Wind speed prediction method and device, electronic equipment, storage medium and computer program product
By training a wind speed prediction model based on climate factor indices and historical wind speed data, the accuracy problem of medium- and long-term wind speed prediction has been solved, achieving more accurate wind speed prediction and supporting power trading and resource optimization.
Patent Information
- Application Number
- CN202411110814.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-13
- Publication Date
- 2026-02-13
AI Technical Summary
In medium- and long-term wind speed forecasting, existing technologies rely on climate model predictions that are idealized and have limited effectiveness in predicting local wind speeds. Furthermore, statistical extrapolation methods based on historical data cannot cope with sudden climate changes, resulting in forecasts that fail to meet the requirements of medium- and long-term power trading.
The wind speed prediction method is adopted. By obtaining the climate factor index of the predetermined area and combining it with historical wind speed data, the wind speed prediction model is trained. The prediction is made using atmospheric circulation and sea surface temperature index. Considering the relationship between climate factors and wind speed, a regression model is established to predict wind speed.
It improves the accuracy of medium- and long-term wind speed forecasts, better reflects the influence of climate such as the atmosphere and ocean, provides more accurate wind speed forecast results, and supports medium- and long-term power generation forecasts and optimal allocation of power resources.
Smart Images
Figure CN121526355A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present disclosure relates to the field of wind speed prediction, and in particular, to a wind speed prediction method and device, electronic equipment, storage medium and computer program product. BACKGROUND
[0002] With the continuous advancement of power market reform, the competitiveness and openness of the power market are gradually enhanced. As an important transaction mode of the power market, the medium and long-term power transaction helps to realize the optimal allocation of power resources and fair competition in the market. The key to the medium and long-term power transaction is the prediction of the medium and long-term power load, and the prediction of the wind turbine power generation is mainly determined by the prediction of the wind speed. Therefore, the medium and long-term wind speed prediction is very important for new energy power transaction.
[0003] The medium and long-term wind speed prediction needs to predict the monthly wind speed in the next 1-2 years in the current month. The current medium and long-term wind speed prediction of the wind power plant mainly falls into two categories. One is to use the prediction results of the climate model. Although the climate model follows certain atmospheric physical equation set laws, it is more inclined to predict large-scale circulation situation, and may be idealized, so the effect on local wind speed is general. The other is to use statistical extrapolation method combined with period and variability to make time series extrapolation prediction based on historical measured wind speed. This method takes into account the historical measured data, but for climate mutation or insufficient historical data, the prediction result cannot reach the level required by the medium and long-term power transaction. SUMMARY
[0004] The wind speed prediction method, device, electronic equipment, storage medium and computer program product provided by the exemplary embodiments of the present disclosure can at least solve the above technical problems and other technical problems not mentioned above.
[0005] According to one aspect of the present disclosure, a wind speed prediction method is provided, comprising: obtaining a climate factor index in a predetermined region in a first time interval; inputting the climate factor index in the first time interval into a wind speed prediction model to obtain a wind speed in a second time interval in the predetermined region; wherein the wind speed prediction model is obtained by training the following steps: obtaining training data, wherein the training data includes climate factor indexes and historical wind speeds in the predetermined region, and the climate factor indexes include multiple atmospheric circulation indexes and multiple sea temperature indexes; taking the climate factor indexes in a third time interval in the predetermined region as input feature data, and taking the historical wind speeds in a fourth time interval as label data, training a wind speed prediction model reflecting the relationship between the climate factor indexes and the wind speed, wherein the third time interval is earlier than the fourth time interval.
[0006] Optionally, the third time interval is at least one predetermined time interval before the fourth time interval; and the obtaining the training data further comprises: for each climate factor index in each predetermined time interval in the third time interval, calculating a correlation between the climate factor index and the historical wind speed of the fourth time interval respectively; performing a significance test on the calculated correlations; and screening the climate factor indices in the training data according to a result of the significance test.
[0007] Optionally, the obtaining the training data further comprises: performing normalization processing on each climate factor index in the screened climate factor indices.
[0008] Optionally, the wind speed prediction model is a regression model.
[0009] Optionally, the historical wind speed of the fourth time interval is an average of wind speed data in the fourth time interval.
[0010] Optionally, the method further comprises: obtaining historical wind speeds in the predetermined area and a wind speed of a target electric field, wherein the target electric field is located in the predetermined area; calculating a correlation coefficient between the wind speeds in the predetermined area and the wind speed of the target electric field; and obtaining a predicted wind speed of the target electric field in the second time interval according to the correlation coefficient and the predicted wind speed of the second time interval.
[0011] Optionally, the calculating the correlation coefficient between the wind speeds in the predetermined area and the wind speed of the target electric field comprises: for historical wind speeds and the wind speed of the target electric field in which a first time identifier is the same and a second time identifier is the same, calculating a ratio of the historical wind speeds and the wind speed of the target electric field; and for the calculated ratios in which the second time identifier is the same, calculating a mean value of the ratios as the correlation coefficient between the wind speeds in the predetermined area and the wind speed of the target electric field.
[0012] According to another aspect of the present disclosure, a wind speed prediction apparatus is also provided, comprising: an index obtaining unit configured to obtain climate factor indexes in a predetermined region in a first time interval; and a wind speed prediction unit configured to input the climate factor indexes in the first time interval into a wind speed prediction model to obtain wind speed in a second time interval in the predetermined region; wherein the wind speed prediction model is trained by the following steps: obtaining training data, wherein the training data comprises climate factor indexes and historical wind speed in the predetermined region, and the climate factor indexes comprise a plurality of atmospheric circulation indexes and a plurality of sea temperature indexes; taking climate factor indexes in a third time interval in the predetermined region as input feature data, taking historical wind speed in a fourth time interval as label data, and training a wind speed prediction model reflecting the relationship between the climate factor indexes and the wind speed, wherein the third time interval is earlier than the fourth time interval.
[0013] According to another aspect of the present disclosure, an electronic device is also provided, comprising: at least one processor; and at least one memory storing computer executable instructions, wherein the computer executable instructions, when executed by the at least one processor, cause the at least one processor to perform the wind speed prediction method according to any one of the above.
[0014] According to another aspect of the present disclosure, a computer readable storage medium storing instructions is also provided, wherein the instructions, when executed by at least one processor, cause the at least one processor to perform the wind speed prediction method according to any one of the above.
[0015] According to another aspect of the present disclosure, a computer program product is also provided, comprising computer program / instructions, which, when executed by a processor, implement the wind speed prediction method according to any one of the above.
[0016] The technical solutions provided by the embodiments of the present disclosure bring at least the following beneficial effects:
[0017] According to the wind speed prediction method, apparatus, electronic device, storage medium and computer program product of the present disclosure, the historical wind speed and the climate factor indexes in a region can be taken as training data of a wind speed prediction model, and the wind speed prediction model can be trained based on historical regional wind speed data and historical climate factor indexes, so that the historical measured data of wind speed can be considered, and the influence of climate such as atmosphere and ocean can also be taken into account, the deficiencies of the traditional dynamic method considering only climate model and the statistical extrapolation prediction model are supplemented, and the prediction effect can be achieved by using the indication of the future wind speed by the climate factor indexes. BRIEF DESCRIPTION OF DRAWINGS
[0018] The accompanying drawings, which are incorporated into 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, and do not constitute an improper limitation on the present disclosure.
[0019] Figure 1 A flow chart showing the training step of the wind speed prediction model in an exemplary embodiment of the present disclosure;
[0020] Figure 2 A flow chart showing the wind speed prediction method in an exemplary embodiment of the present disclosure;
[0021] Figure 3 A flow chart showing a wind speed prediction method in an exemplary embodiment of the present disclosure;
[0022] Figure 4 A schematic diagram showing the effect of the wind speed prediction method in an exemplary embodiment of the present disclosure;
[0023] Figure 5 A block diagram showing a wind speed prediction device in an exemplary embodiment of the present disclosure;
[0024] Figure 6 A block diagram showing an electronic device in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION
[0025] In order to make the ordinary person in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below in conjunction with the drawings.
[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following embodiments do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0027] It should be noted that "at least one of a plurality" appearing in the present disclosure represents three types of alternatives, including "any one of the plurality", "a combination of any multiple of the plurality", and "all of the plurality". For example, "including at least one of A and B" includes the following three alternatives: (1) including A; (2) including B; (3) including A and B. For another example, "performing at least one of step one and step two" represents the following three alternatives: (1) performing step one; (2) performing step two; (3) performing step one and step two.
[0028] Two methods are used in the related art for wind speed prediction: (1) a dynamic prediction method based on a climate model; and (2) an extrapolation prediction method based on a mathematical statistical method. However, these methods have the following disadvantages: method (1) considers the atmospheric motion equation set and can follow certain physical laws, and the wind speed can be directly predicted by the climate model, but the elements in this method are more focused on large-scale circulation, such as 500 hPa height field, surface pressure, and other elements, which can cause large deviations in the prediction of wind speed in the near-surface layer; method (2) is an extrapolation prediction method based on a mathematical statistical method, which considers historical wind speed measurement data of the electric field, but does not consider the influence of atmospheric circulation and the ocean and other external forces, and a pure statistical method cannot extract wind speed mutation information caused by climate change.
[0029] To solve the above problems, the present disclosure provides a wind speed prediction method, device, electronic equipment, storage medium and computer program product, which can use regional historical wind speed and climate factor index as training data of a wind speed prediction model, and train the wind speed prediction model based on historical regional wind speed data and historical early climate factor index, so that both historical measurement data of wind speed and climate influence of atmosphere and ocean can be considered, the deficiencies of traditional dynamic methods of climate model and statistical extrapolation prediction models are supplemented, and the prediction effect can be achieved by using the indication of early climate factor index on future wind speed.
[0030] In the following, the wind speed prediction method, device, electronic equipment, storage medium and computer program product of the present disclosure will be described in detail with reference to the accompanying drawings. Figures 1 to 6 The wind speed prediction method, device, electronic equipment, storage medium and computer program product of the present disclosure will be described in detail.
[0031] Figure 1 A flowchart showing the training steps of the wind speed prediction model in the exemplary embodiment of the present disclosure is shown.
[0032] With reference to the accompanying drawings, Figure 1 The wind speed prediction model can be trained by the following steps:
[0033] At step 101, training data is obtained, wherein the training data comprises climate factor indices and historical wind speeds in a predetermined region, and the climate factor indices comprise a plurality of atmospheric circulation indices and a plurality of sea temperature indices.
[0034] According to an example embodiment of the present disclosure, the predetermined region is a region where the target power plant is located.
[0035] According to an example embodiment of the present disclosure, since wind speed is mainly affected by atmospheric circulation, solar radiation, climate change, etc., changes in the atmosphere and the ocean have certain indicative significance for medium and long-term wind speed; and the National Climate Center defines a plurality of climate factor indices published monthly, which are used to monitor large-scale changes in the atmosphere and the ocean, so these climate factor indices can be used for wind speed prediction.
[0036] The climate factor indices can use 114 indices defined, monitored and published by the National Climate Center, which include 88 atmospheric circulation indices and 26 sea temperature indices. The measured data of the last month will be published at the beginning of each month, and the historical data can be traced back to January 1950, the earliest.
[0037] It can be understood that the number of items, publication and traceable time, definition and monitoring subject of the climate factor indices do not cause any limitation to the climate factor indices used by the present disclosure, as long as the climate factor indices can reflect information about the atmosphere and the ocean.
[0038] According to an example embodiment of the present disclosure, the historical wind speed in the predetermined region can use the fifth-generation atmospheric reanalysis dataset ERA5 (European Centre for Medium-Range Weather Forecasts Integrated Forecast System Reanalysis Version 5) provided by the European Centre for Medium-Range Weather Forecasts. The historical wind speed in the predetermined region can be obtained through the ERA5 reanalysis data.
[0039] According to an example embodiment of the present disclosure, the historical wind speed in the predetermined region can also use any other meteorological reanalysis data source, including but not limited to the Japanese JRA55 (the Japanese 55-year Reanalysis), the American NCAR (National Center for Atmospheric Research), the Chinese CMA (China Meteorological Administration) and other official or unofficial meteorological reanalysis datasets.
[0040] According to the exemplary embodiments of the present disclosure, the obtaining the training data can further include, but is not limited to, the following steps: for the obtained training data, the correlation between each climate factor index of each predetermined time interval in the third time interval and the historical wind speed of the fourth time interval can be calculated respectively; wherein the third time interval is at least one predetermined time interval before the fourth time interval; the calculated correlation is subjected to a significance test; and the climate factor index in the training data is screened according to the result of the significance test. The feature screening can be performed by correlation analysis and the like, so as to obtain the previous climate factor index which has higher indicative significance to the regional wind speed.
[0041] According to the exemplary embodiments of the present disclosure, taking the predetermined time interval as a month interval for example, the third time interval is 12 month intervals (at least one predetermined time interval) before the fourth time interval, and the fourth time interval can be 1 month interval. Each climate factor index of each month interval (predetermined time interval) in the third time interval can be a total of 12*114=1368 climate factor indexes, and each climate factor index can be taken as a separate feature to calculate the correlation between each feature and the historical wind speed of the fourth time interval.
[0042] It can be understood that the predetermined time interval can also be other span time intervals, and the present disclosure can not limit this.
[0043] According to the exemplary embodiments of the present disclosure, for the climate factor index of the third time interval in the obtained training data, the data set can be at least one predetermined time interval before the time interval corresponding to the currently obtainable latest climate factor index; for example, taking the predetermined time interval as a month interval for example, the climate factor index of the third time interval in the training data can be a data set of 12 month intervals (at least one predetermined time interval) before the time interval corresponding to the currently obtainable latest climate factor index.
[0044] For example only, if the current latest climate factor index is the data set of April 2024, the wind speed of one month interval (second time interval) of May 2024 and after needs to be predicted, the prediction data set can be the climate factor index of May 2023 to April 2024 (first time interval), and the training data can be the data set before April 2024 (at least one predetermined time interval) and before April 2023 (third time interval) to predict and train the wind speed of any one month interval (fourth time interval) after April 2023; specifically, when the wind speed of April 2024 (fourth time interval) is predicted and trained, the training data can be the climate factor index of May 2022 to April 2023 (third time interval).
[0045] According to the exemplary embodiments of the present disclosure, in the process of feature screening by calculating the correlation between each feature and the historical wind speed of the fourth time interval, the 1368 climate factor indexes of the third time interval in the training data can be correlated with the historical wind speed of the fourth time interval one by one and subjected to significance test, the top 30 climate factor indexes in the degree of correlation (correlation coefficient) from large to small which pass the significance test can be selected as the climate factor indexes which have greater influence on the historical wind speed, and these climate factor indexes can be considered as the key climate factor indexes of the historical wind speed in the early stage which pass the reliability test. If there are less than 30 climate factor indexes which pass the significance test, they can be directly selected as the key climate factor indexes without sorting.
[0046] It can be understood that the number of key climate factor indexes can also be any other feasible number, and the present disclosure can not be limited thereto.
[0047] According to the exemplary embodiments of the present disclosure, the historical wind speed of the fourth time interval is the average of the wind speed data in the fourth time interval. The average of the interval wind speed can well reflect the overall level of the interval wind speed.
[0048] According to the exemplary embodiments of the present disclosure, obtaining the training data can further include but not limited to the following steps: each climate factor index in the screened climate factor index can be subjected to normalization processing. Normalization can eliminate the influence of the magnitude between data to obtain more accurate results in subsequent calculations.
[0049] According to the exemplary embodiments of the present disclosure, since there can be a large magnitude difference between these climate factor indexes, the key climate factor indexes obtained by feature screening can be subjected to normalization processing to eliminate the influence of the magnitude between factors; specifically, a MinMaxScalaer scaler can be established to perform feature normalization processing.
[0050] It can be understood that other feasible manners can also be used for feature normalization, and the present disclosure can not be limited thereto.
[0051] Referring back to Figure 1 In step 102, the climate factor index of a third time interval in a predetermined area is taken as input feature data, the historical wind speed of a fourth time interval is taken as label data, and a wind speed prediction model reflecting the relationship between the climate factor index and the wind speed is trained, wherein the third time interval is earlier than the fourth time interval.
[0052] According to an exemplary embodiment of the present disclosure, the wind speed prediction model can be a regression model. The regression model can reflect the relationship between the climate factor index and the wind speed for use in predictive analysis of the wind speed according to the climate factor index.
[0053] It can be understood that, in addition to the regression model, the wind speed prediction model can also be any other machine learning model, including but not limited to XGBoost (Extreme Gradient Boosting) and the like.
[0054] According to an exemplary embodiment of the present disclosure, when establishing the regression model, a regression model between the key climate factor index of the wind speed in the early stage in the normalized training data and the average wind speed of the corresponding area can be established, and the established model can be trained based on the training data.
[0055] After the wind speed prediction model is trained, the wind speed prediction model can be used for wind speed prediction.
[0056] Figure 2 A flowchart of a wind speed prediction method in an exemplary embodiment of the present disclosure is shown.
[0057] Referring to Figure 2 In step 201, the climate factor index of a first time interval in a predetermined area is obtained.
[0058] According to an exemplary embodiment of the present disclosure, the climate factor index of the 12-month interval (first time interval) before the time interval corresponding to the latest climate factor index that can be currently obtained in the area where the target electric field is located can be obtained as a prediction data set.
[0059] In step 202, the climate factor index of the first time interval is input into the wind speed prediction model to obtain the wind speed of a second time interval in the predetermined area.
[0060] According to the exemplary embodiments of the present disclosure, the key climate factor indexes corresponding to the wind speed to be predicted in the prediction data set can be input into the trained wind speed prediction model, so as to predict the average wind speed of the second time interval in the area where the target power plant is located.
[0061] According to the exemplary embodiments of the present disclosure, the second time interval can be the future wind speed in at least one predetermined time interval (for example, the at least one predetermined time interval can be a 14-month interval) after the time interval corresponding to the latest climate factor index that can be currently obtained.
[0062] According to the exemplary embodiments of the present disclosure, the wind speed prediction method can further include but is not limited to the following steps: obtaining the historical wind speed in a predetermined area and the wind speed of a target power plant, wherein the target power plant is located in the predetermined area; calculating the correlation coefficient between the wind speed in the predetermined area and the wind speed of the target power plant; and obtaining the predicted wind speed of the target power plant in the second time interval according to the correlation coefficient and the predicted wind speed in the second time interval. The correlation coefficient between the regional wind speed and the power plant wind speed can be used to calculate the power plant wind speed more accurately based on the regional wind speed.
[0063] According to the exemplary embodiments of the present disclosure, the obtained historical wind speed in the predetermined area is the historical wind speed in the training data.
[0064] According to the exemplary embodiments of the present disclosure, the correlation coefficient between the wind speed in the predetermined area and the wind speed of the target power plant can include but is not limited to the Pearson correlation coefficient, the Spearman's rank correlation coefficient, the Kendall's tau coefficient, and the like.
[0065] According to the exemplary embodiments of the present disclosure, the calculation of the correlation coefficient between the wind speed in the predetermined area and the wind speed of the target power plant can include but is not limited to the following steps: for the historical wind speed in the predetermined area and the wind speed of the target power plant, the historical wind speed and the wind speed of the target power plant with the same first time identifier and the same second time identifier are calculated; and for the calculated ratios with the same second time identifier, the mean value of the ratios is calculated as the correlation coefficient between the wind speed in the predetermined area and the wind speed of the target power plant. The mean value of the ratios between the regional wind speed and the power plant wind speed corresponding to the time interval can be used as the correlation coefficient between them, so as to improve the calculation efficiency of the correlation coefficient.
[0066] According to the exemplary embodiments of the present disclosure, the first time identifier can be a year identifier, and the second time identifier can be a month identifier. It can be understood that the first time identifier and the second time identifier can also be other feasible time identifiers, and the present disclosure can not limit this.
[0067] The ratio between the historical wind speed in the predetermined area (area wind speed) and the wind speed of the target electric field (electric field wind speed) obtained can be calculated monthly and the average of the monthly ratios can be calculated to obtain a monthly average coefficient as the correlation coefficient between the wind speed in the predetermined area and the wind speed of the target electric field. For example, the calculation method of the monthly average coefficient in January is to calculate the average of the ratio between all the area wind speeds and the electric field wind speeds in January in the obtained data.
[0068] Figure 3 A flowchart of a wind speed prediction method in the exemplary embodiments of the present disclosure is shown.
[0069] Referring to Figure 3 According to the exemplary embodiments of the present disclosure, the key factor (key climate factor index) with a higher degree of wind speed correlation can be first determined from the historical early stage climate factors (historical data of the climate factor index of the historical wind speed in the predetermined area), and then a regression model can be established and trained according to the historical area wind speed (historical wind speed in the predetermined area) and the key factor. The current key climate factor (key climate factor index of the early stage wind speed in the predetermined area to be predicted) can be input into the trained regression model to obtain the predicted area wind speed (predicted wind speed in the predetermined area), and the predicted single electric field wind speed (predicted electric field wind speed in the predetermined area) in the corresponding area can be obtained according to the predicted area wind speed.
[0070] According to the exemplary embodiments of the present disclosure, the historical wind speed of the target electric field in the predetermined area can be processed as monthly data, and then the key climate factor index of the wind speed early stage indicating the wind speed change can be determined from the climate factor index, and then the long-term wind speed in the electric field can be predicted based on the current key climate factor index (key climate factor index of the early stage electric field wind speed in the predetermined area to be predicted).
[0071] According to the exemplary embodiments of the present disclosure, the wind speed data predicted by the wind speed prediction method in the exemplary embodiments of the present disclosure can be evaluated by an evaluation index. For example, the evaluation can be performed by the mape_acc index, and the larger the value of mape_acc, the more accurate the prediction. The specific formula for calculating mape_acc is as follows:
[0072] mape_acc = 1 - ( | (predicted value - true value) / true value | ).
[0073] According to the exemplary embodiments of the present disclosure, the evaluation results of the wind speed prediction method in the exemplary embodiments of the present disclosure can be demonstrated by the following examples:
[0074] From January 2022 to December 2022, the monthly average wind speed in the next 1-14 months was predicted by the wind speed prediction method in the exemplary embodiments of the present disclosure at the beginning of each month for 26 power plants in a certain region in the northwest, a total of 12 backtests.
[0075] Figure 4 The effect diagram of the wind speed prediction method in the exemplary embodiments of the present disclosure is shown.
[0076] Referring to Figure 4 , the regional wind speed prediction effect is shown, the red line is the measured wind speed, and the blue line is the predicted wind speed, Figure 4 The blue line part of (a) is the prediction result in January 2022, Figure 4 The blue part of (b) is the prediction result in October 2022 (the actual 12 backtest effects are basically the same, only 2 prediction results are shown). The prediction effect can be roughly observed by the degree of coincidence between the blue curve and the red curve. Overall, the wind speed prediction results in the next 1-14 months are consistent with the actual wind speed, especially the trend of the wind speed rising first and then falling can be predicted relatively close, and the relative error is small.
[0077] The following table is a comparison table of the average prediction effect of the wind speed prediction method in the exemplary embodiments of the present disclosure and the time series method in the related art for the 26 wind power plants in the above-mentioned certain region in the northwest under different prediction month lengths:
[0078]
[0079] The first column of the above table is the prediction month length, for example, the wind speed in January 2022 is predicted on January 1, 2022, the prediction month length is 1, the wind speed in February 2022 is predicted, the prediction month length is 2, and so on. The mape_acc index of the prediction result of the wind speed prediction method in the exemplary embodiments of the present disclosure is shown in the second column of the above table, and the mape_acc index of the prediction result of the time series extrapolation method in the related art is shown in the third column. Except for the prediction length of 1 month, the mape_acc index of the wind speed prediction method in the exemplary embodiments of the present disclosure is better than that of the method in the related art, and the average index of the wind speed prediction method in the exemplary embodiments of the present disclosure is also 1.5 points higher than that of the method in the related art.
[0080] Therefore, the wind speed prediction method in the exemplary embodiments of the present disclosure can predict the monthly average wind speed of the wind farm more accurately, and can provide more accurate wind speed prediction for long-term power prediction of the wind farm, and can provide effective decision guidance for the wind farm and the power grid, and can help to realize the optimal allocation of power resources.
[0081] It can be understood that the above evaluation process and evaluation result do not constitute a limitation on the present disclosure.
[0082] According to the exemplary embodiments of the present disclosure, the influence of atmospheric and oceanic changes on regional climate change can be integrated into the regression model for predicting the monthly average wind speed based on the historical data of the regional wind speed, and the leading indication significance of the key climate factor index on the regional wind speed can be fully considered, and the long-term monthly average wind speed in the wind farm can be further predicted according to the relationship between the historical wind speed of the wind farm and the regional wind speed.
[0083] According to the exemplary embodiments of the present disclosure, the monthly average wind speed prediction of a single wind farm can be focused on, and the monthly wind speed prediction for the next 1-14 months can be realized, and compared with the wind speed prediction method in the related art, better results can be achieved in the test.
[0084] According to the exemplary embodiments of the present disclosure, the prediction results of the present disclosure can provide more accurate information for medium and long-term power prediction, which can help to make energy planning and strategy in advance, reduce the operation cost and risk of energy companies, and help to promote the healthy development of power trading and power market.
[0085] According to the exemplary embodiments of the present disclosure, the present disclosure can find the early climate factor index that affects the change of the monthly average wind speed of the region, and establish a regression model for predicting the regional wind speed based on the leading climate factor index as the wind speed prediction model.
[0086] Figure 5 A block diagram of a wind speed prediction device in the exemplary embodiments of the present disclosure is shown.
[0087] With reference to Figure 5 The exemplary embodiments of the present disclosure also provide a wind speed prediction device 500, which can include but is not limited to an index acquisition unit 501 and a wind speed prediction unit 502.
[0088] The index acquisition unit 501 can acquire the climate factor index of a first time interval in a predetermined region.
[0089] The wind speed prediction unit 502 can input the climate factor index of the first time interval into the wind speed prediction model to obtain the wind speed of a second time interval in the predetermined region.
[0090] The wind speed prediction model can be trained by the following steps: obtaining training data, wherein the training data includes climate factor indexes and historical wind speeds in a predetermined area, the climate factor indexes include a plurality of atmospheric circulation indexes and a plurality of sea temperature indexes; taking the climate factor indexes in a third time interval in the predetermined area as input feature data, taking the historical wind speeds in a fourth time interval as label data, and training the wind speed prediction model reflecting the relationship between the climate factor indexes and the wind speeds, wherein the third time interval is earlier than the fourth time interval.
[0091] It can be understood that in the example embodiment of the wind speed prediction device 500, the specific implementation process is substantially the same as that of the example embodiment of the wind speed prediction method described above, and will not be repeated here. The wind speed prediction device 500 can be configured as software, hardware, firmware or any combination of the above to perform specific functions. For example, these devices can correspond to dedicated integrated circuits, and can also correspond to pure software code, and can also correspond to a combination of software and hardware modules. In addition, one or more functions implemented by these devices can also be uniformly executed by components in a physical entity device (for example, a processor, a client or a server, etc.).
[0092] Figure 6 A block diagram of an electronic device illustrating an example embodiment of the present disclosure.
[0093] Referring to Figure 6 The electronic device 600 includes at least one memory 601 and at least one processor 602, and the at least one memory 601 stores a set of computer executable instructions, and when the set of computer executable instructions is executed by the at least one processor 602, the wind speed prediction method according to the example embodiment of the present disclosure is executed.
[0094] As an example, the electronic device 600 can be a PC computer, a tablet device, a personal digital assistant, a smart phone, or other devices capable of executing the above-mentioned instruction set. Here, the electronic device 600 is not necessarily a single electronic device, but can also be a collection of any device or circuit capable of executing the above-mentioned instructions (or instruction set) alone or jointly. The electronic device 600 can also be part of an integrated control system or a system manager, or can be configured as a portable electronic device that interfaces with a local or remote (e.g., via wireless transmission) interface.
[0095] In the electronic device 600, the processor 602 can include a central processor (CPU), a graphics processor (GPU), a programmable logic device, a special-purpose processor system, a microcontroller, or a microprocessor. As an example but not limitation, the processor can also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.
[0096] The processor 602 can execute instructions or code stored in the memory 601, where the memory 601 can also store data. The instructions and data can also be sent and received over a network via a network interface device, which can employ any known transmission protocol.
[0097] The memory 601 can be integrated with the processor 602, for example, by arranging RAM or flash memory within an integrated circuit microprocessor, etc. Further, the memory 601 can include a separate device, such as an external disk drive, memory array, or other storage device usable by any database system. The memory 601 and the processor 602 can be operatively coupled, or can communicate with each other, for example, through I / O ports, network connections, etc., so that the processor 602 can read files stored in the memory.
[0098] Further, the electronic device 600 can also include a video display (such as a liquid crystal display) and a user interface interface (such as a keyboard, mouse, touch input device, etc.). All components of the electronic device 600 can be connected to each other via a bus and / or network.
[0099] According to an exemplary embodiment of the present disclosure, a computer-readable storage medium storing instructions can also be provided, where the instructions, when executed by at least one computing device, cause the at least one computing device to perform the wind speed prediction method described above.
[0100] Examples of the computer readable storage medium herein include a read-only memory (ROM), a random access programmable read-only memory (PROM), an electrically erasable programmable read-only memory (EEPROM), a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), a flash memory, a non-volatile memory, a CD-ROM, a CD-R, a CD+R, a CD-RW, a CD+RW, a DVD-ROM, a DVD-R, a DVD+R, a DVD-RW, a DVD+RW, a DVD-RAM, a BD-ROM, a BD-R, a BD-R LTH, a BD-RE, a Blu-ray or optical disc memory, a hard disk drive (HDD), a solid state drive (SSD), a card-type memory such as a multimedia card, a secure digital (SD) card, or an extreme digital (XD) card, a magnetic tape, a floppy disk, a magneto-optical data storage device, an optical data storage device, a hard disk, a solid state disk, and any other device configured to store a computer program and any associated data, data files, and data structures in a non-transitory manner and provide the computer program and any associated data, data files, and data structures to a processor or computer so that the processor or computer can execute the computer program. The computer program in the above computer readable storage medium can be executed in an environment deployed in a computer device such as a client, a host, an agent device, a server, etc., and in addition, in one example, the computer program and any associated data, data files, and data structures are distributed over a networked computer system so that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner by one or more processors or computers. It should be noted that the instructions can also be used to perform additional steps or more specific processing when executing the above steps, the contents of which have been mentioned in the description of the related method, and thus, here, to avoid repetition, no further elaboration will be made.
[0101] Another embodiment of the present disclosure relates to a computer program product including a computer program / instruction, which, when executed by a processor, implements the wind speed prediction method according to any one of the above.
[0102] According to the wind speed prediction method, device, electronic equipment, storage medium and computer program product provided by the present disclosure, the historical regional wind speed and the climate factor index can be used as the training data of the wind speed prediction model, and the wind speed prediction model is trained based on the historical regional wind speed data and the historical early climate factor index, so that the historical measured data of the wind speed can be considered, and the influence of the atmosphere and the ocean on the climate is also taken into account, which supplements the shortcomings of the traditional dynamic method and the statistical extrapolation prediction model which only consider the climate model, and the prediction effect can be achieved by using the indication of the early climate factor index on the future wind speed.
[0103] In addition, feature screening can be performed by a correlation analysis method to obtain the early climate factor index that has a higher indication significance on the regional wind speed, that is, the key high significant early climate factor index that affects the regional wind speed is obtained by correlation calculation.
[0104] In addition, the average of the interval wind speed can well reflect the overall level of the interval wind speed.
[0105] In addition, normalization can eliminate the influence of the magnitude between data to obtain more accurate results in subsequent calculation.
[0106] In addition, the correlation coefficient between the regional wind speed and the wind speed of the power plant in the region can be used to calculate the wind speed of the power plant more accurately based on the regional wind speed.
[0107] In addition, the average of the ratio between the regional wind speed and the wind speed of the power plant corresponding to the time interval can be used as the correlation coefficient between them to improve the calculation efficiency of the correlation coefficient.
[0108] In addition, the wind speed prediction accuracy can be improved to improve the medium and long term power prediction, and the medium and long term wind speed in a single power plant can be focused on to promote the development of power trading and power market.
[0109] The above describes the exemplary embodiments of the present disclosure, and it should be understood that the above description is only exemplary and is not exhaustive, and the present disclosure is not limited to the disclosed exemplary embodiments. Many modifications and changes are obvious to those skilled in the art without departing from the scope and spirit of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the scope of the claims.
Claims
1. A wind speed prediction method, characterized in that, include: Obtain the climate factor index for the first time interval within the predetermined area; The climate factor index of the first time interval is input into the wind speed prediction model to obtain the wind speed of the second time interval within the predetermined area. The wind speed prediction model is trained through the following steps: Acquire training data, wherein the training data includes climate factor indices and historical wind speeds within the predetermined area, and the climate factor indices include multiple atmospheric circulation indices and multiple sea surface temperature indices; Using the climate factor index of the third time interval within the predetermined area as input feature data and the historical wind speed of the fourth time interval as label data, a wind speed prediction model reflecting the relationship between the climate factor index and wind speed is trained, wherein the third time interval is earlier than the fourth time interval.
2. The wind speed prediction method as described in claim 1, characterized in that, The third time interval is at least one predetermined time interval preceding the fourth time interval; The acquisition of training data also includes: For the acquired training data, the correlation between the climate factor index of each predetermined time interval in the third time interval and the historical wind speed of the fourth time interval is calculated respectively. Perform a significance test on the calculated correlation; The climate factor indices in the training data are filtered based on the results of the significance test.
3. The wind speed prediction method as described in claim 2, characterized in that, The acquisition of training data also includes: Each of the selected climate factor indices is normalized.
4. The wind speed prediction method as described in claim 1, characterized in that, The wind speed prediction model is a regression model.
5. The wind speed prediction method as described in claim 1, characterized in that, The historical wind speed in the fourth time interval is the average of the wind speed data within the fourth time interval.
6. The wind speed prediction method as described in claim 1, characterized in that, Also includes: The historical wind speed and the wind speed of the target electric field within the predetermined area are obtained, wherein the target electric field is located within the predetermined area; Calculate the correlation coefficient between the wind speed within the predetermined area and the wind speed of the target electric field; Based on the correlation coefficient and the predicted wind speed in the second time interval, the predicted wind speed of the target electric field in the second time interval is obtained.
7. The wind speed prediction method as described in claim 6, characterized in that, The calculation of the correlation coefficient between the wind speed within the predetermined area and the wind speed of the target electric field includes: For the historical wind speed within the predetermined area and the wind speed of the target electric field, calculate the ratio of the historical wind speed and the wind speed of the target electric field that have the same first time identifier and the same second time identifier. For the calculated ratios that have the same second time identifier, their mean is calculated as the correlation coefficient between the wind speed in the predetermined area and the wind speed in the target electric field.
8. A wind speed prediction device, characterized in that, include: The index acquisition unit is configured to acquire the climate factor index for the first time interval within a predetermined area. The wind speed prediction unit is configured to input the climate factor index of the first time interval into the wind speed prediction model to obtain the wind speed of the second time interval within the predetermined area. The wind speed prediction model is trained through the following steps: Acquire training data, wherein the training data includes climate factor indices and historical wind speeds within the predetermined area, and the climate factor indices include multiple atmospheric circulation indices and multiple sea surface temperature indices; Using the climate factor index of the third time interval within the predetermined area as input feature data and the historical wind speed of the fourth time interval as label data, a wind speed prediction model reflecting the relationship between the climate factor index and wind speed is trained, wherein the third time interval is earlier than the fourth time interval.
9. An electronic device, characterized in that, include: At least one processor; At least one memory that stores computer-executable instructions. Wherein, when the computer-executable instructions are executed by the at least one processor, the at least one processor causes the at least one processor to execute the wind speed prediction method as described in any one of claims 1-7.
10. A computer-readable storage medium for storing instructions, characterized in that, When the instruction is executed by at least one processor, it causes the at least one processor to perform the wind speed prediction method as described in any one of claims 1-7.
11. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the wind speed prediction method as described in any one of claims 1-7.