Wind power fluctuation description optimization method and system

Abstract

The invention discloses a wind power fluctuation description optimization method and system, and the method comprises the steps: obtaining wind power data outputted by a wind power plant, and calculating the min-level component of the wind power data; based on the min-level component of the wind power data, a wind power fluctuation model is established, and the wind power fluctuation model takes a model parameter value range as a constraint condition and takes a minimum error of predicted wind power fluctuation and actual wind power fluctuation as a target function; and solving the wind power fluctuation model based on a whale optimization algorithm improved by a hybrid greedy selection strategy and a lens imaging reverse learning strategy, selecting an optimal fitting result by using a goodness-of-fit test index of the model, and taking a model parameter corresponding to the optimal fitting result as a final wind power fluctuation description scheme. According to the method, the implementation difficulty and actual requirements of the method are comprehensively considered, the calculation process is simple and convenient, the precision is higher, the stability is better, the cost is low, and the engineering practical value is higher.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to a method and system for optimizing wind power fluctuation description. Background Art

[0002] With the gradual depletion of fossil energy and the intensification of problems such as climate change, the status of renewable energy has become increasingly important. Wind energy is one of the fastest growing clean energy sources in the past decade. As of 2022, the global cumulative installed capacity of wind power has reached 906GW, an increase of 68.5GW compared with 2021, and 37.8 times that of 21 years ago. As the world's largest wind energy market, China's wind power installed capacity accounts for 40.28% of the global total. Although wind energy has many advantages, with its large-scale integration into the power grid, its randomness and intermittency will have an impact on the stable operation of the power grid. Therefore, it is particularly important to accurately describe the fluctuation characteristics of wind power. The accurate description of wind power fluctuations can not only improve the stable operation of the power grid, but also has important guiding significance for the daily dispatching and planning of the power system.

[0003] Existing studies on wind power fluctuation characteristics based on probability density function method have achieved many research results, most of which select the probability density distribution function with the best fitting effect based on the wind power fluctuation index, but its fitting effect is also limited by the subjective classification of the index and the type of the selected distribution function. In addition, the method for obtaining the unknown parameters of the probability density function is still single and the effect is not good. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method and system for optimizing wind power fluctuation description to solve the problems mentioned in the background technology.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a method for optimizing wind power fluctuation description, comprising:

[0009] Obtaining wind power data output by the wind farm, and calculating the min-level component of the wind power data;

[0010] Based on the min-level component of the wind power data, a wind power fluctuation model is established, wherein the wind power fluctuation model takes the range of model parameter values ​​as a constraint condition and takes the minimization error between the predicted wind power fluctuation and the actual wind power fluctuation as an objective function;

[0011] The wind power fluctuation model is solved by an improved whale optimization algorithm based on a hybrid greedy selection strategy and a lens imaging reverse learning strategy, and the optimal fitting result is selected using the goodness-of-fit test index of the model, and the model parameters corresponding to the optimal fitting result are used as the final wind power fluctuation description scheme.

[0012] As a preferred solution of the wind power fluctuation description optimization method described in the present invention, wherein: calculating the min-level component of the wind power data includes: calculating the min-level component of the wind power data using the sliding average method according to the extracted wind power historical data, expressed as:

[0013]

[0014] Among them, f tLs (x) is the probability density function of t Location-scale distribution, Γ(·) is the gamma function, μ, σ, v are the location parameter, scale parameter and shape parameter of the probability density function of t Location-scale distribution, N is the length of the sliding average period and N is an even number, P ft is the continuous component of wind power, P t is the wind power value of the wind farm at time t, P mt is the min-level component of wind power, that is, the variation superimposed on the continuous component, and M is the total number of measured wind power data.

[0015] As a preferred solution of the wind power fluctuation description optimization method of the present invention, wherein: based on the min-level component of the wind power data, establishing a wind power fluctuation model includes:

[0016] The objective function describing wind power fluctuation is expressed as:

[0017]

[0018] Among them, p i is the measured wind power fluctuation frequency, f PDF is the probability density function used for fitting, Ψ is all the parameters to be solved for different distribution functions, i is the time interval, v i are the shape parameters of different distribution functions;

[0019] The model parameter range constraints are expressed as follows: the location parameter, scale parameter, and shape parameter of the location-scale distribution probability density function are all no less than 0 and no greater than 30.

[0020] As a preferred solution of the wind power fluctuation description optimization method described in the present invention, the whale optimization algorithm improved based on the hybrid greedy selection strategy and the lens imaging reverse learning strategy is used to solve the wind power fluctuation model, including:

[0021] Initialize each individual according to the set population size;

[0022] Use the three position update methods of the whale optimization algorithm to update the position of each individual;

[0023] The reverse point position of each individual is calculated through the lens imaging reverse learning strategy;

[0024] If each individual and its reverse point meet the constraint conditions, the individuals that meet the constraint conditions will be added to the offspring population, and if they do not meet the constraint conditions, they will be pulled back to the boundary;

[0025] Calculate the fitness value of each individual and its reverse point according to the objective function, and obtain the point with the optimal fitness value through a greedy selection strategy;

[0026] When the number of iterations reaches the maximum value, the optimal value and parameter results are output, otherwise the selection continues to be updated.

[0027] As a preferred solution of the wind power fluctuation description optimization method of the present invention, it also includes:

[0028] The position of the reverse point in the D-dimensional space is obtained by transformation:

[0029]

[0030] Among them, t is the current iteration number, l is the adaptive scaling factor, and U b and L b are the j-th dimension components of the upper and lower bounds of the decision variable, respectively, x j is the original position of the individual.

[0031] As a preferred solution of the wind power fluctuation description optimization method of the present invention, it also includes:

[0032] A greedy selection strategy is introduced, and the reverse solution is replaced only when its fitness value is better, which can be expressed as:

[0033]

[0034] Among them, x(t)′ is the position of the individual after the greedy algorithm selection.

[0035] As a preferred solution of the wind power fluctuation description optimization method described in the present invention, wherein: the best fitting result is selected by using the model's goodness of fit test index, and the model parameters corresponding to the best fitting result are used as the final wind power fluctuation description solution, including: using the determination coefficient R 2 The three goodness of fit test indicators of RMSE, mean absolute error (MAE) and root mean square error (RMSE) are used to select the optimal fitting result, which is expressed as:

[0036]

[0037]

[0038] in, is the average wind power fluctuation, n is the number of samples, is the calculated value of the probability density function, q i is the actual value of wind power fluctuation frequency.

[0039] In a second aspect, the present invention provides a wind power fluctuation description optimization system, comprising:

[0040] A data extraction module is used to obtain wind power data output by the wind farm and calculate the min-level component of the wind power data;

[0041] A model building module, used to build a wind power fluctuation model based on the min-level component of the wind power data, wherein the wind power fluctuation model uses the model parameter value range as a constraint condition and uses the minimization error between the predicted wind power fluctuation and the actual wind power fluctuation as an objective function;

[0042] The scheme determination module is used to solve the wind power fluctuation model based on the whale optimization algorithm improved by the hybrid greedy selection strategy and the lens imaging reverse learning strategy, and select the optimal fitting result by using the goodness of fit test index of the model, and use the model parameters corresponding to the optimal fitting result as the final wind power fluctuation description scheme.

[0043] In a third aspect, the present invention provides a computing device, comprising:

[0044] Memory and processor;

[0045] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the wind power fluctuation description optimization method are implemented.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the wind power fluctuation description optimization method.

[0047] Compared with the prior art, the present invention has the following beneficial effects: the present invention takes minimizing the difference between the actual wind power fluctuation frequency distribution and each probability density function as the objective function, takes the value range of the unknown parameters of the model as the constraint, and utilizes a whale optimization algorithm improved by a hybrid greedy selection strategy and a lens imaging reverse learning strategy to perform more accurate parameter identification on the model describing the wind power fluctuation, so as to obtain the parameters that best meet the actual wind power fluctuation; the present invention comprehensively considers the implementation difficulty and actual needs of the method, the calculation process is simple, the accuracy is higher, the stability is better, the cost is low, and it has high engineering practical value. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0049] Figure 1 A schematic diagram of a method flow of a wind power fluctuation description optimization method and system according to an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of a flow chart of wind power fluctuation model calculation of a wind power fluctuation description optimization method and system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0054] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0055] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0056] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, 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 also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication 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.

[0057] Example 1

[0058] Reference Figure 1-2 , is an embodiment of the present invention, which provides a method for optimizing wind power fluctuation description, including:

[0059] S1: Obtain wind power data output by the wind farm and calculate the min-level component of the wind power data;

[0060] It should be noted that the four functions selected in the embodiment of the present application are four comparative models optimized using intelligent algorithms. By calculating their unknown parameters through actual wind farm data and obtaining corresponding error evaluation indicators, the optimal model is selected to model the probability of wind power output fluctuations at the best; the four functions are:

[0061] (1)t Location-scale distribution probability density function is as follows:

[0062]

[0063] Where Γ(·) is the gamma function, μ, σ, and v are the location parameter, scale parameter, and shape parameter of the probability density function of the t Location-scale distribution, respectively.

[0064] (2) The probability density function formula of t distribution is as follows:

[0065]

[0066] Here, v1 is the shape parameter.

[0067] (3) The probability density function of the normal distribution is as follows:

[0068]

[0069] Here, μ represents the mean value and σ represents the standard deviation.

[0070] (4) The probability density function of the Logistic distribution is as follows:

[0071]

[0072] In the embodiment of the present application, calculating the min-level component of wind power data includes: calculating the min-level component of wind power data using a sliding average method according to the extracted wind power historical data, expressed as:

[0073]

[0074] Among them, f tLs (x) is the probability density function of t Location-scale distribution, Γ(·) is the gamma function, μ, σ, v are the location parameter, scale parameter and shape parameter of the probability density function of t Location-scale distribution, N is the length of the sliding average period and N is an even number, P ft is the continuous component of wind power, P t is the wind power value of the wind farm at time t, P mt is the min-level component of wind power, that is, the variation superimposed on the continuous component, and M is the total number of measured wind power data.

[0075] S2: Based on the min-level component of wind power data, a wind power fluctuation model is established. The wind power fluctuation model takes the range of model parameter values ​​as constraints and takes the minimization error between the predicted wind power fluctuation and the actual wind power fluctuation as the objective function;

[0076] In the embodiment of the present application, establishing a wind power fluctuation model based on the min-level component of wind power data includes:

[0077] The objective function describing wind power fluctuation is expressed as:

[0078]

[0079] Among them, p i is the measured wind power fluctuation frequency, f PDF is the probability density function used for fitting, Ψ is all the parameters to be solved for different distribution functions, i is the time interval, v i are the shape parameters of different distribution functions;

[0080] The model parameter range constraints are expressed as follows: the location parameter, scale parameter, and shape parameter of the location-scale distribution probability density function are all no less than 0 and no greater than 30.

[0081] It should be noted that in the embodiment of the present application, by considering the minimum difference between the actual wind power fluctuation frequency distribution and each probability density function as the objective function, and taking the value range of the unknown parameters of the model as a constraint, a whale optimization algorithm improved by a hybrid greedy selection strategy and a lens imaging reverse learning strategy is used to perform more accurate parameter identification of the model describing wind power fluctuations.

[0082] S3: The improved whale optimization algorithm based on the hybrid greedy selection strategy and the lens imaging reverse learning strategy is used to solve the wind power fluctuation model, and the best fitting result is selected using the model's goodness of fit test index, and the model parameters corresponding to the best fitting result are used as the final wind power fluctuation description scheme;

[0083] It should be noted that the hybrid greedy selection strategy and lens imaging reverse learning strategy to improve the whale optimization algorithm mainly introduces the greedy selection strategy and lens imaging reverse learning strategy on the existing whale optimization algorithm to perform more accurate parameter identification of the model describing wind power fluctuations.

[0084] In the standard WOA algorithm, assuming the number of whales is N and the search space is D, the position of the i-th whale is The algorithm consists of two steps: wrap-around predation and bubble net attack.

[0085] Surrounding predation: Assuming that the current optimal whale positioning is the prey point, then surround the entire whale group, its position update strategy is as follows:

[0086] X(t+1)=X * (t)-A|C×X * (t)+X(t)|

[0087] Among them, A and C are random coefficients with values ​​of [0,1]; t is the current iteration number, X(t) is the position vector of the whale at the tth iteration, and X * (t) is the optimal position vector of the whale at the tth iteration.

[0088] The calculation expressions of A and C are as follows:

[0089] A=2a×r1-a

[0090] C=2r2

[0091] a=2-2tT max

[0092] Among them, r1, r2 are random vectors with values ​​in [0,1], T max is the maximum number of iterations.

[0093] The bubble net attack includes a shrinking circling mechanism and a spiral positioning; shrinking encirclement mechanism: when A = [-1,1], the whale's search location is the location of the object, which means that it is approaching the object. On the contrary, the whale will avoid the prey; spiral update mechanism: first estimate the distance between the prey, then start circling, the update formula is:

[0094] X(t+1)=D′×e bl ×cos(2πl)+X * (t)

[0095] Where D' represents the distance between the current best position and the prey, D' = |X * (t)-X(t)|; l represents a random number between [-1,1], and b is the logarithmic spiral shape parameter.

[0096] When hunting, humpback whales update their positions by spiral swimming and shrinking circling motion with a 50% chance, and the update formula is:

[0097]

[0098] Where p is a random number between [0,1].

[0099] Predation mechanism: When A>1 or A<-1, move away from prey and look for new prey. The update formula is:

[0100] X(t+1)=X rand -A|C×X rand (t)-X|

[0101] Among them, X rand Represents a randomly generated individual.

[0102] In the embodiment of the present application, the improved whale optimization algorithm based on the hybrid greedy selection strategy and the lens imaging reverse learning strategy solves the wind power fluctuation model including:

[0103] Initialize each individual according to the set population size;

[0104] Use the three position update methods of the whale optimization algorithm to update the position of each individual;

[0105] The reverse point position of each individual is calculated through the lens imaging reverse learning strategy;

[0106] If each individual and its reverse point meet the constraint conditions, the individuals that meet the constraint conditions will be added to the offspring population, and if they do not meet the constraint conditions, they will be pulled back to the boundary;

[0107] Calculate the fitness value of each individual and its reverse point according to the objective function, and obtain the point with the optimal fitness value through the greedy selection strategy;

[0108] When the number of iterations reaches the maximum value, the optimal value and parameter results are output, otherwise the selection continues to be updated.

[0109] It should be noted that the lens imaging principle can be realized by utilizing the refraction phenomenon of convex lenses and the rectilinear propagation of light. Applying this principle to the search phase of whale foraging behavior can help whales better escape from local optimal solutions and improve convergence accuracy and speed.

[0110] In the embodiment of the present application, it also includes:

[0111] The position of the reverse point in the D-dimensional space is obtained by transformation:

[0112]

[0113] Among them, t is the current iteration number, l is the adaptive scaling factor, and U b and L b are the j-th dimension components of the upper and lower bounds of the decision variable, respectively, x j is the original position of the individual.

[0114] It should be noted that the reverse solution generated by reverse learning of lens imaging is not necessarily better than the original solution of the original position update formula. Therefore, a greedy selection strategy is introduced to choose whether to replace the original solution with the reverse solution; that is, the reverse solution is only replaced when the fitness value is better.

[0115] In the embodiment of the present application, it also includes:

[0116] A greedy selection strategy is introduced, and the reverse solution is replaced only when its fitness value is better, which can be expressed as:

[0117]

[0118] Among them, x(t)′ is the position of the individual after the greedy algorithm selection.

[0119] In the embodiment of the present application, the best fitting result is selected by using the goodness of fit test index of the model, and the model parameters corresponding to the best fitting result are used as the final wind power fluctuation description scheme, including: using the determination coefficient R 2 The three goodness of fit test indicators of RMSE, mean absolute error (MAE) and root mean square error (RMSE) are used to select the optimal fitting result, which is expressed as:

[0120]

[0121] in, is the average wind power fluctuation, n is the number of samples, is the calculated value of the probability density function, q i is the actual value of wind power fluctuation frequency.

[0122] The above is a schematic scheme of a wind power fluctuation description optimization method of this embodiment. It should be noted that the technical scheme of this wind power fluctuation description optimization system and the technical scheme of the above wind power fluctuation description optimization method belong to the same concept, and the details of the technical scheme of the wind power fluctuation description optimization system not described in detail in this embodiment can be referred to the description of the technical scheme of the above wind power fluctuation description optimization method.

[0123] In this embodiment, a wind power fluctuation description optimization system includes:

[0124] A data extraction module is used to obtain the wind power data output by the wind farm and calculate the min-level component of the wind power data;

[0125] The model building module is used to build a wind power fluctuation model based on the min-level component of wind power data. The wind power fluctuation model takes the range of model parameter values ​​as constraints and takes the minimization error between the predicted wind power fluctuation and the actual wind power fluctuation as the objective function;

[0126] The scheme determination module is used to solve the wind power fluctuation model based on the whale optimization algorithm improved by the hybrid greedy selection strategy and the lens imaging reverse learning strategy, and select the optimal fitting result using the model's goodness of fit test index, and use the model parameters corresponding to the optimal fitting result as the final wind power fluctuation description scheme.

[0127] This embodiment further provides a computing device, which is applicable to the case of the wind power fluctuation description optimization method, and includes:

[0128] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the wind power fluctuation description optimization method proposed in the above embodiment.

[0129] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for optimizing the description of wind power fluctuations proposed in the above embodiment is implemented.

[0130] The storage medium proposed in this embodiment and the method for optimizing wind power fluctuation description proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0131] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0132] Example 2

[0133] Referring to Tables 1 to 5, an embodiment of the present invention is shown. This embodiment is different from the first embodiment in that this embodiment verifies the beneficial effects of the present invention through specific examples.

[0134] In this embodiment, the actual output power of three wind farms in the northwest region is used. The installed capacity of wind farm A is 60MW, the installed capacity of wind farm B is 105MW, and the installed capacity of wind farm C is 210MW. The sampling interval is 15 minutes, and the data collection time is from 2019.10.30 to 2020.10.30, with a total of 35,000 data. The 15min component of the output power of the three wind farms was extracted using the sliding average method for the experiment. The relevant parameters of the original whale optimization algorithm are set as follows: the population size is set to 50, the number of iterations is set to 50 generations, the parameter b that controls the shape of the logarithmic spiral function is 1, and each algorithm is run independently 100 times.

[0135] The optimization results using the improved whale optimization algorithm of the present application and the traditional whale optimization algorithm are shown in Table 1, Table 2, and Table 3.

[0136] Table 1 Comparison between the improved whale optimization algorithm and the traditional whale optimization algorithm for the 15-min component of wind farm A

[0137]

[0138] Table 2 Comparison between the improved whale optimization algorithm and the traditional whale optimization algorithm for the 15-min component of wind farm B

[0139]

[0140] Table 3 Comparison between the improved whale optimization algorithm and the traditional whale optimization algorithm for the 15-min component of wind farm C

[0141]

[0142] In wind farm A, the three indicators of t Location-scale distribution of parameters obtained using the traditional whale optimization algorithm are: R 2 =0.9855, RMSE = 0.0054, MAE = 0.0021, and the three indicators of the mixed greedy selection strategy and lens imaging reverse learning strategy to improve the whale optimization algorithm are: R 2 =0.9885, RMSE = 0.0048, MAE = 0.0019. Compared with the traditional whale optimization algorithm, the improved whale optimization algorithm has a higher R 2 The difference between the two is more obvious for the normal distribution model, and the R of the improved whale optimization algorithm is 2 The accuracy of the improved whale optimization algorithm was improved by 0.0035, the RMSE was reduced by 0.0003, and the MAE was reduced by 0.0001. In addition, when using the traditional whale optimization algorithm to calculate the parameters of the normal distribution, fitting failures often occur, and the initial values ​​must be changed many times to obtain more ideal parameters. In other models, the accuracy of the improved whale optimization algorithm is improved to varying degrees compared with the fitting toolbox. The specific results are shown in Table 1.

[0143] The experimental conclusions of wind farms B and C are the same as those of wind farm A. The three indicators of each model of the whale optimization algorithm for estimating parameters using the hybrid greedy selection strategy and the lens imaging reverse learning strategy are better than the traditional whale optimization algorithm, and the optimization effect is obvious. The specific results are shown in Tables 2 and 3. The experiments of three wind farms show that compared with the traditional whale optimization algorithm, the hybrid greedy selection strategy and the lens imaging reverse learning strategy of the present application improve the whale optimization algorithm effectively improves the accuracy of parameter identification, and does not require the setting of initial values, which is simple and efficient.

[0144] The wind power fluctuation description optimization method of the improved whale optimization algorithm of this application is adopted, and the optimal parameter results of the four models are shown in Table 4 and Table 5:

[0145] Table 4 Parameters of four models calculated by the traditional whale optimization algorithm for the 15-min component

[0146]

[0147] Table 5 Four model parameters calculated by the improved whale optimization algorithm for the 15-min component

[0148]

[0149]

[0150] From the results after optimization, it can be seen that, in general, no matter which model, the performance of this application in the three wind farms is better than the original method, and the obtained parameters are more accurate. The whale optimization algorithm is improved by using the hybrid greedy selection strategy and the lens imaging reverse learning strategy to solve the wind power fluctuation model, which can improve the accuracy of the model's description of the actual wind power fluctuation, thereby obtaining the optimal wind power output fluctuation probability modeling, which has a certain guiding role in predicting wind power in actual engineering practice and reducing the impact of wind energy fluctuations on the power grid.

[0151] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing wind power fluctuation description, characterized in that: include: Obtaining wind power data output by the wind farm, and calculating the min-level component of the wind power data; Based on the min-level component of the wind power data, a wind power fluctuation model is established, wherein the wind power fluctuation model takes the range of model parameter values ​​as a constraint condition and takes the minimization error between the predicted wind power fluctuation and the actual wind power fluctuation as an objective function; The wind power fluctuation model is solved by an improved whale optimization algorithm based on a hybrid greedy selection strategy and a lens imaging reverse learning strategy, and the optimal fitting result is selected using the goodness-of-fit test index of the model, and the model parameters corresponding to the optimal fitting result are used as the final wind power fluctuation description scheme.

2. The method for optimizing wind power fluctuation description according to claim 1, characterized in that: Calculating the min-level component of the wind power data includes: calculating the min-level component of the wind power data using a sliding average method according to the extracted wind power historical data, expressed as: Among them, f tLs (x) is the probability density function of t Location-scale distribution, Γ(·) is the gamma function, μ, σ, v are the location parameter, scale parameter and shape parameter of the probability density function of t Location-scale distribution, N is the length of the sliding average period and N is an even number, P ft is the continuous component of wind power, P t is the wind power value of the wind farm at time t, P mt is the min-level component of wind power, that is, the variation superimposed on the continuous component, and M is the total number of measured wind power data.

3. The method for optimizing wind power fluctuation description according to claim 2, characterized in that: Based on the min-level component of the wind power data, establishing a wind power fluctuation model includes: The objective function describing wind power fluctuation is expressed as: Among them, p i is the measured wind power fluctuation frequency, f PDF is the probability density function used for fitting, Ψ is all the parameters to be solved for different distribution functions, i is the time interval, v i are the shape parameters of different distribution functions; The model parameter range constraints are expressed as follows: the location parameter, scale parameter, and shape parameter of the location-scale distribution probability density function are all no less than 0 and no greater than 30.

4. The method for optimizing wind power fluctuation description according to claim 3, characterized in that: The improved whale optimization algorithm based on the hybrid greedy selection strategy and the lens imaging reverse learning strategy is used to solve the wind power fluctuation model, including: Initialize each individual according to the set population size; Use the three position update methods of the whale optimization algorithm to update the position of each individual; The reverse point position of each individual is calculated through the lens imaging reverse learning strategy; If each individual and its reverse point meet the constraint conditions, the individuals that meet the constraint conditions will be added to the offspring population, and if they do not meet the constraint conditions, they will be pulled back to the boundary; Calculate the fitness value of each individual and its reverse point according to the objective function, and obtain the point with the optimal fitness value through a greedy selection strategy; When the number of iterations reaches the maximum value, the optimal value and parameter results are output, otherwise the selection continues to be updated.

5. The method for optimizing wind power fluctuation description according to claim 4, characterized in that: Also includes: The position of the reverse point in the D-dimensional space is obtained by transformation: Among them, t is the current iteration number, l is the adaptive scaling factor, and U b and L b are the j-th dimension components of the upper and lower bounds of the decision variable, respectively, x j is the original position of the individual.

6. The method for optimizing wind power fluctuation description according to claim 5, characterized in that: Also includes: A greedy selection strategy is introduced, and the reverse solution is replaced only when its fitness value is better, which can be expressed as: Among them, x(t)′ is the position of the individual after the greedy algorithm selection.

7. The method for optimizing wind power fluctuation description according to claim 6, characterized in that: The best fitting result is selected by using the model's goodness of fit test index, and the model parameters corresponding to the best fitting result are used as the final wind power fluctuation description scheme, including: using the determination coefficient R 2 The three goodness of fit test indicators of root mean square error (RMSE) and mean absolute error (MAE) are used to select the optimal fitting result, which is expressed as: in, is the average wind power fluctuation, n is the number of samples, is the calculated value of the probability density function, q i is the actual value of wind power fluctuation frequency.

8. A wind power fluctuation description optimization system, characterized in that: include: A data extraction module is used to obtain wind power data output by the wind farm and calculate the min-level component of the wind power data; A model building module, used to build a wind power fluctuation model based on the min-level component of the wind power data, wherein the wind power fluctuation model uses the model parameter value range as a constraint condition and uses the minimization error between the predicted wind power fluctuation and the actual wind power fluctuation as an objective function; The scheme determination module is used to solve the wind power fluctuation model based on the whale optimization algorithm improved by the hybrid greedy selection strategy and the lens imaging reverse learning strategy, and select the optimal fitting result by using the goodness of fit test index of the model, and use the model parameters corresponding to the optimal fitting result as the final wind power fluctuation description scheme.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the wind power fluctuation description optimization method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for optimizing wind power fluctuation description as claimed in any one of claims 1 to 7.

Images