Wind power output prediction method and device considering unit wind speed limitation, equipment, medium and product

Abstract

The invention discloses a wind power output prediction method and device considering unit wind speed limitation, equipment, a medium and a product, and relates to the field of wind power output prediction of a power system. Acquiring meteorological data of the target area in a set time period; decomposing the wind speed by adopting an ensemble empirical mode decomposition method to obtain decomposed information data; on the basis of the sum of the wind speed limits of all the wind turbine generators in the target area and the change rate of each eigenmode function, dividing the eigenmode functions to obtain divided information data; performing reconstruction processing according to the division information data to obtain reconstructed signal data; inputting the input feature data into a prediction model to obtain predicted wind power output data; the prediction model is obtained by training by adopting a machine learning method based on historical meteorological data and corresponding wind power processing data; the method aims at efficiently and scientifically solving the regional wind power output prediction problem of the power system.

Description

Technical Field

[0001] The present application relates to the field of wind power output prediction of power systems, and in particular to a method, device, equipment, medium and product for predicting wind power output taking into account wind speed limitations of units. Background Art

[0002] With the rapid development of energy transformation and new energy, wind energy, as a clean and renewable energy, is becoming increasingly important in the global energy structure, and is of great significance for promoting sustainable development, alleviating energy pressure and reducing environmental pollution. However, wind energy is an unstable energy source with random fluctuations. The large-scale integration of wind power into the system will inevitably bring new challenges to the stability of the system. Wind power output is affected by a variety of meteorological factors such as wind speed, wind direction, temperature, etc., showing a high degree of volatility and uncertainty. In order to meet this challenge, the research on wind power output prediction methods is particularly important. Accurate wind power output prediction not only helps to improve the stability and safety of the power system and promote better grid connection of wind power, but also optimizes power dispatching and economic dispatching, and improves the operational efficiency and economic benefits of wind farms. Through wind power power prediction, the power dispatching department can adjust the output of other conventional units according to the wind farm output curve and output change law, and optimize the operation of the power system; at the same time, the wind farm can also reasonably arrange the unit maintenance and overhaul plan according to the prediction results to improve the operational efficiency and capacity factor. Therefore, the research on wind power output prediction methods is of great significance for promoting the development of the wind power industry and improving the overall efficiency and economic benefits of the power system.

[0003] During the actual operation of wind turbines, wind speed, temperature, humidity and air pressure will all have an impact on wind power output: (1) Wind speed directly affects wind power generation efficiency. Generally, when the wind speed is between the minimum wind speed limit (start-up wind speed) and the maximum wind speed limit (cut-out wind speed), the greater the wind speed, the more power will be generated; (2) High temperature will reduce the electrical and mechanical efficiency of wind turbines, and at the same time affect the intensity and stability of wind energy resources; (3) High humidity will accelerate equipment corrosion and aging, resulting in a decrease in the performance of electrical components, and extreme humidity environments (too high or too low) may affect the stable operation of equipment; (4) Air pressure will affect wind speed. When the air pressure difference is large, the wind speed increases. In a high-pressure environment, the air density is large, and the wind power generation efficiency is higher.

[0004] At present, the methods for wind power output prediction are mainly divided into the following categories: (1) Prediction methods based on physical models, which are based on meteorological data such as wind speed, wind direction, temperature, etc. of the wind farm, combined with the physical characteristics and control strategies of the wind turbine, to establish a mathematical model for prediction, usually involving complex computational fluid dynamics simulation and mechanical dynamics analysis, which can simulate the aerodynamic behavior, mechanical structure response and power electronic characteristics of the wind turbine to predict the wind power output. The advantage is that the prediction results are relatively accurate, but the disadvantage is that detailed meteorological data and physical parameters of the wind turbine are required, the calculation complexity is high, and the demand for computing resources is large. (2) Prediction methods based on data, mainly using historical wind power output data, and establishing prediction models through data mining and machine learning techniques, including but not limited to time series analysis methods (such as autoregressive moving average model ARMA, autoregressive integral moving average model ARIMA, etc.), neural network methods, support vector machines, fuzzy logic methods, etc. The advantages are high computational efficiency, easy implementation, and the ability to process large-scale data sets. In theory, when the data is complete, the prediction error can be minimized. The disadvantage is that the prediction accuracy is greatly affected by the quality and quantity of historical data, and requires the support of a large amount of historical data. It is not suitable for newly built wind farms and has high requirements for the consistency of the change law of historical data. (3) The hybrid method is to combine two or more prediction methods and use their respective advantages to improve the prediction accuracy. For example, the physical model, time series analysis and machine learning methods are combined to make up for the shortcomings of a single model. The advantage is that it can better adapt to the complexity and uncertainty of wind power output and improve the reliability and accuracy of the prediction. The disadvantage is that the combination of methods and parameter adjustment may be more complicated and require rich experience and experimental verification. Summary of the invention

[0005] The purpose of this application is to provide a method, device, equipment, medium and product for predicting wind power output taking into account the wind speed limitation of the unit, which can efficiently and scientifically solve the problem of regional wind power output prediction in the power system.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for predicting wind power output taking into account wind speed limitations of a unit, comprising:

[0008] Obtaining meteorological data of the target area during a set period of time; the meteorological data includes: wind speed, temperature, humidity and air pressure;

[0009] The wind speed is decomposed by using a set empirical mode decomposition method to obtain decomposed information data; the decomposed information data includes: N eigenmode functions and afterwave signals;

[0010] Based on the sum of wind speed limits of all wind turbines in the target area and the change rate of each eigenmode function, the eigenmode function is divided to obtain division information data;

[0011] Performing reconstruction processing according to the division information data to obtain reconstructed signal data;

[0012] Input feature data is input into a prediction model to obtain predicted wind power output data; the input feature data includes: temperature, humidity, air pressure and the reconstructed signal data; the prediction model is based on historical meteorological data and corresponding wind power processing data, and is trained using a machine learning method; the predicted wind power output data is used to enable power dispatchers to regulate the output of wind farms in the power system.

[0013] Optionally, based on the sum of wind speed limits of all wind turbines in the target area and the change rates of each eigenmode function, the eigenmode function is divided to obtain division information data, specifically including:

[0014] The intrinsic mode functions are divided based on the maximum active power change rate of each eigenmode function in a unit time scale and the sum of wind speed limits of all wind turbines in a target area;

[0015] If P x (t)≤V min , it is divided into low-frequency part signal;

[0016] If V min <R x (t) <V max , it is divided into intermediate frequency part signal;

[0017] P x (t)≥V max , it is divided into high-frequency part signal;

[0018] Among them, P x (t) is the xth eigenmode function i x (t) Maximum rate of change of active power per unit time scale; V min is the sum of the minimum wind speed limits of all wind turbines in the target area; V max It is the sum of the maximum wind speed limits of all wind turbines in the target area.

[0019] Optionally, the reconstructed signal data includes: a low-frequency reconstructed signal, a medium-frequency reconstructed signal and a high-frequency reconstructed signal;

[0020] The expression of the low-frequency reconstructed signal is:

[0021] S low (t) = i N (t)+iN-1 (t)+…+i l (t);

[0022] The expression of the intermediate frequency reconstruction signal is:

[0023] S mid (t) = i l-1 (t)+i l-2 (t)+…+i h+1 (t);

[0024] The expression of the high frequency reconstructed signal is:

[0025] S high (t) = i h (t)+i h-1 (t)+…+i1(t);

[0026] Among them, S low (t) is the low-frequency reconstructed signal; i N (t) is the Nth eigenmode function; i N-1 (t) is the N-1th eigenmode function; i l (t) is the lth eigenmode function; S mid (t) is the intermediate frequency reconstructed signal; i l-1 (t) is the l-1th eigenmode function; i l-2 (t) is the l-2th eigenmode function; i h+1 (t) is the h+1th eigenmode function; S high (t) is the high-frequency reconstructed signal; i h (t) is the hth eigenmode function; i h-1 (t) is the h-1th intrinsic mode function; i1(t) is the 1st intrinsic mode function.

[0027] Optionally, the method for determining the prediction model specifically includes:

[0028] Obtain historical meteorological data and corresponding wind power processing data;

[0029] The wind speed in the historical meteorological data is decomposed by using the ensemble empirical mode decomposition method to obtain the historical decomposition information data;

[0030] Based on the sum of wind speed limits of all wind turbines in the historical target area and the change rate of each eigenmode function, the historical eigenmode function is divided to obtain historical division information data;

[0031] Reconstructing the historical partition information data to obtain historical reconstructed signal data;

[0032] Build machine learning models;

[0033] Inputting historical input feature data and corresponding wind power processing data into the machine learning model for training to obtain a trained machine learning model;

[0034] The trained machine learning model is determined as a prediction model.

[0035] Optionally, before inputting the historical input feature data and the corresponding wind power processing data into the machine learning model for training to obtain the trained machine learning model, the method further includes:

[0036] The linear scaling method is used to scale the historical input feature data and the corresponding wind power processing data to obtain normalized data scaled to a set interval.

[0037] Optionally, the linear scaling process specifically includes:

[0038]

[0039] Among them, y' is the normalized data; y is the data to be normalized and scaled; y min is the minimum value corresponding to the data that needs to be normalized and scaled; max is the maximum value corresponding to the data that needs to be normalized and scaled.

[0040] In a second aspect, the present application provides a wind power output prediction device taking into account wind speed limitation of a unit, comprising:

[0041] A data acquisition module is used to acquire the meteorological data of the target area during a set period of time; the meteorological data includes: wind speed, temperature, humidity and air pressure;

[0042] A decomposition module, used to decompose the wind speed by using a set empirical mode decomposition method to obtain decomposition information data; the decomposition information data includes: N eigenmode functions and afterwave signals;

[0043] A partitioning module, configured to partition the intrinsic mode function based on the sum of wind speed limits of all wind turbines in the target area and the change rate of each intrinsic mode function to obtain partitioning information data;

[0044] A reconstruction module, used for performing reconstruction processing according to the partition information data to obtain reconstructed signal data;

[0045] The prediction module is used to input the input feature data into the prediction model to obtain the predicted wind power output data; the input feature data includes: temperature, humidity, air pressure and the reconstructed signal data; the prediction model is based on historical meteorological data and corresponding wind power processing data, and is trained using a machine learning method; the predicted wind power output data is used to enable power dispatchers to regulate the output of wind farms in the power system.

[0046] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for predicting wind power output taking into account wind speed limitations of the unit.

[0047] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for predicting wind power output taking into account wind speed limitations of the unit.

[0048] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for predicting wind power output taking into account wind speed limitations of the unit.

[0049] According to the specific embodiments provided in this application, this application has the following technical effects:

[0050] The present application provides a method, device, equipment, medium and product for predicting wind power output taking into account the wind speed limit of the unit, in order to consider the impact of various influencing factors on wind power output, and to comprehensively consider the wind speed frequency domain characteristics, the minimum wind speed limit (start-up wind speed) and maximum wind speed limit (cut-out wind speed) characteristics of the wind turbine, so as to achieve a more flexible, efficient and accurate prediction and estimation effect. Therefore, considering various influencing characteristics such as wind speed, temperature, humidity and air pressure, the frequency domain characteristics of wind speed are decomposed using the ensemble empirical mode decomposition method, and the sum of the wind speed limits of all wind turbines in the target area, that is, the minimum wind speed limit and the maximum wind speed limit of the wind turbine are used to divide the frequency domain signal, and then cumulatively reconstruct it, based on the prediction model trained by machine learning according to historical meteorological data and corresponding wind power processing data, predict wind power output data, and achieve efficient and scientific solution to the problem of regional wind power output prediction in the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 This is a flow chart of a method for predicting wind power output taking into account wind speed limitations of the unit;

[0053] Figure 2 A schematic diagram of the design idea of ​​the wind power output prediction method considering the wind speed limit of the unit;

[0054] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0056] The present application aims at the problem of predicting wind power output under the influence of factors such as wind speed, temperature, humidity and air pressure during the operation of wind turbines, and proposes a wind power output prediction method based on ensemble empirical mode decomposition (EEMD) considering the wind speed limitation of the unit.

[0057] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0058] In an exemplary embodiment, Figure 1 As shown, a method for predicting wind power output considering wind speed limit of a unit is provided. The method is executed by a computer device, specifically, it can be executed by a computer device such as a terminal or a server alone, or it can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to a server as an example for explanation, and includes the following steps.

[0059] like Figure 1 As shown, the embodiment of the present application provides a method for predicting wind power output considering the wind speed limit of the unit, including:

[0060] Step 100: Obtain the meteorological data of the target area during a set period of time. The meteorological data includes: wind speed, temperature, humidity and air pressure.

[0061] Step 200: Decompose the wind speed using an ensemble empirical mode decomposition method to obtain decomposed information data. The decomposed information data includes: N eigenmode functions and afterwave signals.

[0062] Step 300: Based on the sum of wind speed limits of all wind turbines in the target area and the change rates of each intrinsic mode function, the intrinsic mode function is divided to obtain division information data.

[0063] Step 400: Perform reconstruction processing according to the division information data to obtain reconstructed signal data.

[0064] Step 500: Input feature data to the prediction model to obtain predicted wind power output data. The input feature data includes: temperature, humidity, air pressure and the reconstructed signal data; the prediction model is trained based on historical meteorological data and corresponding wind power processing data using a machine learning method; the predicted wind power output data is used to enable power dispatchers to regulate the output of wind farms in the power system.

[0065] In one embodiment, based on the sum of wind speed limits of all wind turbines in the target area and the change rate of each eigenmode function, the eigenmode function is divided to obtain division information data, which specifically includes:

[0066] The intrinsic mode functions are divided based on the maximum active power change rate of each eigenmode function in a unit time scale and the sum of the wind speed limits of all wind turbines in the target area.

[0067] If P x (t)≤V min , it is divided into low-frequency signals.

[0068] If V min <P x (t) <V max , it is divided into the intermediate frequency signal.

[0069] P x (t)≥V max , it is divided into high-frequency part signals.

[0070] Among them, P x (t) is the xth eigenmode function i x (t) Maximum rate of change of active power per unit time scale; V min is the sum of the minimum wind speed limits of all wind turbines in the target area; V max It is the sum of the maximum wind speed limits of all wind turbines in the target area.

[0071] In one embodiment, the reconstructed signal data includes: a low-frequency reconstructed signal, a medium-frequency reconstructed signal, and a high-frequency reconstructed signal.

[0072] The expression of the low-frequency reconstructed signal is:

[0073] S low (t) = i N (t)+i N-1 (t)+…+i l (t).

[0074] The expression of the intermediate frequency reconstructed signal is:

[0075] S mid (t) = i l-1 (t)+i l-2 (t)+…+i h+1 (t).

[0076] The expression of the high-frequency reconstructed signal is:

[0077] S high (t) = i h (t)+i h-1 (t)+…+i1(t).

[0078] Among them, S low (t) is the low-frequency reconstructed signal; i N (t) is the Nth eigenmode function; i N-1 (t) is the N-1th eigenmode function; i l (t) is the lth eigenmode function; S mid (t) is the intermediate frequency reconstructed signal; i l-1 (t) is the l-1th eigenmode function; i l-2 (t) is the l-2th eigenmode function; i h+1 (t) is the h+1th eigenmode function; S high (t) is the high-frequency reconstructed signal; i h (t) is the hth eigenmode function; i h-1 (t) is the h-1th intrinsic mode function; i1(t) is the 1st intrinsic mode function.

[0079] As an optional implementation, the method for determining the prediction model specifically includes:

[0080] Obtain historical meteorological data and corresponding wind power processing data; use the ensemble empirical mode decomposition method to decompose the wind speed in the historical meteorological data to obtain historical decomposition information data.

[0081] Based on the sum of wind speed limits of all wind turbines in the historical target area and the change rate of each intrinsic mode function, the historical intrinsic mode function is divided to obtain historical division information data.

[0082] Reconstruction processing is performed based on the historical division information data to obtain historical reconstructed signal data.

[0083] Construct a machine learning model; input historical input feature data and corresponding wind power processing data into the machine learning model for training to obtain a trained machine learning model; determine the trained machine learning model as a prediction model.

[0084] The process of inputting historical input feature data and corresponding wind power processing data into a machine learning model for training and obtaining a trained machine learning model also includes:

[0085] The linear scaling method is used to scale the historical input feature data and the corresponding wind power processing data to obtain normalized data scaled to a set interval.

[0086] The linear scaling process specifically includes:

[0087]

[0088] Among them, y' is the normalized data; y is the data to be normalized and scaled; y min is the minimum value corresponding to the data that needs to be normalized and scaled; max is the maximum value corresponding to the data that needs to be normalized and scaled.

[0089] like Figure 2 As shown, the technical concept of the method mentioned in this application can be as follows:

[0090] Obtain historical wind power output data W(t), wind speed data V(t), temperature T(t), humidity H(t), air pressure A(t) and other meteorological data for the area to be predicted.

[0091] The historical wind speed data V(t) is decomposed into N intrinsic mode functions (IMF) by EEMD. x (t) (the frequency of the eigenmode function decreases as the sequence number increases) and the afterwave signal res(t), satisfying V(t)=i1(t)+i2(t+…+i N (t)+res(t). Read the sum of the minimum wind speed limits of all wind turbines in the area V min And the sum of the maximum wind speed limits V max .

[0092] According to the change rate of each eigenmode function according to V min and V max It is divided into three parts: low frequency, medium frequency and high frequency. The division method is as follows: the xth eigenmode function i x (t) The maximum rate of change of active power per unit time is P x (t), if P x (t)≤V min Then the intrinsic mode function is divided into low-frequency signals. If V min <P x (t) <V max Then the eigenmode function is divided into the intermediate frequency signal, P x (t)≥V max Then the intrinsic mode function is divided into high-frequency signals. If the low-frequency signal after division is i N (t), i N-1 (t), ..., i l (t), the intermediate frequency signal is i l-1 (t), i l-2 (t), ..., i h+1 (t), the high frequency signal is i h (t), i h-1 (t), ..., i1(t).

[0093] The low frequency, medium frequency and high frequency signals are accumulated and reconstructed into signal S low (t), S mid (t), S high (t), S low (t) = i N (t)+i N-1 (t)+…+i l (t); S mid (t) = i l-1 (t)+i l-2 (t)+…+i h+1 (t); S high (t) = i h (t)+i h-1 (t)+…+i1(t).

[0094] The temperature T(t), humidity H(t), air pressure A(t), and wind speed are used to reconstruct the signal S low (t), S mid (t), S high (t) is used as the input feature data, and the wind power output data W(t) is used as the output. The data is linearly scaled to the interval [0,1] according to the following method:

[0095]

[0096] Among them, y, y min ,y max are the numerical value, minimum value, and maximum value of the input feature or output data sequence that need to be normalized, respectively, and y' is the normalized value. That is, y' is the normalized data; y is the data that needs to be normalized and scaled; y min is the minimum value corresponding to the data that needs to be normalized and scaled; max is the maximum value corresponding to the data that needs to be normalized and scaled.

[0097] The machine learning model can adopt conventional models such as support vector regression, neural network or random forest, etc. The machine learning model is trained using the above normalized input features and output quantities.

[0098] The trained prediction model is used to predict wind power output data. The meteorological data of the required prediction area period, that is, the meteorological data of the target area in the set period, is processed and the corresponding temperature, humidity, air pressure and wind speed three-part reconstructed signals are input into the trained model to obtain the required predicted wind power output data.

[0099] The main technical advantages of this application are as follows:

[0100] This application proposes a wind power output prediction method based on EEMD, which uses the ensemble empirical mode decomposition method to obtain the frequency domain characteristics of wind speed, a key characteristic factor affecting wind power output, and uses the low-frequency, medium-frequency and high-frequency reconstructed signals after signal decomposition and reconstruction as input features of the machine learning model. This method considers factors more fully and comprehensively, and can improve the prediction accuracy of the model.

[0101] The method proposed in the present application obtains each frequency domain feature through a signal decomposition algorithm, takes the minimum wind speed limit and the maximum wind speed limit of the wind turbine as the basis for signal division, and reconstructs the low-frequency, medium-frequency and high-frequency signals according to the division to mine the frequency domain features of the input features. The method is simple, convenient and comprehensive in considering the features.

[0102] Based on the same inventive concept, the embodiment of the present application also provides a wind power output prediction device considering wind speed limit of the unit for implementing the wind power output prediction method considering wind speed limit of the unit involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the wind power output prediction device considering wind speed limit of the unit provided below can refer to the limitations of the wind power output prediction method considering wind speed limit of the unit above, and will not be repeated here.

[0103] In an exemplary embodiment, a wind power output prediction device considering wind speed limitation of a generator set is provided, comprising:

[0104] The data acquisition module is used to obtain the meteorological data of the target area during a set period of time; the meteorological data includes: wind speed, temperature, humidity and air pressure.

[0105] The decomposition module is used to decompose the wind speed using the ensemble empirical mode decomposition method to obtain decomposition information data. The decomposition information data includes: N eigenmode functions and residual wave signals.

[0106] The partitioning module is used to partition the intrinsic mode function based on the sum of wind speed limits of all wind turbines in the target area and the change rate of each intrinsic mode function to obtain partitioning information data.

[0107] The reconstruction module is used to perform reconstruction processing according to the divided information data to obtain reconstructed signal data.

[0108] The prediction module is used to input the input feature data into the prediction model to obtain the predicted wind power output data. The input feature data includes: temperature, humidity, air pressure and reconstructed signal data; the prediction model is based on historical meteorological data and corresponding wind power processing data, and is trained using machine learning methods; the predicted wind power output data is used to enable power dispatchers to regulate the output of wind farms in the power system.

[0109] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store wind power output prediction data considering the wind speed limit of the unit. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting wind power output considering the wind speed limit of the unit is implemented.

[0110] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0111] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0112] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0113] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization of the corresponding device owner. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0114] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0115] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0116] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0117] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for predicting wind power output considering wind speed limit of a wind turbine, characterized in that: The wind power output prediction method considering the wind speed limit of the unit includes: Obtaining meteorological data of the target area during a set period of time; the meteorological data includes: wind speed, temperature, humidity and air pressure; The wind speed is decomposed by using a set empirical mode decomposition method to obtain decomposed information data; the decomposed information data includes: N eigenmode functions and afterwave signals; Based on the sum of wind speed limits of all wind turbines in the target area and the change rate of each eigenmode function, the eigenmode function is divided to obtain division information data; Performing reconstruction processing according to the division information data to obtain reconstructed signal data; Input feature data is input into a prediction model to obtain predicted wind power output data; the input feature data includes: temperature, humidity, air pressure and the reconstructed signal data; the prediction model is based on historical meteorological data and corresponding wind power processing data, and is trained using a machine learning method; the predicted wind power output data is used to enable power dispatchers to regulate the output of wind farms in the power system.

2. The method for predicting wind power output considering wind speed limitation of a generator set according to claim 1, characterized in that: Based on the sum of wind speed limits of all wind turbines in the target area and the change rates of each eigenmode function, the eigenmode function is divided to obtain division information data, specifically including: The intrinsic mode functions are divided based on the maximum active power change rate of each eigenmode function in a unit time scale and the sum of wind speed limits of all wind turbines in a target area; If P x (t)≤V min , it is divided into low-frequency part signal; If V min <P x (t) <V max , it is divided into intermediate frequency part signal; P x (t)≥V max , it is divided into high-frequency part signal; Among them, P x (t) is the xth eigenmode function i x (t) Maximum rate of change of active power per unit time scale; V min is the sum of the minimum wind speed limits of all wind turbines in the target area; V max It is the sum of the maximum wind speed limits of all wind turbines in the target area.

3. The method for predicting wind power output considering wind speed limitation of a generator set according to claim 1, characterized in that: The reconstructed signal data includes: a low-frequency reconstructed signal, a medium-frequency reconstructed signal and a high-frequency reconstructed signal; The expression of the low-frequency reconstructed signal is: S low (t)=i N (t)+i N-1 (t)+…+i l (t); The expression of the intermediate frequency reconstruction signal is: S mid (t)=i l-1 (t)+i l-2 (t)+…+i h+1 (t); The expression of the high frequency reconstructed signal is: S high (t)=i h (t)+i h-1 (t)+…+i1(t); Among them, S low (t) is the low-frequency reconstructed signal; i N (t) is the Nth eigenmode function; i N-1 (t) is the N-1th eigenmode function; i l (t) is the lth eigenmode function; S mid (t) is the intermediate frequency reconstructed signal; i l-1 (t) is the l-1th eigenmode function; i l-2 (t) is the l-2th eigenmode function; i h+1 (t) is the h+1th eigenmode function; S high (t) is the high-frequency reconstructed signal; i h (t) is the hth eigenmode function; i h-1 (t) is the h-1th intrinsic mode function; i1(t) is the 1st intrinsic mode function.

4. The method for predicting wind power output considering wind speed limitation of a generator set according to claim 1, characterized in that: The method for determining the prediction model specifically includes: Obtain historical meteorological data and corresponding wind power processing data; The wind speed in the historical meteorological data is decomposed by using the ensemble empirical mode decomposition method to obtain the historical decomposition information data; Based on the sum of wind speed limits of all wind turbines in the historical target area and the change rate of each eigenmode function, the historical eigenmode function is divided to obtain historical division information data; Reconstructing the historical partition information data to obtain historical reconstructed signal data; Build machine learning models; Inputting historical input feature data and corresponding wind power processing data into the machine learning model for training to obtain a trained machine learning model; The trained machine learning model is determined as a prediction model.

5. The method for predicting wind power output considering wind speed limitation of a generator set according to claim 4, characterized in that: Inputting historical input feature data and corresponding wind power processing data into the machine learning model for training to obtain the trained machine learning model also includes: The linear scaling method is used to scale the historical input feature data and the corresponding wind power processing data to obtain normalized data scaled to a set interval.

6. The method for predicting wind power output considering wind speed limitation of a generator set according to claim 5, characterized in that: The linear scaling process specifically includes: Among them, y' is the normalized data; y is the data to be normalized and scaled; y min is the minimum value corresponding to the data that needs to be normalized and scaled; max is the maximum value corresponding to the data that needs to be normalized and scaled.

7. A wind power output prediction device considering wind speed limit of a unit, characterized in that: The wind power output prediction device considering the wind speed limit of the unit includes: A data acquisition module is used to acquire the meteorological data of the target area during a set period of time; the meteorological data includes: wind speed, temperature, humidity and air pressure; A decomposition module, used to decompose the wind speed by using a set empirical mode decomposition method to obtain decomposition information data; the decomposition information data includes: N eigenmode functions and afterwave signals; A division module, used for dividing the intrinsic mode function based on the sum of wind speed limits of all wind turbines in the target area and the change rate of each intrinsic mode function to obtain division information data; A reconstruction module, used for performing reconstruction processing according to the partition information data to obtain reconstructed signal data; The prediction module is used to input the input feature data into the prediction model to obtain the predicted wind power output data; the input feature data includes: temperature, humidity, air pressure and the reconstructed signal data; the prediction model is based on historical meteorological data and corresponding wind power processing data, and is trained using a machine learning method; the predicted wind power output data is used to enable power dispatchers to regulate the output of wind farms in the power system.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the wind power output prediction method considering the wind speed limitation of the unit as described in any one of claims 1-6.

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 for predicting wind power output taking into account wind speed limitation of a generator set as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting wind power output taking into account wind speed limitation of a generator set as described in any one of claims 1 to 6 is implemented.

Images