Wind power prediction method, device, equipment and medium

Abstract

The invention relates to a wind power prediction method, device and equipment and a medium, and the method comprises the steps: obtaining prediction data used for wind power function prediction in a cold-wave weather scene, and the prediction data comprises meteorological data, wind power data and cold-wave data; performing feature extraction on the cold wave data to obtain target cold wave dynamic features; and through a pre-trained power prediction model, according to the meteorological data, the wind power data and the target cold wave dynamic characteristics, determining a wind power prediction value of the wind power plant in a preset time period. The accuracy and efficiency of wind power prediction can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of wind power prediction, and in particular to a wind power prediction method, device, equipment and medium. Background Art

[0002] The wind power output by wind power technology has the characteristics of strong volatility and uncertainty, which will seriously affect the stability and safety of the power system. Therefore, wind power prediction is very important.

[0003] In the case of cold wave weather and strong winds, wind power fluctuates greatly and is affected by many factors. Traditional wind power forecasting methods mainly rely on wind direction and wind speed data, which cannot adapt well to cold wave weather scenarios, and the forecast error is large and the accuracy is relatively low. Therefore, how to accurately predict wind power in cold wave weather scenarios has become an urgent problem to be solved. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a wind power prediction method, device, equipment and medium.

[0005] According to one aspect of the present disclosure, a wind power prediction method is provided, comprising:

[0006] Acquire forecast data for wind power function forecasting in a cold wave weather scenario, the forecast data including: meteorological data, wind power data and cold wave data;

[0007] Extracting features from the cold wave data to obtain target cold wave dynamic features;

[0008] The wind power prediction value of the wind farm within a preset time period is determined by a pre-trained power prediction model according to the meteorological data, the wind power data and the target cold wave dynamic characteristics.

[0009] According to another aspect of the present disclosure, there is also provided a wind power prediction device comprising:

[0010] A data acquisition module, used to acquire prediction data for wind power function prediction in cold wave weather scenarios, wherein the prediction data includes: meteorological data, wind power data and cold wave data;

[0011] A feature extraction module is used to extract features from the cold wave data to obtain target cold wave dynamic features;

[0012] The wind power prediction module is used to determine the wind power prediction value of the wind farm within a preset time period according to the meteorological data, the wind power data and the target cold wave dynamic characteristics through a pre-trained power prediction model.

[0013] According to another aspect of the present disclosure, an electronic device is provided, the electronic device comprising:

[0014] processor;

[0015] a memory for storing instructions executable by the processor;

[0016] The processor is used to read the executable instructions from the memory and execute the instructions to implement the above method.

[0017] According to another aspect of the present disclosure, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the above method.

[0018] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0019] The technical solution provided by the embodiment of the present disclosure includes: obtaining prediction data for wind power function prediction under cold wave weather scenarios, the prediction data including: meteorological data, wind power data and cold wave data; extracting features from the cold wave data to obtain target cold wave dynamic features; determining the wind power prediction value of the wind farm within a preset time period based on the meteorological data, wind power data and target cold wave dynamic features through a pre-trained power prediction model. Compared with the prior art, the present technical solution newly introduces cold wave data and the target cold wave dynamic features extracted therefrom, takes the target cold wave dynamic features as the key factor for wind power prediction, and combines meteorological data and wind power data to effectively improve the accuracy and prediction precision of wind power prediction. The pre-trained power prediction model is used in the prediction, which can take into account both prediction accuracy and prediction efficiency, thereby providing minute-level rapid predictions to meet the needs of real-time operation of the power system. Therefore, the present disclosure improves the accuracy and efficiency of wind power prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0022] Figure 1 This is a flow chart of the wind power prediction method described in the embodiment of the present disclosure;

[0023] Figure 2It is a structural schematic diagram of the wind power prediction device according to an embodiment of the present disclosure;

[0024] Figure 3 It is a schematic diagram of the structure of the electronic device described in the embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0026] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0027] Figure 1 A flow chart of a wind power prediction method provided in an embodiment of the present disclosure, which can be applied to wind power prediction in cold wave weather scenarios. The wind power prediction method can be executed by a wind power prediction device, which can be implemented in software and / or hardware, such as electronic equipment and servers.

[0028] like Figure 1 As shown, the wind power prediction method provided by this embodiment may include the following steps.

[0029] S102, obtaining prediction data for wind power function prediction in a cold wave weather scenario, the prediction data including: meteorological data, wind power data and cold wave data.

[0030] The meteorological data refers to the meteorological observation data and reanalysis data related to the cold wave weather scenario in the geographical area where the wind farm is located, such as temperature, wind speed, air pressure, wind direction, etc. The meteorological data can be obtained through ground observation stations, satellite remote sensing, numerical forecast model data (such as ERA5, GFS), etc.

[0031] Wind power data includes, for example, historical wind speed, wind direction, wind power output, and other data in the geographical area where the wind farm is located.

[0032] Cold wave data include data on the spatial structure, propagation path, intensity, and spatiotemporal distribution of at least one historical cold wave event that has occurred.

[0033] This embodiment may include: preprocessing the forecast data; wherein the preprocessing includes: data cleaning, and time matching of meteorological data and wind power data.

[0034] Specifically, data cleaning is performed on each prediction data, and the data cleaning includes, for example, removing outliers in each prediction data and completing missing values ​​in each prediction data. Data cleaning can improve the accuracy of the prediction data.

[0035] Then, the meteorological data and wind power data in the forecast data are aligned and synchronized in the time dimension to achieve time matching.

[0036] In addition, initial feature extraction can be performed on the cold wave data, such as extracting data such as temperature drop and wind speed change rate, and adding them to the cold wave data.

[0037] This embodiment performs subsequent steps based on the predicted data after the above preprocessing.

[0038] S104, extracting features from the cold wave data to obtain the target cold wave dynamic features.

[0039] In this embodiment, firstly, according to the preset temperature variation range and wind speed variation range, the target time period for the occurrence of the cold wave event is determined in the cold wave data.

[0040] Specifically, the start and end of the cold wave process can be defined according to the preset temperature change range and wind speed change range. Based on this, the target time period for the occurrence of the cold wave event is determined in the cold wave data according to the temperature change range and wind speed change range.

[0041] Secondly, the target features of the cold wave data within the target time period are extracted to obtain the initial cold wave dynamic characteristics; among which, the target features include: time features, spatial features and key features used to characterize cold wave weather.

[0042] In this embodiment, the target features of the cold wave data in the target time period can be extracted by using a pre-trained feature extraction model. The target features to be extracted are as follows:

[0043] Temporal characteristics: arrival lag and duration of cold waves, etc.;

[0044] Spatial characteristics: the path of the cold wave, the scope of impact, the relative position relationship with the wind farm, etc.;

[0045] Key factors to be investigated: temperature gradient, speed of cold air moving southward, wind field disturbance, pressure gradient, etc.

[0046] Among them, the cold wave data within the target time period can more accurately reflect the characteristics of the real cold wave process, and has a higher reference value when used for wind power prediction; at the same time, only extracting target features of the cold wave data within the target time period can reduce the amount of data processing and improve the efficiency of feature extraction.

[0047] Then, the target cold wave dynamic characteristics related to the electric power change are screened out from the initial cold wave dynamic characteristics.

[0048] This embodiment can screen out the target cold wave dynamic features that are most closely related to the change in electric power from the initial cold wave dynamic features through feature engineering. The specific implementation method can be referred to as shown below.

[0049] The Pearson correlation coefficient is used to analyze the correlation between each target feature in the initial cold wave dynamic characteristics and wind power; based on the correlation, the target cold wave dynamic characteristics related to the change of electric power are screened out from the initial cold wave dynamic characteristics.

[0050] Specifically, the Pearson correlation coefficient between each target feature in the initial cold wave dynamic characteristics and the wind power can be calculated. The larger the absolute value of the Pearson correlation coefficient, the stronger the correlation between the two. Based on this, this embodiment samples the absolute value of the Pearson correlation coefficient to represent the correlation.

[0051] According to the correlation between each target feature and wind power, the features with correlation higher than a preset correlation threshold are selected as the target cold wave dynamic features most closely related to the change of electric power.

[0052] In this embodiment, different target features in the initial cold wave dynamics feature have different effects on wind power. Analyzing the correlation between different features and wind power in advance and selecting closely related target cold wave dynamics features as inputs of the power prediction model has the following benefits:

[0053] By screening the target cold wave dynamic features related to electric power changes, the dimensionality of the power forecast model input can be reduced, the computational complexity can be reduced, the prediction speed can be improved, and computing and storage resources can be saved. The amount of information captured by the model can be increased, which helps to improve the prediction accuracy and reliability of the model. The interpretability of the model is very important for building trust and understanding how the model makes predictions. Reducing the number of input features, especially retaining the most relevant target cold wave dynamic features, can make the model easier to understand and explain.

[0054] S106, determining the wind power forecast value of the wind farm within a preset time period through a pre-trained power forecast model according to meteorological data, wind power data and target cold wave dynamic characteristics.

[0055] The model structure of the power prediction model in this embodiment can be an algorithm model such as a neural network model, a support vector machine model, and a decision tree regression model, which is not limited here. The power prediction model can combine the wind energy conversion formula and the principle of atmospheric dynamics to budget wind power.

[0056] In this embodiment, meteorological data, wind power data and target cold wave dynamic characteristics are input into the power prediction model; among them, meteorological data include temperature, wind speed, wind direction, air pressure, etc., wind power data include height and length of wind farm, etc., and target tidal dynamic characteristics include temperature gradient, pressure gradient, wind speed change rate, etc.

[0057] The power prediction model is used to process meteorological data, wind power data and target cold wave dynamic characteristics according to the preset wind energy conversion formula and atmospheric dynamics principles, and outputs the predicted wind power value of the wind farm in the future preset time period (such as 1 hour, 3 hours, 6 hours, 24 hours).

[0058] In one embodiment, the operating speed of the power prediction model can be improved based on high performance computing (HPC) or an edge computing platform, the prediction timeliness can be optimized, and the prediction of wind power in minutes can be achieved.

[0059] Based on the above embodiments, the present disclosure may further include: acquiring a current wind power value, and generating risk warning information when a change range between a predicted wind power value and a current wind power value exceeds a preset range threshold.

[0060] In this embodiment, the variation between the predicted wind power value and the current wind power value exceeds the preset amplitude threshold, indicating that the cold wave may cause a large fluctuation in wind power. In this case, risk warning information is generated to realize the warning function.

[0061] Regarding the power prediction model involved in the aforementioned embodiment, in order to enable the power prediction model to be used for wind power prediction and achieve the expected prediction effect, model training needs to be performed in advance. Based on this, this embodiment provides a power prediction model training method, including:

[0062] A training data set is obtained, wherein the training data in the training data set includes: sample meteorological data, sample wind power data, sample cold wave dynamic characteristics and sample wind power values; a power prediction model to be trained is iteratively trained according to the training data set to obtain a power prediction model.

[0063] In specific implementation, the power prediction model to be trained can be iteratively trained according to the training data set. During each training process, the loss value corresponding to the current training process is obtained, and the model parameters of the power prediction model are updated using the loss value until the model converges to obtain the final power prediction model.

[0064] Take the Kth (K≥1) training as an example. During the Kth training process, the sample meteorological data, sample wind power data, and sample cold wave dynamic characteristics are input into the power prediction model to be trained to obtain the intermediate power prediction value. It can be understood that when K is equal to 1, the power prediction model is trained for the first time, and the intermediate power prediction model at this time is the initial power prediction model to be trained. Thereafter, the power prediction model used each time is the model after the parameters of the last training are adjusted, that is, the intermediate power prediction model.

[0065] Next, according to a preset error function (such as root mean square error RMSE, mean absolute percentage error MAPE, etc.), the loss value between the intermediate power prediction value and the sample wind power value is calculated, and it is detected whether the loss value is less than a preset loss value threshold.

[0066] If the loss value is not less than the loss value threshold, the intermediate power prediction model is used as a new power prediction model to be trained and the next round of training is continued.

[0067] If the loss value is less than the loss value threshold, the model is determined to have converged, and the intermediate power prediction model corresponding to the current iteration process is used as the trained power prediction model.

[0068] This embodiment iteratively trains the power prediction model according to the training data set, so that the trained power prediction model can accurately realize the prediction of wind power, improve the adaptability of the power prediction model to the characteristics of different cold wave weather scenarios, enhance the model generalization ability of the power prediction model, and better cope with complex weather systems.

[0069] In addition, in practical applications, the accuracy of the prediction effect of the trained power prediction model can be verified based on the real meteorological data, real electricity data, real cold wave dynamic characteristics and real wind power values ​​corresponding to the historical cold wave events that have occurred in the past. And if the verification fails, the power prediction model can be trained again through data enhancement and other methods to improve the prediction accuracy of the power prediction model.

[0070] In summary, the wind power prediction method provided by the embodiment of the present disclosure includes: obtaining prediction data for wind power function prediction under cold wave weather scenarios, the prediction data including: meteorological data, wind power data and cold wave data; extracting features from the cold wave data to obtain target cold wave dynamic features; determining the wind power prediction value of the wind farm within a preset time period according to the meteorological data, wind power data and target cold wave dynamic features through a pre-trained power prediction model. Compared with the prior art, the present technical solution newly introduces cold wave data and the target cold wave dynamic features extracted therefrom, takes the target cold wave dynamic features as the key factor for wind power prediction, and combines meteorological data and wind power data to effectively improve the accuracy and prediction precision of wind power prediction. The pre-trained power prediction model is used in the prediction, which can take into account both prediction accuracy and prediction efficiency, thereby providing minute-level rapid prediction to meet the needs of real-time operation of the power system. Therefore, the present disclosure improves the accuracy and efficiency of wind power prediction.

[0071] Figure 2 The following is a schematic diagram of the structure of a wind power prediction device provided by an embodiment of the present disclosure. Figure 2 As shown, the wind power prediction device may include the following modules.

[0072] The data acquisition module 210 is used to acquire prediction data for wind power function prediction in a cold wave weather scenario, wherein the prediction data includes: meteorological data, wind power data and cold wave data;

[0073] A feature extraction module 220 is used to extract features from the cold wave data to obtain target cold wave dynamic features;

[0074] The wind power prediction module 230 is used to determine the wind power prediction value of the wind farm within a preset time period according to the meteorological data, the wind power data and the target cold wave dynamic characteristics through a pre-trained power prediction model.

[0075] In one embodiment, the feature extraction module 220 is further used to:

[0076] Determining a target time period for a cold wave event to occur in the cold wave data according to a preset temperature variation range and wind speed variation range;

[0077] Extracting target features from the cold wave data within the target time period to obtain initial cold wave dynamic features; wherein the target features include: time features, spatial features, and key features for characterizing cold wave weather;

[0078] Target cold wave dynamic characteristics related to electric power changes are screened out from the initial cold wave dynamic characteristics.

[0079] The implementation principle and technical effects of the device provided in this embodiment are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0080] Figure 3 The structure diagram of an electronic device provided by the embodiment of the present disclosure is shown in FIG. Figure 3 As shown, the electronic device 300 includes one or more processors 301 and a memory 302 .

[0081] The processor 301 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 300 to perform desired functions.

[0082] The memory 302 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 301 may run the program instructions to implement the wind power prediction method of the embodiment of the present disclosure described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0083] In one example, the electronic device 300 may further include: an input device 303 and an output device 304 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0084] In addition, the input device 303 may also include, for example, a keyboard, a mouse, and the like.

[0085] The output device 303 can output various information to the outside, including the determined distance information, direction information, etc. The output device 304 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0086] Of course, to simplify, Figure 3 Only some of the components related to the present disclosure in the electronic device 300 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 300 may also include any other appropriate components.

[0087] Furthermore, this embodiment also provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the above-mentioned wind power prediction method.

[0088] A computer program product of a wind power prediction method, device, electronic device and medium provided in the embodiments of the present disclosure includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be found in the method embodiments and will not be repeated here.

[0089] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0090] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A wind power prediction method, characterized in that: include: Acquire forecast data for wind power function forecasting in a cold wave weather scenario, the forecast data including: meteorological data, wind power data and cold wave data; Extracting features from the cold wave data to obtain target cold wave dynamic features; The wind power prediction value of the wind farm within a preset time period is determined by a pre-trained power prediction model according to the meteorological data, the wind power data and the target cold wave dynamic characteristics.

2. The method according to claim 1, characterized in that The step of extracting features from the cold wave data to obtain target cold wave dynamic features includes: Determining a target time period for a cold wave event to occur in the cold wave data according to a preset temperature variation range and wind speed variation range; Extracting target features from the cold wave data within the target time period to obtain initial cold wave dynamic features; wherein the target features include: time features, spatial features, and key features for characterizing cold wave weather; Target cold wave dynamic characteristics related to electric power changes are screened out from the initial cold wave dynamic characteristics.

3. The method according to claim 2, characterized in that The step of selecting target cold wave dynamic features related to electric power changes from the initial cold wave dynamic features includes: The Pearson correlation coefficient is used to analyze the correlation between each target feature and wind power in the initial cold wave dynamics characteristics; According to the correlation, target cold wave dynamic characteristics related to electric power changes are screened out from the initial cold wave dynamic characteristics.

4. The method according to claim 1, characterized in that: The method further comprises: The current wind power value is obtained, and when the variation range between the wind power prediction value and the current wind power value exceeds a preset range threshold, risk warning information is generated.

5. The method according to claim 1, characterized in that The method further comprises: Acquire a training data set, wherein the training data in the training data set includes: sample meteorological data, sample wind power data, sample cold wave dynamic characteristics, and sample wind power values; The power prediction model to be trained is iteratively trained according to the training data set to obtain the power prediction model.

6. The method according to claim 1, characterized in that The method comprises: The forecast data is preprocessed; wherein the preprocessing includes: data cleaning, and time matching of the meteorological data and the wind power data.

7. A wind power prediction device, characterized in that: include: A data acquisition module, used to acquire prediction data for wind power function prediction in cold wave weather scenarios, wherein the prediction data includes: meteorological data, wind power data and cold wave data; A feature extraction module is used to extract features from the cold wave data to obtain target cold wave dynamic features; The wind power prediction module is used to determine the wind power prediction value of the wind farm within a preset time period according to the meteorological data, the wind power data and the target cold wave dynamic characteristics through a pre-trained power prediction model.

8. The device according to claim 7, characterized in that The feature extraction module is also used for: Determining a target time period for a cold wave event to occur in the cold wave data according to a preset temperature variation range and wind speed variation range; Extracting target features from the cold wave data within the target time period to obtain initial cold wave dynamic features; wherein the target features include: time features, spatial features, and key features for characterizing cold wave weather; Target cold wave dynamic characteristics related to electric power changes are screened out from the initial cold wave dynamic characteristics.

9. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device implements the method according to any one of claims 1 to 6.

Images