Wind power prediction method and system based on wind speed inversion and Chatterjee-GPT correction

Abstract

The application discloses a wind power prediction method and system based on wind speed inversion and Chatterjee-GPT correction, and the method comprises the following steps: constructing a wind speed inversion model of a wind farm according to multiple information, and solving the wind speed inversion model of the wind farm to obtain an inversion wind speed; extracting a key factor set affecting the error between the inversion wind speed and a meteorological measured wind speed based on Chatterjee; inputting the key factor set, the inversion wind speed and the meteorological measured wind speed into a preset GPT model, and outputting a difference value from the GPT model; correcting the inversion wind speed according to the difference value to obtain a target inversion wind speed, and inputting the target inversion wind speed into a preset wind power prediction model, and outputting wind power from the wind power prediction model. The method can identify and quantify the difference in real time, provide data support for wind speed correction, and significantly improve the power prediction accuracy and real-time performance.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system regulation, and in particular relates to a wind power prediction method and system based on wind speed inversion and Chatterjee-GPT correction. Background Art

[0002] Integrating multi-source information for wind speed inversion and correcting the results based on meteorological data can effectively improve the accuracy of wind farm power forecasts. This has the following implications: By building a wind speed inversion model using multivariate data (including meteorological factors, historical power data, and environmental characteristics), wind speed data that is closer to reality can be obtained. When the inversion results are compared with measured meteorological data and corrected using a difference correction model (such as the error correction output by the GPT model), the accuracy of wind speed forecasts is further improved, thereby enhancing power forecast accuracy. A major challenge in wind power forecasting is the uncertainty of wind speed forecasts. Inverting wind speed using multi-source information and comparing and correcting it with measured meteorological data in post-processing can effectively reduce the uncertainty caused by model errors and environmental disturbances. High-precision wind power forecasting technology not only promotes the robust integration of renewable energy but also reduces deviation settlement costs and unnecessary backup power requirements, thereby improving the economic benefits and competitiveness of wind power projects.

[0003] However, existing wind power forecasting methods suffer from the following shortcomings: 1) Single information source and lack of multivariate data fusion. Traditional wind speed or power forecasting models often rely on single-source wind speed data or basic meteorological parameters, which are insufficiently capable of characterizing complex meteorological conditions and the heterogeneous wind field distribution within wind farms. This lack of multivariate information fusion results in low forecast accuracy and susceptibility to errors or uncertainties in a single data source. 2) Lack of a mechanism for screening key influencing factors: Faced with numerous potential influencing parameters (such as temperature, air pressure, humidity, and wind direction), traditional methods often lack systematic and quantitative methods to identify the most critical factors affecting wind speed errors. Indiscriminate use of all input variables can increase model complexity and computational cost, leading to overfitting and unstable performance. 3) Imperfect dynamic identification and correction of wind speed errors: Traditional methods lack refined, dynamically adaptable identification and correction methods for discrepancies between inverted wind speed and measured meteorological data, resulting in reduced wind speed and power forecast accuracy under time-varying meteorological conditions. 4) Insufficient coupling between wind speed error correction and power prediction: In existing methods, wind speed correction and power prediction are usually performed separately, making it difficult to transmit the corrected wind speed information to the power prediction link in a timely manner, resulting in difficulty in achieving synchronous optimization of the prediction results. Summary of the Invention

[0004] The present invention provides a wind power prediction method and system based on wind speed inversion and Chatterjee-GPT correction, which are used to solve the technical problem of inaccurate wind power prediction.

[0005] In a first aspect, the present invention provides a wind power prediction method based on wind speed inversion and Chatterjee-GPT correction, comprising:

[0006] Constructing a wind speed inversion model for a wind farm based on multivariate information, and solving the wind speed inversion model for the wind farm to obtain an inverted wind speed;

[0007] Extracting a set of key factors that affect the error between the inverted wind speed and the meteorologically measured wind speed based on Chatterjee;

[0008] Inputting the key factor set, the inverted wind speed, and the meteorological measured wind speed into a preset GPT model, the GPT model outputting a difference value;

[0009] The inverted wind speed is corrected according to the difference value to obtain a target inverted wind speed, and the target inverted wind speed is input into a preset wind power prediction model, and the wind power prediction model outputs the wind power.

[0010] In a second aspect, the present invention provides a wind power prediction system based on wind speed inversion and Chatterjee-GPT correction, comprising:

[0011] A solution module is configured to construct a wind speed inversion model of the wind farm based on the multivariate information, and solve the wind speed inversion model of the wind farm to obtain an inverted wind speed;

[0012] An extraction module configured to extract a set of key factors affecting the error between the inverted wind speed and the meteorological measured wind speed based on Chatterjee;

[0013] a first output module configured to input the key factor set, the inverted wind speed, and the meteorological measured wind speed into a preset GPT model, and the GPT model outputs a difference value;

[0014] The second output module is configured to correct the inverted wind speed according to the difference value to obtain a target inverted wind speed, and input the target inverted wind speed into a preset wind power prediction model, and the wind power prediction model outputs the wind power.

[0015] In a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the wind power prediction method based on wind speed inversion and Chatterjee-GPT correction of any embodiment of the present invention.

[0016] In a fourth aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon. When the program instructions are executed by a processor, the processor executes the steps of the wind power prediction method based on wind speed inversion and Chatterjee-GPT correction of any embodiment of the present invention.

[0017] The wind power prediction method and system based on wind speed inversion and Chatterjee-GPT correction of the present application realizes a more comprehensive and accurate inversion of the actual wind speed of the wind farm, uses the Chatterjee correlation coefficient to accurately identify and screen out the most significant influencing factors, improves the efficiency and robustness of the subsequent prediction model, and uses the powerful feature extraction and nonlinear relationship modeling capabilities of the GPT model to identify and quantify differences in real time, providing data support for wind speed correction, thereby significantly improving the accuracy and real-time performance of power prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 A flow chart of a wind power prediction method based on wind speed inversion and Chatterjee-GPT correction provided by one embodiment of the present invention;

[0020] Figure 2 A structural block diagram of a wind power prediction system based on wind speed inversion and Chatterjee-GPT correction provided by one embodiment of the present invention;

[0021] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] See also Figure 1 , which shows a flow chart of a wind power prediction method based on wind speed inversion and Chatterjee-GPT correction of the present application.

[0024] like Figure 1 As shown in FIG, the wind power prediction method based on wind speed inversion and Chatterjee-GPT correction specifically includes the following steps:

[0025] Step S101 : constructing a wind farm wind speed inversion model based on multivariate information, and solving the wind farm wind speed inversion model to obtain an inverted wind speed.

[0026] In this step, the multivariate information includes: wind speed, temperature, air pressure, humidity, wind direction, air density, wind turbine swept area, and overall wind farm power.

[0027] The wind speed inversion model of a wind farm is constructed based on wind speed, temperature, air pressure, humidity, wind direction, air density, wind turbine swept area, and overall power of the wind farm. The expression of the wind speed inversion model of a wind farm is:

[0028] ,

[0029] ,

[0030] ,

[0031] Where, is the fan output power, is the air pressure, is the air density, is the wind sweeping area of ​​the fan, is the wind energy utilization coefficient, is the wind speed, is the air constant, is the virtual temperature, calculated from temperature and humidity. is the overall power of the wind farm, To invert the wind speed, is the wind energy utilization coefficient obtained by inverting wind speed.

[0032] The wind speed inversion model of the wind farm is solved to obtain the inverted wind speed.

[0033] Step S102: extracting a set of key factors that affect the error between the inverted wind speed and the meteorologically measured wind speed based on Chatterjee.

[0034] In this step, the wind speed error is calculated based on the inverted wind speed and the meteorological measured wind speed, wherein the expression of the wind speed error is:

[0035] ,

[0036] Where, is the wind speed error at the i-th time point, is the inverted wind speed at the i-th time point, is the meteorological measured wind speed at the i-th time point;

[0037] According to each key factor Calculate the Chatterjee correlation coefficient with the wind speed error, where For temperature, For air pressure, For humidity, is the wind direction, and the expression of Chatterjee correlation coefficient is:

[0038] ,

[0039] Where, is the Chatterjee correlation coefficient between factor X and wind speed error e, n is the number of observations, is the rank of X after considering the wind speed error e in the i+1th group, is the rank of X after considering the wind speed error e in group i;

[0040] choose The absolute value of a number of key factors is greater than the preset threshold, and the key factors are divided into key factor sets middle.

[0041] Step S103: input the key factor set, the inverted wind speed, and the meteorological measured wind speed into a preset GPT model, and the GPT model outputs a difference value.

[0042] In this step, the expression for calculating the difference value is:

[0043] ,

[0044] Where, It is a GPT identification model based on the difference between the inverted wind speed and meteorological data. is the difference value, is the key factor set, To invert the wind speed, Measuring wind speed for meteorology.

[0045] Step S104 , correcting the inverted wind speed according to the difference value to obtain a target inverted wind speed, and inputting the target inverted wind speed into a preset wind power prediction model, which outputs wind power.

[0046] In this step, the expression for calculating the target inverted wind speed is:

[0047] ,

[0048] Where, is the difference value, To invert the wind speed, Retrieve wind speed for the target;

[0049] The expression for calculating the wind power is:

[0050] ,

[0051] Where, The wind power prediction model outputs the wind power. is the air density, is the wind sweeping area of ​​the fan, is the wind energy utilization coefficient of the corrected wind speed.

[0052] In summary, the method of the present application achieves a more comprehensive and accurate inversion of the actual wind speed in the wind farm, uses the Chatterjee correlation coefficient to accurately identify and screen out the most significant influencing factors, improves the efficiency and robustness of subsequent prediction models, and based on the powerful feature extraction and nonlinear relationship modeling capabilities of the GPT model, identifies and quantifies differences in real time, provides data support for wind speed correction, and thus significantly improves the accuracy and real-time performance of power prediction.

[0053] See also Figure 2 , which shows a structural block diagram of a wind power prediction system based on wind speed inversion and Chatterjee-GPT correction of the present application.

[0054] like Figure 2 As shown, the wind power prediction system 200 includes a solution module 210 , an extraction module 220 , a first output module 230 and a second output module 240 .

[0055] Among them, the solution module 210 is configured to construct a wind farm wind speed inversion model based on multivariate information, and solve the wind farm wind speed inversion model to obtain the inverted wind speed; the extraction module 220 is configured to extract the key factor set that affects the error between the inverted wind speed and the meteorological measured wind speed based on Chatterjee; the first output module 230 is configured to input the key factor set, the inverted wind speed and the meteorological measured wind speed into a preset GPT model, and the GPT model outputs a difference value; the second output module 240 is configured to correct the inverted wind speed according to the difference value to obtain a target inverted wind speed, and input the target inverted wind speed into a preset wind power prediction model, and the wind power prediction model outputs wind power.

[0056] It should be understood that Figure 2 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects are also applicable to Figure 2 The modules in it will not be described in detail here.

[0057] In other embodiments, embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor is caused to execute the wind power prediction method based on wind speed inversion and Chatterjee-GPT correction in any of the above method embodiments;

[0058] As an embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows:

[0059] Constructing a wind speed inversion model for a wind farm based on multivariate information, and solving the wind speed inversion model for the wind farm to obtain an inverted wind speed;

[0060] Extracting a set of key factors that affect the error between the inverted wind speed and the meteorologically measured wind speed based on Chatterjee;

[0061] Inputting the key factor set, the inverted wind speed, and the meteorological measured wind speed into a preset GPT model, the GPT model outputting a difference value;

[0062] The inverted wind speed is corrected according to the difference value to obtain a target inverted wind speed, and the target inverted wind speed is input into a preset wind power prediction model, and the wind power prediction model outputs the wind power.

[0063] The computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the wind power prediction system based on wind speed inversion and Chatterjee-GPT correction, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include a memory remotely located relative to the processor, and these remote memories may be connected to the wind power prediction system based on wind speed inversion and Chatterjee-GPT correction via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0064] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 3 The example of the bus connection is taken. The memory 320 is the computer-readable storage medium mentioned above. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, implements the wind power prediction method based on wind speed inversion and Chatterjee-GPT correction in the above method embodiment. The input device 330 can receive input digital or character information, and generate key signal input related to user settings and function control of the wind power prediction system based on wind speed inversion and Chatterjee-GPT correction. The output device 340 may include a display device such as a display screen.

[0065] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0066] As an embodiment, the electronic device is applied to a wind power prediction system based on wind speed inversion and Chatterjee-GPT correction, and is used for a client, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0067] Constructing a wind speed inversion model for a wind farm based on multivariate information, and solving the wind speed inversion model for the wind farm to obtain an inverted wind speed;

[0068] Extracting a set of key factors that affect the error between the inverted wind speed and the meteorologically measured wind speed based on Chatterjee;

[0069] Inputting the key factor set, the inverted wind speed, and the meteorological measured wind speed into a preset GPT model, the GPT model outputting a difference value;

[0070] The inverted wind speed is corrected according to the difference value to obtain a target inverted wind speed, and the target inverted wind speed is input into a preset wind power prediction model, and the wind power prediction model outputs the wind power.

[0071] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods of each embodiment or certain portions of the embodiments.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. 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 various embodiments of the present invention.

Claims

1. A wind power prediction method based on wind speed inversion and Chatterjee-GPT correction, characterized in that: include: Constructing a wind speed inversion model for a wind farm based on multivariate information, and solving the wind speed inversion model to obtain an inverted wind speed, wherein the multivariate information includes wind speed, temperature, air pressure, humidity, wind direction, air density, wind turbine swept area, and overall wind farm power; The wind farm wind speed inversion model is constructed based on multivariate information, and the wind farm wind speed inversion model is solved to obtain the inverted wind speed, including: A wind speed inversion model for a wind farm is constructed based on wind speed, temperature, air pressure, humidity, wind direction, air density, wind turbine swept area, and overall wind farm power. The expression of the wind speed inversion model for a wind farm is: ， ， ， Where, is the fan output power, is the air pressure, is the air density, is the wind sweeping area of ​​the fan, is the wind energy utilization coefficient, is the wind speed, is the air constant, is the virtual temperature, calculated from temperature and humidity. is the overall power of the wind farm, To invert the wind speed, is the wind energy utilization coefficient obtained by inverting wind speed; Solving the wind speed inversion model of the wind farm to obtain an inverted wind speed; A set of key factors influencing the error between the inverted wind speed and the meteorologically measured wind speed is extracted based on Chatterjee, wherein the set of key factors influencing the error between the inverted wind speed and the meteorologically measured wind speed is extracted based on Chatterjee and includes: The wind speed error is calculated based on the inverted wind speed and the meteorological measured wind speed, wherein the expression of the wind speed error is: ， Where, is the wind speed error at the i-th time point, is the inverted wind speed at the i-th time point, is the meteorological measured wind speed at the i-th time point; According to each key factor Calculate the Chatterjee correlation coefficient with the wind speed error, where For temperature, For air pressure, For humidity, is the wind direction, and the expression of Chatterjee correlation coefficient is: ， Where, is the Chatterjee correlation coefficient between factor X and wind speed error e, n is the number of observations, is the rank of X after considering the wind speed error e in the i+1th group, is the rank of X after considering the wind speed error e in group i; choose The absolute value of a number of key factors is greater than the preset threshold, and the key factors are divided into key factor sets middle; Inputting the key factor set, the inverted wind speed, and the meteorological measured wind speed into a preset GPT model, the GPT model outputting a difference value; The inverted wind speed is corrected according to the difference value to obtain a target inverted wind speed, and the target inverted wind speed is input into a preset wind power prediction model, and the wind power prediction model outputs the wind power.

2. A wind power prediction method based on wind speed inversion and Chatterjee-GPT correction according to claim 1, characterized in that: in, The expression for calculating the difference value is: ， Where, It is a GPT identification model based on the difference between the inverted wind speed and meteorological data. is the difference value, is the key factor set, To invert the wind speed, Measuring wind speed for meteorology.

3. The wind power prediction method based on wind speed inversion and Chatterjee-GPT correction according to claim 1 is characterized in that: in, The expression for calculating the target inversion wind speed is: ， Where, is the difference value, To invert the wind speed, Retrieve wind speed for the target; The expression for calculating the wind power is: ， Where, The wind power prediction model outputs the wind power. is the air density, is the wind sweeping area of ​​the fan, is the wind energy utilization coefficient of the corrected wind speed.

4. A wind power prediction system based on wind speed inversion and Chatterjee-GPT correction according to any one of the methods of claims 1 to 3, characterized in that: include: A solution module is configured to construct a wind speed inversion model of the wind farm based on the multivariate information, and solve the wind speed inversion model of the wind farm to obtain an inverted wind speed; An extraction module configured to extract a set of key factors affecting the error between the inverted wind speed and the meteorological measured wind speed based on Chatterjee; a first output module configured to input the key factor set, the inverted wind speed, and the meteorological measured wind speed into a preset GPT model, and the GPT model outputs a difference value; The second output module is configured to correct the inverted wind speed according to the difference value to obtain a target inverted wind speed, and input the target inverted wind speed into a preset wind power prediction model, and the wind power prediction model outputs the wind power.

5. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images