Wind power prediction device, system, method and equipment

Abstract

The invention relates to a wind power prediction device, system, method and equipment, and relates to the technical field of wind power generation, and the device is characterized in that the wind power prediction device is deployed in a cabin of a target fan and is connected with a meteorological sensor of the target fan; the wind power prediction device is used for receiving the meteorological data, measured by the meteorological sensor, of the target draught fan and predicting the wind power of the target draught fan based on the meteorological data. According to the technical scheme, the wind power prediction device can be deployed in the cabin of the target fan, the meteorological data measured by the meteorological sensor are directly received, and then the wind power prediction is performed based on the meteorological data, so that the real-time prediction of the wind power of the target fan is realized; the time delay caused by the fact that the meteorological data are transmitted back to the centralized control system to be processed is reduced, the real-time performance of wind power prediction is further improved, and the accuracy of wind power prediction of all draught fans is improved.

Description

Technical Field

[0001] The present application relates to the technical field of wind power generation, and in particular to a wind power prediction device, system, method and equipment. Background Art

[0002] Wind power forecasting can predict the power output of wind turbines within a specific period of time in the future, and plays an important role in the dispatching of power grids, trading activities in the electricity market, and the operation and management of wind farms.

[0003] At present, in the related technology, wind farms generally adopt a centralized wind power prediction system for the entire field, using a centralized control system to receive data from multiple wind towers and then calculate the overall wind power data of the wind farm.

[0004] However, in the related art, when a centralized control system is used to collect and process data from all wind towers for unified prediction, the transmission of data from each wind tower to the centralized control system is prone to data delay, resulting in poor real-time performance of wind power prediction, which in turn affects the accuracy of wind power prediction. Summary of the invention

[0005] In view of this, the present application provides a wind power prediction device, system, method and equipment, the main purpose of which is to improve the current related technology that uses a centralized control system to collect and process data from all wind towers. When making a unified prediction, the data transmitted from each wind tower to the centralized control system is prone to data delay, resulting in poor real-time performance of wind power prediction, which in turn affects the accuracy of wind power prediction.

[0006] In a first aspect, the present application provides a wind power prediction device, which is deployed in the nacelle of the target wind turbine and connected to a meteorological sensor of the target wind turbine;

[0007] The wind power prediction device is used to receive the meteorological data of the target wind turbine measured by the meteorological sensor, and predict the wind power of the target wind turbine based on the meteorological data.

[0008] Optionally, the wind power prediction device includes: an analog-to-digital conversion module and a field programmable gate array (FPGA) module;

[0009] The output end of the analog-to-digital conversion module is connected to the input end of the FPGA module;

[0010] The analog-to-digital conversion module is used to convert the meteorological analog signal corresponding to the meteorological data into a meteorological digital signal, and serially input the meteorological digital signal into the FPGA module.

[0011] Optionally, the FPGA module includes: a prediction module;

[0012] The prediction module is used to generate a wind power prediction time series of a target time length based on the meteorological digital signal by using a preset wind power prediction model;

[0013] The preset wind power prediction model is used to extract features from the meteorological digital signal of the target wind turbine, and predict the wind power of the target wind turbine according to the feature extraction result.

[0014] Optionally, the FPGA module also includes: an input module and an output module; the input module is used to store the meteorological digital signal in a register group, and output the meteorological digital signal to the prediction module in response to receiving an input enable signal sent by the prediction module; the output module is used to store the wind power prediction time series in a register group in response to receiving an output enable signal sent by the prediction module.

[0015] Optionally, the wind power prediction device further comprises: an input mother port;

[0016] The input end of the input female port is connected to the input end of the meteorological sensor, and the output end of the input female port is connected to the input end of the analog-to-digital conversion module;

[0017] The input female port is used to access the meteorological analog signal corresponding to the meteorological sensor, and send the meteorological analog signal to the analog-to-digital conversion module.

[0018] Optionally, the wind power prediction device further includes: a serial port output interface;

[0019] The input end of the serial port output interface is connected to the output end of the FPGA module, and the output end of the serial port output interface is connected to the input end of the fan control cabinet;

[0020] The serial port output interface is used to receive the wind power prediction time series predicted by the FPGA module, and output the wind power prediction time series to the preset embedded system of the wind turbine control cabinet, and the preset embedded system is used to control the target wind turbine according to the wind power prediction time series.

[0021] In a second aspect, the present application provides a wind power prediction system, which includes a target wind turbine nacelle, a meteorological sensor and a wind power prediction device as described in any one of claims 1 to 6, wherein the wind power prediction device is deployed in the target wind turbine nacelle and connected to the meteorological sensor of the target wind turbine.

[0022] In a third aspect, the present application provides a wind power prediction method, which is applied to a wind power prediction device, and the method includes:

[0023] Acquiring meteorological data of a target wind turbine measured by the meteorological sensor;

[0024] The wind power of the target wind turbine is predicted based on the meteorological data.

[0025] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the wind power prediction method described in the third aspect.

[0026] In a fifth aspect, the present application provides an electronic device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the wind power prediction method described in the third aspect when executing the computer program.

[0027] By means of the above technical scheme, the present application provides a wind power prediction device, system, method and equipment, wherein the wind power prediction device is deployed in the nacelle of the target wind turbine and connected to the meteorological sensor of the target wind turbine; the wind power prediction device is used to receive the meteorological data of the target wind turbine measured by the meteorological sensor, and predict the wind power of the target wind turbine based on the meteorological data. Compared with the current prior art, the present application can deploy a wind power prediction device in the nacelle of the target wind turbine, directly receive the meteorological data measured by the meteorological sensor, and then predict the wind power based on the meteorological data, thereby realizing the real-time prediction of the wind power of the target wind turbine, reducing the time delay caused by the transmission of meteorological data back to the centralized control system for processing, thereby improving the real-time nature of the wind power prediction and the accuracy of the wind power prediction of each wind turbine.

[0028] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0031] Figure 1A schematic diagram of the structure of a wind power prediction device provided in an embodiment of the present application is shown;

[0032] Figure 2 A schematic diagram of the structure of a wind power prediction device provided in an embodiment of the present application is shown;

[0033] Figure 3 A schematic diagram of the structure of a wind power prediction system provided in an embodiment of the present application is shown;

[0034] Figure 4 A schematic flow chart of a wind power prediction method provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0035] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0036] In order to improve the related technology of using a centralized control system to collect and process the data of all wind towers and make a unified prediction, the transmission of data from each wind tower to the centralized control system is prone to data delay, resulting in poor real-time performance of wind power prediction, which in turn affects the accuracy of wind power prediction. This embodiment provides a wind power prediction device 11, such as Figure 1 and Figure 2 As shown, the device can be deployed in the target wind turbine nacelle 1 and connected to the meteorological sensor 12 of the target wind turbine; the wind power prediction device 11 can be used to receive the meteorological data of the target wind turbine measured by the meteorological sensor 12, and predict the wind power of the target wind turbine based on the meteorological data.

[0037] Optionally, the wind power prediction device may include: an analog-to-digital conversion module 116 and an FPGA module 117; the output end of the analog-to-digital conversion module 116 is connected to the input end of the FPGA module 117; the analog-to-digital conversion module 116 can be used to convert the meteorological analog signal corresponding to the meteorological data into a meteorological digital signal, and serially input the meteorological digital signal to the FPGA module 117; the FPGA module 117 can be used to predict the wind power of the target wind turbine based on the meteorological digital signal.

[0038] Exemplarily, the analog-to-digital conversion module 117 may include an analog-to-digital conversion chip and its supporting peripheral circuits, which are used to convert the analog quantity of each input signal of the meteorological sensor 12 into a digital quantity. Specifically, in order to meet the requirements of multi-channel acquisition and signal selection, the physical quantity can be converted into a digital quantity requiring an eight-bit width according to the data channel requirements.

[0039] Further optionally, the FPGA module 117 may include: a prediction module; the prediction module can be used to generate a wind power prediction time series of a target time length based on the meteorological digital signal using a preset wind power prediction model; the preset wind power prediction model can be used to extract features of the meteorological digital signal of the target wind turbine, and predict the wind power of the target wind turbine based on the feature extraction results.

[0040] Specifically, the FPGA module 117 may include an FPGA chip, i.e., peripheral components and circuits, which are used to set a preset wind power prediction model and realize the wind power prediction function. Specifically, the module peripheral components may include a crystal oscillator, a random access memory (RAM), and a Flash to provide a suitable clock frequency and storage requirements for the FPGA. The input and output pins are responsible for data exchange with other modules and interfaces on the circuit board 114, mainly including the hardware description burning of the burning chip, the input signal of the analog-to-digital conversion module 116, and the output of the final prediction result.

[0041] Optionally, the FPGA module 117 may also include: an input module and an output module; the input module may be used to store the meteorological digital signal in a register group, and output the meteorological digital signal to the prediction module in response to receiving an input enable signal sent by the prediction module; the output module may be used to store the wind power prediction time series in the register group in response to receiving an output enable signal sent by the prediction module.

[0042] Optionally, the wind power prediction device 11 may also include: an input mother port 113; the input end of the input mother port 113 is connected to the input end of the meteorological sensor 12, and the output end of the input mother port 113 is connected to the input end of the analog-to-digital conversion module 116; the input mother port 113 can be used to access the meteorological simulation signal corresponding to the meteorological sensor 12, and send the meteorological simulation signal to the analog-to-digital conversion module 116.

[0043] Exemplarily, the input female port 113 may be a terminal busbar, which may be used to access signals of meteorological sensors 12 such as wind speed, wind direction, temperature, and humidity. The signals are generally analog signals with a maximum high potential of 5V.

[0044] Optionally, the wind power prediction device 11 may also include: a serial port output interface 118; the input end of the serial port output interface 118 is connected to the output end of the FPGA module, and the output end of the serial port output interface 118 is connected to the input end of the wind turbine control cabinet; the serial port output interface 118 can be used to receive the wind power prediction time series predicted by the FPGA module, and output the wind power prediction time series to a preset embedded system of the wind turbine control cabinet, and the preset embedded system can be used to control the target wind turbine according to the wind power prediction time series.

[0045] Exemplarily, the serial output interface 118 may be a terminal bus bar, which can be used to connect to the system to be embedded for result output.

[0046] Optionally, the wind power prediction device 11 may further include: a device protection shell 111. Exemplarily, the device protection shell 111 can be used to ensure that the device can operate stably in a working environment, and the bayonet designed at the back can enable it to be installed in the wind turbine electrical control cabinet. The shell material can be a thermoplastic polymer material (Acrylonitrile Butadiene Styrene, ABS), or a material that is the same as or better than ABS, and the shell protection level can reach IP66, so that the wind power prediction device 11 has the ability to prevent dust, dirt and interference in the cabin environment, and has wear resistance, scratch resistance and impact resistance to meet the requirements of the wind turbine use environment.

[0047] Optionally, the wind power prediction device 11 may further include: a power supply mother port 112. Exemplarily, the power supply mother port 112 may be a terminal busbar, which is used to access a unified 24V DC power supply of the system to be embedded, to ensure that the device and various sensors of the system have the same low potential.

[0048] Optionally, the wind power prediction device 11 may further include: a circuit board 114. Exemplarily, the circuit board 114 may be a carrier board for electronic components of the device, ensuring circuit integration and good signal integrity to adapt to temperature changes and vibrations in the working environment of the wind turbine. The surface of the circuit board 114 may be treated with moisture-proof and anti-oxidation treatment to improve its durability in harsh environments.

[0049] Optionally, the wind power prediction device 11 may further include: a step-down module 115. Exemplarily, the step-down module 115 may be a step-down chip and its supporting peripheral circuits, which can reduce the input voltage to a suitable voltage for device operation. The input voltage of the step-down module 115 can be between 5V and 24V to ensure that it can withstand slight voltage fluctuations, and the output voltage can be 3.3V to drive all components in the circuit board 114 to work normally, the maximum current can be 3A, and the operating temperature and humidity meet the wind turbine operating environment.

[0050] As a possible implementation, the input mother port 113 and the serial output port interface 118 of the wind power prediction device 11 are connected to the sensors and serial ports of the system to be embedded, and then the power is turned on through the power supply mother port 112. After the input pin of the analog-to-digital conversion module 116 receives the voltage signal, it can be adjusted and calibrated by controlling the variable resistor in the device to ensure that the voltage input is within the specified value range, so that the obtained voltage data can well linearly represent the four physical quantities of wind speed, wind direction, temperature, and humidity. Then, the voltage value is converted into an eight-bit digital quantity through the analog-to-digital conversion module 116, and the physical quantities are output one by one according to the signal transmitted from the addressing output pin set by the FPGA chip, and the four digital quantities are serially input to the input pin set by the FPGA chip.

[0051] Correspondingly, the RAM in the FPGA module 117 is mainly used as a register, and the logic circuit burned in the FPGA chip mainly includes an input module, a prediction module (such as a neural network processing module) and an output module. Among them, the input module includes a 32-bit data register group and an addressing logic. The data register is used to merge and store 4 digital quantities into one register, and the addressing logic is used to read and store data from the register once per 32 bits. After the addressing logic receives the rising edge of the data input start signal transmitted by the neural network processing module, it will start from the data moving first address and increase the address in sequence to input the value in the register into the neural network processing module. After meeting the input quantity requirements, the input start signal rising and falling edges will be detected, and data sampling will be performed once. The sampled data will be stored in the register of the next address, and the data moving first address will be increased by one to move the sequence of the next output data backward by one, and then repeat the above operation. After reading and sampling through the register group, it will start again from the register group starting address.

[0052] Specifically, the neural network processing module is designed to consist of a convolutional neural network model (CNN)-long short-term memory network model (LSTM) body and its cache registers and control logic. The cache registers are designed with a capacity based on the accuracy required for prediction. When the control logic sends a data input start signal to the input module, the input digital quantities are accessed one by one. Prediction and reasoning begins when all cache registers are full.

[0053] Correspondingly, the output module may include a register group, a serial communication module and a control logic, wherein the number of register groups is the same as the length of the wind power prediction time series. When the output module receives the enable signal output by the neural network processing module, each LSTM neural network output pipeline data is stored in the register one by one, and an end signal is sent to the neural network processing module after completion. The data in the register is read and transmitted to the serial communication module one by one, and then converted into decimal integer data and transmitted from the serial output pin set by the FPGA to the next level system according to the serial protocol and the set baud rate, so as to dynamically start and stop the wind turbine units in the wind farm that exceeds the grid capacity in time, realize the dynamic adjustment of the wind farm and the grid capacity, thereby maximizing the online power while reducing the loss of wind turbine use, thereby ensuring the stability of the grid system.

[0054] Compared with the current existing technology, this embodiment can deploy a wind power prediction device 11 in the target wind turbine nacelle 1, directly receive the meteorological data measured by the meteorological sensor 12, and then predict the wind power based on the meteorological data, so as to achieve the real-time prediction of the wind power of the target wind turbine, reduce the time delay caused by the transmission of meteorological data back to the centralized control system for processing, thereby improving the real-time nature of the wind power prediction and the accuracy of the wind power prediction of each wind turbine. In addition, it is possible to dynamically start and stop the wind turbine units in a wind farm that exceeds the grid capacity, realize the dynamic adjustment of the wind farm and the grid capacity, thereby maximizing the amount of electricity connected to the grid while reducing the loss of wind turbine use, thereby ensuring the stability of the grid system.

[0055] Further, in order to illustrate the specific use process of the device, this embodiment provides a wind power prediction system, such as Figure 3 As shown, the system includes a target wind turbine nacelle 1, a meteorological sensor 12 and a wind power prediction device 11. The wind power prediction device 11 is deployed in the target wind turbine nacelle 1 and connected to the meteorological sensor 12 of the target wind turbine.

[0056] Exemplarily, the input end of the wind power prediction device 11 can be connected to the output end of the meteorological sensor 12 to obtain meteorological data in real time. The output end of the wind power prediction device 11 can be connected to the input end of the wind turbine control cabinet of the target wind turbine. The wind power prediction device 11 can send the predicted wind power to the wind turbine control cabinet of the target wind turbine, so that the preset embedded system in the wind turbine control cabinet controls the target wind turbine based on the wind power, provides high-quality decision-making information, and effectively improves the control capability and efficiency of the intelligent joint control of the wind turbine, so as to ensure the stability of the power grid system, realize the dynamic adjustment of the wind farm and the power grid capacity, and promptly start and stop the wind turbine units dynamically for wind farms that exceed the power grid capacity, thereby maximizing the online power while reducing the loss of wind turbine use.

[0057] As a possible implementation method, the wind power prediction device 11 can be installed in the wind turbine electrical control cabinet of the target wind turbine cabin 1. The input end of the wind power prediction device 11 can be connected to the signal lines of the laser anemometer and the thermometer and hygrometer. The output end of the wind power prediction device 11 can be connected to the PLC digital signal receiving port. After being connected, the wind power prediction information can be output after the register is full of data.

[0058] Compared with the current existing technology, this embodiment can deploy a wind power prediction device 11 in the target wind turbine nacelle 1, directly receive meteorological data measured by the meteorological sensor 12, and then perform wind power prediction based on the meteorological data, thereby realizing real-time prediction of the wind power of the target wind turbine, reducing the time delay caused by the transmission of meteorological data back to the centralized control system for processing, thereby improving the real-time nature of wind power prediction and improving the accuracy of wind power prediction for each wind turbine.

[0059] Further, in order to illustrate the specific use process of this device, as shown in FIG. Figure 4 As shown, this embodiment provides a wind power prediction method, the method comprising:

[0060] Step 301: Receive meteorological data of a target wind turbine measured by a meteorological sensor.

[0061] In this embodiment, the meteorological data of the target wind turbine measured by the meteorological sensor can be used to predict the wind power of the target wind turbine. The target wind turbine can be the wind turbine for which wind power prediction is to be performed; the meteorological sensor can include but is not limited to a wind speed sensor, a wind direction sensor, a temperature sensor, a humidity sensor, an air pressure sensor, a rainfall sensor, a snowfall sensor, etc.; the meteorological data can include but is not limited to wind speed, wind direction, temperature, humidity, air pressure, rainfall, snowfall, etc. For example, the corresponding meteorological data can be collected by using an anemometer and other equipment in the target wind turbine.

[0062] Step 302: predict the wind power of the target wind turbine based on meteorological data.

[0063] In some examples, after obtaining the meteorological data, the meteorological data can be directly processed to obtain the predicted wind power. For example, the wind power of a target wind turbine in the short term can be predicted, and a wind power prediction time series of a target time length can be generated based on the meteorological data using a preset wind power prediction model; wherein the preset wind power prediction model can be used to extract features from the meteorological data of the target wind turbine, and the wind power of the target wind turbine can be predicted based on the feature extraction results.

[0064] In this way, the present embodiment can first receive the meteorological data of the target wind turbine measured by the meteorological sensor, and then predict the wind power of the target wind turbine based on the meteorological data, thereby improving the prediction efficiency and accuracy of the wind power.

[0065] In some examples, the preset wind power prediction model can be a combination model of a CNN model and an LSTM model, wherein the CNN model is responsible for extracting data features of meteorological data, and the LSTM model is responsible for inferring and predicting the wind power of the wind turbine based on the extracted data features. In a specific application scenario, CNN includes an input layer, a hidden layer, and an output layer. The input layer and the output layer are composed of a one-dimensional convolution vector layer and a one-dimensional maximum pooling layer. Each layer sets the dimension of the convolution layer, the convolution kernel size, and the activation function according to the length of the input signal, and the size and step size of the maximum pooling layer are determined by the accuracy of the input data. Usually, the number of channels is set to the number of cache registers; the output layer is a fully connected layer, and the final output is a one-dimensional sequence with the same number of channels and cache registers. A single element of the sequence is eight bits, which is then passed to the LSMT model.

[0066] Correspondingly, the LSTM model contains hidden layers, fully connected layers, and relay registers, where the number of hidden layers is the same as the number of input parameters. After the model inference is completed, the last output sequence of all hidden layers is saved in the relay register in sequence, and then the data is passed to the fully connected layer. The number of output channels of the fully connected layer is the same as the target time length required and finally predicted. Finally, the output result of the fully connected layer is the wind power prediction time series of the target time length. When the result is obtained, the neural network processing logic sends an output enable signal and waits for the end signal to clear all registers and turn off the enable.

[0067] Exemplarily, in the training process of the preset wind power prediction model, the training data set may include training samples and training labels, the training samples may be the historical meteorological data of each wind turbine in the wind farm, and the training labels may be the historical wind power. Exemplarily, the training data set may be obtained by sampling at preset time intervals, for example: the numerical conversion of wind speed, temperature, humidity, wind direction and other data recorded every five minutes and sampled every 10 days in the past year into voltage values, and the corresponding wind power.

[0068] As a possible implementation, in the scenario of predicting the target wind turbine in the wind farm (which may include at least one wind turbine), the historical meteorological data and historical wind power of the wind turbine can be first obtained to generate a model training set, and then the model structure and training parameters of the preset wind power prediction model can be configured. Exemplarily, the input layer of the CNN model in the preset wind power prediction model can be set according to the following data: input 10 channels (ten channels collect data every five minutes), 4 dimensions (four digital quantities such as wind speed), the convolution kernel can be 2, the output dimension can be 16, the activation function can be a relu convolution layer, the added layer size can be 2, and the step size can be 1 maximum pooling; the hidden layer can be set according to the following data: the convolution kernel can be 2, the output dimension can be 32, the activation function can be a relu convolution layer, the added layer size can be 2, and the step size can be 1 maximum pooling; the output layer can be set according to the following data: the output channel can be a fully connected layer of 10. After the CNN model, an LSTM model with ten inputs and ten outputs can be connected, and then the ten outputs can be connected to a fully connected layer with six outputs. The sequence composed of the six output results is the wind power time series within a preset time (such as within the next half an hour). Finally, curve data can be generated based on the output wind power time series to facilitate wind power analysis and statistics.

[0069] Correspondingly, in the process of training the preset wind power prediction model in the computer, the learning rate can be set to 0.05, the number of iterations can be set to 1500, and the error accuracy can be set to 0.05. After the training is completed, all the parameters in the neural network are converted to integers, and then filled in the hardware description file written in the Verilog language, and then burned into the wind power prediction device, so as to solidify the preset wind power prediction model in the wind power prediction device, continuously provide wind power prediction function, and there is no need to transmit meteorological data back to the center point for prediction, so as to realize real-time prediction of wind power of target wind turbines and improve wind power prediction efficiency and accuracy.

[0070] Further optionally, the predicted wind power can be sent directly to the wind turbine control cabinet corresponding to the target wind turbine, and the control system in the wind turbine control cabinet controls the wind turbine (such as starting and stopping the wind turbine, etc.) based on the predicted wind power, so that the preset embedded system in the wind turbine control cabinet controls the target wind turbine based on the wind power to ensure the stability of the power grid system, realize the dynamic adjustment of the wind farm and the power grid capacity, and dynamically start and stop the wind turbine units in a timely manner for wind farms that exceed the power grid capacity, thereby maximizing the amount of electricity connected to the grid while reducing the loss of wind turbine use. Specifically, the serial port output interface can be used to receive the wind power prediction time series predicted by the FPGA chip, and the wind power prediction time series output by the preset wind power prediction model can be output to the preset embedded system of the wind turbine control cabinet, so that the preset embedded system controls the target wind turbine according to the wind power prediction time series.

[0071] Compared with the centralized prediction method in the current prior art, this embodiment can use a preset wind power prediction model to predict the wind power of the target wind turbine, thereby realizing short-term wind power prediction of a single wind turbine, which has higher accuracy than the centralized prediction method; at the same time, the method of this embodiment can be applied to a wind power prediction device 11, and the wind power prediction device 11 is deployed in the target wind turbine nacelle 1, so as to obtain meteorological data such as wind speed in time, improve the prediction rate and accuracy, and effectively reduce the transmission cost.

[0072] Based on the above Figure 4 The method shown in the embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figure 4 The method shown.

[0073] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the method of the implementation scenario of the present application.

[0074] Based on the above Figure 4 In order to achieve the above-mentioned purpose, the embodiment of the present application also provides an electronic device, such as a personal computer, a server, which includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 4 The method shown.

[0075] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0076] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0077] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0078] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform, or by hardware. By applying the technical solution of this embodiment, this embodiment can deploy a wind power prediction device 11 in the target wind turbine nacelle 1, directly receive the meteorological data measured by the meteorological sensor 12, and then predict the wind power based on the meteorological data, thereby realizing the real-time prediction of the wind power of the target wind turbine, reducing the time delay caused by the transmission of meteorological data back to the centralized control system for processing, thereby improving the real-time nature of the wind power prediction, and improving the accuracy of the wind power prediction of each wind turbine. In addition, it is possible to dynamically start and stop wind turbine units in a wind farm that exceeds the capacity of the power grid in a timely manner, realize the dynamic adjustment of the wind farm and the power grid capacity, thereby maximizing the amount of power connected to the grid while reducing the loss of wind turbine use, thereby ensuring the stability of the power grid system.

[0079] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0080] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features applied for herein.

Claims

1. A wind power prediction device, characterized in that: include: The wind power prediction device is deployed in the nacelle of the target wind turbine and connected to the meteorological sensor of the target wind turbine; The wind power prediction device is used to obtain the meteorological data of the target wind turbine measured by the meteorological sensor, and predict the wind power of the target wind turbine based on the meteorological data.

2. The device according to claim 1, characterized in that The wind power prediction device comprises: an analog-to-digital conversion module and an FPGA module; The output end of the analog-to-digital conversion module is connected to the input end of the FPGA module; The analog-to-digital conversion module is used to convert the meteorological analog signal corresponding to the meteorological data into a meteorological digital signal, and serially input the meteorological digital signal into the FPGA module.

3. The device according to claim 2, characterized in that The FPGA module includes: a prediction module; The prediction module is used to generate a wind power prediction time series of a target time length based on the meteorological digital signal by using a preset wind power prediction model; The preset wind power prediction model is used to extract features from the meteorological digital signal of the target wind turbine, and predict the wind power of the target wind turbine according to the feature extraction result.

4. The device according to claim 3, characterized in that The FPGA module also includes: an input module and an output module; The input module is used to store the meteorological digital signal in a register group, and in response to receiving an input enable signal sent by the prediction module, output the meteorological digital signal to the prediction module; The output module is used for storing the wind power prediction time series into a register group in response to receiving an output enable signal sent by the prediction module.

5. The device according to claim 2, characterized in that The wind power prediction device further comprises: an input mother port; The input end of the input female port is connected to the input end of the meteorological sensor, and the output end of the input female port is connected to the input end of the analog-to-digital conversion module; The input female port is used to access the meteorological analog signal corresponding to the meteorological sensor, and send the meteorological analog signal to the analog-to-digital conversion module.

6. The device according to claim 2, characterized in that The wind power prediction device also includes: a serial port output interface; The input end of the serial port output interface is connected to the output end of the FPGA module, and the output end of the serial port output interface is connected to the input end of the fan control cabinet; The serial port output interface is used to receive the wind power prediction time series predicted by the FPGA module, and output the wind power prediction time series to the preset embedded system of the wind turbine control cabinet, and the preset embedded system is used to control the target wind turbine according to the wind power prediction time series.

7. A wind power prediction system, characterized in that: It comprises a target wind turbine nacelle, a meteorological sensor and a wind power prediction device as claimed in any one of claims 1 to 6, wherein the wind power prediction device is deployed in the target wind turbine nacelle and connected to the meteorological sensor of the target wind turbine.

8. A wind power prediction method, characterized in that: The wind power prediction device applied to any one of claims 1 to 6, the method comprising: Acquiring meteorological data of a target wind turbine measured by the meteorological sensor; The wind power of the target wind turbine is predicted based on the meteorological data.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to claim 8 is implemented.

10. An electronic device comprising a storage medium, a processor and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to claim 8 is implemented.

Images