CN116054240A

CN116054240A - Wind power grid-connected operation control optimization method and system based on power prediction

Info

Publication number: CN116054240A
Application number: CN202211589430.2A
Authority: CN
Inventors: 刘燕; 丛聪; 王蕊; 刘彦鹏; 孙坤元; 闫敬书
Original assignee: Datang Hainan New Energy Development Co ltd; China Datang Corp Science and Technology Research Institute Co Ltd
Current assignee: Datang Hainan New Energy Development Co ltd; China Datang Corp Science and Technology Research Institute Co Ltd
Priority date: 2022-12-09
Filing date: 2022-12-09
Publication date: 2023-05-02

Abstract

The invention discloses a wind power grid-connected operation control optimization method and system based on power prediction, and relates to the field of power grid control, wherein the method comprises the following steps: obtaining a target power grid data set and a target fan data set; obtaining target wind power demand information; inputting the forecast meteorological data and the target fan data set into a fan power generation power prediction model to obtain a fan power generation power prediction result; adding target wind power demand information, a target fan data set and a fan power generation power prediction result to a wind power characteristic database, and carrying out principal component analysis on the wind power characteristic database to obtain wind power characteristic data information; and inputting the wind power characteristic data information into a control optimization model to obtain a grid-connected operation control scheme, and sending the grid-connected operation control scheme to the wind power grid-connected control module. The method solves the technical problems that in the prior art, the grid-connected operation control accuracy for wind power is not high, and the wind power grid-connected operation control effect is poor.

Description

Wind power grid-connected operation control optimization method and system based on power prediction

Technical Field

The invention relates to the field of power grid control, in particular to a wind power grid-connected operation control optimization method and system based on power prediction.

Background

Wind power generation is one of the important power generation modes. Because wind energy has the characteristics of volatility, intermittence, uncontrollability and the like, large-scale wind power grid connection brings great challenges to safe and stable operation of a power system. Therefore, the method for optimally controlling the wind power grid connection is researched and designed, and has important economic significance and practical value.

In the prior art, the technical problems of poor control accuracy of grid-connected operation of wind power and poor control effect of grid-connected operation of wind power are caused.

Disclosure of Invention

The application provides a wind power grid-connected operation control optimization method and system based on power prediction. The method solves the technical problems that in the prior art, the grid-connected operation control accuracy for wind power is not high, and the wind power grid-connected operation control effect is poor. The dynamic matching of the power generation capacity of the fan and the power grid requirement is realized, the influence of the power generation grid connection of the fan on the running state of the power grid is reduced, and powerful guarantee is provided for the safe and stable running of the power grid; the accuracy and the adaptation degree of wind power grid-connected operation control are improved, and the technical effect of the wind power grid-connected operation control quality is improved.

In view of the above problems, the application provides a wind power grid-connected operation control optimization method and system based on power prediction.

In a first aspect, the present application provides a wind power grid-connected operation control optimization method based on power prediction, where the method is applied to a wind power grid-connected operation control optimization system based on power prediction, and the method includes: acquiring information based on the wind power grid-connected control module to obtain a target power grid data set and a target fan data set; analyzing wind power demand parameters based on the target power grid data set to obtain target wind power demand information; constructing a fan power generation power prediction model; obtaining forecast meteorological data, and inputting the forecast meteorological data and the target fan dataset into the fan power generation power prediction model to obtain a fan power generation power prediction result; adding the target wind power demand information, the target fan data set and the wind power generation power prediction result to a wind power characteristic database, and carrying out principal component analysis on the wind power characteristic database to obtain wind power characteristic data information; and inputting the wind power characteristic data information into a control optimization model to obtain a grid-connected operation control scheme, and sending the grid-connected operation control scheme to the wind power grid-connected control module.

In a second aspect, the present application further provides a wind power grid-connected operation control optimization system based on power prediction, where the system includes: the information acquisition module is used for acquiring information based on the wind power grid-connected control module to obtain a target power grid data set and a target fan data set; the wind power demand parameter analysis module is used for analyzing wind power demand parameters based on the target power grid data set to obtain target wind power demand information; the construction module is used for constructing a fan power generation power prediction model; the power prediction module is used for obtaining forecast meteorological data, inputting the forecast meteorological data and the target fan dataset into the fan power generation power prediction model, and obtaining a fan power generation power prediction result; the principal component analysis module is used for adding the target wind power demand information, the target fan data set and the fan power generation power prediction result to a wind power characteristic database, and carrying out principal component analysis on the wind power characteristic database to obtain wind power characteristic data information; the control module is used for inputting the wind power characteristic data information into a control optimization model, obtaining a grid-connected operation control scheme and sending the grid-connected operation control scheme to the wind power grid-connected control module.

In a third aspect, the present application further provides an electronic device, including: a memory for storing executable instructions; and the processor is used for realizing the wind power grid-connected operation control optimization method based on power prediction when executing the executable instructions stored in the memory.

In a fourth aspect, the present application further provides a computer readable storage medium storing a computer program, where the program when executed by a processor implements the wind power grid-connected operation control optimization method based on power prediction provided by the present application.

One or more technical solutions provided in the present application have at least the following technical effects or advantages:

acquiring information through a wind power grid-connected control module to obtain a target power grid data set and a target fan data set; analyzing wind power demand parameters according to the target power grid data set to obtain target wind power demand information; inputting the forecast meteorological data and the target fan data set into a fan power generation power prediction model to obtain a fan power generation power prediction result; adding target wind power demand information, a target fan data set and a fan power generation power prediction result to a wind power characteristic database, and carrying out principal component analysis on the wind power characteristic database to obtain wind power characteristic data information; and inputting the wind power characteristic data information into a control optimization model to obtain a grid-connected operation control scheme, and sending the grid-connected operation control scheme to a wind power grid-connected control module. The dynamic matching of the power generation capacity of the fan and the power grid requirement is realized, the influence of the power generation grid connection of the fan on the running state of the power grid is reduced, and powerful guarantee is provided for the safe and stable running of the power grid; the accuracy and the adaptation degree of wind power grid-connected operation control are improved, and the technical effect of the wind power grid-connected operation control quality is improved.

The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.

FIG. 1 is a schematic flow chart of a wind power grid-connected operation control optimization method based on power prediction;

FIG. 2 is a schematic structural diagram of a wind power grid-connected operation control optimization system based on power prediction;

fig. 3 is a schematic structural diagram of an exemplary electronic device of the present application.

Reference numerals illustrate: the wind power demand parameter analysis system comprises an information acquisition module 11, a wind power demand parameter analysis module 12, a construction module 13, a power prediction module 14, a principal component analysis module 15, a control module 16, a processor 31, a memory 32, an input device 33 and an output device 34.

Detailed Description

The wind power grid-connected operation control optimization method and system based on power prediction are provided. The method solves the technical problems that in the prior art, the grid-connected operation control accuracy for wind power is not high, and the wind power grid-connected operation control effect is poor. The dynamic matching of the power generation capacity of the fan and the power grid requirement is realized, the influence of the power generation grid connection of the fan on the running state of the power grid is reduced, and powerful guarantee is provided for the safe and stable running of the power grid; the accuracy and the adaptation degree of wind power grid-connected operation control are improved, and the technical effect of the wind power grid-connected operation control quality is improved.

Example 1

Referring to fig. 1, the present application provides a wind power grid-connected operation control optimization method based on power prediction, wherein the method is applied to a wind power grid-connected operation control optimization system based on power prediction, the system comprises a wind power grid-connected control module, and the method specifically comprises the following steps:

step S100: acquiring information based on the wind power grid-connected control module to obtain a target power grid data set and a target fan data set;

further, step S100 of the present application further includes:

step S110: the wind power grid-connected control module is in communication connection with a target power grid and a target wind power generator;

step S120: acquiring information based on the target power grid to obtain a target power grid data set;

step S130: and acquiring information based on the target wind driven generator to obtain a target fan data set.

Specifically, the wind power grid-connected control module is in communication connection with a target power grid and a target wind driven generator. And acquiring information of the target power grid to obtain a target power grid data set. And acquiring information of the target wind driven generator to obtain a target fan data set. The target power grid is any power grid which performs intelligent wind power grid-connected control by using the wind power grid-connected operation control optimizing system based on power prediction. The target wind power generator is any wind power generator for carrying out wind power generation on a target power grid. The target power grid data set comprises data information such as power supply task information, power supply form information, power supply areas, real-time power supply quantity, real-time power supply power and the like of a target power grid. The target fan data set comprises data information such as the position, model specification, structural composition, working voltage, working wind speed, rated power and the like of the target wind driven generator. The method achieves the technical effects of determining the target power grid data set and the target fan data set and laying a foundation for the follow-up grid-connected operation control of the target wind driven generator.

Step S200: analyzing wind power demand parameters based on the target power grid data set to obtain target wind power demand information;

further, step S200 of the present application further includes:

step S210: acquiring power supply task information and power supply form information based on the target power grid data set;

specifically, power supply task information and power supply form information are extracted from the target power grid data set. The power supply task information comprises the power supply demand of a target power grid. The power supply form information comprises power generation mode composition information such as thermal power generation, wind power generation, hydroelectric power generation and the like of a target power grid.

Step S220: carrying out power supply duty ratio prediction based on the power supply form information to obtain a power supply duty ratio prediction result;

further, step S220 of the present application further includes:

step S221: acquiring historical information of a target power grid based on the power supply form information to obtain a historical power supply data set, wherein the historical power supply data set comprises a plurality of pieces of historical power supply information and a plurality of pieces of historical power supply form information;

step S222: performing cluster analysis on the plurality of historical power supply information based on the plurality of historical power supply form information to obtain a historical power supply characteristic data set;

step S223: and carrying out power supply duty ratio calculation based on the historical power supply characteristic data set to obtain the power supply duty ratio prediction result.

Step S230: based on the power supply duty ratio prediction result, a wind power duty ratio prediction result is obtained;

step S240: and obtaining the target wind power demand information based on the power supply task information and the wind power duty ratio prediction result.

Specifically, historical information acquisition is performed on a target power grid based on power supply form information, and a historical power supply data set is obtained. The historical power supply data set includes a plurality of historical power supply information and a plurality of historical power supply form information. And, the plurality of historical power supply information has a corresponding relation with the plurality of historical power supply form information. The plurality of historical power supply information includes a plurality of historical power generation parameters of the target power grid. The plurality of historical power supply form information comprises historical power generation mode information corresponding to each of the plurality of historical power supply information. And further, performing cluster analysis on the plurality of historical power supply information according to the plurality of historical power supply form information to obtain a historical power supply characteristic data set. The cluster analysis refers to classifying a plurality of historical power supply information corresponding to the same historical power supply form information. The historical power supply characteristic data set comprises a plurality of historical power supply characteristic data such as firepower historical power supply characteristic data, wind power historical power supply characteristic data and hydraulic power historical power supply characteristic data. Each of the historical power supply characteristic data includes a plurality of historical power supply information identical to the historical power supply form information.

And then, calculating the power supply duty ratio based on the historical power supply characteristic data set, namely, respectively counting a plurality of historical power supply characteristic data such as firepower historical power supply characteristic data, wind power historical power supply characteristic data, hydraulic power historical power supply characteristic data and the like in the historical power supply characteristic data set to obtain a plurality of historical characteristic power supply quantities such as firepower historical characteristic power supply quantity, wind power historical characteristic power supply quantity, hydraulic power historical characteristic power supply quantity and the like. The plurality of historical power supply amounts include a sum of a plurality of historical power supply information corresponding to each of the plurality of historical power supply characteristic data. And adding the plurality of historical characteristic power supply quantities to obtain the historical characteristic total power supply quantity. And respectively calculating the ratio of the plurality of historical characteristic power supply quantities to the historical characteristic total power supply quantity to obtain a plurality of power supply duty ratio prediction coefficients such as a thermal power supply duty ratio prediction coefficient, a wind power supply duty ratio prediction coefficient, a hydraulic power supply duty ratio prediction coefficient and the like, and outputting the plurality of power supply duty ratio prediction coefficients as power supply duty ratio prediction results. Further, a wind power duty ratio prediction result is extracted from the power supply duty ratio prediction result, wherein the wind power duty ratio prediction result comprises a wind power supply duty ratio prediction coefficient. And multiplying the power supply task information and the wind power duty ratio prediction result to obtain target wind power demand information. The method achieves the technical effects of analyzing wind power demand parameters through the target power grid data set and obtaining target wind power demand information, thereby improving accuracy and adaptability of wind power grid-connected operation control.

Step S300: constructing a fan power generation power prediction model;

further, step S300 of the present application further includes:

step S310: obtaining a plurality of sample wind generators;

step S320: acquiring information based on the plurality of sample wind turbines to obtain a sample database, wherein the sample database comprises a plurality of sample meteorological data, a plurality of sample fan data sets and a plurality of fan power generation powers;

step S330: randomly dividing based on the sample data set to obtain a sample training set and a sample testing set;

step S340: and training and testing the sample training set and the sample testing set based on the BP neural network to obtain the fan power generation power prediction model.

Specifically, a plurality of sample wind turbines are obtained based on the target wind turbine. The plurality of sample wind turbines includes a plurality of wind turbines of the same type similar to the target wind turbine. And acquiring information of the plurality of sample wind driven generators to obtain a sample database. The sample database comprises a plurality of sample meteorological data, a plurality of sample fan data sets and a plurality of fan power generation powers. The plurality of sample meteorological data comprise historical operation environment information such as a plurality of historical operation wind power parameters, a plurality of historical operation wind direction parameters, a plurality of historical operation temperature parameters, a plurality of historical operation humidity parameters and the like corresponding to the plurality of sample wind driven generators. The plurality of sample fan data sets comprise data information such as positions, model specifications, structural compositions, working voltages, working wind speeds, rated power and the like of the plurality of sample wind driven generators. The plurality of fan power generation comprises a plurality of historical power generation information of a plurality of sample wind driven generators under a plurality of sample meteorological data.

Further, the sample data set is randomly divided, and a sample training set and a sample testing set are obtained. Illustratively, 80% of the data information in the sample data set is divided into sample training sets. 20% of the data information in the sample data set is divided into sample test sets. Based on the BP neural network, the sample training set is continuously self-trained and learned to a convergence state, and a fan power generation power prediction model is obtained. And taking the sample test set as input information, inputting the sample test set into a fan power generation power prediction model, and testing and parameter updating the fan power generation power prediction model through the sample test set. The BP neural network is a multi-layer feedforward neural network trained according to an error back propagation algorithm. The BP neural network comprises an input layer, a plurality of layers of neurons and an output layer. The BP neural network can perform forward calculation and backward calculation. When calculating in the forward direction, the input information is processed layer by layer from the input layer through a plurality of layers of neurons and is turned to the output layer, and the state of each layer of neurons only affects the state of the next layer of neurons. If the expected output cannot be obtained at the output layer, the reverse calculation is carried out, the error signal is returned along the original connecting path, and the weight of each neuron is modified to minimize the error signal. The fan power generation power prediction model meets the BP neural network. The fan power generation power prediction model comprises an input layer, an hidden layer and an output layer, and has the function of intelligent fan power generation power prediction.

Step S400: obtaining forecast meteorological data, and inputting the forecast meteorological data and the target fan dataset into the fan power generation power prediction model to obtain a fan power generation power prediction result;

specifically, the position information of the target wind driven generator is extracted from the target fan data set, weather forecast inquiry is conducted based on the position information, and forecast weather data are obtained. And further, taking the forecast meteorological data and the target fan data set as input information, inputting the input information into a fan power generation power prediction model, and obtaining a fan power generation power prediction result. The forecast meteorological data comprise environmental forecast information such as a plurality of forecast wind power parameters, a plurality of forecast wind direction parameters, a plurality of forecast temperature parameters, a plurality of forecast humidity parameters and the like corresponding to the position information of the target wind driven generator. The wind turbine power generation power prediction result comprises predicted power generation power information of the target wind turbine. The wind power generation power prediction method and the wind power generation system achieve the technical effects that the wind power generation power prediction model is used for accurately and efficiently predicting and analyzing the generated power, and a reliable wind power generation power prediction result is obtained, so that the rationality and the adaptation degree of wind power grid-connected operation control are improved.

Step S500: adding the target wind power demand information, the target fan data set and the wind power generation power prediction result to a wind power characteristic database, and carrying out principal component analysis on the wind power characteristic database to obtain wind power characteristic data information;

further, step S500 of the present application further includes:

step S510: obtaining a first wind power characteristic data set according to the wind power characteristic database;

step S520: performing decentralization treatment on the first wind power characteristic data set to obtain a second wind power characteristic data set;

step S530: obtaining a covariance matrix of a first wind power characteristic data set according to the second wind power characteristic data set;

step S540: obtaining a first eigenvalue and a first eigenvector according to the covariance matrix of the first wind power characteristic data set;

step S550: and obtaining the wind power characteristic data information according to the first characteristic value and the first characteristic vector.

Specifically, target wind power demand information, a target fan data set and a fan power generation power prediction result are added to a wind power characteristic database, and principal component analysis is performed on the wind power characteristic database. The wind power characteristic database comprises target wind power demand information, target fan data sets and fan power generation power prediction results. Principal component analysis is the most commonly used linear dimension reduction method, and aims to map a high-dimensional wind power characteristic database into a low-dimensional space through a certain linear projection, and expect the maximum information content of data in the projected dimension, so that fewer data dimensions are used, and meanwhile, the characteristics of more original data points are reserved. The principal component analysis has unsupervised learning using variance measurement information, and is not limited by a sample; eliminating the interaction among the original data components; the few indexes replace the majority indexes, so that the workload is reduced; the calculation method is simple and easy to realize.

On the basis of obtaining a wind power characteristic database, carrying out numerical processing on the wind power characteristic database to obtain a first wind power characteristic data set. And then, carrying out decentralization processing on each characteristic data in the first wind power characteristic data set. Firstly, solving the average value of all the characteristic data in the first wind power characteristic data set, then subtracting the average value of each characteristic data for all samples, and then obtaining a new characteristic value, wherein a second wind power characteristic data set is formed by the new characteristic data set, and is a data matrix. And further, calculating the second wind power characteristic data set through a covariance formula to obtain a covariance matrix of the first wind power characteristic data set. Further, through matrix operation, eigenvalues and eigenvectors of a covariance matrix of the first wind power characteristic data set are obtained, and each eigenvalue corresponds to one eigenvector, so that a first eigenvalue and a first eigenvector are obtained. The first eigenvalue is any eigenvalue obtained after matrix operation is carried out on the covariance matrix of the first wind power characteristic data set. The first feature vector is a feature vector corresponding to the first feature value. Further, selecting the first K largest eigenvalues and the corresponding eigenvectors from the first eigenvalues and the first eigenvector, and projecting the original data in the first wind power characteristic data set onto the selected eigenvectors to obtain wind power characteristic data information. The method has the advantages that the wind power characteristic database is subjected to dimension reduction processing by using a principal component analysis method, redundant data are removed on the premise of guaranteeing the information quantity, and the sample quantity of the wind power characteristic database is reduced; and after the dimension is reduced, wind power characteristic data information with minimum information quantity loss is obtained, so that the technical effect of matching efficiency of a follow-up grid-connected control scheme is improved.

Step S600: and inputting the wind power characteristic data information into a control optimization model to obtain a grid-connected operation control scheme, and sending the grid-connected operation control scheme to the wind power grid-connected control module.

Specifically, wind power characteristic data information is used as input information, and is input into a control optimization model to obtain a grid-connected operation control scheme. The grid-connected operation control scheme is sent to a wind power grid-connected control module, and the wind power grid-connected control module performs grid-connected operation control on the target wind driven generator according to the grid-connected operation control scheme. The control optimization model is obtained through training a large amount of data information related to wind power characteristic data information, and has the functions of intelligently analyzing the input wind power characteristic data information and matching grid-connected control schemes. The grid-connected operation control scheme comprises grid-connected operation control parameter information such as fan blade adjustment parameters of the target wind driven generator. The wind power characteristic data information is analyzed through the control optimization model, and an accurate grid-connected operation control scheme is obtained, so that the technical effect of improving the wind power grid-connected operation control quality is achieved.

In summary, the wind power grid-connected operation control optimization method based on power prediction provided by the application has the following technical effects:

1. acquiring information through a wind power grid-connected control module to obtain a target power grid data set and a target fan data set; analyzing wind power demand parameters according to the target power grid data set to obtain target wind power demand information; inputting the forecast meteorological data and the target fan data set into a fan power generation power prediction model to obtain a fan power generation power prediction result; adding target wind power demand information, a target fan data set and a fan power generation power prediction result to a wind power characteristic database, and carrying out principal component analysis on the wind power characteristic database to obtain wind power characteristic data information; and inputting the wind power characteristic data information into a control optimization model to obtain a grid-connected operation control scheme, and sending the grid-connected operation control scheme to a wind power grid-connected control module. The dynamic matching of the power generation capacity of the fan and the power grid requirement is realized, the influence of the power generation grid connection of the fan on the running state of the power grid is reduced, and powerful guarantee is provided for the safe and stable running of the power grid; the accuracy and the adaptation degree of wind power grid-connected operation control are improved, and the technical effect of the wind power grid-connected operation control quality is improved.

2. And analyzing wind power demand parameters through the target power grid data set to obtain target wind power demand information, so that accuracy and adaptability of wind power grid-connected operation control are improved.

3. The wind power generation power prediction model is used for accurately and efficiently predicting and analyzing the generated power, and a reliable wind power generation power prediction result is obtained, so that the rationality and the adaptation degree of wind power grid-connected operation control are improved.

4. Principal component analysis is the most commonly used linear dimension reduction method, and aims to map a high-dimensional wind power characteristic database into a low-dimensional space through a certain linear projection, and expect the maximum information content of data in the projected dimension, so that fewer data dimensions are used, and meanwhile, the characteristics of more original data points are reserved. The principal component analysis has unsupervised learning using variance measurement information, and is not limited by a sample; eliminating the interaction among the original data components; the few indexes replace the majority indexes, so that the workload is reduced; the calculation method is simple and easy to realize.

Example two

Based on the same inventive concept as the wind power grid-connected operation control optimization method based on power prediction in the foregoing embodiment, the present invention further provides a wind power grid-connected operation control optimization system based on power prediction, referring to fig. 2, the system includes:

the information acquisition module 11 is used for acquiring information based on the wind power grid-connected control module to obtain a target power grid data set and a target fan data set;

the wind power demand parameter analysis module 12, wherein the wind power demand parameter analysis module 12 is used for analyzing wind power demand parameters based on the target power grid data set to obtain target wind power demand information;

the construction module 13 is used for constructing a fan power generation power prediction model;

the power prediction module 14 is configured to obtain forecast weather data, input the forecast weather data and the target fan dataset into the fan power generation power prediction model, and obtain a fan power generation power prediction result;

the principal component analysis module 15 is configured to add the target wind power demand information, the target fan dataset, and the fan power generation prediction result to a wind power feature database, and perform principal component analysis on the wind power feature database to obtain wind power feature data information;

the control module 16 is used for inputting the wind power characteristic data information into a control optimization model, obtaining a grid-connected operation control scheme and sending the grid-connected operation control scheme to the wind power grid-connected control module.

Further, the system further comprises:

the connection module is used for the communication connection between the wind power grid-connected control module and a target power grid and a target wind driven generator;

the target power grid data set acquisition module is used for acquiring information based on the target power grid to acquire a target power grid data set;

the target fan data set acquisition module is used for acquiring information based on the target wind driven generator to acquire a target fan data set.

Further, the system further comprises:

the first execution module is used for obtaining power supply task information and power supply form information based on the target power grid data set;

the power supply duty ratio prediction module is used for predicting the power supply duty ratio based on the power supply form information to obtain a power supply duty ratio prediction result;

the wind power duty ratio prediction result obtaining module is used for obtaining a wind power duty ratio prediction result based on the power supply duty ratio prediction result;

the second execution module is used for obtaining the target wind power demand information based on the power supply task information and the wind power duty ratio prediction result.

Further, the system further comprises:

the historical information acquisition module is used for acquiring historical information of the target power grid based on the power supply form information to obtain a historical power supply data set, wherein the historical power supply data set comprises a plurality of historical power supply information and a plurality of historical power supply form information;

the cluster analysis module is used for carrying out cluster analysis on the plurality of historical power supply information based on the plurality of historical power supply form information to obtain a historical power supply characteristic data set;

and the duty ratio calculation module is used for calculating the power supply duty ratio based on the historical power supply characteristic data set to obtain the power supply duty ratio prediction result.

Further, the system further comprises:

the sample fan obtaining module is used for obtaining a plurality of sample wind driven generators;

the sample information acquisition module is used for acquiring information based on the plurality of sample wind generators to obtain a sample database, wherein the sample database comprises a plurality of sample meteorological data, a plurality of sample fan data sets and a plurality of fan power generation powers;

the dividing module is used for carrying out random division based on the sample data set to obtain a sample training set and a sample testing set;

and the training test module is used for training and testing the sample training set and the sample test set based on the BP neural network to obtain the fan power generation power prediction model.

Further, the system further comprises:

the first wind power characteristic data set acquisition module is used for acquiring a first wind power characteristic data set according to the wind power characteristic database;

the decentralization processing module is used for decentralizing the first wind power characteristic data set to obtain a second wind power characteristic data set;

the covariance matrix obtaining module is used for obtaining a covariance matrix of the first wind power characteristic data set according to the second wind power characteristic data set;

the matrix calculation module is used for obtaining a first eigenvalue and a first eigenvector according to the covariance matrix of the first wind power characteristic data set;

and the wind power characteristic data information determining module is used for obtaining the wind power characteristic data information according to the first characteristic value and the first characteristic vector.

The wind power grid-connected operation control optimization system based on the power prediction provided by the embodiment of the invention can execute the wind power grid-connected operation control optimization method based on the power prediction provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

All the included modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention.

Example III

Fig. 3 is a schematic structural diagram of an electronic device provided in a third embodiment of the present invention, and shows a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present invention. The electronic device shown in fig. 3 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention. As shown in fig. 3, the electronic device includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the electronic device may be one or more, in fig. 3, one processor 31 is taken as an example, and the processors 31, the memory 32, the input device 33 and the output device 34 in the electronic device may be connected by a bus or other means, in fig. 3, by bus connection is taken as an example.

The memory 32 is used as a computer readable storage medium for storing software programs, computer executable programs and modules, such as program instructions/modules corresponding to a wind power grid-connected operation control optimization method based on power prediction in the embodiment of the invention. The processor 31 executes various functional applications and data processing of the computer device by running software programs, instructions and modules stored in the memory 32, i.e. implements the above-mentioned wind power grid-connected operation control optimization method based on power prediction.

The application provides a wind power grid-connected operation control optimization method based on power prediction, wherein the method is applied to a wind power grid-connected operation control optimization system based on power prediction, and the method comprises the following steps: acquiring information through a wind power grid-connected control module to obtain a target power grid data set and a target fan data set; analyzing wind power demand parameters according to the target power grid data set to obtain target wind power demand information; inputting the forecast meteorological data and the target fan data set into a fan power generation power prediction model to obtain a fan power generation power prediction result; adding target wind power demand information, a target fan data set and a fan power generation power prediction result to a wind power characteristic database, and carrying out principal component analysis on the wind power characteristic database to obtain wind power characteristic data information; and inputting the wind power characteristic data information into a control optimization model to obtain a grid-connected operation control scheme, and sending the grid-connected operation control scheme to a wind power grid-connected control module. The method solves the technical problems that in the prior art, the grid-connected operation control accuracy for wind power is not high, and the wind power grid-connected operation control effect is poor. The dynamic matching of the power generation capacity of the fan and the power grid requirement is realized, the influence of the power generation grid connection of the fan on the running state of the power grid is reduced, and powerful guarantee is provided for the safe and stable running of the power grid; the accuracy and the adaptation degree of wind power grid-connected operation control are improved, and the technical effect of the wind power grid-connected operation control quality is improved.

Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.

Claims

1. The wind power grid-connected operation control optimization method based on power prediction is characterized by being applied to a wind power grid-connected operation control optimization system based on power prediction, wherein the system comprises a wind power grid-connected control module, and the method comprises the following steps:

acquiring information based on the wind power grid-connected control module to obtain a target power grid data set and a target fan data set;

analyzing wind power demand parameters based on the target power grid data set to obtain target wind power demand information;

constructing a fan power generation power prediction model;

obtaining forecast meteorological data, and inputting the forecast meteorological data and the target fan dataset into the fan power generation power prediction model to obtain a fan power generation power prediction result;

adding the target wind power demand information, the target fan data set and the wind power generation power prediction result to a wind power characteristic database, and carrying out principal component analysis on the wind power characteristic database to obtain wind power characteristic data information;

and inputting the wind power characteristic data information into a control optimization model to obtain a grid-connected operation control scheme, and sending the grid-connected operation control scheme to the wind power grid-connected control module.

2. The method of claim 1, wherein information is collected based on the wind power grid-tie control module to obtain a target grid dataset and a target fan dataset, the method further comprising:

the wind power grid-connected control module is in communication connection with a target power grid and a target wind power generator;

acquiring information based on the target power grid to obtain a target power grid data set;

and acquiring information based on the target wind driven generator to obtain a target fan data set.

3. The method of claim 1, wherein wind power demand parameter analysis is performed based on the target grid dataset to obtain target wind power demand information, the method further comprising:

acquiring power supply task information and power supply form information based on the target power grid data set;

carrying out power supply duty ratio prediction based on the power supply form information to obtain a power supply duty ratio prediction result;

based on the power supply duty ratio prediction result, a wind power duty ratio prediction result is obtained;

and obtaining the target wind power demand information based on the power supply task information and the wind power duty ratio prediction result.

4. The method of claim 3, wherein the power supply duty cycle prediction is performed based on the power supply form information to obtain a power supply duty cycle prediction result, the method further comprising:

acquiring historical information of a target power grid based on the power supply form information to obtain a historical power supply data set, wherein the historical power supply data set comprises a plurality of pieces of historical power supply information and a plurality of pieces of historical power supply form information;

performing cluster analysis on the plurality of historical power supply information based on the plurality of historical power supply form information to obtain a historical power supply characteristic data set;

and carrying out power supply duty ratio calculation based on the historical power supply characteristic data set to obtain the power supply duty ratio prediction result.

5. The method of claim 1, wherein a fan generated power prediction model is constructed, the method further comprising:

obtaining a plurality of sample wind generators;

acquiring information based on the plurality of sample wind turbines to obtain a sample database, wherein the sample database comprises a plurality of sample meteorological data, a plurality of sample fan data sets and a plurality of fan power generation powers;

randomly dividing based on the sample data set to obtain a sample training set and a sample testing set;

and training and testing the sample training set and the sample testing set based on the BP neural network to obtain the fan power generation power prediction model.

6. The method of claim 1, wherein wind power characteristic data information is obtained, the method further comprising:

obtaining a first wind power characteristic data set according to the wind power characteristic database;

performing decentralization treatment on the first wind power characteristic data set to obtain a second wind power characteristic data set;

obtaining a covariance matrix of a first wind power characteristic data set according to the second wind power characteristic data set;

obtaining a first eigenvalue and a first eigenvector according to the covariance matrix of the first wind power characteristic data set;

and obtaining the wind power characteristic data information according to the first characteristic value and the first characteristic vector.

7. A wind power grid-connected operation control optimization system based on power prediction, the system comprising a wind power grid-connected control module, the system comprising:

the information acquisition module is used for acquiring information based on the wind power grid-connected control module to obtain a target power grid data set and a target fan data set;

the wind power demand parameter analysis module is used for analyzing wind power demand parameters based on the target power grid data set to obtain target wind power demand information;

the construction module is used for constructing a fan power generation power prediction model;

the power prediction module is used for obtaining forecast meteorological data, inputting the forecast meteorological data and the target fan dataset into the fan power generation power prediction model, and obtaining a fan power generation power prediction result;

the principal component analysis module is used for adding the target wind power demand information, the target fan data set and the fan power generation power prediction result to a wind power characteristic database, and carrying out principal component analysis on the wind power characteristic database to obtain wind power characteristic data information;

the control module is used for inputting the wind power characteristic data information into a control optimization model, obtaining a grid-connected operation control scheme and sending the grid-connected operation control scheme to the wind power grid-connected control module.

8. An electronic device, the electronic device comprising:

a memory for storing executable instructions;

the processor is configured to implement the wind power grid-connected operation control optimization method based on power prediction according to any one of claims 1 to 6 when executing the executable instructions stored in the memory.

9. A computer readable medium having stored thereon a computer program, which when executed by a processor implements a power prediction based wind power grid tie operation control optimization method according to any one of claims 1 to 6.