecting the actual weather conditions at sea.

[0036] In some embodiments, the prediction platform may be a server, a host computer, etc., which has data processing capabilities and can realize offshore wind power prediction based on various acquired data, including weather forecast data, sound information, vibration information, etc.

[0037] Therefore, in some embodiments, the prediction platform is also in communication with the weather forecast platform and can obtain weather forecast data from the weather forecast platform.

[0038] Figure 2This is a flowchart of an offshore wind power prediction method based on high-frequency updated weather forecasts according to an exemplary embodiment. The prediction method can be applied to Figure 1 The prediction platform shown, such as Figure 1 As shown, the prediction method includes the following steps:

[0039] Step S21 : obtaining weather forecast data for the offshore wind power station, where the update frequency of the weather forecast data is higher than a preset frequency.

[0040] Step S22: obtaining target information for characterizing the actual meteorological conditions of the offshore wind power station.

[0041] Step S23: Correcting the weather forecast data according to the target information to obtain corrected weather forecast data.

[0042] Step S24 , predicting the power generation of the offshore wind power station based on the corrected weather forecast data to obtain the predicted power generation.

[0043] In some embodiments, the update frequency of weather forecast data is higher than a preset frequency. The preset frequency may be a frequency higher than a normal update frequency. For example, normal weather forecast data is updated every other day, while high-frequency weather forecast data may be updated every 4 hours.

[0044] In some embodiments, a communication protocol may be established between the prediction platform and the weather forecast platform, wherein the communication protocol stipulates that the weather forecast platform synchronizes weather forecast data to the prediction platform according to an update frequency.

[0045] In some embodiments, the weather forecast data in step S21 may be weather forecast data currently synchronized with the forecasting platform, so as to realize online real-time offshore power generation prediction based on high-frequency updated weather forecast data.

[0046] In step S22, the target information represents the actual meteorological conditions. In combination with the description of the above embodiment, the target information can be determined based on the vibration information and the sound information.

[0047] Therefore, as an optional implementation, step S22 includes: obtaining vibration information corresponding to multiple wind turbines respectively; obtaining sound information corresponding to multiple wind turbines respectively; obtaining position distribution characteristics, which are used to characterize the position distribution of multiple wind turbines in the target sea area; and determining target information based on the vibration information, sound information and position distribution characteristics.

[0048] In this embodiment, the location distribution feature may be preset information related to the location distribution of the plurality of wind turbines in the target sea area. The target sea area may be the area where the plurality of wind turbines are installed.

[0049] In some embodiments, the vibration information may include: vibration intensity, vibration amplitude, and vibration frequency.

[0050] In some embodiments, the sound information may include: sound decibels and sound frequency.

[0051] In some embodiments, the target information is determined based on the vibration information, the sound information and the position distribution characteristics, including: generating multiple position distribution matrices corresponding to multiple wind turbines based on the position distribution characteristics, wherein each position distribution matrix includes multiple first matrix elements, one first matrix element corresponds to one wind turbine, and different position distribution matrices correspond to different wind directions and different starting wind turbines; generating multiple vibration distribution matrices based on the vibration information and the multiple position distribution matrices, wherein each vibration distribution matrix includes multiple second matrix elements, and one second matrix element corresponds to the vibration information of a wind turbine; generating multiple sound distribution matrices based on the sound information and the multiple position distribution matrices, wherein each sound distribution matrix includes multiple third matrix elements, and one third matrix element corresponds to the sound information of a wind turbine; and determining the target information based on the multiple vibration distribution matrices and the multiple sound distribution matrices.

[0052] In some embodiments, different position distribution matrices may be used as a sea breeze propagation sequence with different wind turbines as starting wind turbines under different wind directions.

[0053] Figure 3 FIG. 1 is a schematic diagram showing the location distribution of a wind turbine according to an exemplary embodiment. Figure 3 As shown, the wind turbines include five wind turbines F1 to F3, and these three wind turbines are distributed along the same horizontal line.

[0054] Then, based on Figure 5 The position distribution matrix of the wind turbines shown in FIG. 1 can be generated, for example, the position distribution matrix corresponding to the wind direction from north to south: , which means that the propagation of wind is not affected by position. The wind energy received by each wind turbine is basically the same. The position distribution matrix corresponding to the wind direction from west to east is: [F1 F2 F3], which means that the propagation of wind is affected by position. The wind energy received by F2 and F3 is affected by F1, and the wind energy received by F3 is also affected by F1. It means that the wind will propagate in sequence along the wind direction. The position distribution matrix corresponding to the wind direction from northwest to southeast is: , which means that the propagation of wind is affected by the position. The wind energy received by F1 and F2 affects each other, and the wind energy received by F2 affects the wind energy received by F3.

[0055] In some embodiments, when the positions of the wind turbines are fixed, the position distribution characteristics are also fixed. However, if the positions of the wind turbines change, the position distribution characteristics will also change accordingly. A corresponding position distribution matrix can be generated based on the specific position distribution characteristics.

[0056] Furthermore, based on the vibration information and the multiple position distribution matrices, multiple vibration distribution matrices may be generated.

[0057] In some embodiments, the first matrix element may be replaced with corresponding vibration information in the position distribution matrix.

[0058] For example, assuming that the position distribution matrix is ​​[F1 F2 F3], then F1 can be replaced by the vibration information corresponding to F1. For example, the vibration information includes: vibration intensity, vibration amplitude and vibration frequency, then the vibration information can form the matrix , d represents the vibration intensity, h represents the vibration amplitude, and f represents the vibration frequency. Then, the vibration distribution matrix can be: , d1~d3 represent the vibration intensities of F1~F3 respectively, h1~h3 represent the vibration amplitudes of F1~F3 respectively, and f1~f3 represent the vibration frequencies of F1~F3 respectively.

[0059] In some embodiments, the first matrix element may be replaced with corresponding sound information in the position distribution matrix.

[0060] For example, assuming the position distribution matrix is ​​[F1 F2 F3], then F1 can be replaced by the sound information corresponding to F1. For example, the sound information includes: sound intensity, sound amplitude and sound frequency, then the sound information can form the matrix , db represents the sound intensity, vf represents the sound frequency. Then, the sound distribution matrix can be: , db1~db3 represent the sound intensity of F1~F3 respectively, and vf1~vf3 represent the sound frequency of F1~F3 respectively.

[0061] Furthermore, target information may be determined based on a plurality of vibration distribution matrices and a plurality of sound distribution matrices.

[0062] As an optional implementation, target information is determined based on multiple vibration distribution matrices and multiple sound distribution matrices, including: performing dimensionality reduction processing on multiple vibration distribution matrices respectively to obtain multiple reduced-dimensional vibration distribution matrices; performing dimensionality reduction processing on multiple sound distribution matrices respectively to obtain multiple reduced-dimensional sound distribution matrices; performing deduplication processing on multiple reduced-dimensional vibration distribution matrices to obtain a target vibration distribution matrix; performing deduplication processing on multiple reduced-dimensional sound distribution matrices to obtain a target sound distribution matrix; determining the matrix characteristics of the target vibration distribution matrix as the first meteorological characteristics; determining the matrix characteristics of the target sound distribution matrix as the second meteorological characteristics; and determining the first meteorological characteristics and the second meteorological characteristics as target information.

[0063] In some embodiments, dimensionality reduction processing for a single vibration distribution matrix or a single sound distribution matrix may involve operations such as removing invalid matrix elements and normalizing matrix elements. Deduplication processing for multiple vibration distribution matrices or multiple sound distribution matrices after dimensionality reduction may involve operations such as reducing the number of similar matrices to make the matrices different from each other.

[0064] Furthermore, for the target vibration distribution matrix, the first meteorological feature can be obtained by extracting the matrix feature. Also, for the target sound distribution matrix, the second meteorological feature can be obtained by extracting the matrix feature.

[0065] As an example, the matrix characteristics may be the eigenvalues ​​or eigenvectors of the matrix. For example, for a square matrix A, if there exists a scalar λ and a non-zero vector v such that Av=λv, then λ is the eigenvalue of A and v is the corresponding eigenvector.

[0066] In some embodiments, the first meteorological feature may represent the difference in vibration distribution, for example, the larger the matrix eigenvalue, the greater the difference in vibration distribution. The second meteorological feature may represent the difference in sound distribution, for example, the larger the matrix eigenvalue, the greater the difference in sound distribution.

[0067] Therefore, the first meteorological feature is used to characterize the difference in vibration distribution of the multiple wind turbines, and the second meteorological feature is used to characterize the difference in sound distribution of the multiple wind turbines.

[0068] Through the above features, vibration information, sound information and location distribution characteristics can be converted into meteorological characteristics that represent differences, thereby realizing data processing.

[0069] In step S23, the weather forecast data is corrected according to the target information to obtain corrected weather forecast data.

[0070] As an optional implementation, the weather forecast data is corrected according to the target information to obtain corrected weather forecast data, including: predicting the vibration distribution of multiple wind turbines according to the weather forecast data to obtain vibration distribution prediction information; predicting the sound distribution of multiple wind turbines according to the weather forecast data to obtain sound distribution prediction information; correcting the vibration-related data and the sound-related data in the weather forecast data according to the vibration distribution prediction information, the first meteorological feature, the sound distribution prediction information and the second meteorological feature to obtain corrected weather forecast data.

[0071] In some embodiments, the method further includes: acquiring simulation data previously obtained through simulation, the simulation data including meteorological simulation data, vibration distribution simulation information corresponding to the meteorological simulation data, and sound distribution simulation information corresponding to the meteorological simulation data;

[0072] In this embodiment, a simulation model of the offshore power station is pre-built, and vibration and sound distribution simulations can be performed using this simulation model. The meteorological simulation data can be real meteorological data, and simulations using this meteorological data can generate vibration and sound distribution simulation information.

[0073] Furthermore, based on the weather forecast data, the vibration distribution of multiple wind turbines is predicted to obtain vibration distribution prediction information, including: determining the vibration distribution prediction information based on the weather forecast data, the weather simulation data and the vibration distribution simulation information corresponding to the weather simulation data.

[0074] In some embodiments, the vibration distribution prediction information may be vibration distribution difference information among a plurality of wind turbines, and the method for determining the vibration distribution difference information may refer to the method for determining the first meteorological characteristic.

[0075] And, based on the weather forecast data, the sound distribution of multiple wind turbines is predicted to obtain sound distribution prediction information, including: determining the sound distribution prediction information based on the weather forecast data, weather simulation data and sound distribution simulation information corresponding to the weather simulation data.

[0076] In some embodiments, the sound distribution prediction information may be sound distribution difference information between multiple wind turbines, and the method for determining the sound distribution difference information may refer to the method for determining the second meteorological feature.

[0077] In some embodiments, the vibration-related data includes wind speed and wind force, and the sound-related data includes wind speed, wind force, and wind direction.

[0078] Therefore, as an optional implementation, the vibration-related data and the sound-related data in the meteorological forecast data are corrected according to the vibration distribution prediction information, the first meteorological characteristic, the sound distribution prediction information and the second meteorological characteristic to obtain the corrected meteorological forecast data, including: for wind speed and wind force, corrections are made according to the vibration distribution prediction information, the first meteorological characteristic, the sound distribution prediction information and the second meteorological characteristic to obtain the corrected wind speed and wind force; for wind direction, corrections are made according to the sound distribution prediction information and the second meteorological characteristic to obtain the corrected wind direction; and the corrected meteorological forecast data is determined according to the corrected wind speed, the corrected wind force and the corrected wind direction.

[0079] In some embodiments, with respect to wind speed or wind force, the vibration distribution prediction information can be compared with the first meteorological characteristic, and the sound distribution prediction information can be compared with the second meteorological characteristic to determine the situation with the greater difference. For example, if the vibration distribution prediction information differs more significantly from the first meteorological characteristic, the wind speed or wind force in the vibration-related data is corrected. If the sound distribution prediction information differs more significantly from the second meteorological characteristic, the wind speed or wind force in the sound-related data is corrected.

[0080] In some embodiments, the wind speed or wind force can be corrected based on the specific difference. For example, the relationship between the differentiated information and the wind speed or wind force is determined in advance through offline testing, for example: V=i×R1×V0, N=j×R2×N0, where V represents the corrected wind speed, N represents the corrected wind force, V0 represents the wind speed to be corrected, N0 represents the wind force to be corrected, R1 and R2 represent differentiated information, which may be vibration differences or sound differences, i represents the wind speed correction coefficient, and j represents the wind force correction coefficient, which are pre-calibrated through offline testing and the values ​​are not limited here.

[0081] In some embodiments, the wind direction can be corrected directly based on the difference between the sound distribution prediction information and the second meteorological feature. For example, the wind direction can be corrected based on the specific difference. For example, the relationship between the differentiated information and the wind direction is determined in advance through offline testing, for example: O=k×R3×O0, where O represents the corrected wind direction (expressed as an angle), O0 represents the wind direction to be corrected, R3 represents the differentiated information, which is the sound difference, and k represents the wind direction correction coefficient, which is pre-calibrated through offline testing and the value is not limited here.

[0082] Furthermore, based on the corrected wind speed, the corrected wind force and the corrected wind direction, corrected weather forecast data can be obtained.

[0083] Furthermore, after obtaining the corrected weather forecast data, the power generation prediction can be performed by referring to the mature power generation prediction methods in this field.

[0084] For example, power generation prediction can be performed using a pre-trained machine learning model or a pre-configured functional relationship.

[0085] In some embodiments, historical information may also be combined to perform power generation prediction.

[0086] As an optional implementation, the power generation power of the offshore wind power station is predicted based on the revised weather forecast data to obtain the predicted power generation power, including: determining the prediction weight based on the update frequency of the weather forecast data; obtaining the historical power generation power and the historical weather forecast data corresponding to the historical power generation power; and predicting the power generation power of the offshore wind power station based on the prediction weight, the historical power generation power, the historical weather forecast data and the revised weather forecast data through a pre-trained power generation prediction model to obtain the predicted power generation power.

[0087] In some embodiments, the pre-trained power generation prediction model can be various types of neural network models.

[0088] In some embodiments, the training data for the pre-trained power generation prediction model may include: weight samples (determined based on the update frequency samples), historical power generation samples, historical weather forecast data samples, weather forecast data samples, and actual power generation. Model training based on this training data enables the power generation prediction model to predict power generation based on multi-dimensional information.

[0089] In some embodiments, the prediction weight may be directly the update frequency, or the update frequency may be modified to obtain the prediction weight.

[0090] In some embodiments, the historical weather forecast data corresponding to the historical power generation power may be corrected weather forecast data or uncorrected weather forecast data.

[0091] It can be understood that in the embodiment of the present disclosure, due to the special operating environment of the offshore power station, it is usually difficult to verify the authenticity of the weather forecast data through real weather sensor data. Therefore, the weather forecast data can be corrected using both sound and vibration information to reduce the error of the weather forecast data.

[0092] In some embodiments, the prediction method may also include: determining power generation change information based on the predicted power generation and historical power generation; determining meteorological change information based on historical meteorological forecast data and revised meteorological forecast data; and updating the update frequency of meteorological forecast data based on the power generation change information and meteorological change information.

[0093] In some embodiments, the power generation change information may be a power generation change rate, a power generation change value, or the like.

[0094] In some embodiments, the weather change information may be a weather change rate, a weather change value, or the like.

[0095] Furthermore, the update frequency of the weather forecast data can be adjusted in combination with the power generation change information and the weather change information.

[0096] In some embodiments, the greater the degree of change in generated power represented by the generated power change information and / or the greater the degree of change in weather represented by the weather change information, the greater the update frequency may be increased. Otherwise, the update frequency may remain unchanged.

[0097] Through the technical solutions of the embodiments of the present disclosure, information representing the actual meteorological conditions of an offshore wind power station is obtained, meteorological forecast data based on high-frequency updates is corrected, and the generated power of the offshore wind power station is predicted using the corrected meteorological forecast data. Because the meteorological forecast data is corrected using information representing the actual meteorological conditions of the offshore wind power station, the corrected meteorological forecast data can be made closer to the actual meteorological conditions, improving the accuracy of the corrected meteorological forecast data. As a result, the generated power can be predicted using the more accurate meteorological forecast data, improving the accuracy of offshore power generation predictions and, in turn, improving the operational stability of the offshore wind power station.

[0098] Figure 4 FIG. 1 is a block diagram of an offshore wind power prediction device based on high-frequency updated weather forecasts according to an exemplary embodiment. Figure 4 As shown, the device may include:

[0099] The acquisition module 401 is used to acquire weather forecast data of an offshore wind power station, where the update frequency of the weather forecast data is higher than a preset frequency; and to acquire target information for characterizing the actual weather conditions of the offshore wind power station.

[0100] The correction module 402 is used to correct the weather forecast data according to the target information to obtain corrected weather forecast data.

[0101] The prediction module 403 is configured to predict the power generation of the offshore wind power station according to the corrected weather forecast data to obtain the predicted power generation.

[0102] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0103] Figure 5FIG. 5 is a block diagram of an electronic device 500 according to an exemplary embodiment. Figure 5 As shown, the electronic device 500 may include: a processor 501 , a memory 502 , and may further include one or more of a multimedia component 503 , an input / output (I / O) interface 504 , and a communication component 505 .

[0104] The processor 501 is used to control the overall operation of the electronic device 500 to complete all or part of the steps in the above-mentioned offshore wind power prediction method based on high-frequency updated weather forecasts. The memory 502 is used to store various types of data to support the operation of the electronic device 500. This data may include, for example, instructions for any application or method operating on the electronic device 500, as well as application-related data, such as contact information, sent and received messages, pictures, audio, video, etc. The memory 502 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 503 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 502 or transmitted via the communication component 505. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 504 provides an interface between the processor 501 and other interface modules. The above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more thereof, so the corresponding communication component 505 may include: a Wi-Fi module, a Bluetooth module, an NFC module.

[0105] In an exemplary embodiment, the electronic device 500 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the above-mentioned offshore wind power prediction method based on high-frequency updated weather forecasts.

[0106] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided. When executed by a processor, the program instructions implement the steps of the above-described offshore wind power forecasting method based on high-frequency updated weather forecasts. For example, the computer-readable storage medium may be the aforementioned memory 502 including the program instructions. The program instructions may be executed by the processor 501 of the electronic device 500 to implement the above-described offshore wind power forecasting method based on high-frequency updated weather forecasts.

[0107] In another exemplary embodiment, a computer program product is further provided, which includes a computer program that can be executed by a processor, and when the computer program is executed by the processor, the steps of the above-mentioned offshore wind power prediction method based on high-frequency updated weather forecasts are implemented.

[0108] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the scope of protection of the present disclosure.

[0109] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0110] In addition, the various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A method for predicting offshore wind power based on high-frequency updated weather forecasts, characterized in that: include: Obtaining weather forecast data for the offshore wind power station, where the update frequency of the weather forecast data is higher than a preset frequency; Acquiring target information for characterizing real meteorological conditions of the offshore wind power station, the offshore wind power station including a plurality of wind turbines disposed in a target sea area, the target information including a first meteorological feature and a second meteorological feature, the first meteorological feature being used to characterize vibration distribution of the plurality of wind turbines, and the second meteorological feature being used to characterize sound distribution of the plurality of wind turbines; Correcting the weather forecast data according to the target information to obtain corrected weather forecast data; forecasting the power generation of the offshore wind power station based on the corrected weather forecast data to obtain a predicted power generation; The offshore wind power station is provided with a plurality of wind turbines in a target sea area, and acquiring target information for characterizing the actual meteorological conditions of the offshore wind power station includes: Obtaining vibration information corresponding to each of the plurality of wind turbines; Acquiring sound information corresponding to each of the plurality of wind turbines; Acquire a position distribution feature, where the position distribution feature is used to characterize the position distribution of the plurality of wind turbines in the target sea area; determining the target information according to the vibration information, the sound information, and the position distribution characteristics; The determining the target information according to the vibration information, the sound information, and the position distribution characteristics includes: generating, based on the position distribution characteristics, a plurality of position distribution matrices corresponding to the plurality of wind turbines, wherein each position distribution matrix includes a plurality of first matrix elements, one first matrix element corresponds to one wind turbine, and different position distribution matrices correspond to different wind directions and different starting wind turbines; generating a plurality of vibration distribution matrices according to the vibration information and the plurality of position distribution matrices, wherein each vibration distribution matrix includes a plurality of second matrix elements, and each second matrix element corresponds to the vibration information of one wind turbine; generating a plurality of sound distribution matrices according to the sound information and the plurality of position distribution matrices, wherein each sound distribution matrix includes a plurality of third matrix elements, and one third matrix element corresponds to the sound information of one wind turbine; determining the target information according to the plurality of vibration distribution matrices and the plurality of sound distribution matrices; The determining the target information according to the multiple vibration distribution matrices and the multiple sound distribution matrices includes: performing dimensionality reduction processing on the plurality of vibration distribution matrices respectively to obtain a plurality of vibration distribution matrices after dimensionality reduction; performing dimensionality reduction processing on the plurality of sound distribution matrices respectively to obtain a plurality of sound distribution matrices after dimensionality reduction; performing deduplication processing on the plurality of vibration distribution matrices after dimensionality reduction to obtain a target vibration distribution matrix; performing deduplication processing on the plurality of sound distribution matrices after dimensionality reduction to obtain a target sound distribution matrix; determining a matrix feature of the target vibration distribution matrix as a first meteorological feature; determining a matrix feature of the target sound distribution matrix as a second meteorological feature; The first meteorological feature and the second meteorological feature are determined as the target information.

2. The offshore wind power prediction method according to claim 1, characterized in that: The step of correcting the weather forecast data according to the target information to obtain corrected weather forecast data includes: predicting vibration distribution of the plurality of wind turbines based on the weather forecast data to obtain vibration distribution prediction information; Predicting sound distribution of the plurality of wind turbines based on the weather forecast data to obtain sound distribution prediction information; According to the vibration distribution prediction information, the first meteorological characteristics, the sound distribution prediction information and the second meteorological characteristics, the vibration-related data and the sound-related data in the meteorological forecast data are corrected to obtain corrected meteorological forecast data.

3. The offshore wind power prediction method according to claim 2, characterized in that: The offshore wind power prediction method further includes: Acquiring simulation data previously obtained through simulation, the simulation data including meteorological simulation data, vibration distribution simulation information corresponding to the meteorological simulation data, and sound distribution simulation information corresponding to the meteorological simulation data; The step of predicting the vibration distribution of the plurality of wind turbines based on the weather forecast data to obtain vibration distribution prediction information includes: determining vibration distribution prediction information based on the weather forecast data, the weather simulation data, and vibration distribution simulation information corresponding to the weather simulation data; The step of predicting the sound distribution of the plurality of wind turbines based on the weather forecast data to obtain sound distribution prediction information includes: Sound distribution prediction information is determined based on the weather forecast data, the weather simulation data, and sound distribution simulation information corresponding to the weather simulation data.

4. The offshore wind power prediction method according to claim 2, characterized in that: The vibration-related data includes wind speed and wind force, and the sound-related data includes wind speed, wind force, and wind direction. The vibration-related data and sound-related data in the weather forecast data are corrected based on the vibration distribution prediction information, the first meteorological characteristic, the sound distribution prediction information, and the second meteorological characteristic to obtain corrected weather forecast data, including: Correcting the wind speed and wind force according to the vibration distribution prediction information, the first meteorological characteristic, the sound distribution prediction information, and the second meteorological characteristic to obtain corrected wind speed and wind force; Correcting the wind direction according to the sound distribution prediction information and the second meteorological characteristic to obtain a corrected wind direction; The revised weather forecast data is determined based on the revised wind speed, the revised wind force and the revised wind direction.

5. The offshore wind power prediction method according to claim 1, characterized in that: The step of predicting the power generation of the offshore wind power station based on the corrected weather forecast data to obtain the predicted power generation includes: Determining a prediction weight according to an update frequency of the weather forecast data; Obtaining historical generated power and historical weather forecast data corresponding to the historical generated power; The power generation power of the offshore wind power station is predicted by a pre-trained power generation prediction model according to the prediction weight, the historical power generation power, the historical weather forecast data and the revised weather forecast data to obtain the predicted power generation power.

6. The offshore wind power prediction method according to claim 5, characterized in that: The offshore wind power prediction method further includes: Determining power generation change information based on the predicted power generation and the historical power generation; determining weather change information based on the historical weather forecast data and the revised weather forecast data; The updating frequency of the weather forecast data is adjusted according to the power generation change information and the weather change information.

7. An offshore wind power prediction system based on high-frequency updated weather forecasts, characterized in that: include: A vibration sensing device, the vibration sensing device being arranged on the wind turbine and used for collecting vibration information of the wind turbine; A sound sensing device, the sound sensing device is provided on the wind turbine and is used to collect sound information of the wind turbine; A prediction platform is communicatively connected to the vibration sensing device and the sound sensing device respectively, and is used to execute the offshore wind power prediction method based on high-frequency updated weather forecast as described in any one of claims 1 to 6.

Images