Wind power prediction model generation method and device and wind power prediction method and device

Abstract

The invention provides a wind power prediction model generation method and device and a wind power prediction method and device, and relates to the technical field of wind power prediction. Processing the historical operation data based on a variable speed prediction model to obtain first prediction data, and processing the historical operation data based on a steady speed prediction model to obtain second prediction data; determining a first weight of a variable speed prediction model and a second weight of a steady speed prediction model based on the first prediction data and the second prediction data; and determining a target wind motor prediction model based on the first weight, the second weight, the variable speed prediction model and the steady speed prediction model. The first weight and the second weight are determined according to the output results of the variable-speed prediction model and the steady-speed prediction model, so that the target wind motor prediction model is generated, compared with the prior art, power prediction of the variable-speed stage and the constant-speed stage can be considered at the same time, and the robustness and accuracy of wind power prediction are improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of wind power prediction, and in particular to a method and device for generating a wind power prediction model and a wind power prediction method. Background Art

[0002] In recent years, wind energy has been vigorously developed and applied by many countries due to its advantages such as being pollution-free, renewable, and widely available. However, the intermittent and uncertain nature of wind power itself increases the difficulty of grid planning and scheduling. Therefore, further research on methods to improve the accuracy of wind power prediction is of great significance.

[0003] The ultimate goal of the optimization control of the whole offshore wind turbine is multi-objective coordinated optimization, that is, to achieve the comprehensive optimization of increasing power generation, smoothing output power and reducing load. There have been a lot of studies on the control objectives of increasing power generation, smoothing output power and reducing load for wind turbines, and corresponding optimization control strategies have been proposed for each objective. However, when these control strategies are applied at the same time, coupling or contradiction problems may occur. For example, reducing the moment of inertia of the unit is conducive to improving the dynamic tracking ability of the unit's speed change section, so that the unit can better maintain the optimal tip speed ratio and increase power generation. Increasing the moment of inertia of the unit is conducive to reducing the fluctuation of the unit's output power, but the existing control strategy cannot always take into account the two optimization objectives of maximum power point tracking (MPPT) tracking performance and power smoothing in the speed change section. Therefore, it is necessary to carry out research on multi-objective comprehensive optimization control. Summary of the invention

[0004] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, an object of the present disclosure is to propose a method for generating a wind power prediction model.

[0006] The second objective of the present disclosure is to provide a wind power prediction method.

[0007] The third objective of the present disclosure is to provide a wind power prediction model generation device.

[0008] The fourth objective of the present disclosure is to provide a wind power prediction device.

[0009] A fifth objective of the present disclosure is to provide an electronic device.

[0010] A sixth object of the present disclosure is to provide a non-transitory computer-readable storage medium.

[0011] A seventh objective of the present disclosure is to provide a computer program product.

[0012] To achieve the above-mentioned purpose, the first aspect of the present disclosure proposes a method for generating a wind power prediction model, including: obtaining historical operating data of a wind turbine group; processing the historical operating data based on a variable speed prediction model to obtain first prediction data, and processing the historical operating data based on a steady speed prediction model to obtain second prediction data; determining a first weight of the variable speed prediction model and a second weight of the steady speed prediction model based on the first prediction data and the second prediction data; determining a target wind turbine prediction model based on the first weight, the second weight, the variable speed prediction model and the steady speed prediction model.

[0013] According to one embodiment of the present disclosure, obtaining the first weight of the speed change prediction model and the second weight of the steady speed prediction model includes: inputting the historical operating data into the speed change prediction model and the steady speed prediction model, respectively, to obtain the first predicted power and the second predicted power of the historical operating data, respectively; determining the first weight of the speed change prediction model and the second weight of the steady speed prediction model based on the first predicted power, the second predicted power and the actual power in the historical operating data.

[0014] According to one embodiment of the present disclosure, the first weight of the speed change prediction model and the second weight of the steady speed prediction model are determined based on the first predicted power, the second predicted power and the real power in the historical operation data, including: establishing a first power trajectory based on the first predicted power, establishing a second power trajectory based on the second predicted power, and establishing the real power trajectory shown based on the real power; establishing a predicted power trajectory based on a first candidate weight, the first power trajectory, the second candidate weight and the second power trajectory; determining the first weight of the speed change prediction model and the second weight of the steady speed prediction model based on the real power trajectory and the predicted power trajectory.

[0015] According to one embodiment of the present disclosure, determining the first weight of the speed change prediction model and the second weight of the steady speed prediction model based on the real power trajectory and the predicted power trajectory includes: calculating the sum of squared errors between the real power trajectory and the predicted power trajectory; determining an optimal weight set based on a minimum optimization criterion and the sum of squared errors, wherein the optimal weight set includes at least one set of optimal first weights and optimal second weight combinations; and determining the first weight of the speed change prediction model and the second weight of the steady speed prediction model from the optimal weight set based on a preset convergence condition.

[0016] According to one embodiment of the present disclosure, determining the optimal weight set based on the minimum optimization criterion and the sum of squared errors includes: obtaining an induced matrix; based on the induced matrix, determining the first candidate weight and the second candidate weight when the sum of squared errors is less than a preset threshold as the optimal first weight and the optimal second weight; and constructing the optimal weight set based on the optimal first weight and the optimal second weight.

[0017] According to an embodiment of the present disclosure, after the historical operation data of the wind turbine is acquired, the steps include: removing abnormal data from the historical operation data; and correcting the data of the historical operation data after the abnormal data is removed.

[0018] To achieve the above-mentioned purpose, the second aspect embodiment of the present disclosure proposes a wind power prediction method, comprising: obtaining operating data of the wind turbine to be predicted; processing the operating data based on a target wind turbine prediction model to generate predicted wind power, wherein the target wind turbine prediction model is generated by the wind power prediction model generation method described in the first aspect embodiment.

[0019] To achieve the above-mentioned purpose, the third aspect embodiment of the present disclosure proposes a wind power prediction model generating device, characterized in that it includes: an acquisition model for acquiring historical operation data of a wind turbine; a processing module for processing the historical operation data based on a variable speed prediction model to obtain first prediction data, and processing the historical operation data based on a steady speed prediction model to obtain second prediction data; a calculation module for determining a first weight of the variable speed prediction model and a second weight of the steady speed prediction model based on the first prediction data and the second prediction data; and a fusion module for determining a target wind turbine prediction model based on the first weight, the second weight, the variable speed prediction model and the steady speed prediction model.

[0020] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present disclosure proposes a wind power prediction device, characterized in that it includes: a receiving module, used to obtain the operating data of the wind turbine to be predicted; a prediction module, used to process the operating data based on a target wind turbine prediction model to generate predicted wind power, wherein the target wind turbine prediction model is generated by the wind power prediction model generation method as described in the first aspect embodiment.

[0021] To achieve the above-mentioned purpose, the fifth aspect embodiment of the present disclosure proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to implement the wind power prediction model generation method as described in the first aspect embodiment of the present disclosure.

[0022] To achieve the above-mentioned purpose, the sixth aspect embodiment of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement a wind power prediction model generation method as described in the first aspect embodiment of the present disclosure or a wind power prediction method as described in the second aspect embodiment.

[0023] To achieve the above-mentioned purpose, the seventh aspect embodiment of the present disclosure proposes a computer program product, including a computer program, which, when executed by a processor, is used to implement the wind power prediction model generation method as described in the first aspect embodiment of the present disclosure or a wind power prediction method as described in the second aspect embodiment.

[0024] The first weight and the second weight are determined by the output results of the variable speed prediction model and the steady speed prediction model, thereby generating a target wind turbine prediction model. Compared with the current technology, it can take into account the power prediction of both the variable speed and constant speed stages, thereby improving the robustness and accuracy of wind power prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 is a schematic diagram of a method for generating a wind power prediction model according to an embodiment of the present disclosure;

[0026] Figure 2 is a schematic diagram of a method for generating a wind power prediction model according to an embodiment of the present disclosure;

[0027] Figure 3 is a schematic diagram of a method for generating a wind power prediction model according to an embodiment of the present disclosure;

[0028] Figure 4 is a schematic diagram of a wind power prediction method according to an embodiment of the present disclosure;

[0029] Figure 5 is a schematic diagram of a wind power prediction model generating device according to one embodiment of the present disclosure;

[0030] Figure 6 is a schematic diagram of a wind power prediction device according to one embodiment of the present disclosure;

[0031] Figure 7 is a schematic diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0033] Figure 1 A schematic diagram of an exemplary implementation of a method for generating a wind power prediction model proposed in the present disclosure is shown as follows: Figure 1 As shown, the wind power prediction model generation method includes the following steps:

[0034] S101, obtaining historical operation data of a wind turbine generator system.

[0035] The wind power prediction model generation method of the embodiment of the present application can be applied to the scenario of wind turbine power prediction. The executor of the wind power prediction model generation of the embodiment of the present application can be the wind power prediction model generation device of the embodiment of the present application, and the wind power prediction model generation device can be set on an electronic device.

[0036] In the embodiments of the present disclosure, there are many methods for obtaining historical operation data, which are not limited here. For example, the historical operation logs of all wind turbines can be obtained, and the historical operation data of all wind turbines can be determined by analysis, or the historical operation data of all wind turbines can be collected by sensors.

[0037] In the embodiments of the present disclosure, the historical operation data may include a variety of information, which is not limited here and may be limited according to actual design requirements. For example, it may include air density, wind speed, temperature, air pressure, etc.

[0038] In the embodiment of the present disclosure, after the historical operation data is acquired, the historical operation data may be further processed to facilitate subsequent data processing.

[0039] S102, processing the historical operation data based on the speed change prediction model to obtain first prediction data, and processing the historical operation data based on the steady speed prediction model to obtain second prediction data.

[0040] In the disclosed embodiment, the speed change prediction model is a power prediction model applicable to the speed change stage, and the steady speed prediction model is a power prediction model applicable when the speed is stable.

[0041] It should be noted that the speed change prediction model and the steady speed prediction model can be pre-trained models, and the corresponding model types can be various, without any limitation here, and can be specifically limited according to actual design needs.

[0042] S103, determining a first weight of the speed change prediction model and a second weight of the speed steady prediction model based on the first prediction data and the second prediction data.

[0043] It should be noted that the first weight of the first prediction data and the second weight of the second prediction data may be different in different locations and different wind farms, and no limitation is made here.

[0044] In the embodiment of the present disclosure, after the first prediction data and the second prediction data are acquired, there may be multiple methods for determining the first weight and the second weight, which are not limited here.

[0045] Optionally, the first prediction data and the second prediction data may be processed by a weight generation model to obtain a first weight and a second weight. The weight generation model is trained in advance and stored in a storage space of the electronic device to facilitate retrieval and use when needed.

[0046] Optionally, the first prediction data and the second prediction data may be calculated by a weight generation algorithm to obtain a first weight and a second weight.

[0047] S104, determining a target wind turbine prediction model based on the first weight, the second weight, the variable speed prediction model and the steady speed prediction model.

[0048] In the embodiment of the present disclosure, there may be multiple methods for determining the target wind turbine prediction model based on the first weight, the second weight, the variable speed prediction model and the steady speed prediction model, which are not limited here.

[0049] Optionally, the output results of the speed change prediction model and the steady speed prediction model can be processed by the first weight and the second weight. That is, when a prediction is completed, the output result of the speed change prediction model is adjusted by the first weight, and the output result of the steady speed prediction model is adjusted by the second weight, and then the adjusted result is used as the overall prediction result.

[0050] Optionally, the variable speed prediction model and the steady speed prediction model may be fused based on the first weight and the second weight to generate a fused target wind turbine prediction model.

[0051] In the disclosed embodiment, the historical operation data of the wind turbine is first obtained, and then the historical operation data is processed based on the variable speed prediction model to obtain the first prediction data, and the historical operation data is processed based on the steady speed prediction model to obtain the second prediction data, and then the first weight of the variable speed prediction model and the second weight of the steady speed prediction model are determined based on the first prediction data and the second prediction data, and finally the target wind turbine prediction model is determined based on the first weight, the second weight, the variable speed prediction model and the steady speed prediction model. By determining the first weight and the second weight based on the output results of the variable speed prediction model and the steady speed prediction model, the target wind turbine prediction model is generated. Compared with the current technology, the power prediction of both the variable speed and the constant speed stages can be taken into account at the same time, thereby improving the robustness and accuracy of wind power prediction.

[0052] In the disclosed embodiment, after obtaining the historical operation data of the wind turbine generator set, abnormal data can be removed from the historical operation data, and then the removed historical operation data can be corrected, thereby improving the integrity of the data during subsequent model training.

[0053] In the above embodiment, the first weight of the speed change prediction model and the second weight of the speed steady prediction model are obtained, and the Figure 2 Explaining further, the method includes:

[0054] S201, inputting historical operation data into a speed change prediction model and a steady speed prediction model respectively, to obtain a first predicted power and a second predicted power of the historical operation data respectively.

[0055] S202: Determine a first weight of a speed change prediction model and a second weight of a speed steady prediction model based on the first predicted power, the second predicted power and real power in historical operation data.

[0056] In the disclosed embodiment, a first power trajectory may be first established based on the first predicted power, a second power trajectory may be established based on the second predicted power, and a real power trajectory may be established based on the real power. Then, a predicted power trajectory may be established based on the first candidate weight, the first power trajectory, the second candidate weight, and the second power trajectory. Finally, based on the real power trajectory and the predicted power trajectory, a first weight of the speed change prediction model and a second weight of the steady speed prediction model may be determined.

[0057] It should be noted that, based on the actual power trajectory and the predicted power trajectory, the first weight of the speed change prediction model and the second weight of the steady speed prediction model are determined. The sum of squared errors between the actual power trajectory and the predicted power trajectory can be calculated first, and then the optimal weight set is determined based on the minimum optimization criterion and the sum of squared errors, wherein the optimal weight set includes at least one set of optimal first weights and optimal second weight combinations. Finally, based on the preset convergence condition, the first weight of the speed change prediction model and the second weight of the steady speed prediction model are determined from the optimal weight set.

[0058] In the embodiment of the present disclosure, the convergence conditions may include multiple conditions, for example, the prediction proportion, time proportion, etc. of the variable speed prediction model or the steady speed prediction model.

[0059] In the embodiment of the present disclosure, the optimal weight set is determined based on the minimum optimization criterion and the error square sum, and the optimal weight set can also be determined by Figure 3 Explaining further, the method includes:

[0060] S301, obtaining an induced matrix.

[0061] In the embodiment of the present disclosure, the induced matrix is ​​a preset matrix used to induce calculation of the first weight and the second weight.

[0062] S302, based on the induced matrix, determining the first candidate weight and the second candidate weight when the sum of squared errors is less than a preset threshold, as the optimal first weight and the optimal second weight.

[0063] It can be understood that the element points on the actual power trajectory and the predicted power trajectory are in one-to-one correspondence.

[0064] In the embodiment of the present disclosure, the error of each corresponding element can be determined by using the real power trajectory and the predicted power trajectory. A square sum matrix is ​​obtained for all errors, and the square sum matrix is ​​multiplied based on the induced matrix to obtain the error square sum.

[0065] After obtaining the sum of squared errors, the squared errors can be compared with a preset threshold. When the squared errors are less than the preset threshold, it is considered that the weight at this time can allow the model to converge and meet the conditions for being the optimal weight.

[0066] S303: construct an optimal weight set based on the optimal first weight and the optimal second weight.

[0067] In the embodiment of the present disclosure, the induced matrix is ​​first obtained, and then based on the induced matrix, the first candidate weight and the second candidate weight when the sum of squared errors is less than a preset threshold are determined as the optimal first weight and the optimal second weight, and finally the optimal weight set is constructed based on the optimal first weight and the optimal second weight. In this way, the first weight of the variable speed prediction model and the second weight of the steady speed prediction model corresponding to the target wind farm can be accurately determined through the variable weight combination prediction method, thereby improving the accuracy of the prediction.

[0068] Figure 4 A schematic diagram of an exemplary implementation of a wind power prediction method proposed in the present disclosure is shown as follows: Figure 4 As shown, the method comprises the following steps:

[0069] S401, obtaining operation data of a wind turbine to be predicted.

[0070] In the embodiments of the present disclosure, there are many methods for obtaining operation data, which are not limited herein. For example, the operation data of all wind turbines can be obtained by obtaining operation logs of all wind turbines and determining the operation data of all wind turbines through analysis, or by collecting data of all wind turbines through sensors to obtain operation data.

[0071] S402: Processing the operating data based on the target wind turbine prediction model to generate predicted wind power.

[0072] It should be noted that the target wind turbine prediction model is generated by the wind power prediction model generation method in the above embodiment, and the specific generation process will not be repeated here.

[0073] In the disclosed embodiment, the operation data of the wind turbine to be predicted is first obtained, and then the operation data is processed based on the target wind turbine prediction model to generate predicted wind power. By processing the operation data through the target wind turbine prediction model, the power prediction of both the variable speed and uniform speed stages can be considered at the same time, thereby improving the robustness and accuracy of wind power prediction.

[0074] Corresponding to the wind power prediction model generation method provided in the above-mentioned embodiments, an embodiment of the present disclosure also provides a wind power prediction model generation device. Since the wind power prediction model generation device provided in the embodiment of the present disclosure corresponds to the wind power prediction model generation method provided in the above-mentioned embodiments, the implementation method of the above-mentioned wind power prediction model generation method is also applicable to the wind power prediction model generation device provided in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.

[0075] Figure 5 A schematic diagram of a wind power prediction model generation device proposed in the present disclosure is shown in FIG. Figure 5As shown, the wind power prediction model generating device 500 includes: an acquisition model 510, a processing module 520, a calculation module 530 and a fusion module 540.

[0076] The acquisition model 510 is used to acquire the historical operation data of the wind turbine generator set.

[0077] The processing module 520 is used to process the historical operation data based on the speed change prediction model to obtain first prediction data, and to process the historical operation data based on the steady speed prediction model to obtain second prediction data.

[0078] The calculation module 530 is used to determine a first weight of the speed change prediction model and a second weight of the speed steady prediction model based on the first prediction data and the second prediction data.

[0079] The fusion module 540 is used to determine the target wind turbine prediction model based on the first weight, the second weight, the variable speed prediction model and the steady speed prediction model.

[0080] In one embodiment of the present disclosure, the calculation module 530 is also used to: input the historical operating data into the speed change prediction model and the steady speed prediction model respectively to obtain the first predicted power and the second predicted power of the historical operating data respectively; based on the first predicted power, the second predicted power and the actual power in the historical operating data, determine the first weight of the speed change prediction model and the second weight of the steady speed prediction model.

[0081] In one embodiment of the present disclosure, the calculation module 530 is further used to: establish a first power trajectory based on the first predicted power, establish a second power trajectory based on the second predicted power, and establish the actual power trajectory shown based on the actual power; establish a predicted power trajectory based on the first candidate weight, the first power trajectory, the second candidate weight and the second power trajectory; determine the first weight of the speed change prediction model and the second weight of the steady speed prediction model based on the actual power trajectory and the predicted power trajectory.

[0082] In one embodiment of the present disclosure, the calculation module 530 is also used to: calculate the sum of squared errors between the actual power trajectory and the predicted power trajectory; determine an optimal weight set based on a minimum optimization criterion and the sum of squared errors, wherein the optimal weight set includes at least one set of optimal first weights and optimal second weight combinations; and determine a first weight of a speed change prediction model and a second weight of a steady speed prediction model from the optimal weight set based on a preset convergence condition.

[0083] In one embodiment of the present disclosure, the calculation module 530 is also used to: obtain an induced matrix; based on the induced matrix, determine the first candidate weight and the second candidate weight when the sum of squared errors is less than a preset threshold as the optimal first weight and the optimal second weight; and construct an optimal weight set based on the optimal first weight and the optimal second weight.

[0084] In one embodiment of the present disclosure, the acquisition model 510 is also used to: remove abnormal data from the historical operation data; and perform data correction on the removed historical operation data.

[0085] The first weight and the second weight are determined by the output results of the variable speed prediction model and the steady speed prediction model, thereby generating a target wind turbine prediction model. Compared with the current technology, it can take into account the power prediction of both the variable speed and constant speed stages, thereby improving the robustness and accuracy of wind power prediction.

[0086] Figure 6 A schematic diagram of a wind power prediction model generation device proposed in the present disclosure is shown in FIG. Figure 6 As shown, the wind power prediction model generating device 600 includes: a receiving module 610 and a prediction module 620.

[0087] In one embodiment of the present disclosure, the receiving module 610 is used to obtain the operating data of the wind turbine to be predicted.

[0088] The prediction module 620 is used to process the operation data based on the target wind turbine prediction model to generate predicted wind power.

[0089] By processing the operating data through the target wind turbine prediction model, the power prediction in both the variable speed and uniform speed stages can be taken into account, thereby improving the robustness and accuracy of wind power prediction.

[0090] In order to implement the above embodiment, the present disclosure also provides an electronic device 700, such as Figure 7 As shown, the electronic device 700 includes: a processor 701 and a memory 702 communicatively connected to the processor, the memory 702 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 701 to implement a wind power prediction model generation method as described in the first aspect of the present disclosure.

[0091] In order to implement the above embodiments, the embodiments of the present disclosure further propose a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to implement a wind power prediction model generation method as described in the first aspect of the embodiments of the present disclosure.

[0092] In order to implement the above embodiments, the embodiments of the present disclosure further propose a computer program product, including a computer program, which, when executed by a processor, implements the wind power prediction model generation method as described in the first aspect of the embodiments of the present disclosure.

[0093] In the description of the present disclosure, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present disclosure and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present disclosure.

[0094] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present disclosure, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0095] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0096] Although the embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present disclosure. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present disclosure.

Claims

1. A method for generating a wind power prediction model, characterized in that: include: Obtain historical operation data of wind turbines; Processing the historical operation data based on the speed change prediction model to obtain first prediction data, and processing the historical operation data based on the steady speed prediction model to obtain second prediction data; Determine a first weight of the speed change prediction model and a second weight of the steady speed prediction model based on the first prediction data and the second prediction data; A target wind turbine prediction model is determined based on the first weight, the second weight, the variable speed prediction model, and the steady speed prediction model.

2. The method according to claim 1, characterized in that Obtaining a first weight of the speed change prediction model and a second weight of the speed steady prediction model includes: Inputting the historical operation data into the speed change prediction model and the steady speed prediction model respectively, so as to obtain a first predicted power and a second predicted power of the historical operation data respectively; Based on the first predicted power, the second predicted power and the real power in the historical operation data, a first weight of the speed change prediction model and a second weight of the steady speed prediction model are determined.

3. The method according to claim 2, characterized in that The determining, based on the first predicted power, the second predicted power and the real power in the historical operation data, a first weight of the speed change prediction model and a second weight of the speed steady prediction model comprises: establishing a first power trajectory based on the first predicted power, establishing a second power trajectory based on the second predicted power, and establishing a real power trajectory based on the real power; establishing a predicted power trajectory based on a first candidate weight, the first power trajectory, a second candidate weight, and the second power trajectory; Based on the actual power trajectory and the predicted power trajectory, a first weight of the speed change prediction model and a second weight of the steady speed prediction model are determined.

4. The method according to claim 3, characterized in that The determining, based on the real power trajectory and the predicted power trajectory, a first weight of the speed change prediction model and a second weight of the steady speed prediction model comprises: Calculating a sum of squares of errors between the actual power trajectory and the predicted power trajectory; Determine an optimal weight set based on a minimum optimization criterion and the error sum of squares, wherein the optimal weight set includes at least one set of optimal first weights and optimal second weight combinations; Based on a preset convergence condition, a first weight of the speed change prediction model and a second weight of the speed steady prediction model are determined from the optimal weight set.

5. The method according to claim 4, characterized in that The determining of the optimal weight set based on the minimum optimization criterion and the error sum of squares comprises: Get the induced matrix; Based on the induced matrix, determining a first candidate weight and a second candidate weight when the sum of squared errors is less than a preset threshold, as the optimal first weight and the optimal second weight; The optimal weight set is constructed based on the optimal first weight and the optimal second weight.

6. The method according to claim 1, characterized in that After the historical operation data of the wind turbine generator set is obtained, the method includes: Eliminating abnormal data from the historical operation data; The historical operating data after elimination will be corrected.

7. A wind power prediction method, characterized in that: include: Obtaining the operating data of the wind turbine to be predicted; The operating data is processed based on a target wind turbine prediction model to generate predicted wind power, wherein the target wind turbine prediction model is generated by the wind power prediction model generation method according to any one of claims 1 to 6.

8. A wind power prediction model generation device, characterized in that: include: An acquisition model is used to obtain historical operation data of wind turbines; a processing module, configured to process the historical operation data based on a speed change prediction model to obtain first prediction data, and to process the historical operation data based on a speed stability prediction model to obtain second prediction data; a calculation module, configured to determine a first weight of the speed change prediction model and a second weight of the speed steady prediction model based on the first prediction data and the second prediction data; A fusion module is used to determine a target wind turbine prediction model based on the first weight, the second weight, the variable speed prediction model and the steady speed prediction model.

9. A wind power prediction device, characterized in that: include: A receiving module, used for acquiring the operation data of the wind turbine to be predicted; A prediction module is used to process the operating data based on a target wind turbine prediction model to generate predicted wind power, wherein the target wind turbine prediction model is generated by the wind power prediction model generation method according to any one of claims 1-6.

10. An electronic device, characterized in that: Including memory and processor; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the wind power prediction model generation method as described in any one of claims 1 to 6 or the wind power prediction method as described in claim 7.

Images