Offshore wind power output prediction error calculation method and device, equipment and storage medium

Abstract

The invention discloses an offshore wind power output prediction error calculation method and device, equipment and a storage medium, which are used for solving the technical problem of low accuracy of offshore wind power output volatility analysis. The method comprises the following steps: acquiring wind power output data of a wind turbine generator of an offshore wind plant; an Ornstein-Uhlenbeck process of the wind power output data is constructed, and the Ornstein-Uhlenbeck process of the wind power output data is constructed; a stochastic differential equation of the Ornstein-Uhlenbeck process is constructed, and a stochastic differential equation of the Ornstein-Uhlenbeck process is constructed; constructing an optimal parameter estimation model of a stochastic differential equation optimized based on a least square method; solving the optimal parameter estimation model by adopting an improved genetic algorithm to obtain optimal parameters; optimizing the stochastic differential equation according to the optimal parameter to obtain an optimized stochastic differential equation; and calculating an offshore wind power output prediction error according to the optimized stochastic differential equation and the wind power output data.

Description

Technical Field

[0001] The present invention relates to the field of wind power output technology, and in particular to a method, device, equipment and storage medium for calculating offshore wind power output prediction errors. Background Art

[0002] The climate crisis and energy crisis are common challenges facing the world today. Wind power offers the advantages of widespread distribution, abundant resources, and zero pollution. Offshore wind energy resources are more abundant than onshore wind power, but offshore wind power exhibits significant randomness and volatility, as well as typical peak-shaving characteristics. The resulting mismatch between offshore wind power output and load demand is increasingly impacting the steady-state and dynamic operation of power systems, increasing the risk of unreliable power system dispatch. Summary of the Invention

[0003] The present invention provides a method, device, equipment and storage medium for calculating offshore wind power output prediction errors, which are used to solve the technical problem of low accuracy in offshore wind power output fluctuation analysis.

[0004] The present invention provides a method for calculating offshore wind power output prediction error, comprising:

[0005] Obtain wind power output data of wind turbines in offshore wind farms;

[0006] Constructing an Ornstein-Uhlenbeck process for the wind power output data;

[0007] Constructing a stochastic differential equation for the Ornstein-Uhlenbeck process;

[0008] Construct an optimal parameter estimation model for stochastic differential equations based on least squares optimization;

[0009] Using an improved genetic algorithm to solve the optimal parameter estimation model to obtain optimal parameters;

[0010] Optimizing the stochastic differential equation according to the optimal parameters to obtain an optimized stochastic differential equation;

[0011] An offshore wind power output prediction error is calculated based on the optimized stochastic differential equation and the wind power output data.

[0012] Optionally, the Ornstein-Uhlenbeck process describing the volatility of the wind power output data is as follows:

[0013]

[0014] in, is the predicted value of offshore wind power output, is the prediction error of offshore wind power output.

[0015] Optionally, the stochastic differential equation is as follows:

[0016]

[0017] in, is the prediction error of offshore wind power output at time t The time domain expression of It is Brownian motion, which is used to characterize random disturbances in the environment; is the prediction error In infinitesimal time intervals The instantaneous change in is the drift term of the equation, is the mean reversion rate, is the volatility parameter, It is an external unpredictable random disturbance.

[0018] Optionally, the step of using an improved genetic algorithm to solve the optimal parameter estimation model to obtain optimal parameters includes:

[0019] generating an initial population of the optimal parameter estimation model, wherein the initial population includes a plurality of individuals;

[0020] Calculating the fitness of each individual by a fitness function;

[0021] Performing selection, mutation and crossover operations on the individuals through a mutation rate function to generate new individuals;

[0022] Eliminating individuals whose fitness is lower than a preset threshold from the initial population, and adding the new individuals to the initial population to obtain a new population;

[0023] Determine whether the fitness function change of the best individual in the new population is within the preset range;

[0024] If not, return to the step of calculating the fitness of each individual using the fitness function;

[0025] If so, the optimal individual is output as the optimal parameter.

[0026] The present invention also provides an offshore wind power output prediction error calculation device, comprising:

[0027] A wind power output data acquisition module is used to obtain wind power output data of wind turbines in offshore wind farms;

[0028] An Ornstein-Uhlenbeck process construction module, used to construct the Ornstein-Uhlenbeck process of the wind power output data;

[0029] a stochastic differential equation building module for building the stochastic differential equation of the Ornstein-Uhlenbeck process;

[0030] Optimal parameter estimation model building module, used to build the optimal parameter estimation model of stochastic differential equations based on least squares optimization;

[0031] A solution module, configured to solve the optimal parameter estimation model using an improved genetic algorithm to obtain optimal parameters;

[0032] an optimization module, configured to optimize the stochastic differential equation according to the optimal parameters to obtain an optimized stochastic differential equation;

[0033] The offshore wind power output prediction error calculation module is used to calculate the offshore wind power output prediction error based on the optimized stochastic differential equation and the wind power output data.

[0034] Optionally, the Ornstein-Uhlenbeck process describing the volatility of the wind power output data is as follows:

[0035]

[0036] in, is the predicted value of offshore wind power output, is the prediction error of offshore wind power output.

[0037] Optionally, the stochastic differential equation is as follows:

[0038]

[0039] in, is the prediction error of offshore wind power output at time t The time domain expression of It is Brownian motion, which is used to characterize random disturbances in the environment; is the prediction error In infinitesimal time intervals The instantaneous change in is the drift term of the equation, is the mean reversion rate, is the volatility parameter, It is an external unpredictable random disturbance.

[0040] Optionally, the solution module includes:

[0041] A population initialization submodule, used to generate an initial population of the optimal parameter estimation model, wherein the initial population includes a plurality of individuals;

[0042] A fitness calculation submodule, used for calculating the fitness of each individual through a fitness function;

[0043] A new individual generation submodule is used to select, mutate and crossover the individuals through a mutation rate function to generate new individuals;

[0044] A population update submodule is used to remove individuals whose fitness is lower than a preset threshold from the initial population and add the new individuals into the initial population to obtain a new population;

[0045] The judgment submodule is used to judge whether the fitness function change of the optimal individual in the new population is within the preset range;

[0046] Return submodule, used to return to the fitness calculation submodule if no;

[0047] The optimal parameter output submodule is used to output the optimal individual as the optimal parameter if so.

[0048] The present invention further provides an electronic device, comprising a processor and a memory:

[0049] The memory is used to store program code and transmit the program code to the processor;

[0050] The processor is used to execute the offshore wind power output prediction error calculation method as described in any one of the above items according to the instructions in the program code.

[0051] The present invention also provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute the offshore wind power output prediction error calculation method as described in any one of the above items.

[0052] As can be seen from the above technical solutions, the present invention has the following advantages: The present invention discloses a method for calculating offshore wind power output prediction errors, and specifically discloses: obtaining wind power output data of wind turbines in offshore wind farms; constructing an Ornstein-Uhlenbeck process for the wind power output data; constructing a stochastic differential equation for the Ornstein-Uhlenbeck process; constructing an optimal parameter estimation model for the stochastic differential equation based on least squares optimization; using an improved genetic algorithm to solve the optimal parameter estimation model to obtain optimal parameters; optimizing the stochastic differential equation based on the optimal parameters to obtain an optimized stochastic differential equation; and calculating the offshore wind power output prediction error based on the optimized stochastic differential equation and the wind power output data. The present invention improves the accuracy and robustness of wind power prediction by introducing a random process model and an optimized parameter estimation method, thereby meeting the needs of offshore wind power output prediction. Based on the improved genetic algorithm, a least squares parameter estimation method for the stochastic differential equation is proposed. According to the discrete wind power output data, the stochastic differential equation parameters obtained by the improved genetic algorithm are used to accurately characterize the volatility of offshore wind power output. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 paying any creative work.

[0054] Figure 1 A flowchart of a method for calculating offshore wind power output prediction error provided by an embodiment of the present invention;

[0055] Figure 2 Waveform diagrams of training data and test data provided by an embodiment of the present invention;

[0056] Figure 3 A comparison diagram of the simulated value and the actual value of the wind power output prediction error provided by an embodiment of the present invention;

[0057] Figure 4 This is a structural block diagram of a device for calculating offshore wind power output prediction errors provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] Embodiments of the present invention provide a method, device, equipment and storage medium for calculating offshore wind power output prediction errors, which are used to solve the technical problem of low accuracy in offshore wind power output fluctuation analysis.

[0059] In order to make the purpose, features, and advantages of the present invention more obvious and easy to understand, 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 embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0060] See also Figure 1 , Figure 1 A flowchart of the steps of a method for calculating offshore wind power output prediction error provided by an embodiment of the present invention.

[0061] The present invention provides a method for calculating offshore wind power output prediction error, which may specifically include the following steps:

[0062] Step 101, obtaining wind power output data of wind turbines in an offshore wind farm;

[0063] Step 102, constructing the Ornstein-Uhlenbeck process of wind power output data;

[0064] The Ornstein-Uhlenbeck process is a stochastic process used to describe the effects of random noise. It consists of two elements: Brownian motion and regression. Brownian motion is a random walk, where the position changes at random steps within infinitesimal time intervals. In the Ornstein-Uhlenbeck process, Brownian motion is used to model random noise. Regression refers to the tendency of a physical system to return to an equilibrium point after a random change. In the Ornstein-Uhlenbeck process, this regression is used to model the recovery tendency of a physical system.

[0065] In an embodiment of the present invention, the Ornstein-Uhlenbeck process can be used to describe the volatility of offshore wind power output; in the stage of constructing the offshore wind power output volatility model, based on the long-tail effect of the offshore wind power output prediction error, its probability distribution is difficult to be accurately described by the normal distribution, and the nonlinear Ito process is used to describe its volatility.

[0066] In the specific implementation, the Ornstein-Uhlenbeck process that describes the volatility of wind power output data is as follows:

[0067]

[0068] in, is the predicted value of offshore wind power output, is the prediction error of offshore wind power output.

[0069] Step 103, constructing a stochastic differential equation of the Ornstein-Uhlenbeck process;

[0070] In the embodiment of the present invention, it is possible to define for Prediction error of offshore wind power output at any given moment The time domain expression of the prediction error The change of has Markov property, and its dynamic behavior depends only on the current moment Based on the Markov property of and the mean reversion characteristics of the prediction error, the Ornstein-Uhlenbeck process under the Ito process framework is used to For modeling, the stochastic differential equation is as follows:

[0071]

[0072] in, is the prediction error of offshore wind power output at time t The time domain expression of It is Brownian motion, which is used to characterize random disturbances in the environment. is the prediction error In infinitesimal time intervals The instantaneous change in is the drift term of the equation, is the mean reversion rate, is the volatility parameter, It is an external unpredictable random disturbance.

[0073] Step 104, constructing an optimal parameter estimation model for the stochastic differential equation based on least squares optimization;

[0074] Next, The function is discretized and converted into , and then construct the optimal parameter estimation model of the stochastic differential equation based on least squares optimization as follows:

[0075]

[0076] Where: It is the discrete actual value of the wind power output forecast error, generated by a holdout forecast (i.e., rolling calculation based on historical data, for example, calculating the wind power forecast error for the 101st day using 100 days of historical wind power data). is the discrete analog value of the wind power output forecast error, using the parameters to be estimated and Monte-Carlo method to simulate Ornstein-Uhlenbeck process generation; Should satisfy the stochastic differential equation The discrete form of is: , time step Depends on the time interval of historical data sampling; is the optimal solution of each round of calculation (see claim 4, “optimal parameter estimation of stochastic differential equations based on an improved genetic algorithm”); is based on The value of is calculated using the following three formulas:

[0077] Compute the transition density function of the Ornstein-Uhlenbeck process:

[0078]

[0079] Calculate the form of its likelihood function:

[0080]

[0081] Through the likelihood function of the Ornstein-Uhlenbeck process, we can get The maximum likelihood estimate of :

[0082]

[0083] Step 105, using an improved genetic algorithm to solve the optimal parameter estimation model to obtain the optimal parameters;

[0084] In an embodiment of the present invention, the improved genetic algorithm is as follows:

[0085] (1) Improvement of crossover operator: The monarch scheme is used for crossover operation. The monarch scheme refers to the use of a designated individual as the "monarch" in the population in the genetic algorithm; this individual has a high fitness and has the function of leading the search direction of the entire population, improving the convergence speed and preventing the algorithm from converging to the local optimal solution too early;

[0086] (2) Improvement of the mutation operator: By introducing a mutation rate function, the mutation rate is gradually reduced with the number of iterations; in the early stage of the algorithm, the solution space is searched more widely, while in the later stage, the local area is searched more finely to balance the convergence speed and convergence accuracy;

[0087] (3) Random initialization: In genetic algorithms, in order to increase the diversity of the population and prevent the algorithm from falling into a local optimal solution, adding random new individuals to the new population is called population diversity maintenance or population reset. The random initialization method is used: each time the population is updated, a part of the optimal individuals is retained, and then the remaining population vacancies are filled with randomly generated individuals.

[0088] In an embodiment of the present invention, the step of using an improved genetic algorithm to solve the optimal parameter estimation model to obtain the optimal parameters may include the following sub-steps:

[0089] S51, generating an initial population of the optimal parameter estimation model, the initial population including a number of individuals;

[0090] S52, calculate the fitness of each individual through the fitness function;

[0091] S53, select, mutate and crossover the individuals through the mutation rate function to generate new individuals;

[0092] S54, removing individuals whose fitness is lower than a preset threshold from the initial population, and adding new individuals to the initial population to obtain a new population;

[0093] S55, judging whether the change of the fitness function of the best individual in the new population is within a preset range;

[0094] S56, if not, return to the step of calculating the fitness of each individual using the fitness function;

[0095] S57: If yes, output the optimal individual as the optimal parameter.

[0096] In the specific implementation, the solution process of the optimal parameter estimation model is as follows:

[0097] (1) Initialization :Use random initialization strategy to generate The diversity of initial values ​​helps to accelerate the convergence speed of the algorithm and improve the global search ability;

[0098] (2) Determine the fitness function: The fitness function is a numerical indicator for evaluating the quality of individuals in the population. After each iteration, each individual in the population must calculate its fitness function value; the fitness function is defined as the optimization objective function, as follows:

[0099]

[0100] (3) Determine the selection, crossover, and mutation operators: The selection operator is ranking selection, which ranks individuals in the population according to their fitness, and then determines the selection probability based on the ranking order. Individuals with higher fitness have higher selection probabilities.

[0101] The mutation operator introduces a mutation rate function to make the mutation rate gradually decrease with the number of iterations;

[0102]

[0103] Where: The population is The probability of generational mutation, It is the initial mutation probability of the population, which improves the ability of the search space in the early stage of the algorithm search and helps to increase the diversity of the population; is the population mutation rate function, which is about the number of iterations The function gradually decreases with the increase of the number of iterations;

[0104] (4) Termination condition of genetic algorithm: when the fitness function of the optimal individual in the population changes within a pre-set positive value after iteration If the number of iterations reaches the maximum, the program terminates.

[0105] The specific steps of using genetic algorithm to solve the optimal estimated values ​​of the parameters of stochastic differential equations are as follows:

[0106] a. Randomly generate the initial population, and use binary coding for individuals;

[0107] b. Evaluate the fitness value of each individual through the fitness function; the fitness value reflects the degree of individual's proficiency in solving the problem;

[0108] c. Introduce the mutation rate function to select, mutate and crossover individuals to generate new individuals;

[0109] d. Sort by fitness value, retain individuals with high fitness value, exclude individuals with low fitness value, and randomly generate new individuals to join the new population to avoid local optimal solution;

[0110] e. Determine whether the termination condition is met. If so, the algorithm ends and outputs the optimal solution; otherwise, return to step b to execute.

[0111] Step 106, optimizing the stochastic differential equation according to the optimal parameters to obtain an optimized stochastic differential equation;

[0112] Step 107 : Calculate the offshore wind power output prediction error based on the optimized stochastic differential equation and the wind power output data.

[0113] In an embodiment of the present invention, after the optimal parameters are calculated, an optimized stochastic differential equation may be generated, and the optimized stochastic differential equation and wind power output data may be used to calculate the offshore wind power output prediction error.

[0114] This paper introduces a stochastic process model and an optimized parameter estimation method to improve the accuracy and robustness of wind power forecasting, meeting the requirements of offshore wind power output forecasting. Furthermore, based on an improved genetic algorithm, a least-squares parameter estimation method for stochastic differential equations is proposed. Based on discrete wind power output data, the stochastic differential equation parameters derived by the improved genetic algorithm are used to accurately characterize the volatility of offshore wind power output.

[0115] For ease of understanding, the embodiments of the present invention are described below with reference to specific examples:

[0116] The output data of a wind turbine in an offshore wind farm is extracted to solve the parameters of the stochastic differential equation that describes the output volatility of the wind turbine. The sampling interval of the actual data of the offshore wind turbine output is 30 minutes. The actual data of the offshore wind power output of the previous three days is used as the training set, and the actual data of the offshore wind power output of the next day is used as the test set. The quantity to be estimated is the prediction error of the offshore wind output. Considering that the statistical characteristics of the prediction error may be related to the prediction algorithm adopted, in order to eliminate the influence of different prediction algorithms on the offshore wind power output data, a prediction based on the Monte-Carlo method is adopted. The actual value of the offshore wind power at the previous moment is used as the predicted value of the offshore wind power output at the next moment. The prediction error is the difference between the actual value and the predicted value of the offshore wind power output. The waveforms of the training data and the test data are as follows. Figure 2 shown.

[0117] The parameters of the improved genetic algorithm in the optimal parameter estimation model based on stochastic differential equations in this example are shown in Table 1:

[0118] Table 1 Parameters of the model based on the improved genetic algorithm

[0119]

[0120] According to the principle of least squares method, the parameter estimates of the stochastic differential equation obtained by calculating the improved genetic algorithm are shown in Table 2 below:

[0121] Table 2 Parameter estimates of the stochastic differential equation

[0122]

[0123] After determining the parameters of the stochastic differential equation, the simulated value of the wind power output forecast error can be obtained. The comparison between the simulated value and the actual value is shown in Figure 3 The maximum, average and standard deviation of the simulated values ​​and the actual data are compared as shown in Table 3 below:

[0124] Table 3 Comparison of simulated values ​​and actual values

[0125]

[0126] analyze Figure 3 The optimal estimates of the parameters of the stochastic differential equation obtained by the genetic algorithm show that the waveforms of the data simulated using the Monte-Carlo method almost completely overlap with the actual data, with only some peaks and troughs not overlapping with the actual data. The standard deviation and mean of the simulated data are close to those of the actual data.

[0127] Through example simulation, it is confirmed that the embodiment of the present invention can accurately describe the volatility of offshore wind power output prediction errors.

[0128] See also Figure 4 , Figure 4 This is a structural block diagram of a device for calculating offshore wind power output prediction errors provided by an embodiment of the present invention.

[0129] An embodiment of the present invention provides a device for calculating offshore wind power output prediction error, comprising:

[0130] The wind power output data acquisition module 401 is used to acquire wind power output data of wind turbines in offshore wind farms;

[0131] An Ornstein-Uhlenbeck process construction module 402 is used to construct an Ornstein-Uhlenbeck process for wind power output data;

[0132] a stochastic differential equation construction module 403 for constructing a stochastic differential equation of an Ornstein-Uhlenbeck process;

[0133] An optimal parameter estimation model construction module 404 is used to construct an optimal parameter estimation model of a stochastic differential equation based on least squares optimization;

[0134] A solution module 405 is used to solve the optimal parameter estimation model using an improved genetic algorithm to obtain optimal parameters;

[0135] An optimization module 406 is configured to optimize the stochastic differential equation according to the optimal parameters to obtain an optimized stochastic differential equation;

[0136] The offshore wind power output prediction error calculation module 407 is used to calculate the offshore wind power output prediction error based on the optimized stochastic differential equation and wind power output data.

[0137] In an embodiment of the present invention, the Ornstein-Uhlenbeck process describing the volatility of wind power output data is as follows:

[0138]

[0139] in, is the predicted value of offshore wind power output, is the prediction error of offshore wind power output.

[0140] In an embodiment of the present invention, the stochastic differential equation is as follows:

[0141]

[0142] in, is the prediction error of offshore wind power output at time t The time domain expression of It is Brownian motion, which is used to characterize random disturbances in the environment. is the prediction error In infinitesimal time intervals The instantaneous change in is the drift term of the equation, is the mean reversion rate, is the volatility parameter, It is an external unpredictable random disturbance.

[0143] In this embodiment of the present invention, the solution module 405 includes:

[0144] The population initialization submodule is used to generate the initial population of the optimal parameter estimation model. The initial population includes several individuals.

[0145] The fitness calculation submodule is used to calculate the fitness of each individual through the fitness function;

[0146] The new individual generation submodule is used to select, mutate and crossover individuals through the mutation rate function to generate new individuals;

[0147] The population update submodule is used to remove individuals whose fitness is lower than the preset threshold from the initial population and add new individuals into the initial population to obtain a new population;

[0148] The judgment submodule is used to judge whether the fitness function change of the optimal individual in the new population is within the preset range;

[0149] Return submodule, used to return to the fitness calculation submodule if no;

[0150] The optimal parameter output submodule is used to output the optimal individual as the optimal parameter if so.

[0151] An embodiment of the present invention further provides an electronic device, the device including a processor and a memory:

[0152] The memory is used to store program codes and transmit the program codes to the processor;

[0153] The processor is used to execute the offshore wind power output prediction error calculation method of the embodiment of the present invention according to the instructions in the program code.

[0154] An embodiment of the present invention further provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute the offshore wind power output prediction error calculation method of the embodiment of the present invention.

[0155] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0156] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0157] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, embodiments of the present invention may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware. Furthermore, embodiments of 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0158] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the 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 the 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 terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal 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.

[0159] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1A step that specifies a function in one or more boxes.

[0161] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0162] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0163] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0164] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for calculating offshore wind power output prediction error, characterized in that: include: Obtain wind power output data of wind turbines in offshore wind farms; Constructing an Ornstein-Uhlenbeck process for the wind power output data; Constructing a stochastic differential equation for the Ornstein-Uhlenbeck process; Construct an optimal parameter estimation model for stochastic differential equations based on least squares optimization; Using an improved genetic algorithm to solve the optimal parameter estimation model to obtain optimal parameters; Optimizing the stochastic differential equation according to the optimal parameters to obtain an optimized stochastic differential equation; An offshore wind power output prediction error is calculated based on the optimized stochastic differential equation and the wind power output data.

2. The method according to claim 1, characterized in that The Ornstein-Uhlenbeck process that describes the volatility of the wind power output data is as follows: in, is the predicted value of offshore wind power output, is the prediction error of offshore wind power output.

3. The method according to claim 2, characterized in that The stochastic differential equation is as follows: in, is the prediction error of offshore wind power output at time t The time domain expression of It is Brownian motion, which is used to characterize random disturbances in the environment; is the prediction error In infinitesimal time intervals The instantaneous change in is the drift term of the equation, is the mean reversion rate, is the volatility parameter, It is an external unpredictable random disturbance.

4. The method according to claim 1, wherein The step of using an improved genetic algorithm to solve the optimal parameter estimation model to obtain the optimal parameters includes: generating an initial population of the optimal parameter estimation model, wherein the initial population includes a plurality of individuals; Calculating the fitness of each individual by a fitness function; Performing selection, mutation and crossover operations on the individuals through a mutation rate function to generate new individuals; Eliminating individuals whose fitness is lower than a preset threshold from the initial population, and adding the new individuals to the initial population to obtain a new population; Determine whether the fitness function change of the best individual in the new population is within the preset range; If not, return to the step of calculating the fitness of each individual using the fitness function; If so, the optimal individual is output as the optimal parameter.

5. A device for calculating offshore wind power output prediction error, characterized in that: include: A wind power output data acquisition module is used to obtain wind power output data of wind turbines in offshore wind farms; An Ornstein-Uhlenbeck process construction module, used to construct the Ornstein-Uhlenbeck process of the wind power output data; a stochastic differential equation building module for building the stochastic differential equation of the Ornstein-Uhlenbeck process; Optimal parameter estimation model building module, used to build the optimal parameter estimation model of stochastic differential equations based on least squares optimization; A solution module, configured to solve the optimal parameter estimation model using an improved genetic algorithm to obtain optimal parameters; an optimization module, configured to optimize the stochastic differential equation according to the optimal parameters to obtain an optimized stochastic differential equation; The offshore wind power output prediction error calculation module is used to calculate the offshore wind power output prediction error based on the optimized stochastic differential equation and the wind power output data.

6. The device according to claim 5, characterized in that The Ornstein-Uhlenbeck process that describes the volatility of the wind power output data is as follows: in, is the predicted value of offshore wind power output, is the prediction error of offshore wind power output.

7. The device according to claim 6, characterized in that The stochastic differential equation is as follows: in, is the prediction error of offshore wind power output at time t The time domain expression of It is Brownian motion, which is used to characterize random disturbances in the environment; is the prediction error In infinitesimal time intervals The instantaneous change in is the drift term of the equation, is the mean reversion rate, is the volatility parameter, It is an external unpredictable random disturbance.

8. The device according to claim 5, characterized in that The solution module includes: A population initialization submodule, used to generate an initial population of the optimal parameter estimation model, wherein the initial population includes a plurality of individuals; A fitness calculation submodule, used for calculating the fitness of each individual through a fitness function; A new individual generation submodule is used to select, mutate and crossover the individuals through a mutation rate function to generate new individuals; A population update submodule is used to remove individuals whose fitness is lower than a preset threshold from the initial population and add the new individuals into the initial population to obtain a new population; The judgment submodule is used to judge whether the fitness function change of the optimal individual in the new population is within the preset range; Return submodule, used to return to the fitness calculation submodule if no; The optimal parameter output submodule is used to output the optimal individual as the optimal parameter if so.

9. An electronic device, characterized in that: The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the offshore wind power output prediction error calculation method according to any one of claims 1-4 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store program code, and the program code is used to execute the offshore wind power output prediction error calculation method according to any one of claims 1 to 4.

Images