Multi-station annual wind power output scene generation method and system

Abstract

The invention discloses a multi-station annual wind power output scene generation method and system, and the method comprises the steps: firstly, analyzing the time-space distribution characteristics, frequency, intensity and other information of extreme meteorological events, and determining the specific influence of the information on the wind speed; then, selecting a specific area, constructing a mathematical model of wind speed change by using the extreme meteorological event data, and suitably inserting the mathematical model into a year time sequence; gaussian process regression and Copula function technologies are adopted to capture the space-time relevance of the wind speed, and a multi-station annual wind speed scene is generated. And finally, converting the wind speed scenes into corresponding annual wind power output scenes by means of a physical mechanism model. According to the method, the influence of an extreme wind speed event on the wind speed and the space-time correlation of wind speed scenes are considered, and a multi-station annual wind speed scene is generated and then mapped to an annual wind power output scene; the extreme degree of the generated scene can be adjusted by changing the type and number of extreme meteorological events inserted on the annual time sequence.

Description

Technical Field

[0001] The present invention belongs to the field of power system automation and relates to a method and system for generating annual wind power output scenarios of multiple stations. Background Art

[0002] In recent years, the scale of new energy grid connection has been increasing. Unlike traditional thermal power generation, wind power generation and photovoltaic power generation, as the main forms of new energy power generation, are easily affected by external meteorological factors, and the power generation capacity is intermittent and volatile. With the intensification of climate warming, extreme weather is showing a trend of large number of occurrences, wide impact areas, and increasing intensity and extremeness. Therefore, the coupling relationship between meteorology and the power grid continues to intensify. With the continuous increase in the penetration rate of new energy in the power grid, how to ensure the stable operation of the power grid and the high-level consumption of new energy is a problem that needs to be paid attention to at this stage. This problem is partly caused by the disturbance brought to the power grid by the uncertainty of new energy output. Therefore, it is necessary to study the prediction of new energy output or the scene generation method of new energy output.

[0003] At present, a large number of studies are mainly based on the methodological research of the above problems from the perspective of historical renewable energy output data, such as some data-driven modeling renewable energy output scenario generation methods, including statistical learning methods and artificial intelligence methods. The above methods usually statistically analyze or directly learn the evolution characteristics of renewable energy output from historical renewable energy output data to construct renewable energy output scenarios with similar distributions, but they have limitations in dealing with the complex relationship between meteorological events and renewable energy output, and cannot fully describe the characteristics of renewable energy output under extreme weather. In addition, the existing generation models generate more renewable energy output scenarios for short time scales. In summary, with the frequent and intensified extreme weather, the uncertainty of system scenarios has increased sharply, and its planning and operation requires long-term grid scenarios with different extreme conditions. Summary of the invention

[0004] The purpose of the present invention is to solve the problem that the prior art cannot fully describe the output characteristics of new energy under extreme weather conditions, and to provide a method and system for generating annual wind power output scenarios for multiple stations.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] The present invention proposes a method for generating a multi-station annual wind power output scenario, comprising:

[0007] Determine the influencing factors of extreme weather on wind power, establish an extreme wind speed time model based on the influencing factors, obtain discrete extreme wind speed data based on the extreme wind speed time model, and insert the discrete extreme wind speed data into the annual time series;

[0008] The discrete extreme wind speed data of the annual time series are processed according to the Gaussian process regression method to obtain the time-continuous wind speed data;

[0009] Based on the time-continuous wind speed data, the wind speed data of multiple stations are obtained, and based on the wind speed data of multiple stations, the wind power output data is obtained to realize the annual wind power output prediction of multiple stations under extreme weather conditions.

[0010] Preferably, the determining of the influence factors of extreme weather on wind power and establishing an extreme wind speed time model according to the influence factors of extreme weather on wind power are specifically as follows:

[0011]

[0012] Where f(x) is a polynomial function, a i is the coefficient of the i-th term, is the i-th term of order n, J is the objective function, f(x i ) is the polynomial function value corresponding to the i-th data, y i is the actual value corresponding to the i-th data.

[0013] Preferably, the discrete extreme wind speed data of the annual time series is processed according to the Gaussian process regression method to obtain the time-continuous wind speed data, specifically:

[0014] The joint prior distribution between the observed and predicted values ​​is established through the discrete extreme wind speed data. Based on the annual time series of inserted extreme meteorological events, the posterior distribution is calculated through the joint prior distribution to obtain time-continuous wind speed data.

[0015] Preferably, the joint prior distribution is expressed as follows:

[0016]

[0017] The posterior distribution is expressed as follows:

[0018]

[0019] Among them, y is the observation value corresponding to the model training set input, that is, the observed wind speed value, and f * is the predicted value of the test point passing through the model, that is, the predicted wind speed value, K is the covariance matrix, X is the input of the model training set, that is, the time point, is the variance of the distribution satisfied by the noise, I n is the n-dimensional identity matrix, x * is the test point, k is the covariance between the test point and itself, N(·) represents the normal distribution, is the mean of the predicted values, and cov(·) represents the covariance function.

[0020] Preferably, the method of acquiring wind speed data of multiple stations based on time-continuous wind speed data is specifically as follows:

[0021] The optimal marginal distribution of wind speed distribution in the two places is found, and the spatial correlation of wind speed scenes between the two places is analyzed by the Frank-Copula model to obtain the output parameters of the Frank-Copula model. The output parameters are decomposed by the joint cumulative distribution function to obtain the wind speed data of multiple stations.

[0022] Preferably, the Frank-Copula model is expressed as follows:

[0023]

[0024] Among them, C θ (u,v) is the joint distribution function of the distribution function u of variable 1 and the distribution function v of variable 2, θ is the Copula parameter, e -θu is the exponential term of the distribution function u, e -θv is the exponential term of the distribution function v, e -θ is the exponential term of the copula parameter as variable, u is the distribution function of variable 1, and v is the distribution function of variable 2.

[0025] Preferably, the wind power output data is obtained based on the wind speed data of multiple stations to realize the prediction of wind power output of multiple stations under extreme weather conditions, specifically: the wind power output data is obtained based on the wind speed data of multiple stations, that is, the power of the wind turbine generator, and the power of the wind turbine generator is obtained to realize the prediction of annual wind power output of multiple stations under extreme weather conditions;

[0026]

[0027] Among them, p w is the power of the wind turbine, ρ is the air density, R is the blade radius of the wind turbine, K is the wind energy utilization coefficient of the wind turbine, and v h is the wind speed captured by the wind turbine. v 10 is the wind speed at a height of 10 m above the ground, h is the hub height of the wind turbine, m c is the coefficient of friction.

[0028] The present invention proposes a multi-station annual wind power output scenario generation system, comprising:

[0029] A model building module, wherein the model building module is used to determine the influencing factors of extreme weather on wind power, establish an extreme wind speed time model according to the influencing factors, obtain discrete extreme wind speed data based on the extreme wind speed time model, and insert the discrete extreme wind speed data into an annual time series;

[0030] A data acquisition module, wherein the data acquisition module is used to process the discrete extreme wind speed data of the annual time series according to the Gaussian process regression method to obtain time-continuous wind speed data;

[0031] A data processing module is used to obtain wind speed data of multiple stations based on time-continuous wind speed data, obtain wind power output data based on the wind speed data of multiple stations, and realize annual wind power output prediction of multiple stations under extreme weather conditions.

[0032] A terminal device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a method for generating a multi-station annual wind power output scenario when executing the computer program.

[0033] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for generating a multi-station annual wind power output scenario.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention proposes a method for generating annual wind power output scenarios for multiple stations. The method first determines the specific impact of extreme meteorological events (such as cold waves, sandstorms, etc.) on wind speed by analyzing their spatiotemporal distribution characteristics, frequency, intensity and other information. Then, a specific area is selected, and a mathematical model of wind speed changes is constructed using these extreme meteorological event data, which is appropriately inserted into the annual time series; Gaussian process regression and Copula function technology are used to capture the spatiotemporal correlation of wind speed and generate annual wind speed scenarios for multiple stations. Finally, with the help of a physical mechanism model, these wind speed scenarios are converted into corresponding annual wind power output scenarios. The present invention considers the impact of extreme wind speed events on wind speed and the spatiotemporal correlation of wind speed scenarios, generates annual wind speed scenarios for multiple stations, and then maps them to annual wind power output scenarios; the generated scenarios can adjust their extreme degree by changing the types and numbers of extreme meteorological events inserted into the annual time series.

[0036] The invention proposes a multi-station annual wind power output scenario generation system, which divides the system into a model building module, a data acquisition module and a data processing module, obtains wind power output data based on wind speed data of multiple stations, and realizes the prediction of wind power output of multiple stations under extreme weather conditions. The modular concept is adopted to make each module independent of each other, which is convenient for unified management of each module. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 This is a flow chart of the method for generating multi-station annual wind power output scenarios of the present invention.

[0039] Figure 2 Schematic diagram of inserting annual time series of extreme meteorological events in the present invention.

[0040] Figure 3 A comparison curve chart of annual wind speed scenario and historical wind speed scenario is generated for the GPR of the present invention.

[0041] Figure 4 A system diagram is generated for the multi-station annual wind power output scenario of the present invention.

[0042] Figure 5 The figure is a schematic structural diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0044] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0046] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0047] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0048] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0050] With the widespread application of new energy and its susceptibility to weather, the stable operation of new power systems faces challenges from meteorological factors, especially extreme meteorological events. To this end, the present invention proposes a method for generating annual wind power output scenarios for multiple stations, such as Figure 1 As shown, the following steps are included:

[0051] S1. Determine the influencing factors of extreme weather on wind power, establish an extreme wind speed time model based on the influencing factors, obtain discrete extreme wind speed data based on the extreme wind speed time model, and insert the discrete extreme wind speed data into the annual time series;

[0052] The determining of the influence factors of extreme weather on wind power and establishing the extreme wind speed time model according to the influence factors of extreme weather on wind power are specifically as follows:

[0053]

[0054] Where f(x) is a polynomial function, a i is the coefficient of the i-th term, is the i-th item of order n, J is the objective function, i.e., the error between the modeled wind speed data and the actual wind speed data, f(x i ) is the polynomial function value corresponding to the i-th data, y i is the actual value corresponding to the i-th data.

[0055] S2, processing the discrete extreme wind speed data of the annual time series according to the Gaussian process regression method to obtain time-continuous wind speed data;

[0056] The discrete extreme wind speed data of the annual time series is processed according to the Gaussian process regression method to obtain the time-continuous wind speed data, specifically:

[0057] The joint prior distribution between the observed and predicted values ​​is established through the discrete extreme wind speed data. Based on the annual time series of inserted extreme meteorological events, the posterior distribution is calculated through the joint prior distribution to obtain time-continuous wind speed data.

[0058] The joint prior distribution is expressed as follows:

[0059]

[0060] The posterior distribution is expressed as follows:

[0061]

[0062] Among them, y is the observation value corresponding to the model training set input, that is, the observed wind speed value, and f * is the predicted value of the test point passing through the model, that is, the predicted wind speed value, K is the covariance matrix, X is the input of the model training set, that is, the time point, is the variance of the distribution satisfied by the noise, I n is the n-dimensional identity matrix, x * is the test point, k is the covariance between the test point and itself, N(·) represents the normal distribution, is the mean of the predicted values, and cov(·) represents the covariance function.

[0063] S3. Obtain wind speed data of multiple stations based on time-continuous wind speed data, and obtain wind power output data based on wind speed data of multiple stations to achieve annual wind power output prediction of multiple stations under extreme weather conditions.

[0064] The method of obtaining wind speed data of multiple stations based on time-continuous wind speed data is specifically as follows:

[0065] The optimal marginal distribution of wind speed distribution in the two places is found, and the spatial correlation of wind speed scenes between the two places is analyzed by the Frank-Copula model to obtain the output parameters of the Frank-Copula model. The output parameters are decomposed by the joint cumulative distribution function to obtain the wind speed data of multiple stations.

[0066] The Frank-Copula model is expressed as follows:

[0067]

[0068] Among them, C θ (u,v) is the joint distribution function of the distribution function u of variable 1 and the distribution function v of variable 2, θ is the Copula parameter, e -θu is the exponential term of the distribution function u, e -θv is the exponential term of the distribution function v, e -θ is the exponential term of the copula parameter as variable, u is the distribution function of variable 1, and v is the distribution function of variable 2.

[0069] The wind power output data is obtained based on the wind speed data of multiple stations to realize the prediction of wind power output of multiple stations under extreme weather conditions. Specifically, the wind power output data is obtained based on the wind speed data of multiple stations, that is, the power of the wind turbine generator, and the power of the wind turbine generator is obtained to realize the prediction of annual wind power output of multiple stations under extreme weather conditions;

[0070]

[0071] Among them, p w is the power of the wind turbine, ρ is the air density, R is the blade radius of the wind turbine, K is the wind energy utilization coefficient of the wind turbine, and v h is the wind speed captured by the wind turbine. v 10 is the wind speed at a height of 10 m above the ground, h is the hub height of the wind turbine, m c is the coefficient of friction.

[0072] The following is a detailed description of the method. The steps are as follows:

[0073] Step 1: Analyze the temporal and spatial distribution characteristics of extreme meteorological events (such as cold waves, sandstorms, etc.), model them according to their impact on wind speed, and insert extreme meteorological events into the annual time series;

[0074] Step 2: Use historical wind speed data to optimize the parameters of the RBFKernel and ScaleKernel kernel functions, and generate a complete annual wind speed scenario through Gaussian process regression model fitting;

[0075] Step 3: Based on the generated annual wind speed scenario, the annual wind speed scenario of multiple stations is obtained through Frank-Copula;

[0076] Step 4: Map the annual wind speed scenario to the annual wind power output scenario through the wind speed-wind power output physical mechanism model.

[0077] Step 1 The specific steps are as follows:

[0078] Analyze the temporal and spatial distribution characteristics of extreme meteorological events (such as cold waves, sandstorms, etc.). Taking the northwest region of my country as an example, the local area often encounters extreme weather, such as strong winds, cold waves and sandstorms. When the above extreme meteorological events occur, they will affect the size of the wind speed. According to the location and time of the extreme wind speed event, the corresponding historical wind speed data is selected to perform polynomial fitting through the least squares method to obtain the corresponding extreme wind speed event modeling, where the polynomial f(x) and the objective function J are shown in the following formula:

[0079]

[0080] After obtaining the modeling of various extreme meteorological events, various extreme meteorological events are appropriately inserted into the annual time series according to the local meteorological characteristics, as shown in the schematic diagram Figure 2 shown.

[0081] Step 2 The specific steps are as follows:

[0082] Due to the temporal correlation of wind speed scenes, that is, the wind speed at a certain time node is related to the wind speed of its adjacent nodes, the covariance function is considered to describe its temporal correlation, so GPR is used as the generation model of wind speed scenes. Gaussian Process (GP) is a set of any finite random variables with joint Gaussian distribution, and its properties are completely determined by the mean function m(x) and the covariance function k(x,x'):

[0083]

[0084] x is a certain point in time, f(x) is its function value, E[f(x)] is the mean of the function value, and the same is true for x'; E[(f(x)-m(x))(f(x')-m(x'))] is the covariance form of x and x', m(x) is the mean function, and k(x,x') is the covariance function.

[0085] GPR is a non-parametric model based on kernel functions. The principle of generating scenes through GPR is as follows:

[0086] For regression problems, the following form is generally considered:

[0087] y=f(x)+ε

[0088] Where x is the input vector, f(x) is its corresponding function value, and y is the observed value after adding noise. If we assume that the noise N(·) represents the normal distribution, is the variance of the normal distribution, then we can get the observed value y and the predicted value f * The joint prior distribution of is as follows:

[0089]

[0090] where K(X,X)=(k ij ) n×n is a symmetric positive definite covariance matrix of order n×n, with matrix element k ij = k(x i ,x j ) describes x i and x j The correlation between K(X,x * )=K(x * ,X) T is the input X of the training set and the test point x * n×1 order covariance matrix between; k(x * ,x * ) is the test point x * Its covariance, I n is an n-dimensional unit matrix. The predicted value f is calculated based on its joint prior distribution * The posterior distribution of is as follows:

[0091]

[0092] Its mean and covariance satisfy the following formula:

[0093]

[0094] In the formula, is the mean of the predicted values, cov(f * ) is the covariance function of the predicted value, K(X,X)=(k ij ) n×n is a symmetric positive definite covariance matrix of order n×n, with matrix element k ij = k(x i ,x j ) describes x i and x j The correlation between K(X,x * )=K(x * ,X) T is the input X of the training set and the test point x * n×1 order covariance matrix between; k(x * ,x *) is the test point x * Its covariance with itself, is the variance of the normal distribution satisfied by the noise, I n is the n-dimensional identity matrix and y is the observed value.

[0095] The covariance function in the above formula selects the combination of two covariance functions, ScaleKernel and RBFKernel in gpytorch.

[0096]

[0097] In the formula, k scaled represents the ScaleKernel covariance function, θ scale is the hyperparameter of ScaleKernel, k orig is the basic covariance function in ScaleKernel, and RBFKernael is selected as the basic covariance function here; k RBF represents the RBFKernel covariance function, x1 and x2 are two input vectors, θ l is the hyperparameter of RBFKernel, also called the length scale parameter, exp is the exponential function, (x1-x2) T (x1-x2) represents the expression of the dot product of the vector. The two covariance functions are combined to obtain the total covariance function of the Gaussian process regression model. First, the joint joint prior distribution between the observed value and the predicted value is established through the historical wind speed data, and the hyperparameters of the total covariance function of the GPR model are optimized; then, based on the annual time series of the extreme meteorological events inserted, its posterior distribution is calculated through the GPR model to obtain the time-continuous wind speed data, that is, the complete annual wind speed scenario.

[0098] Step 3 The specific steps are as follows:

[0099] The geomorphic features within a certain range do not vary much, so the wind speed scenes within a limited area are spatially correlated. In order to reasonably describe the spatial correlation of wind speed scenes in multiple locations of new energy stations, the present invention uses the Copula function to capture the wind speed laws of multiple locations, connecting the joint distribution function of the wind speed scenes of the two locations and their respective marginal distributions. The Copula function is a method for dealing with the correlation problem of random variables in statistics. According to Sklar's theorem, let H be an n-dimensional random variable X1, X2, ..., X n The joint distribution function of and its corresponding marginal distributions are F1, F2, …, F n , then there exists an n-dimensional Copula function C such that for all (x1,x2,…,x n )∈[-∞,+∞] n ,have:

[0100] H(x1,x2,...,x n )=C(F1(x1),F2(x2),...,F n (x n ))

[0101] Corollary from Sklar's theorem: Let the random variables X1, X2, ..., X n The distribution functions F1(x1), F2(x2),…, F n (x n ) are continuous, U1=F1(x1),U2=F2(x2),…,U n =F n (x n ) all obey the uniform distribution on [0,1], then the random variables U1,U2,…,U n The joint distribution of is:

[0102]

[0103] where F i -1 (u i ) is F i (x i ) is the pseudo-inverse function of .

[0104] When n=2, C is a binary Copula function, and H(x1,x2) is a joint distribution function with marginal distributions F(x1) and G(x2). Binary Copula functions are generally divided into two categories, namely the elliptic function family and the Archimedean function family. Among them, the Gaussian-Copula function and the t-Copula function belong to the elliptic function family, while the Gumbel-Copula function, Clayton-Copula function and Frank-Copula function belong to the Archimedean function family. According to the peak and thick tail characteristics of wind speed data distribution, this paper uses the Frank-Copula function, and its formula is as follows:

[0105]

[0106] In the formula, θ is the model parameter of Frank-Copula. The Copula function is used to generate the wind speed scenes of the two places. The specific steps are as follows: find the optimal marginal distribution for the wind speed distribution of the two places; analyze the spatial correlation of the wind speed scenes between the two places through the Frank-Copula model to obtain the model parameters; use the conditional probability distribution to decompose the joint cumulative distribution function of the multi-dimensional variables to obtain the wind speed data of multiple stations, that is, the wind speed scenes of multiple stations.

[0107] Step 4 The specific steps are as follows:

[0108] The power of a wind turbine is related to factors such as wind speed, blade area, and hub height. For a specific wind turbine, its parameters such as blade area and hub height are fixed, so the power of the wind turbine is mainly related to the wind speed, and can generally be considered to be proportional to the cube of the wind speed. The relationship between the wind turbine power and the wind speed captured by the wind turbine is as follows: when the wind speed is greater than the cut-in wind speed of the wind turbine, the wind turbine starts to generate electricity; when the wind speed is greater than the rated wind speed and less than the cut-out wind speed, the wind turbine reaches the rated power; when the wind speed is less than the cut-in wind speed or greater than the cut-out wind speed, the wind turbine stops generating electricity. The relationship between wind power output and wind speed can be described by a mathematical relationship:

[0109]

[0110] p w is the fan output, ρ is the air density, R is the fan blade radius, K is the fan wind energy utilization coefficient, v h is the wind speed captured by the wind turbine. Since the hub height of the wind turbine cannot be ignored, it is necessary to convert the near-ground wind speed. 10 is the wind speed at a height of 10 m above the ground, h is the hub height of the wind turbine, m c is the coefficient of friction.

[0111] According to the extreme event statistics of historical wind speed scenarios, the inserted event settings are made when generating the reconstructed wind speed scenarios. The types and numbers of extreme meteorological events inserted in the annual time series are shown in Table 1. In order to verify that the reconstructed meteorological scenarios meet the meteorological characteristics and whether their extreme degree increases with the increase in the frequency of extreme meteorological events, the number of extreme meteorological events inserted in the reconstructed meteorological scenarios is increased.

[0112] Table 1 Statistics of extreme events in wind speed scenarios

[0113]

[0114] Based on the annual time series of extreme meteorological events inserted in step 1, the annual wind speed scenario is generated, such as Figure 3 As shown, from Figure 3 It can be seen that the trend of the generated wind speed scenario is roughly the same as that of the historical wind speed scenario. The statistical index comparison of the two wind speed scenarios is shown in Table 2. The table shows that the reconstructed wind speed scenario is higher than the historical wind speed scenario in the set indicators. In the historical annual wind speed scenario, strong winds caused wind turbine shutdowns 333 times, while in the reconstructed wind speed scenario, it occurred 484 times. The results show that the extreme degree of the generated wind speed scenario can be adjusted by changing the number or type of inserted extreme wind speed events:

[0115] Table 2 Statistical indicators of two wind speed scenarios

[0116]

[0117] The method first determines the specific impact of extreme meteorological events (such as cold waves, sandstorms, etc.) on wind speed by analyzing their spatiotemporal distribution characteristics, frequency, and intensity. Then, a specific area is selected, and a mathematical model of wind speed change is constructed using these extreme meteorological event data, which is appropriately inserted into the annual time series. Gaussian Process Regression (GPR) and Copula function technology are used to capture the spatiotemporal correlation of wind speed and generate multi-station annual wind speed scenarios. With the help of the physical mechanism model, these wind speed scenarios are converted into corresponding annual wind power output scenarios.

[0118] Example 2

[0119] The present invention proposes a multi-station annual wind power output scenario generation system, such as Figure 4 As shown, including:

[0120] A model building module, wherein the model building module is used to determine the influencing factors of extreme weather on wind power, establish an extreme wind speed time model according to the influencing factors, obtain discrete extreme wind speed data based on the extreme wind speed time model, and insert the discrete extreme wind speed data into an annual time series;

[0121] The determining of the influence factors of extreme weather on wind power and establishing the extreme wind speed time model according to the influence factors of extreme weather on wind power are specifically as follows:

[0122]

[0123] Where f(x) is a polynomial function, a i is the coefficient of the i-th term, is the i-th item of order n, J is the objective function, i.e., the error between the modeled wind speed data and the actual wind speed data, f(x i ) is the polynomial function value corresponding to the i-th data, y i is the actual value corresponding to the i-th data.

[0124] A data acquisition module, wherein the data acquisition module is used to process the discrete extreme wind speed data of the annual time series according to the Gaussian process regression method to obtain time-continuous wind speed data;

[0125] The discrete extreme wind speed data of the annual time series is processed according to the Gaussian process regression method to obtain the time-continuous wind speed data, specifically:

[0126] The joint prior distribution between the observed and predicted values ​​is established through the discrete extreme wind speed data. Based on the annual time series of inserted extreme meteorological events, the posterior distribution is calculated through the joint prior distribution to obtain time-continuous wind speed data.

[0127] The joint prior distribution is expressed as follows:

[0128]

[0129] The posterior distribution is expressed as follows:

[0130]

[0131] Among them, y is the observation value corresponding to the model training set input, that is, the observed wind speed value, and f * is the predicted value of the test point passing through the model, that is, the predicted wind speed value, K is the covariance matrix, X is the input of the model training set, that is, the time point, is the variance of the distribution satisfied by the noise, I n is the n-dimensional identity matrix, x * is the test point, k is the covariance between the test point and itself, N(·) represents the normal distribution, is the mean of the predicted values, and cov(·) represents the covariance function.

[0132] A data processing module is used to obtain wind speed data of multiple stations based on time-continuous wind speed data, obtain wind power output data based on the wind speed data of multiple stations, and realize annual wind power output prediction of multiple stations under extreme weather conditions.

[0133] The method of obtaining wind speed data of multiple stations based on time-continuous wind speed data is specifically as follows:

[0134] The optimal marginal distribution of wind speed distribution in the two places is found, and the spatial correlation of wind speed scenes between the two places is analyzed by the Frank-Copula model to obtain the output parameters of the Frank-Copula model. The output parameters are decomposed by the joint cumulative distribution function to obtain the wind speed data of multiple stations.

[0135] The Frank-Copula model is expressed as follows:

[0136]

[0137] Among them, C θ (u,v) is the joint distribution function of the distribution function u of variable 1 and the distribution function v of variable 2, θ is the Copula parameter, e -θu is the exponential term of the distribution function u, e -θv is the exponential term of the distribution function v, e -θ is the exponential term of the copula parameter as variable, u is the distribution function of variable 1, and v is the distribution function of variable 2.

[0138] The wind power output data is obtained based on the wind speed data of multiple stations to realize the prediction of wind power output of multiple stations under extreme weather conditions. Specifically, the wind power output data is obtained based on the wind speed data of multiple stations, that is, the power of the wind turbine generator, and the power of the wind turbine generator is obtained to realize the prediction of annual wind power output of multiple stations under extreme weather conditions;

[0139]

[0140] Among them, p w is the power of the wind turbine, ρ is the air density, R is the blade radius of the wind turbine, K is the wind energy utilization coefficient of the wind turbine, and v h is the wind speed captured by the wind turbine. v 10 is the wind speed at a height of 10 m above the ground, h is the hub height of the wind turbine, m c is the coefficient of friction.

[0141] Example 3

[0142] See also Figure 5 As shown, the present invention also provides an electronic device 100 for generating a multi-station annual wind power output scenario; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0143] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the method for generating the multi-station annual wind power output scenario described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0144] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0145] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a method for generating a multi-station annual wind power output scenario, and the processor 102 can execute the plurality of instructions to implement:

[0146] Determine the influencing factors of extreme weather on wind power, establish an extreme wind speed time model based on the influencing factors, obtain discrete extreme wind speed data based on the extreme wind speed time model, and insert the discrete extreme wind speed data into the annual time series;

[0147] The discrete extreme wind speed data of the annual time series are processed according to the Gaussian process regression method to obtain the time-continuous wind speed data;

[0148] Based on the time-continuous wind speed data, the wind speed data of multiple stations are obtained, and based on the wind speed data of multiple stations, the wind power output data is obtained to realize the annual wind power output prediction of multiple stations under extreme weather conditions.

[0149] Example 4

[0150] If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0151] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may 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.

[0152] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes 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 a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0153] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0154] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for generating multi-station annual wind power output scenarios, characterized in that: include: Determine the influencing factors of extreme weather on wind power, establish an extreme wind speed time model based on the influencing factors, obtain discrete extreme wind speed data based on the extreme wind speed time model, and insert the discrete extreme wind speed data into the annual time series; The discrete extreme wind speed data of the annual time series are processed according to the Gaussian process regression method to obtain the time-continuous wind speed data; Based on the time-continuous wind speed data, the wind speed data of multiple stations are obtained, and based on the wind speed data of multiple stations, the wind power output data is obtained to realize the annual wind power output prediction of multiple stations under extreme weather conditions.

2. The method for generating multi-station annual wind power output scenarios according to claim 1, characterized in that: The determining of the influence factors of extreme weather on wind power and establishing the extreme wind speed time model according to the influence factors of extreme weather on wind power are specifically as follows: Where f(x) is a polynomial function, a i is the coefficient of the i-th term, is the i-th term of order n, J is the objective function, f(x i ) is the polynomial function value corresponding to the i-th data, y i is the actual value corresponding to the i-th data.

3. The method for generating multi-station annual wind power output scenarios according to claim 1, characterized in that: The discrete extreme wind speed data of the annual time series is processed according to the Gaussian process regression method to obtain the time-continuous wind speed data, specifically: The joint prior distribution between the observed and predicted values ​​is established through the discrete extreme wind speed data. Based on the annual time series of inserted extreme meteorological events, the posterior distribution is calculated through the joint prior distribution to obtain time-continuous wind speed data.

4. The method for generating multi-station annual wind power output scenarios according to claim 3, characterized in that: The joint prior distribution is expressed as follows: The posterior distribution is expressed as follows: Among them, y is the observation value corresponding to the model training set input, that is, the observed wind speed value, and f * is the predicted value of the test point passing through the model, that is, the predicted wind speed value, K is the covariance matrix, X is the input of the model training set, that is, the time point, is the variance of the distribution satisfied by the noise, I n is the n-dimensional identity matrix, x * is the test point, k is the covariance between the test point and itself, N(·) represents the normal distribution, is the mean of the predicted values, and cov(·) represents the covariance function.

5. The method for generating multi-station annual wind power output scenarios according to claim 1, characterized in that: The method of obtaining wind speed data of multiple stations based on time-continuous wind speed data is specifically as follows: The optimal marginal distribution of wind speed distribution in the two places is found, and the spatial correlation of wind speed scenes between the two places is analyzed by the Frank-Copula model to obtain the output parameters of the Frank-Copula model. The output parameters are decomposed by the joint cumulative distribution function to obtain the wind speed data of multiple stations.

6. The method for generating multi-station annual wind power output scenarios according to claim 5, characterized in that: The Frank-Copula model is expressed as follows: Among them, C θ (u,v) is the joint distribution function of the distribution function u of variable 1 and the distribution function v of variable 2, θ is the Copula parameter, e -θu is the exponential term of the distribution function u, e -θv is the exponential term of the distribution function v, e -θ is the exponential term of the copula parameter as variable, u is the distribution function of variable 1, and v is the distribution function of variable 2.

7. The method for generating multi-station annual wind power output scenarios according to claim 1, characterized in that: The wind power output data is obtained based on the wind speed data of multiple stations to realize the prediction of wind power output of multiple stations under extreme weather conditions. Specifically, the wind power output data is obtained based on the wind speed data of multiple stations, that is, the power of the wind turbine generator, and the power of the wind turbine generator is obtained to realize the prediction of annual wind power output of multiple stations under extreme weather conditions; Among them, p w is the power of the wind turbine, ρ is the air density, R is the blade radius of the wind turbine, K is the wind energy utilization coefficient of the wind turbine, and v h is the wind speed captured by the wind turbine. v 10 is the wind speed at a height of 10 m above the ground, h is the hub height of the wind turbine, m c is the coefficient of friction.

8. A multi-station annual wind power output scenario generation system, characterized in that: include: A model building module, wherein the model building module is used to determine the influencing factors of extreme weather on wind power, establish an extreme wind speed time model according to the influencing factors, obtain discrete extreme wind speed data based on the extreme wind speed time model, and insert the discrete extreme wind speed data into an annual time series; A data acquisition module, wherein the data acquisition module is used to process the discrete extreme wind speed data of the annual time series according to the Gaussian process regression method to obtain time-continuous wind speed data; A data processing module is used to obtain wind speed data of multiple stations based on time-continuous wind speed data, obtain wind power output data based on the wind speed data of multiple stations, and realize annual wind power output prediction of multiple stations under extreme weather conditions.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for generating a multi-station annual wind power output scenario as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for generating a multi-station annual wind power output scenario are implemented as described in any one of claims 1 to 7.

Images