Backup capacity prediction method and device, computing equipment and machine readable storage medium

Abstract

The embodiment of the invention discloses a reserve capacity prediction method and device, computing equipment and a machine readable storage medium, and belongs to the field of data analysis. The reserve capacity prediction method comprises the following steps: acquiring target geographic information and current operation data corresponding to a target wind generating set; determining meteorological elements for icing the wind driven generator; extracting meteorological elements in the meteorological forecast data in the target time period to obtain target meteorological data; inputting the target geographic information and the target meteorological data into a first preset model to obtain refined meteorological data; and inputting the refined meteorological data and the current operation data into a second preset model to obtain the predicted icing reserve capacity of the target wind generating set. And the refinement capacity prediction accuracy of the wind driven generator can be improved through refined meteorological data. In addition, the back-backup capacity prediction is carried out through the meteorological data and the operation data, so that the back-backup capacity prediction accuracy is further improved.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and particularly to a method, device, computing device and machine-readable storage medium for predicting the reserve capacity of a decommissioned device. Background Art

[0002] A wind turbine is a device that converts wind energy into mechanical energy, drives a rotor to rotate through the mechanical energy, and outputs electrical energy. Usually, a wind turbine generator set is located in a high-altitude area. Under the conditions of high humidity and low temperature, it is easy to cause condensation and freezing on the blade surface to form ice, that is, the blades of the wind turbine are prone to icing in high-altitude areas, which will affect the performance of the wind turbine. When the number of wind turbines is small, the impact of wind turbine icing shutdown on the power grid is small.

[0003] However, wind energy is a renewable energy source. To increase the proportion of clean energy, the number of deployed wind turbines is constantly increasing. The reserve capacity refers to the capacity that can provide an alternative power source when the wind turbine stops operating. Under cold weather conditions, it is usually impossible to accurately predict the reserve capacity of the wind turbine, and it is impossible to schedule electric energy in a timely manner, which will cause a large number of wind turbines to stop operating, seriously affecting the safe and reliable supply of electric power. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a method, device, computing device and machine-readable storage medium for predicting the reserve capacity of a decommissioned device, which is used to solve the problem of inability to accurately predict the reserve capacity of a wind turbine.

[0005] To achieve the above purpose, in the first aspect, the present application provides a method for predicting the reserve capacity of a decommissioned device, and the method for predicting the reserve capacity of a decommissioned device includes: Obtain the target geographical information and current operation data corresponding to the target wind turbine generator set, where the target wind turbine generator set includes at least one wind turbine; Determine the meteorological elements that cause icing of the wind turbine; Extract the meteorological elements from the meteorological forecast data within the target time period to obtain target meteorological data; Input the target geographical information and the target meteorological data into a first preset model to obtain refined meteorological data, where the first preset model is trained based on meteorological elements and geographical information; Input the refined meteorological data and the current operation data into a second preset model to obtain the predicted icing reserve capacity of the target wind turbine generator set, where the second preset model is trained based on meteorological data and operation data.

[0006] In the embodiments of the present application, determining the meteorological elements that cause icing of the wind turbine includes: Obtain the historical operation data of multiple wind turbines and the corresponding historical meteorological data of the historical operation data; Preprocess the historical operation data to obtain the preprocessed historical operation data; Preprocess the historical meteorological data to obtain the preprocessed historical meteorological data; Determine the meteorological elements that cause icing on the wind turbine according to the preprocessed historical operation data and the preprocessed historical meteorological data.

[0007] In the embodiments of the present application, determining the meteorological elements that cause icing on the wind turbine according to the preprocessed historical operation data and the preprocessed historical meteorological data includes: Based on the preprocessed historical operation data and the preprocessed historical meteorological data, determine the icing process of the wind turbine; Determine the meteorological elements that cause icing on the wind turbine according to the preprocessed historical operation data, the preprocessed historical meteorological data and the icing process.

[0008] In the embodiments of the present application, the reserve capacity prediction method further includes: Generate reserve capacity warning information according to the predicted icing reserve capacity of the target wind turbine unit.

[0009] In the embodiments of the present application, the reserve capacity prediction method further includes: Update the first preset model and the second preset model according to the current operation data and the refined meteorological data.

[0010] In the embodiments of the present application, the training steps of the first preset model include: Based on the deep neural network structure, construct the first initial model; Based on the historical meteorological data and the geographical information, construct the first sample set; Input the first sample set into the first initial model, and train the first initial model to obtain the first preset model.

[0011] In the embodiments of the present application, the training steps of the second preset model include: Construct a mapping relationship with meteorological elements and operation data as inputs and predicted icing reserve capacity as outputs; According to the mapping relationship, construct the second initial model; Based on the historical meteorological data and the historical operation data of multiple wind turbines, construct the second sample set; Input the second sample set into the second initial model, and train the second initial model to obtain the second preset model.

[0012] In a second aspect, the present application provides a reserve capacity prediction device, and the reserve capacity prediction device includes: A data acquisition module, configured to acquire target geographical information and current operation data corresponding to a target wind power generating set, where the target wind power generating set includes at least one wind turbine; A meteorological element determination module, configured to determine meteorological elements that cause icing on the wind turbine; A meteorological data extraction module, configured to extract meteorological elements from meteorological forecast data within a target time period to obtain target meteorological data; A meteorological data refinement module, configured to input the target geographical information and the target meteorological data into a first preset model to obtain refined meteorological data, where the first preset model is trained based on meteorological elements and geographical information; A derating capacity prediction module, configured to input the refined meteorological data and the current operation data into a second preset model to obtain the predicted icing derating capacity of the target wind power generating set, where the second preset model is trained based on meteorological data and operation data.

[0013] In a third aspect, the present application provides a computing device, including: A memory, configured to store instructions; A processor, configured to call instructions from the memory and capable of implementing the above-mentioned derating capacity prediction method when executing the instructions.

[0014] In a fourth aspect, the present application provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to cause a machine to execute the above-mentioned derating capacity prediction method.

[0015] The present application provides a derating capacity prediction method, including: acquiring target geographical information and current operation data corresponding to a target wind power generating set; determining meteorological elements that cause icing on the wind turbine; extracting meteorological elements from meteorological forecast data within a target time period to obtain target meteorological data; inputting the target geographical information and the target meteorological data into a first preset model to obtain refined meteorological data; inputting the refined meteorological data and the current operation data into a second preset model to obtain the predicted icing derating capacity of the target wind power generating set. The accuracy of the derating capacity prediction of the wind turbine can be improved through the refined meteorological data. In addition, by predicting the derating capacity together with meteorological data and operation data, the accuracy of the derating capacity prediction is further improved.

[0016] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent specific implementation part. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification, and are used to explain the embodiments of the present invention together with the following specific implementation manners, but do not constitute a limitation to the embodiments of the present invention. In the drawings: Figure 1 The flowchart of the standby capacity prediction method provided by the embodiment of the present application is shown; Figure 2 The structural schematic diagram of the standby capacity prediction device provided by the embodiment of the present application is shown. Detailed implementation manners

[0018] Next, the specific implementation manners of the embodiments of the present invention will be described in detail with reference to the accompanying drawings in the embodiments of the present invention. It should be understood that the specific implementation manners described herein are only used to illustrate and explain the embodiments of the present invention, and are not used to limit the embodiments of the present invention.

[0019] Generally, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0020] In the following, the terms "including", "having" and their cognates that can be used in various embodiments of the present invention are only intended to represent specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be construed as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0021] In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0022] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the various embodiments of the present invention belong. Terms (such as those defined in a general use dictionary) will be construed to have the same meaning as the contextual meaning in the relevant technical field and will not be construed to have an idealized meaning or an overly formal meaning unless clearly defined in the various embodiments of the present invention.

[0023] Embodiment 1 Please refer to Figure 1 , Figure 1 The flowchart of the standby capacity prediction method provided by the embodiment of the present application is shown. Figure 1 The standby capacity prediction method in S110. Obtain the target geographic information and current operating data corresponding to the target wind turbine generator set, where the target wind turbine generator set includes at least one wind turbine generator.

[0024] In the case where it is necessary to predict the power capacity of the target area, determine the target wind turbine generator set in the target area. The target wind turbine generator set includes at least one wind turbine generator. Obtain the current operating data of the target wind turbine generator set from the SCADA (Supervisory Control And Data Acquisition) system. Obtain the target geographic information corresponding to the wind farm where the target wind turbine generator set is located from the geographic information system.

[0025] The data types of the operating data and geographic information are set according to actual requirements. The operating data can be the status data and active power data of the wind turbine generator, etc. The geographic information can be the altitude, terrain height, slope direction, etc. of the wind farm. There is no limitation here. The change of the operating data of the wind turbine generator will affect the icing of the blades. At the same time, the change of the geographic information will also affect the icing of the blades of the wind turbine generator.

[0026] S120. Determine the meteorological elements that cause icing on the wind turbine generator.

[0027] Determine the meteorological elements that cause icing on the wind turbine generator. The meteorological elements are determined according to actual requirements and there is no limitation here. For the sake of understanding, in the embodiments of the present application, it is determined that under high humidity and low temperature conditions, the risk of icing on the blades of the wind turbine generator will increase, that is, it is determined that the meteorological elements include temperature and humidity.

[0028] In the embodiments of the present application, determining the meteorological elements that cause icing on the wind turbine generator includes: Obtain the historical operating data of multiple wind turbine generators and the historical meteorological data corresponding to the historical operating data; Preprocess the historical operating data to obtain the preprocessed historical operating data; Preprocess the historical meteorological data to obtain the preprocessed historical meteorological data; According to the preprocessed historical operating data and the preprocessed historical meteorological data, determine the meteorological elements that cause icing on the wind turbine generator.

[0029] In this embodiment, meteorological monitoring is carried out through a wind measurement tower, and then the historical operating data of multiple wind turbine generators are obtained, and the historical meteorological data corresponding to the historical operating data are obtained based on the time series. It should be understood that the historical operating data of other multiple wind turbine generators outside the target wind turbine generator set can be obtained, which will not be elaborated here.

[0030] Preprocess the historical operation data to obtain the preprocessed historical operation data. Preprocess the historical meteorological data to obtain the preprocessed historical meteorological data. It should be understood that the steps of preprocessing are set according to actual needs and are not limited herein. For ease of understanding, in the embodiments of the present application, the preprocessing includes missing value processing, outlier processing, and time series alignment processing.

[0031] Missing values can be processed using interpolation methods or mean filling methods. Generally, interpolation methods include linear interpolation and spline interpolation, etc., which will not be elaborated herein. By processing missing values, missing data points can be effectively estimated. In this embodiment, statistical methods are used to detect outliers, which are deleted or replaced with neighboring values for outlier processing. After completing the data preprocessing, according to the preprocessed historical operation data and the preprocessed historical meteorological data, determine the meteorological elements that cause icing on the wind turbine.

[0032] In the embodiments of the present application, according to the preprocessed historical operation data and the preprocessed historical meteorological data, determine the meteorological elements that cause icing on the wind turbine, including: Based on the preprocessed historical operation data and the preprocessed historical meteorological data, determine the icing process of the wind turbine; According to the preprocessed historical operation data, the preprocessed historical meteorological data, and the icing process, determine the meteorological elements that cause icing on the wind turbine.

[0033] Based on the preprocessed historical operation data and the preprocessed historical meteorological data, determine the icing process of the wind turbine. Specifically, data analysis algorithms such as clustering analysis algorithms or decision tree algorithms can be used to analyze the historical operation data and historical meteorological data, and then identify and mark different stages in the icing process.

[0034] After data preprocessing, extract the key feature data in the operation data and meteorological data. For ease of understanding, in the embodiments of the present application, the key feature data in the meteorological data are the lowest temperature and the highest humidity, etc., to better analyze the changes in meteorological conditions during the icing process. Analyze according to the preprocessed historical operation data, the preprocessed historical meteorological data, and the icing process, that is, perform corresponding statistical analysis on the operation key feature data and meteorological key feature data at each stage during the icing process to determine the meteorological elements that cause icing on the wind turbine.

[0035] S130, extract the meteorological elements in the meteorological forecast data within the target time period to obtain the target meteorological data.

[0036] In this embodiment, the target time period is the time period for which the reserve capacity needs to be predicted. Usually, the target time period is the time period after the current time. After obtaining the meteorological forecast data within the target time period, meteorological elements in the meteorological forecast data are extracted to obtain the target meteorological data. For ease of understanding, in the embodiments of the present application, the meteorological forecast data includes temperature, humidity, and fine particulate matter diameter. Only the temperature and humidity in the meteorological forecast data are extracted to avoid the influence of other factors other than meteorological elements on the reserve capacity prediction result.

[0037] In this embodiment, the WRF (Weather Research and Forecasting) model is used to obtain the predicted meteorological data for the refined meteorological prediction of the wind farm. Twice the predicted meteorological data is obtained for the wind farm area where the wind turbines are located every day. The predicted meteorological data includes elements such as precipitation, wind speed, wind direction, air temperature, and vertical temperature profile, which will not be elaborated here.

[0038] S140. Input the target geographical information and the target meteorological data into the first preset model to obtain the refined meteorological data, where the first preset model is trained based on meteorological elements and geographical information.

[0039] The first preset model is trained based on meteorological elements and geographical information and is used to correct the predicted meteorological data. Inputting the target geographical information and the target meteorological data into the first preset model and performing meteorological data correction through the first preset model can significantly improve the prediction accuracy of meteorological data such as wind speed, wind direction, temperature, and humidity, and reduce the prediction error caused by geographical differences, thereby obtaining the refined meteorological data.

[0040] Perform meteorological data correction through the first preset model to correct the predicted meteorological data. Through the correction function of the neural network model of the first preset model, the numerical prediction result can be dynamically adjusted according to the existing meteorological data characteristics to generate refined meteorological data that better conforms to the micro-topography characteristics of the wind farm. In addition, performing meteorological data correction through the first preset model can significantly improve the prediction accuracy of meteorological data such as wind speed, wind direction, temperature, and humidity, and reduce the prediction error caused by the influence of geographical information such as micro-topography.

[0041] The corrected refined meteorological data is used for the operation scheduling and power generation prediction of the wind farm, providing high-precision meteorological data support for the operation management of the wind farm. By applying the first preset model in a complex micro-topography environment, the prediction data accuracy of the wind farm is significantly improved, the risk caused by prediction errors is reduced, and it helps the safe and efficient operation of the wind farm.

[0042] S150. Input the refined meteorological data and the current operation data into the second preset model to obtain the predicted ice-covering reserve capacity of the target wind turbine generator, where the second preset model is trained based on meteorological data and operation data.

[0043] The second preset model is trained based on meteorological data and operation data and is used to predict the reserve capacity of the wind turbine under ice-covering conditions, that is, to determine the power output decrease of the wind turbine caused by icing. Inputting the refined meteorological data and the current operation data into the second preset model can obtain the predicted ice-covering reserve capacity of the target wind turbine generator under different meteorological conditions.

[0044] In this embodiment, a physical data hybrid-driven model is constructed for reserve capacity prediction. The icing mechanism is analyzed based on physical principles, and the data-driven machine learning technology is combined to improve the accuracy of reserve capacity prediction. Specifically, meteorological forecast data within the target time period is obtained through a physical model to analyze the icing mechanism and conditions. The data-driven model fits multi-dimensional data through machine learning methods using meteorological data and operation data to enhance the prediction ability of the model. The refined meteorological data can improve the accuracy of the reserve capacity prediction of the wind turbine generator. In addition, the reserve capacity prediction is carried out by combining meteorological data and operation data, further improving the accuracy of the reserve capacity prediction.

[0045] In the embodiments of this application, the reserve capacity prediction method further includes: Generate a reserve capacity warning message according to the predicted ice-covering reserve capacity of the target wind turbine generator.

[0046] When the predicted ice-covering reserve capacity is obtained, according to the predicted ice-covering reserve capacity of the target wind turbine generator, short-term ice-covering reserve prediction is introduced at the predicted reserve starting point of the fan for warning judgment, and then a reserve capacity warning message is generated. Based on the reserve capacity warning message, more accurate wind power prediction can be carried out under cold weather conditions, which can better guide the anti-icing and de-icing operations of the wind turbine generator, reduce the failure rate and downtime of the wind turbine generator during the ice-covering period, and thus better cope with the imbalance between power supply and demand, ensuring the stability and reliability of the power system. By improving the efficiency and accuracy of wind power operation management, the development of wind power energy can be promoted, and the adjustment and optimization of the energy structure can be driven.

[0047] In the embodiments of this application, the reserve capacity prediction method further includes: Update the first preset model and the second preset model according to the current operation data and the refined meteorological data.

[0048] Update the first preset model and the second preset model according to the current operation data and the refined meteorological data. Specifically, update the sample set of the first preset model based on the refined meteorological data and the actual meteorological data, and then update the first preset model through the updated sample set. Update the sample set of the second preset model based on the current operation data, and then update the second preset model through the updated sample set. By continuously updating the parameters of the model, the prediction ability of the second preset model is improved to obtain a more accurate prediction result of the reserve capacity.

[0049] In the embodiments of the present application, the training steps of the first preset model include: Construct a first initial model based on the deep neural network structure; Construct a first sample set based on the historical meteorological data and the geographical information; Input the first sample set into the first initial model and train the first initial model to obtain the first preset model.

[0050] Construct a first initial model for describing the relationship between meteorology and geography based on the deep neural network (DNN) structure. The model calculates with the wind farm as the central area and combines the geographical data and meteorological data of the area. Specifically, the first initial model in this embodiment includes an input layer, a hidden layer, and an output layer. The deep neural network performs layer-by-layer non-linear transformation on the input data through multiple hidden layers. Each hidden layer sets a different number of neurons according to requirements to capture the complex influence of the terrain in the micro-geographical information on the meteorological elements. By processing the data with an activation function in each layer, the model can learn the non-linear features in the meteorological elements and enhance the expression ability of high-dimensional and non-linear data.

[0051] For the structural design of the first initial model, the input layer is used to receive each meteorological element and geographical information, the hidden layer is used to extract the complex features of the data and combine the information, and the output layer finally generates the corrected result of the meteorological element, that is, the refined meteorological data is output. The design of the first initial model is set according to the actual requirements due to the dimension and the number of features of the data, and is not limited here. The number of network layers and neurons of the first initial model is also set according to the actual requirements to ensure the effectiveness and generalization ability of the model in complex scenarios, and is not limited here.

[0052] Construct a first sample set based on the historical meteorological data and the geographical information. Specifically, extract meteorological elements such as wind speed, wind direction, temperature, and humidity from the historical meteorological data, and extract geographical feature data such as altitude, terrain slope, and slope aspect from the geographical information to obtain the input of the model. It should be understood that preprocessing such as standardizing the historical meteorological data and geographical information and filling in missing values can also be performed to eliminate possible outliers and noises in the data and improve the accuracy of the data, which will not be elaborated here.

[0053] Input the first sample set into the first initial model and train the first initial model to obtain the first preset model. The first preset model can take the measured meteorological data and numerical weather prediction data as inputs, and continuously adjust the model parameters through the backpropagation algorithm to gradually reduce the prediction error. The mean square error (MSE) is used as the loss function during model training, and the model weight parameters are optimized by the gradient descent method to ensure that the model can accurately capture the variation characteristics of meteorological elements. It should be understood that a validation set can also be constructed based on historical meteorological data and geographical information. After training, the model performance is evaluated through the validation set, and model hyperparameters such as the learning rate, the number of hidden layers, and the number of neurons are adjusted to improve the fitting effect and prediction accuracy of the model.

[0054] In the embodiments of the present application, the training steps of the second preset model include: Construct a mapping relationship with meteorological elements and operation data as inputs and the predicted ice-covered reserve capacity as the output; Construct a second initial model according to the mapping relationship; Construct a second sample set based on historical operation data and historical meteorological data; Input the second sample set into the second initial model and train the second initial model to obtain the second preset model.

[0055] Construct a mapping relationship with meteorological elements and operation data as inputs and the predicted ice-covered reserve capacity as the output, determine the error evaluation index of the model and conduct cross-modeling analysis to use the model for predicting the reserve capacity. It should be understood that before constructing the mapping relationship with multiple inputs, the historical operation data and historical meteorological data can also be preprocessed and data-expanded to ensure the data quality and improve the adaptability of the model to extreme ice-covered conditions.

[0056] Construct a second sample set based on historical operation data and historical meteorological data. Input the second sample set into the second initial model and train the second initial model to obtain the second preset model. Use machine learning algorithms to extract features from input variables, and through training, learn the influence law of input variables on the ice-covered reserve capacity under different conditions to ensure that the model can accurately predict the fan reserve situation under different meteorological conditions.

[0057] The present application provides a method for predicting the reserve capacity, including: obtaining the target geographical information and current operation data corresponding to the target wind turbine generator set; determining the meteorological elements that cause icing on the wind turbine; extracting the meteorological elements from the meteorological forecast data within the target time period to obtain target meteorological data; inputting the target geographical information and the target meteorological data into a first preset model to obtain refined meteorological data; and inputting the refined meteorological data and the current operation data into a second preset model to obtain the predicted icing reserve capacity of the target wind turbine generator set. The accuracy of predicting the reserve capacity of the wind turbine can be improved through the refined meteorological data. In addition, by predicting the reserve capacity together with the meteorological data and the operation data, the accuracy of predicting the reserve capacity is further improved.

[0058] Embodiment 2 Please refer to Figure 2 , Figure 2 which shows a schematic structural diagram of the reserve capacity prediction device provided by the embodiment of the present application. Figure 2 The reserve capacity prediction device 200 in includes: A data acquisition module 210, configured to acquire the target geographical information and current operation data corresponding to the target wind turbine generator set, where the target wind turbine generator set includes at least one wind turbine; A meteorological element determination module 220, configured to determine the meteorological elements that cause icing on the wind turbine; A meteorological data extraction module 230, configured to extract the meteorological elements from the meteorological forecast data within the target time period to obtain target meteorological data; A meteorological data refinement module 240, configured to input the target geographical information and the target meteorological data into a first preset model to obtain refined meteorological data, where the first preset model is trained based on meteorological elements and geographical information;

[0059] In the embodiment of the present application, the meteorological element determination module 220 includes: A historical data acquisition sub-module, configured to acquire the historical operation data of multiple wind turbines and the historical meteorological data corresponding to the historical operation data; An operation data preprocessing sub-module, configured to preprocess the historical operation data to obtain the preprocessed historical operation data; A meteorological data preprocessing sub-module, configured to preprocess the historical meteorological data to obtain the preprocessed historical meteorological data; An element determination sub-module, configured to determine meteorological elements that cause icing on a wind turbine according to pre-processed historical operation data and pre-processed historical meteorological data.

[0060] In an embodiment of the present application, the element determination sub-module is further configured to determine the icing process of the wind turbine based on the pre-processed historical operation data and the pre-processed historical meteorological data; Determine the meteorological elements that cause icing on the wind turbine according to the pre-processed historical operation data, the pre-processed historical meteorological data, and the icing process.

[0061] In an embodiment of the present application, the reserve capacity prediction device 200 further includes: An early warning information generation module, configured to generate reserve capacity early warning information according to the predicted icing reserve capacity of the target wind turbine generator set.

[0062] In an embodiment of the present application, the reserve capacity prediction device 200 further includes: A model update module, configured to update the first preset model and the second preset model according to the current operation data and the refined meteorological data.

[0063] In an embodiment of the present application, the training steps of the first preset model include: Construct a first initial model based on a deep neural network structure; Construct a first sample set based on historical meteorological data and geographical information; Input the first sample set into the first initial model, and train the first initial model to obtain the first preset model.

[0064] In an embodiment of the present application, the training steps of the second preset model include: Construct a mapping relationship with meteorological elements and operation data as inputs and predicted icing reserve capacity as outputs; Construct a second initial model according to the mapping relationship; Construct a second sample set based on historical meteorological data and historical operation data of multiple wind turbines; Input the second sample set into the second initial model, and train the second initial model to obtain the second preset model.

[0065] The reserve capacity prediction device 200 is configured to execute the corresponding steps in the above-mentioned reserve capacity prediction method, and the specific implementation of each function will not be described in detail here. In addition, the optional examples in the reserve capacity prediction method are also applicable to the reserve capacity prediction device 200.

[0066] An embodiment of the present application further provides a computing device, including: A memory, configured to store instructions; A processor configured to call instructions from a memory and capable of implementing the above-mentioned reserve capacity prediction method when executing the instructions.

[0067] In this embodiment, the data acquisition module 210, the meteorological element determination module 220, the meteorological data extraction module 230, the meteorological data refinement module 240, the reserve capacity prediction module 250, etc. are all stored in the memory as program units, and the processor executes the above program units stored in the memory to implement corresponding functions.

[0068] The processor includes a kernel, and the kernel retrieves corresponding program units from the memory. One or more kernels can be set, and the above-mentioned reserve capacity prediction method can be implemented by adjusting the kernel parameters.

[0069] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of, for example, read-only memory (ROM) or flash RAM (flash RAM), and the memory includes at least one storage chip.

[0070] This application embodiment also provides a machine-readable storage medium with instructions stored thereon for causing a machine to execute the above-mentioned reserve capacity prediction method.

[0071] Those skilled in the art should understand that the embodiments of this application can be provided as a method, a system, or a computer program product. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or Figure 1 one block or multiple blocks.

[0073] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction means that implements the function specified in one or more of the blocks and / or processes. Figure 1 in one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing steps for implementing the function specified in one or more of the processes and / or blocks Figure 1 in one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0075] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0076] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0077] Machine-readable storage media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0078] It should also be noted that the term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements not only includes those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0079] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for predicting standby capacity, characterized in that: The method for predicting the back-up capacity includes: Acquire target geographic information and current operation data corresponding to a target wind turbine generator set, wherein the target wind turbine generator set includes at least one wind turbine generator; Identify meteorological factors that cause ice to form on wind turbines; Extract meteorological elements from meteorological forecast data within a target time period to obtain target meteorological data; Inputting the target geographic information and the target meteorological data into a first preset model to obtain refined meteorological data, wherein the first preset model is trained based on the meteorological elements and geographic information; The refined meteorological data and the current operating data are input into a second preset model to obtain the predicted icing standby capacity of the target wind turbine generator set, wherein the second preset model is trained based on the meteorological data and the operating data.

2. The method for predicting the backup capacity according to claim 1, characterized in that: The determination of meteorological factors causing ice coating on wind turbines includes: Acquire historical operating data of a plurality of wind turbines, and historical meteorological data corresponding to the historical operating data; Preprocessing the historical operation data to obtain preprocessed historical operation data; Preprocessing the historical meteorological data to obtain preprocessed historical meteorological data; The meteorological elements causing ice coating on the wind turbine are determined according to the preprocessed historical operation data and the preprocessed historical meteorological data.

3. The method for predicting the backup capacity according to claim 2, characterized in that: The step of determining the meteorological factors causing ice coating on the wind turbine generator according to the pre-processed historical operation data and the pre-processed historical meteorological data includes: Determining an icing process of a wind turbine based on the preprocessed historical operation data and the preprocessed historical meteorological data; The meteorological factors causing the wind turbine to be covered with ice are determined according to the pre-processed historical operation data, the pre-processed historical meteorological data and the icing process.

4. The method for predicting the backup capacity according to claim 1, characterized in that: The method for predicting the back-up capacity further includes: Generate reserve capacity warning information based on the predicted icing reserve capacity of the target wind turbine generator set.

5. The method for predicting the backup capacity according to claim 1, characterized in that: The method for predicting the back-up capacity further includes: The first preset model and the second preset model are updated according to the current operating data and the refined meteorological data.

6. The method for predicting the backup capacity according to claim 1, characterized in that: The training step of the first preset model includes: Based on the deep neural network structure, build the first initial model; Based on historical meteorological data and geographic information, the first sample set is constructed; The first sample set is input into the first initial model, and the first initial model is trained to obtain a first preset model.

7. The method for predicting the backup capacity according to claim 1, characterized in that: The training step of the second preset model includes: Construct a mapping relationship with meteorological elements and operation data as input and predicted ice cover reserve capacity as output; According to the mapping relationship, construct a second initial model; constructing a second sample set based on historical meteorological data and historical operation data of multiple wind turbines; The second sample set is input into the second initial model, and the second initial model is trained to obtain a second preset model.

8. A device for predicting standby capacity, characterized in that: The standby capacity prediction device comprises: A data acquisition module, used to acquire target geographic information and current operation data corresponding to a target wind turbine generator set, wherein the target wind turbine generator set includes at least one wind turbine generator; A meteorological element determination module, used to determine the meteorological elements that cause ice on the wind turbine; A meteorological data extraction module is used to extract meteorological elements from meteorological forecast data within a target time period to obtain target meteorological data; A meteorological data refinement module, used for inputting the target geographic information and the target meteorological data into a first preset model to obtain refined meteorological data, wherein the first preset model is obtained by training based on the meteorological elements and geographic information; A standby capacity prediction module is used to input the refined meteorological data and the current operating data into a second preset model to obtain the predicted icing standby capacity of the target wind turbine generator set, wherein the second preset model is trained based on the meteorological data and the operating data.

9. A computing device, characterized in that include: a memory configured to store instructions; A processor is configured to call the instruction from the memory and to implement the backup capacity prediction method according to any one of claims 1 to 7 when executing the instruction.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions, and the instructions are used to enable a machine to execute the backup capacity prediction method according to any one of claims 1 to 7.

Images