Output characteristic prediction method and system for planning wind-solar complementary power station, electronic equipment, storage medium and computer program product

Abstract

The invention provides an output characteristic prediction method and system for planning a wind-solar complementary power station, electronic equipment, a storage medium and a computer program product. The output characteristic prediction method comprises the following steps: acquiring first actually measured meteorological data and first standard meteorological data of an established power station in a preset historical time period at a target position; determining predicted meteorological data of a preset position of the wind-solar complementary power station based on the first actually measured meteorological data and the first standard meteorological data; inputting the predicted meteorological data and preset parameter information of the planned wind-solar complementary power station into a generated power back-calculation model based on a physical principle to obtain back-calculation power of the planned wind-solar complementary power station; training the initial power prediction model according to the back calculation power to obtain a target power prediction model; and according to the target power prediction model, outputting predicted power based on the back-calculation power, and determining predicted power output characteristics of the planned wind-solar complementary power station according to the predicted power. The operation reliability of the new energy power grid is improved by predicting the output characteristics.

Description

Technical Field

[0001] The present application relates to the technical field of output characteristic analysis of wind-solar complementary power stations, and specifically to a method and system for predicting output characteristics of planned wind-solar complementary power stations, an electronic device, a storage medium, and a computer program product. Background Art

[0002] The design process for a wind-solar power system that integrates wind and solar energy involves site selection assessment and output characteristic prediction for the planned wind-solar hybrid power station. Design elements for a planned wind-solar hybrid power station include site selection assessment and configuration parameter setting. Before finalizing the site for the planned wind-solar hybrid power station, predicting and analyzing its output characteristics can provide technical support and reference for the safe operation of the new energy grid.

[0003] The inventors of this application have found that the current analysis and prediction of the output characteristics of wind-solar complementary power stations are limited to the wind-solar complementary power stations that have been built, and there is a lack of effective analysis and prediction methods for the output characteristics of planned wind-solar complementary power stations that have not been built (i.e., are under planning).

[0004] The contents of the background technology section are merely technologies known to the public and do not necessarily represent the existing technologies in this field. Summary of the Invention

[0005] The present application provides a method and system for predicting the output characteristics of a wind-solar complementary power station, an electronic device, a storage medium, and a computer program product, aiming to solve at least one of the above-mentioned technical problems.

[0006] According to one aspect of the present application, a method for predicting the output characteristics of a planned wind-solar complementary power station is provided. The output characteristics include predicted power output characteristics. The output characteristics prediction method includes collecting first measured meteorological data and first standard meteorological data of a built power station within a preset historical time period of the target location; determining the predicted meteorological data of a preset location of the planned wind-solar complementary power station within the preset historical time period based on the first measured meteorological data and the first standard meteorological data; inputting the predicted meteorological data and the preset parameter information of the planned wind-solar complementary power station into a power generation back-calculation model based on physical principles to obtain the back-calculated power of the planned wind-solar complementary power station; training an initial power prediction model based on a preset neural network according to the back-calculated power to obtain a target power prediction model; outputting the predicted power of the planned wind-solar complementary power station within a preset future time period based on the back-calculated power according to the target power prediction model, so as to determine the predicted power output characteristics of the planned wind-solar complementary power station according to the predicted power.

[0007] According to some embodiments of the present application, predicted meteorological data of a preset location of a planned wind-solar complementary power station within a preset historical time period is determined based on first measured meteorological data and first standard meteorological data, including determining a correction coefficient of second standard meteorological data of the preset location within the preset historical time period based on the first measured meteorological data and the first standard meteorological data; and determining predicted meteorological data based on the correction coefficient and the second standard meteorological data.

[0008] According to some embodiments of the present application, a correction coefficient of second standard meteorological data at a preset location within a preset historical time period is determined based on first measured meteorological data and first standard meteorological data, including normalizing the first measured meteorological data and the first standard meteorological data; and determining the correction coefficient based on the normalized first measured meteorological data and the first standard meteorological data.

[0009] According to some embodiments of the present application, the power generation back-calculation model includes a wind power conversion model based on physical principles and a photovoltaic conversion model based on physical principles, and the predicted meteorological data includes predicted wind data and predicted photovoltaic data. The predicted meteorological data and the preset parameter information of the planned wind-solar complementary power station are input into the power generation back-calculation model based on physical principles to obtain the back-calculated power of the planned wind-solar complementary power station, including inputting the predicted wind data and the preset parameter information into the wind power conversion model to obtain the wind power back-calculated power of the planned wind-solar complementary power station; inputting the predicted photovoltaic data and the preset parameter information into the photovoltaic conversion model to obtain the photovoltaic back-calculated power of the planned wind-solar complementary power station; and determining the back-calculated power based on the wind power back-calculated power and the photovoltaic back-calculated power.

[0010] According to some embodiments of the present application, the output characteristics also include predicted stability output characteristics. After determining the calculated power based on the wind power calculated power and the photovoltaic calculated power, it also includes determining the wind-solar complementarity data of the wind power calculated power and the photovoltaic calculated power; and determining the predicted stability output characteristics based on the wind-solar complementarity data.

[0011] According to some embodiments of the present application, an initial power prediction model based on a preset neural network is trained according to the back-calculated power to obtain a target power prediction model, including performing outlier processing on the back-calculated power; and the initial power prediction model is trained based on the back-calculated power after outlier processing to obtain a target power prediction model.

[0012] According to another aspect of the application, an output characteristic analysis system for planning a wind-solar complementary power station is also provided. The output characteristic analysis system is used to execute the output characteristic analysis method described above. The output characteristic analysis system includes a data acquisition module, a data processing module and a model training module. The data acquisition module collects first measured meteorological data and first standard meteorological data. The data processing module determines predicted meteorological data based on the first measured meteorological data and the first standard meteorological data. The model training module inputs the predicted meteorological data and preset parameter information into the power generation power back-calculation model to obtain the back-calculated power. The model training module also trains the initial power prediction model based on the back-calculated power to obtain a target power prediction model. The model training module also outputs predicted power based on the back-calculated power according to the target power prediction model to determine the predicted power output characteristics based on the predicted power.

[0013] According to another aspect of the present application, an electronic device is provided. The electronic device includes one or more processors and a storage device. The storage device is configured to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the output characteristic prediction method of the present application.

[0014] According to another aspect of the present application, the present application further provides a non-volatile computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the output characteristic prediction method of the present application.

[0015] According to another aspect of the present application, a computer program product is provided, including a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the output characteristic prediction method of the present application.

[0016] Beneficial effects

[0017] This application determines the predicted meteorological data of the planned wind-solar complementary power station by analyzing the first measured meteorological data and the first standard meteorological data of the power station built within the preset historical time period of the target location, inputs the predicted meteorological data and the preset parameter information of the planned wind-solar complementary power station into the power generation power back-calculation model to determine the back-calculated power, and then trains the initial power prediction model based on the preset neural network through the back-calculated power, and finally obtains the photovoltaic back-calculated power and predicted power output characteristics of the planned wind-solar complementary power station. This application can realize the prediction of the power output characteristics of the planned wind-solar complementary power station, and provide technical support for the safe operation of the new energy power grid with wind power and photovoltaic grid-connected operation, thereby improving the operational reliability of the new energy power grid. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0019] Figure 1 A schematic diagram showing a flow chart of a method for predicting output characteristics of a wind-solar hybrid power station according to an embodiment of the present application is shown;

[0020] Figure 2 A flow chart showing step S200 of the method for predicting output characteristics of a wind-solar hybrid power station according to an embodiment of the present application is shown;

[0021] Figure 3 A flow chart showing step S210 of the method for predicting output characteristics of a wind-solar hybrid power station according to an embodiment of the present application is shown;

[0022] Figure 4 A flow chart showing step S300 of the method for predicting output characteristics of a wind-solar hybrid power station according to an embodiment of the present application is shown;

[0023] Figure 5 A flow chart showing steps S340 and S350 of the method for predicting output characteristics of a wind-solar hybrid power station according to an embodiment of the present application is shown;

[0024] Figure 6 A flow chart showing step S400 of the method for predicting output characteristics of a wind-solar hybrid power station according to an embodiment of the present application is shown;

[0025] Figure 7 A schematic structural diagram of an output characteristic prediction system according to an embodiment of the present application is shown.

[0026] Description of reference numerals:

[0027] Output characteristic analysis system 1; data acquisition module 11, data processing module 12; model training module 13. DETAILED DESCRIPTION

[0028] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. Like reference numerals in the drawings represent like or similar parts, and thus repetitive description thereof will be omitted.

[0029] The described features, structures or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of these specific details, or other methods, components, materials, devices, etc. may be employed. In these cases, well-known structures, methods, devices, implementations, materials or operations will not be shown or described in detail.

[0030] Furthermore, the terms "include," "comprise," and "have," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0031] The terms "first", "second" and the like in the specification, claims and drawings of this application are used to distinguish different objects rather than to describe a specific order.

[0032] The following is a clear and complete description of the technical solution of this application in conjunction with the drawings in the embodiments of this application. The described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0033] According to one aspect of the present application, the present application provides a method for predicting output characteristics of a planned wind-solar complementary power station.

[0034] For example, a planned wind-solar hybrid power station is a wind-solar hybrid power station that is under planning (not yet built). A wind-solar hybrid power station is a wind-photovoltaic hybrid power station.

[0035] For example, the output characteristics of a wind-solar hybrid power station can be defined as the temporal variation of the wind power generation and photovoltaic power generation of the wind-solar hybrid power station. This reflects the power generation capacity, efficiency, and stability of the wind-solar hybrid power station over different time periods. For example, the output characteristics may include predicted power output characteristics.

[0036] Figure 1 A flow chart of a method for predicting output characteristics of a wind-solar complementary power station according to an embodiment of the present application is shown.

[0037] According to an example embodiment, Figure 1 As shown, the output characteristic prediction method includes steps S100 to S500. Exemplarily, the output characteristic prediction method may be executed by an output characteristic prediction system.

[0038] In step S100 , the output characteristic prediction system collects first measured meteorological data and first standard meteorological data of a power station built at a target location within a preset historical time period.

[0039] For example, the preset location of a planned wind-solar hybrid power station can be a planned geographic location. An existing power station is an existing power station that has been completed and successfully operated for a preset historical period. For example, an existing power station can be a wind-solar hybrid power station. The type of existing power station is not limited here.

[0040] The target location is the actual geographical location of the built power station. The distance between the target location and the preset location of the planned wind-solar hybrid power station can be customized by the user.

[0041] For example, the distance between the target location and the preset location of the planned wind-solar hybrid power station can be set to 0-30 km. ， That is, select an existing power station within a range of 0-30km from the preset location.

[0042] The preset historical time period can be a historical time period set by the user. For example, the preset historical time period can be set to a time period 20 years before the current moment.

[0043] For example, the first measured meteorological data may be meteorological data measured at an existing power station within a preset historical time period. The first measured meteorological data may include wind power data and photovoltaic data measured at a target location within the preset historical time period. The first measured meteorological data may be obtained through detection by equipment such as ground automatic stations, weather radars, and satellite cloud wind guides.

[0044] The first standard meteorological data may be meteorological reanalysis data of a target location of a built power station within a preset historical time period.

[0045] For example, the meteorological reanalysis data may be meteorological data published by the European Centre for Medium-Range Weather Forecasts (ECMWF). The meteorological reanalysis data may include meteorological data such as wind speed, irradiance, air pressure, and temperature. For example, the output characteristic prediction system may collect the first measured meteorological data by calling an API interface of a meteorological data service provider. The first standard meteorological data may be locally stored by the user for collection by the output characteristic prediction system.

[0046] In step S200, the output characteristic prediction system determines predicted meteorological data of a preset location of a planned wind-solar hybrid power station within a preset historical time period based on first measured meteorological data and first standard meteorological data.

[0047] For example, the predicted meteorological data may include predicted wind power data and predicted photovoltaic data. The preset location of the planned wind-solar hybrid power station may be a planned geographical location. The predicted meteorological data may be predicted meteorological data for the preset location of the planned wind-solar hybrid power station within a preset historical time period.

[0048] For example, if the distance between the target location and the preset location of the planned wind-solar hybrid power station is 0-30 km, the climate patterns at the target location can be equated with the climate patterns at the preset location of the planned wind-solar hybrid power station. The output characteristics analysis system can calculate the predicted meteorological data for the preset location of the planned wind-solar hybrid power station within the preset historical time period by statistically analyzing the data relationship between the first measured meteorological data and the first standard meteorological data within the preset historical time period.

[0049] In step S300, the output characteristic prediction system inputs the predicted meteorological data and the preset parameter information of the planned wind-solar hybrid power station into a power generation back-calculation model based on physical principles to obtain the back-calculated power of the planned wind-solar hybrid power station.

[0050] For example, the preset parameter information may include parameter information such as single wind turbine capacity, wind turbine blade diameter, photovoltaic panel capacity, total power station capacity, etc. The power generation power back-calculation model based on physical principles may include a wind power conversion model based on physical principles and a photovoltaic conversion model based on physical principles.

[0051] For example, the power generation recovery model is a mathematical model based on physical principles such as aerodynamics, fluid mechanics, semiconductor physics, and optics. The wind power conversion model is a mathematical model for wind power generation based on physical principles such as aerodynamics, thermodynamics, and fluid mechanics. The photovoltaic conversion model is a mathematical model for photovoltaic power generation based on semiconductor physics and optics.

[0052] For example, the output characteristics prediction system can simultaneously input preset parameter information into the wind power conversion model and the photovoltaic conversion model, and input the predicted wind power data and predicted photovoltaic data contained in the predicted meteorological data into the wind power conversion model and the photovoltaic conversion model, respectively. The output of the wind power conversion model is the wind power return power, and the output of the photovoltaic conversion model is the photovoltaic return power. The sum of the wind power return power and the photovoltaic return power is the return power of the wind-solar hybrid power station.

[0053] In step S400 , the output characteristic prediction system trains an initial power prediction model based on a preset neural network according to the back-calculated power to obtain a target power prediction model.

[0054] For example, the initial power prediction model of the preset neural network can be a power prediction model based on an LSTM (Long Short-Term Memory) network. The output characteristics prediction system trains the initial power prediction model of the preset neural network by back-calculating power to adjust the parameters of the initial power prediction model of the preset neural network to obtain a target power prediction model.

[0055] In step S500, the output characteristic prediction system presets the predicted power of the planned wind-solar complementary power station in the future time period based on the back-calculated power output according to the target power prediction model, so as to determine the predicted power output characteristics of the planned wind-solar complementary power station according to the predicted power.

[0056] For example, the predicted power output characteristic may be the predicted power generation capacity of the planned wind-solar hybrid power station.

[0057] Through the above embodiments, the present application determines the predicted meteorological data of the planned wind-solar complementary power station by analyzing the first measured meteorological data and the first standard meteorological data of the power station built within the preset historical time period of the target location, inputs the predicted meteorological data and the preset parameter information of the planned wind-solar complementary power station into the power generation power back-calculation model to determine the back-calculated power, and then trains the initial power prediction model based on the preset neural network through the back-calculated power, and finally obtains the photovoltaic back-calculated power and predicted power output characteristics of the planned wind-solar complementary power station. The present application can realize the prediction of the power output characteristics of the planned wind-solar complementary power station, and provide technical support for the safe operation of the new energy power grid with wind power and photovoltaic grid-connected operation, thereby improving the operational reliability of the new energy power grid.

[0058] Figure 2 FIG2 is a flow chart showing step S200 of the method for predicting the output characteristics of a wind-solar hybrid power station according to an embodiment of the present application. Figure 2 As shown, step S200 includes step S210 and step S220.

[0059] In step S210 , the output characteristic prediction system determines a correction coefficient of second standard meteorological data of a preset location within a preset historical time period based on the first measured meteorological data and the first standard meteorological data.

[0060] For example, the second standard meteorological data may be meteorological reanalysis data of a preset location of the planned wind-solar hybrid power station within a preset historical time period.

[0061] For example, the calculation formula of the correction coefficient may be:

[0062]

[0063] Where K is the correction coefficient, T is the time series of the preset historical time period (for example, T can be hourly), β i is the first measured meteorological data of different time nodes of the built power station, α i It can be the first standard meteorological data of different time nodes of the built power station.

[0064] In step S220 , the output characteristic prediction system determines predicted meteorological data based on the correction coefficient and the second standard meteorological data.

[0065] Exemplarily, the predicted meteorological data may be the product of the correction coefficient and the second standard meteorological data.

[0066] Through the above embodiments, the present application confirms the correction coefficient through the first measured meteorological data and the first standard meteorological data, and then calculates the predicted meteorological data based on the product of the correction coefficient and the second standard meteorological data, thereby realizing the prediction of meteorological data for the preset location of the planned wind and solar power station within a preset historical time period.

[0067] Figure 3 FIG2 is a flow chart showing step S210 of the method for predicting the output characteristics of a wind-solar hybrid power station according to an embodiment of the present application. Figure 3 As shown, step S210 includes step S211 and step S212.

[0068] In step S211 , the output characteristic prediction system normalizes the first measured meteorological data and the first standard meteorological data.

[0069] For example, the first measured meteorological data and the first standard meteorological data may be normalized using a maximum-minimum normalization method, and the specific formula is:

[0070]

[0071] Wherein, X′ can be the normalized first measured meteorological data and the first standard meteorological data, X can be the original data of the first measured meteorological data and the first standard meteorological data, and X max and X min They can be the maximum and minimum values ​​of the original data respectively.

[0072] In step S212 , the output characteristic prediction system determines a correction coefficient based on the normalized first measured meteorological data and the first standard meteorological data.

[0073] The process of determining the correction coefficient has been described in detail in step S210 and will not be repeated here.

[0074] Through the above embodiments, the present application improves the accuracy of the correction coefficient calculation by first calculating the first measured meteorological data and the first standard meteorological data, and then using the corrected first measured meteorological data and the first standard meteorological data to calculate the correction coefficient, thereby improving the accuracy of the predicted meteorological data.

[0075] Figure 4 FIG. 1 is a flow chart showing step S300 of the method for predicting the output characteristics of a wind-solar hybrid power station according to an embodiment of the present application. Figure 4 As shown, step S300 includes steps S310-S330.

[0076] In step S310 , the output characteristic prediction system inputs the predicted wind power data and preset parameter information into the wind power conversion model to obtain the wind power return power of the planned wind-solar hybrid power station.

[0077] For example, the output characteristic prediction system can train the wind power conversion model through the wind power estimation function to obtain a trained wind power conversion model.

[0078] For example, the wind power estimation function is:

[0079]

[0080] Among them, P1 is the wind power calculation power, ρ is the air density, υ i is the wind speed at different time nodes in the preset historical time period, n represents the time series of the preset historical time period (for example, n can be hourly), S is the swept area of ​​the wind turbine, is the maximum wind energy utilization coefficient of the wind turbine.

[0081] In step S320, the output characteristic prediction system inputs the preset parameter information of the predicted photovoltaic data into the photovoltaic conversion model to obtain the photovoltaic back-calculated power of the planned wind-solar hybrid power station.

[0082] For example, the output characteristic prediction system can train the photoelectric conversion model through the photoelectric power estimation function to obtain a trained photoelectric conversion model.

[0083] Exemplarily, the photoelectric power estimation function is:

[0084] P2=η s *[1-α′(T c -25)]*I T *S*K1*K2*K3*K4*0.001;

[0085] Among them, P2 is the wind power calculation power, η s is the photoelectric conversion efficiency, α′ is the temperature coefficient, T cis the array board temperature, I T is the irradiance, S is the effective area of ​​the photovoltaic modules of the power station, K1 is the photovoltaic array aging loss coefficient, K2 is the photovoltaic array mismatch loss coefficient (for example, K2 can be 0.95-0.98), K3 is the dust shielding loss coefficient (for example, K3 can be 0.9-0.95), and K4 is the DC link line loss coefficient (for example, K3 can be 0.95-0.98).

[0086] In step S330 , the output characteristic prediction system determines the back-calculated power based on the wind power back-calculated power and the photovoltaic power back-calculated power.

[0087] For example, the back-calculated power may be the sum of the wind power back-calculated power and the photovoltaic power back-calculated power.

[0088] Through the above embodiments, the present application calculates the wind power return power and the photovoltaic return power through the wind power conversion model and the photovoltaic conversion model respectively, and then obtains the return power.

[0089] Figure 5 FIG2 is a flow chart showing steps S340 and S350 of the method for predicting the output characteristics of a wind-solar hybrid power station according to an embodiment of the present application. Figure 5 shown.

[0090] In step S340 , the output characteristic prediction system determines wind-solar complementarity data of wind power back-calculated power and photovoltaic power back-calculated power.

[0091] For example, the wind-solar complementarity data calculation formula may be:

[0092]

[0093] Where β′ is the wind-solar complementarity data, T is the time series of the preset historical time period (for example, T can be hourly), P1(T) is the wind power back-calculated power at different time nodes, P2(T) is the photovoltaic power back-calculated power at different time nodes, P total The average hourly calculated power over a preset historical period. β′ = 0 indicates that wind power and photovoltaic power are fully complementary. β′ > 0 indicates that wind power and photovoltaic power are not fully complementary, indicating that the combined output fluctuates.

[0094] In step S350 , the output characteristic prediction system determines a predicted stability output characteristic based on the wind-solar complementarity data.

[0095] For example, the wind-solar complementarity data may characterize the predicted stability output characteristics of a planned wind-solar complementarity power station.

[0096] Through the above embodiments, the present application calculates the wind-solar complementarity data and then characterizes it sideways to obtain the predicted stability output characteristics of the planned wind-solar complementary power station.

[0097] Figure 6 FIG4 is a flow chart showing step S400 of the method for predicting the output characteristics of a wind-solar hybrid power station according to an embodiment of the present application. Figure 6 As shown, step S400 also includes step S410 and step S420.

[0098] In step S410 , the output characteristic prediction system performs abnormal value processing on the back-calculated power.

[0099] For example, outliers can include null values, which are missing data, and dead values, which are values ​​that have not changed over a period of time.

[0100] For example, when the null value ratio is less than 5%, the output characteristic prediction system can delete the null value. For example, the output characteristic prediction system can fill the null values ​​that are continuous and certain in a short period of time by linear interpolation (for example, fill the data of adjacent equal-length time periods to the time period where the null value exists).

[0101] For example, the output characteristic prediction system may delete detected dead values ​​and may fill in and replace the dead values ​​with data from the same period of adjacent years.

[0102] In step S420 , the output characteristic prediction system trains an initial power prediction model based on the back-calculated power after outlier processing to obtain a target power prediction model.

[0103] Through the above embodiments, the present application improves the accuracy and efficiency of the training process by performing outlier processing on the back-calculated power and then using the back-calculated power after outlier processing to train the initial power prediction model.

[0104] According to another aspect of the application, a system for analyzing output characteristics of a wind-solar complementary power station is also provided. Figure 7 A schematic structural diagram of an output characteristic prediction system according to an embodiment of the present application is shown.

[0105] According to an example embodiment, Figure 7 As shown, the output characteristic analysis system is used to execute the output characteristic analysis method described above. The output characteristic analysis system includes a data acquisition module 11 , a data processing module 12 and a model training module 13 .

[0106] Optionally, the data acquisition module 11 can collect first measured meteorological data and first standard meteorological data. For example, the data acquisition module 11 can collect the first measured meteorological data by calling an API interface of a meteorological data service provider. The first standard meteorological data can be locally stored by the user for collection by the output characteristic prediction system 1.

[0107] Optionally, the data processing module 12 is connected to the data acquisition module 11 and can obtain the first measured meteorological data and the first standard meteorological data collected by the data acquisition module 11. The data processing module 12 can determine the predicted meteorological data based on the first measured meteorological data and the first standard meteorological data.

[0108] For example, the predicted meteorological data may be the predicted meteorological data for the preset location of the planned wind-solar hybrid power station within a preset historical time period. If the distance between the target location and the preset location of the planned wind-solar hybrid power station is 0-30 km, the climate patterns at the target location may be equated with the climate patterns at the preset location of the planned wind-solar hybrid power station. By statistically analyzing the data relationship between the first measured meteorological data and the first standard meteorological data within the preset historical time period, the predicted meteorological data for the preset location of the planned wind-solar hybrid power station within the preset historical time period may be calculated.

[0109] For example, the data processing module 12 may further determine a correction coefficient for second standard meteorological data at a preset location within a preset historical time period based on the first measured meteorological data and the first standard meteorological data. For example, the second standard meteorological data may be meteorological reanalysis data at a preset location within a preset historical time period for the planned wind-solar hybrid power station.

[0110] For example, the calculation formula of the correction coefficient may be:

[0111]

[0112] Where K is the correction coefficient, T is the time series of the preset historical time period (for example, T can be hourly), β i is the first measured meteorological data of different time nodes of the built power station, α i It can be the first standard meteorological data of different time nodes of the built power station.

[0113] For example, the data processing module 12 may also calculate the product of the correction coefficient and the second standard meteorological data to obtain the predicted meteorological data. For example, the data processing module 12 may normalize the first measured meteorological data and the first standard meteorological data, and determine the correction coefficient based on the normalized first measured meteorological data and the first standard meteorological data.

[0114] For example, the first measured meteorological data and the first standard meteorological data may be normalized using a maximum-minimum normalization method, and the specific formula is:

[0115]

[0116] Wherein, X′ can be the normalized first measured meteorological data and the first standard meteorological data, X can be the original data of the first measured meteorological data and the first standard meteorological data, and X max and X min They can be the maximum and minimum values ​​of the original data respectively.

[0117] For example, the data processing module 12 may also determine wind-solar complementarity data of wind power back-calculated power and photovoltaic power back-calculated power.

[0118] For example, the wind-solar complementarity data calculation formula may be:

[0119]

[0120] Where β′ is the wind-solar complementarity data, T is the time series of the preset historical time period (for example, T can be hourly), P1(T) is the wind power back-calculated power at different time nodes, P2(T) is the photovoltaic power back-calculated power at different time nodes, P total The average hourly calculated power over a preset historical period. β′ = 0 indicates that wind power and photovoltaic power are fully complementary. β′ > 0 indicates that wind power and photovoltaic power are not fully complementary, indicating that the combined output fluctuates.

[0121] For example, the data processing module 12 may determine the predicted stability output characteristics based on the wind-solar complementarity data. For example, the wind-solar complementarity data may represent the predicted stability output characteristics of the planned wind-solar complementarity power station.

[0122] For example, the data processing module 12 may also perform outlier processing on the back-calculated power. For example, outliers may include null values ​​and dead values. Null values ​​are missing data, and dead values ​​are values ​​that have not changed over a period of time.

[0123] For example, when the null value ratio is less than 5%, the data processing module 12 can delete the null value. Exemplarily, the data processing module 12 can fill the null values ​​that are continuous for a short period of time by linear interpolation (for example, filling the data of adjacent equal-length time periods into the time period where the null value exists). Exemplarily, the data processing module 12 can delete the detected dead values ​​and fill in and replace the dead values ​​with data from the same period of adjacent years.

[0124] Optionally, the model training module 13 is connected to the data acquisition module 11 and the data training module 12. The model training module 13 can obtain predicted meteorological data and preset parameter information. The model training module 13 can input the predicted meteorological data and preset parameter information into the power generation power back-calculation model to obtain the back-calculated power. The model training module 13 can also train an initial power prediction model based on the back-calculated power to obtain a target power prediction model. The model training module 13 also outputs predicted power based on the back-calculated power according to the target power prediction model, thereby determining predicted power output characteristics based on the predicted power.

[0125] For example, the preset parameter information may include single wind turbine capacity, wind turbine blade diameter, photovoltaic panel capacity, total power station capacity, etc. For example, the power generation back-calculation model based on physical principles may include a wind power conversion model based on physical principles and a photovoltaic conversion model based on physical principles.

[0126] For example, the model training module 13 can simultaneously input preset parameter information into the wind power conversion model and the photovoltaic conversion model, and input the predicted wind power data and predicted photovoltaic data contained in the predicted meteorological data into the wind power conversion model and the photovoltaic conversion model, respectively. The output of the wind power conversion model is the wind power return power. The output of the photovoltaic conversion model is the photovoltaic return power. The sum of the wind power return power and the photovoltaic return power is the return power of the wind-solar hybrid power station.

[0127] For example, the model training module 13 may train the wind power conversion model using a wind power estimation function to obtain a trained wind power conversion model.

[0128] For example, the wind power estimation function is:

[0129]

[0130] Among them, P1 is the wind power calculation power, ρ is the air density, υ i is the wind speed at different time nodes in the preset historical time period, n represents the time series of the preset historical time period (for example, n can be hourly), S is the swept area of ​​the wind turbine, is the maximum wind energy utilization coefficient of the wind turbine.

[0131] For example, the model training module 13 may train the photoelectric conversion model using a photoelectric power estimation function to obtain a trained photoelectric conversion model.

[0132] Exemplarily, the photoelectric power estimation function is:

[0133] P2=η s *[1-α′(T c -25)]*I T *S*K1*K2*K3*K4*0.001;

[0134] Among them, P2 is the wind power calculation power, η s is the photoelectric conversion efficiency, α′ is the temperature coefficient, T c is the array board temperature, I T is the irradiance, S is the effective area of ​​the photovoltaic modules of the power station, K1 is the photovoltaic array aging loss coefficient, K2 is the photovoltaic array mismatch loss coefficient (for example, K2 can be 0.95-0.98), K3 is the dust shielding loss coefficient (for example, K3 can be 0.9-0.95), and K4 is the DC link line loss coefficient (for example, K3 can be 0.95-0.98).

[0135] For example, the initial power prediction model of the preset neural network can be a power prediction model based on LSTM (Long Short-Term Memory). The initial power prediction model of the preset neural network is trained by back-calculating power to adjust the parameters of the initial power prediction model of the preset neural network to obtain a target power prediction model. The predicted power output characteristics can be the predicted power generation capacity of the planned wind-solar hybrid power station. For example, the predicted power output characteristics can be characterized by the predicted power.

[0136] Through the above embodiments, the present application determines the predicted meteorological data of the planned wind-solar complementary power station by analyzing the first measured meteorological data and the first standard meteorological data of the power station built within the preset historical time period of the target location, inputs the predicted meteorological data and the preset parameter information of the planned wind-solar complementary power station into the power generation power back-calculation model to determine the back-calculated power, and then trains the initial power prediction model based on the preset neural network through the back-calculated power, and finally obtains the photovoltaic back-calculated power and predicted power output characteristics of the planned wind-solar complementary power station. The present application can realize the prediction of the power output characteristics of the planned wind-solar complementary power station, and provide technical support for the safe operation of the new energy power grid with wind power and photovoltaic grid-connected operation, thereby improving the operational reliability of the new energy power grid.

[0137] According to another aspect of the present application, an electronic device is provided. The electronic device includes one or more processors and a storage device. The storage device is configured to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the output characteristic prediction method of the present application.

[0138] According to another aspect of the present application, the present application further provides a non-volatile computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the output characteristic prediction method of the present application.

[0139] According to another aspect of the present application, a computer program product is provided, including a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the output characteristic prediction method of the present application.

[0140] Finally, it should be noted that the above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Although the present application is described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions of the aforementioned embodiments or replace some of the technical features therein with equivalents. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for predicting output characteristics of a wind-solar hybrid power station, characterized in that: The output characteristics include predicted power output characteristics, and the output characteristics prediction method includes: Collecting first measured meteorological data and first standard meteorological data of a power station built within a preset historical time period at a target location; Determining predicted meteorological data for a preset location of the planned wind-solar hybrid power station within the preset historical time period based on the first measured meteorological data and the first standard meteorological data; Inputting the predicted meteorological data and the preset parameter information of the planned wind-solar hybrid power station into a power generation back-calculation model based on physical principles to obtain the back-calculated power of the planned wind-solar hybrid power station; Training an initial power prediction model based on a preset neural network according to the back-calculated power to obtain a target power prediction model; The predicted power of the planned wind-solar complementary power station in a future time period is preset based on the target power prediction model and the back-calculated power output, so as to determine the predicted power output characteristics of the planned wind-solar complementary power station according to the predicted power.

2. The output characteristic prediction method according to claim 1, characterized in that The method of determining the predicted meteorological data of the preset location of the planned wind-solar hybrid power station within the preset historical time period based on the first measured meteorological data and the first standard meteorological data includes: Determining a correction coefficient of second standard meteorological data of the preset location within the preset historical time period based on the first measured meteorological data and the first standard meteorological data; The predicted meteorological data is determined based on the correction coefficient and the second standard meteorological data.

3. The output characteristic prediction method according to claim 2, characterized in that: The step of determining the correction coefficient of the second standard meteorological data of the preset location within the preset historical time period based on the first measured meteorological data and the first standard meteorological data includes: Normalizing the first measured meteorological data and the first standard meteorological data; The correction coefficient is determined according to the normalized first measured meteorological data and the first standard meteorological data.

4. The output characteristic prediction method according to claim 1, characterized in that: The power generation back-calculation model includes a wind power conversion model based on physical principles and a photoelectric conversion model based on physical principles. The predicted meteorological data includes predicted wind power data and predicted photovoltaic data. Inputting the predicted meteorological data and the preset parameter information of the planned wind-solar complementary power station into the power generation back-calculation model based on physical principles to obtain the back-calculated power of the planned wind-solar complementary power station includes: Inputting the predicted wind power data and the preset parameter information into the wind power conversion model to obtain the wind power return power of the planned wind-solar hybrid power station; Inputting the preset parameter information of the predicted photovoltaic data into the photoelectric conversion model to obtain the photovoltaic back-calculated power of the planned wind-solar complementary power station; The back-calculated power is determined based on the wind power back-calculated power and the photovoltaic back-calculated power.

5. The output characteristic prediction method according to claim 4, characterized in that: The output characteristics further include predicted stability output characteristics, and after determining the back-calculated power based on the wind power back-calculated power and the photovoltaic back-calculated power, the method further includes: Determining wind-solar complementarity data of the wind power back-calculated power and the photovoltaic back-calculated power; The predicted stability output characteristic is determined according to the wind-solar complementarity data.

6. The output characteristic prediction method according to claim 1, characterized in that: The training of an initial power prediction model based on a preset neural network according to the back-calculated power to obtain a target power prediction model includes: performing outlier processing on the back-calculated power; The initial power prediction model is trained based on the back-calculated power after the outlier processing to obtain the target power prediction model.

7. A system for analyzing output characteristics of a wind-solar hybrid power station, characterized in that: The output characteristic analysis system is used to execute the output characteristic analysis method according to any one of claims 1 to 6, and the output characteristic analysis system includes: A data acquisition module, for acquiring the first measured meteorological data and the first standard meteorological data; a data processing module, for determining the predicted meteorological data based on the first measured meteorological data and the first standard meteorological data; The model training module inputs the predicted meteorological data and the preset parameter information into the power generation back-calculation model to obtain the back-calculated power; the model training module also trains the initial power prediction model based on the back-calculated power to obtain the target power prediction model; the model training module also outputs the predicted power based on the back-calculated power according to the target power prediction model to determine the predicted power output characteristics according to the predicted power.

8. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the output characteristic prediction method according to any one of claims 1 to 6.

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

10. A computer program product, characterized in that The method comprises a computer program stored on a computer-readable storage medium, wherein the computer program comprises program instructions, and when the program instructions are executed by a computer, the computer is caused to execute the output characteristic prediction method according to any one of claims 1 to 6.

Images