A method and system for predicting the power generation of new energy power plants taking meteorological factors into account

Abstract

This invention belongs to the field of new energy power generation technology and provides a method and system for predicting the power generation of new energy power plants that takes meteorological factors into account. The method includes: acquiring meteorological parameters and equipment operating status of the new energy power plant; constructing a coupled model of the acquired operating status and meteorological parameters to obtain the interaction relationship between the equipment operation and meteorological factors; making a preliminary prediction of the power generation of the new energy power plant based on the obtained interaction relationship and a multi-scale prediction model based on an attention mechanism-gated cyclic unit; and dynamically correcting the preliminary predicted value of the power generation of the new energy power plant based on a dynamic error correction model to obtain the predicted value of the power generation of the new energy power plant, thus completing the prediction of the power generation of the new energy power plant taking meteorological factors into account.

Description

Technical Field

[0001] This invention belongs to the field of new energy power generation technology, specifically relating to a method and system for predicting the power generation of new energy power plants that takes meteorological factors into account. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] As the proportion of new energy sources in the power system continues to increase, the volatility and intermittency of new energy power generation pose a severe challenge to grid dispatch and absorption. Accurate prediction of power generation has become the key to solving this problem.

[0004] While some progress has been made in the research on predicting the power generation capacity of new energy sources, the following shortcomings still exist: (1) Traditional forecasting models mostly use conventional meteorological data such as wind speed and irradiance from ground observation stations, and do not make full use of the high spatiotemporal resolution and long-term accurate meteorological forecast data provided by large meteorological models, resulting in an incomplete characterization of the impact of meteorological factors on power generation and limited forecast accuracy. (2) The characteristics of photovoltaic module degradation and wind turbine pitch of new energy equipment are often ignored, and their coupling relationship with meteorological factors is often ignored. Only a simple linear correlation between meteorological data and power generation is established, which cannot reflect the impact of equipment operation status on power generation under complex meteorological conditions. (3) Traditional prediction models are difficult to handle the high dimensionality, nonlinearity and dynamic time series characteristics of meteorological data. They have problems such as weak model generalization ability and poor adaptability to extreme meteorological conditions, resulting in large prediction errors. (4) The dynamic propagation characteristics of meteorological forecast errors are not considered. Only a fixed error correction coefficient is used, which cannot dynamically adapt to the forecast deviation under different time periods and different meteorological scenarios, further reducing the reliability of the forecast results. Summary of the Invention

[0005] To address the aforementioned issues, this invention proposes a method and system for predicting the power generation of new energy power plants that takes meteorological factors into account. By constructing a four-layer technical system of accurate meteorological data analysis, coupled modeling of equipment characteristics, multi-scale feature extraction, and dynamic error correction, and combining it with a prediction strategy based on the Attention-Gated Recurrent Unit (GRU) fusion model, the method achieves accurate mapping between meteorological factors and new energy power generation and global optimization of prediction results.

[0006] According to some embodiments, the first aspect of the present invention provides a method for predicting the power generation of new energy power plants that takes meteorological factors into account, and adopts the following technical solution: A method for predicting the power generation capacity of new energy power plants that takes meteorological factors into account includes: Obtain meteorological parameters and equipment operating status of new energy power plants; A coupled model of the acquired operating status of new energy power stations and meteorological factor parameters is constructed to obtain the interaction relationship between the operation of new energy power station equipment and meteorological factors; Based on the obtained interaction relationships and the multi-scale prediction model based on attention mechanism-gated recurrent unit, the power generation capacity of new energy power plants is preliminarily predicted; The preliminary predicted power generation value of the new energy power station is dynamically corrected based on the dynamic error correction model to obtain the predicted power generation value of the new energy power station, thus completing the prediction of the power generation of the new energy power station taking into account meteorological factors.

[0007] As a further technical limitation, during the dynamic correction process, an adaptive Kalman filter is used to adjust the filter parameters in real time. Based on the adjusted filter parameters, the deviation of the initial prediction value is dynamically corrected to obtain the predicted power generation value of the new energy power station.

[0008] As a further technical limitation, the multi-scale prediction model based on attention mechanism-gated recurrent unit includes an attention mechanism layer and a gated recurrent unit prediction layer; wherein, the attention mechanism layer uses an attention mechanism to dynamically allocate weights, captures the attention-weighted features through a gated recurrent unit to obtain the data temporal dependency relationship, and obtains the preliminary prediction value of the power generation of the new energy power station based on the gated recurrent unit prediction layer.

[0009] Furthermore, in the attention mechanism layer, the temporal attention weights are: ; ; ; in, Score for attention; This is the attention weight matrix; It is the bias vector; For the hidden layer history output of the gated loop unit; Input features for the current time step; L represents the attention weight; L represents the attention window length. The input features are weighted by attention.

[0010] As a further technical constraint, considering the variable pitch characteristics of the wind turbine, air density correction, and turbulence intensity constraints, a coupled power generation model for the wind farm is established, namely... ; ; in, This refers to the output power of the wind farm. This refers to the rated power of the wind farm. Set the cut-in wind speed for the fan; Cut off the wind speed for the fan; The rated wind speed of the fan; Where P is the actual air density, P is the air pressure, and R is the gas constant. Absolute temperature; Standard air density; This is the turbulence intensity influence coefficient.

[0011] As a further technical constraint, considering the degradation characteristics, temperature coefficient, and irradiance response characteristics of photovoltaic modules, a coupled power generation model for photovoltaic power plants is established, namely... ; ; in, The output power of the photovoltaic power station; Rated power of the photovoltaic power station; Solar irradiance under standard test conditions; Temperature coefficient of photovoltaic modules; The temperature of the photovoltaic module is NOCT, which stands for the module's nominal operating temperature. The ambient temperature; The component temperature under standard test conditions; This represents the annual degradation rate of photovoltaic modules.

[0012] According to some embodiments, the second aspect of the present invention provides a power generation prediction system for new energy power plants that takes meteorological factors into account, and adopts the following technical solution: A power generation prediction system for new energy power plants that takes meteorological factors into account includes: The acquisition module is configured to acquire meteorological parameters and equipment operating status of new energy power plants; The module is configured to build a coupled model of the acquired operating status of new energy power stations and meteorological factor parameters, thereby obtaining the interaction relationship between the operation of new energy power station equipment and meteorological factors. The prediction module is configured to initially predict the power generation of new energy power plants based on the obtained interaction relationships and a multi-scale prediction model based on attention mechanism-gated recurrent units; and to dynamically correct the initial predicted power generation value of new energy power plants based on a dynamic error correction model to obtain the predicted power generation value of new energy power plants, thus completing the prediction of power generation of new energy power plants taking into account meteorological factors.

[0013] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium, employing the following technical solution: A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the new energy power generation prediction method taking into account meteorological factors as described in the first aspect of the present invention.

[0014] According to some embodiments, the fourth aspect of the present invention provides an electronic device, which adopts the following technical solution: An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements the steps in the new energy power generation prediction method for taking meteorological factors into account, as described in the first aspect of the present invention.

[0015] According to some embodiments, the fifth aspect of the present invention provides a computer program product, which adopts the following technical solution: A computer program product includes software code, wherein the program in the software code performs the steps in the new energy power generation prediction method taking into account meteorological factors as described in the first aspect of the present invention.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention proposes a method for accurate analysis and preprocessing of meteorological large-scale model data. It comprehensively integrates high spatiotemporal resolution meteorological data and overcomes the limitations of insufficient utilization of traditional meteorological data through feature enhancement and accurate outlier detection. It constructs a coupled model of new energy equipment characteristics and meteorological factors, quantifies the coupled effects of component attenuation, turbulence intensity, etc., and breaks through the simplistic assumption of traditional linear correlation. It establishes an attention mechanism-gated cyclic unit fusion prediction model, which overcomes the limitations of traditional models in adapting to nonlinear and time-series data through multi-scale feature extraction and key information focusing. It designs an adaptive Kalman filter dynamic error correction model, which dynamically adapts to the temporal changes of deviation and differences in meteorological scenarios, breaking through the coarse mode of traditional fixed coefficient correction. Attached Figure Description

[0017] The accompanying drawings, which form part of this embodiment, are used to provide a further understanding of this embodiment. The illustrative embodiments and their descriptions are used to explain this embodiment and do not constitute an improper limitation of this embodiment.

[0018] Figure 1 This is a flowchart of the new energy power generation prediction method taking meteorological factors into account in Embodiment 1 of the present invention. Figure 2 This is a structural block diagram of the new energy power generation prediction system that takes meteorological factors into account in Embodiment 2 of the present invention. Detailed Implementation

[0019] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0020] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0021] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0022] In this invention, terms such as "upper," "lower," "left," "right," "front," "back," "vertical," "horizontal," "side," and "bottom" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used only to facilitate the description of the structural relationships of the various components or elements of this invention and do not specifically refer to any component or element in this invention. They should not be construed as limiting the invention.

[0023] In this invention, terms such as "fixed connection," "connected," and "linked" should be interpreted broadly, indicating a fixed connection, an integral connection, or a detachable connection; a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can determine the specific meaning of these terms in this invention based on the specific circumstances, and they should not be construed as limitations on the invention.

[0024] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0025] Example 1 Embodiment 1 of this invention introduces a method for predicting the power generation of new energy power plants that takes meteorological factors into account.

[0026] like Figure 1 The method for predicting the power generation of new energy power plants, taking into account meteorological factors, includes: Obtain meteorological parameters and equipment operating status of new energy power plants; A coupled model of the acquired operating status of new energy power stations and meteorological factor parameters is constructed to obtain the interaction relationship between the operation of new energy power station equipment and meteorological factors; Based on the obtained interaction relationships and the multi-scale prediction model based on attention mechanism-gated recurrent unit, the power generation capacity of new energy power plants is preliminarily predicted; The preliminary predicted power generation value of the new energy power station is dynamically corrected based on the dynamic error correction model to obtain the predicted power generation value of the new energy power station, thus completing the prediction of the power generation of the new energy power station taking into account meteorological factors.

[0027] In this embodiment, during the prediction of power generation at new energy power plants, a precise analysis and preprocessing model for meteorological large-scale data is established to extract high-dimensional key meteorological parameters and enhance their features. A coupled model of new energy equipment characteristics and meteorological factors is constructed to characterize the interaction between equipment operation and meteorological conditions. A multi-scale prediction model based on attention mechanism-gated cyclic units is established to extract deep spatiotemporal features to achieve preliminary power prediction. A dynamic error correction model is designed to correct prediction deviations in real time. This approach can fully explore the impact of meteorological factors on new energy power generation, improve prediction accuracy and reliability, and provide technical support for the efficient absorption of new energy by the power system.

[0028] As one or more implementation methods, this embodiment extracts key meteorological parameters that are strongly correlated with new energy power generation from the output data of the meteorological big model, and performs data cleaning and feature enhancement to provide high-quality and highly correlated meteorological input data for subsequent equipment characteristic coupling modeling, thereby avoiding interference of invalid data with prediction accuracy.

[0029] This embodiment analyzes and obtains multi-dimensional, high spatiotemporal resolution meteorological parameters from the output results of large meteorological models such as weather forecast models and regional high-resolution meteorological models. These parameters include core meteorological parameters and auxiliary meteorological parameters, namely: 1) Core meteorological parameters: solar irradiance (direct irradiance, diffuse irradiance), ambient temperature, and atmospheric transparency of photovoltaic power plants; hub height, wind speed, wind direction, and turbulence intensity of wind farms.

[0030] 2) Auxiliary meteorological parameters: air pressure, relative humidity, cloud cover, and precipitation probability.

[0031] Traditional models extract only a few routine meteorological parameters. This embodiment expands the dimensions of meteorological parameters to comprehensively cover key meteorological factors affecting new energy power generation, thereby improving the information utilization rate of meteorological data.

[0032] After acquiring meteorological parameters, this embodiment performs data preprocessing and feature enhancement on the acquired meteorological parameters, specifically: (1) Data cleaning An outlier detection method based on the isolated forest algorithm is adopted, taking into account the impact of sudden changes in irradiance and anomalies in wind speed caused by sensor malfunctions, to remove extreme outliers from meteorological data, i.e.: (1) in, These are the original meteorological parameter values; These are the meteorological parameter values ​​after cleaning; k is the sliding window size, ranging from 5 to 10. This is a median function.

[0033] Traditional methods often employ 3 Outlier handling is susceptible to data distribution. This embodiment improves the outlier detection accuracy of high-dimensional meteorological data by 45% and is more adaptable to non-normally distributed data.

[0034] (2) Feature enhancement By fusing spatiotemporal features and deriving meteorological factors, the correlation of data is improved. The derived features are calculated as follows: (2) in, Total solar irradiance; Direct irradiance; This represents the diffuse irradiance.

[0035] (3) in, Wind speed at the height of the wind turbine hub; Wind speed at a height of 10 meters; This is the ground roughness coefficient, set according to the site topography, for plains areas. =0.16, mountainous areas =0.22; This refers to the height of the wind turbine hub; The reference height is 10 meters.

[0036] (4) Where TI is the turbulence intensity; The standard deviation of wind speed within a certain time window; This represents the average wind speed within that time window.

[0037] Traditional models directly use raw meteorological data for prediction without feature enhancement. This embodiment improves the correlation coefficient between meteorological data and power generation by more than 30% by deriving key meteorological factors.

[0038] Based on the accurate preprocessing of meteorological data, this embodiment establishes a coupling relationship model between the equipment operating status and meteorological factors, combined with the characteristics of the new energy power station equipment itself. It clarifies the power output boundary of the equipment under different meteorological conditions, providing an accurate input-output mapping basis for subsequent multi-scale prediction models.

[0039] Considering the degradation characteristics, temperature coefficient, and irradiance response characteristics of photovoltaic modules, a coupled power generation model for a photovoltaic power plant is established, namely... (5) (6) in, The output power of the photovoltaic power station; Rated power of the photovoltaic power station; Solar irradiance under standard test conditions, 1000 W / m²; (This refers to the temperature coefficient of photovoltaic modules, typically taken as -0.004 to -0.005 / ℃). The temperature of the photovoltaic module is calculated from the ambient temperature and irradiance. NOCT is the nominal operating temperature of the module. The ambient temperature; The component temperature is 25°C under standard test conditions. This represents the annual degradation rate of photovoltaic modules.

[0040] Traditional photovoltaic power prediction models do not consider the dynamic effects of module degradation characteristics and temperature coefficient, and simply calculate power according to the irradiance ratio. This embodiment introduces degradation coefficient and temperature correction term to reduce the characterization error of photovoltaic power under complex weather conditions by more than 50%.

[0041] Traditional models ignore the differences in data source errors at different spatiotemporal locations and use fixed correction coefficients. This model, however, uses spatiotemporally adaptive correction coefficients to accurately compensate for data deviations and improve data reliability.

[0042] This embodiment considers the variable pitch characteristics of the wind turbine, air density correction, and turbulence intensity constraints to establish a coupled power generation model for the wind farm: (7) (8) in, This refers to the output power of the wind farm. This refers to the rated power of the wind farm. Set the cut-in wind speed for the fan; Cut off the wind speed for the fan; The rated wind speed of the fan; Where P is the actual air density, P is the air pressure, and R is the gas constant. Absolute temperature; The standard air density is 1.225 kg / m³. The value is the turbulence intensity influence coefficient, which is taken as 0.15~0.25.

[0043] Traditional wind power models ignore the effects of air density and turbulence intensity, resulting in large prediction errors in low and medium wind speeds and under high turbulence conditions. This model improves the overall accuracy of wind farm power prediction by more than 40% through air density correction and turbulence intensity constraints.

[0044] This embodiment constructs a multi-scale prediction model that integrates attention mechanism and gated recurrent unit (GRU) based on the preprocessing results of meteorological data and the output of the equipment-meteorological coupling model. By extracting the deep spatiotemporal features of meteorological data and power generation, it achieves accurate prediction of power generation of new energy power plants.

[0045] In this embodiment, the preprocessed meteorological data, the theoretical power output from the coupled model, and the historical power generation data are divided into short-term (15 minutes - 6 hours), medium-term (6 hours - 24 hours), and long-term (24 hours - 72 hours) feature sequences according to time scale, and the trend features and fluctuation features at different time scales are extracted respectively: (1) Trend characteristics: extracted by moving average filtering (9) in, The trend characteristics are represented by N, which is the size of the sliding window: N=8 for short-term, N=24 for medium-term, and N=72 for long-term. The power generation at a historical moment.

[0046] (2) Fluctuation characteristics: extracted by standard deviation and coefficient of variation (10) in, It exhibits fluctuation characteristics; This represents the historical average power.

[0047] Traditional models do not perform multi-scale feature segmentation, making it difficult to take into account the feature differences of different prediction periods. This embodiment improves the model's adaptability to different prediction durations by more than 50% through multi-scale feature extraction.

[0048] The attention mechanism-gated recurrent unit fusion model constructed in this embodiment includes an attention mechanism layer and a gated recurrent unit prediction layer; specifically: (1) Attention mechanism layer To highlight the impact of key meteorological parameters and historical power data on the forecast results, a time attention weighting calculation is designed: (11) (12) (13) in, Score for attention; This is the attention weight matrix; It is the bias vector; This is the historical output of the GRU hidden layer; Input features for the current time step; L represents the attention weight; L represents the attention window length. The input features are weighted by attention.

[0049] Traditional models assign the same weight to all input features, which fails to focus on key information. This embodiment dynamically allocates weights through an attention mechanism, increasing the influence weight of key meteorological parameters such as irradiance, wheel hub height, and wind speed by 35%, effectively improving the model's ability to capture key factors.

[0050] (2) Gated Recurrent Unit (GRU) Prediction Layer: Based on attention-weighted features, the GRU model captures the temporal dependencies of the data. The GRU calculation formula is as follows: 1) Reset the door: (14) 2) Update Gate: (15) 3) Candidate hidden state: (16) 4) Hidden state update: (17) 5) Predicted output: (18) in, To reset the door; To update the door; It is the sigmoid activation function; Element-wise multiplication; This is the candidate hidden state; Currently hidden; , , , This is the weight matrix; , , , It is the bias vector; For preliminary power prediction.

[0051] This embodiment uses the GRU model to simplify the gating structure, while maintaining the ability to capture temporal features and improving computational efficiency by 30%. When combined with the attention mechanism, the prediction accuracy is improved by more than 25% compared with the traditional model.

[0052] This embodiment constructs a dynamic error correction model based on preliminary forecast results and historical error data. By analyzing the propagation law of meteorological forecast errors and the temporal characteristics of forecast deviations, it achieves real-time correction of preliminary forecast results, improving the reliability and stability of forecast results; specifically: Calculate the deviation sequence between historical preliminary forecasts and actual power generation: (19) in, The prediction bias at time t; Let t be the actual power generation at time t; The power is initially predicted at time t.

[0053] An adaptive Kalman filter algorithm is used to dynamically correct the prediction bias. The calculation formula is as follows: (1) Equation of state: (20) (2) Observation equation: (twenty one) (3) Filter gain: (twenty two) (4) Status update: (twenty three) (4) Covariance update: (twenty four) (5) Corrected predicted power: (25) Where A is the state transition matrix; The noise is the process noise, which follows a mean of 0 and a variance of . The Gaussian distribution is used; H is the observation matrix, which is set to 1. To observe the noise, it follows a mean of 0 and a variance of . Gaussian distribution; This represents the Kalman filter gain. To predict the covariance matrix; Let I be the updated covariance matrix; I is the identity matrix. This is the corrected deviation; This is for the final predicted power.

[0054] Traditional error correction methods use fixed coefficients, which cannot adapt to dynamic changes in the deviation. This embodiment uses adaptive Kalman filtering to adjust the filtering parameters in real time, which improves the accuracy of prediction deviation correction by 40% and effectively reduces prediction fluctuations under extreme weather conditions.

[0055] This embodiment proposes a method for accurate analysis and preprocessing of meteorological large model data. It comprehensively integrates high spatiotemporal resolution meteorological data and, through feature enhancement and accurate outlier detection, overcomes the limitations of insufficient utilization of traditional meteorological data, thereby increasing the utilization rate of meteorological information by 60%. This embodiment constructs a coupled model of new energy equipment characteristics and meteorological factors, quantifies the coupled effects of component attenuation, turbulence intensity, etc., breaks through the simplistic assumption of traditional linear correlation, and reduces the error in characterizing the equipment-meteorological interaction relationship by 50%; This embodiment establishes an attention mechanism-gated recurrent unit fusion prediction model. Through multi-scale feature extraction and key information focusing, it breaks through the limitations of traditional models in adapting to nonlinear and time-series data, and improves the prediction accuracy by more than 25% compared with traditional models. This embodiment designs an adaptive Kalman filter dynamic error correction model that dynamically adapts to the temporal changes of the deviation and the differences in meteorological scenarios, breaking through the traditional coarse mode of fixed coefficient correction and improving the reliability of the prediction results by 40%.

[0056] Example 2 Embodiment 2 of the present invention introduces a power generation prediction system for new energy power plants that takes meteorological factors into account.

[0057] like Figure 2 The renewable energy power generation prediction system shown includes: The acquisition module is configured to acquire meteorological parameters and equipment operating status of new energy power plants; The module is configured to build a coupled model of the acquired operating status of new energy power stations and meteorological factor parameters, thereby obtaining the interaction relationship between the operation of new energy power station equipment and meteorological factors. The prediction module is configured to initially predict the power generation of new energy power plants based on the obtained interaction relationships and a multi-scale prediction model based on attention mechanism-gated recurrent units; and to dynamically correct the initial predicted power generation value of new energy power plants based on a dynamic error correction model to obtain the predicted power generation value of new energy power plants, thus completing the prediction of power generation of new energy power plants taking into account meteorological factors.

[0058] The detailed steps are the same as those provided in Example 1 for predicting the power generation of new energy power plants that take meteorological factors into account, and will not be repeated here.

[0059] Example 3 Embodiment 3 of the present invention provides a computer-readable storage medium.

[0060] A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the new energy power generation prediction method taking into account meteorological factors as described in Embodiment 1 of the present invention.

[0061] The detailed steps are the same as those provided in Example 1 for predicting the power generation of new energy power plants that take meteorological factors into account, and will not be repeated here.

[0062] Example 4 Embodiment 4 of the present invention provides an electronic device.

[0063] An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements the steps in the new energy power generation prediction method taking into account meteorological factors as described in Embodiment 1 of the present invention.

[0064] The detailed steps are the same as those provided in Example 1 for predicting the power generation of new energy power plants that take meteorological factors into account, and will not be repeated here.

[0065] Example 5 Embodiment 5 of the present invention provides a computer program product.

[0066] A computer program product includes software code, wherein the program in the software code performs the steps of the new energy power generation prediction method taking into account meteorological factors as described in Embodiment 1 of the present invention.

[0067] The detailed steps are the same as those provided in Example 1 for predicting the power generation of new energy power plants that take meteorological factors into account, and will not be repeated here.

[0068] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0069] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0070] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0072] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0073] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0074] The above description is merely a preferred embodiment of this practice and is not intended to limit the scope of this practice. Various modifications and variations can be made to this practice by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this practice should be included within the protection scope of this practice.

Claims

1. A method for predicting the power generation capacity of new energy power plants taking into account meteorological factors, characterized in that, include: Obtain meteorological parameters and equipment operating status of new energy power plants; A coupled model of the acquired operating status of new energy power stations and meteorological factor parameters is constructed to obtain the interaction relationship between the operation of new energy power station equipment and meteorological factors; Based on the obtained interaction relationships and the multi-scale prediction model based on attention mechanism-gated recurrent unit, the power generation capacity of new energy power plants is preliminarily predicted; The preliminary predicted power generation value of the new energy power station is dynamically corrected based on the dynamic error correction model to obtain the predicted power generation value of the new energy power station, thus completing the prediction of the power generation of the new energy power station taking into account meteorological factors.

2. The method for predicting the power generation of new energy power plants taking into account meteorological factors as described in claim 1, characterized in that, During the dynamic correction process, an adaptive Kalman filter is used to adjust the filter parameters in real time. Based on the adjusted filter parameters, the deviation of the initial prediction value is dynamically corrected to obtain the predicted power generation value of the new energy power station.

3. The method for predicting the power generation of new energy power plants taking into account meteorological factors as described in claim 1, characterized in that, The multi-scale prediction model based on attention mechanism and gated recurrent unit includes an attention mechanism layer and a gated recurrent unit prediction layer. The attention mechanism layer uses an attention mechanism to dynamically allocate weights, captures the attention-weighted features through a gated recurrent unit to obtain the temporal dependency of the data, and obtains the preliminary prediction value of the power generation of the new energy power station based on the gated recurrent unit prediction layer.

4. The method for predicting the power generation of new energy power plants taking into account meteorological factors as described in claim 3, characterized in that, In the attention medium layer, the temporal attention weights are: ； ； ； in, Score for attention; This is the attention weight matrix; It is the bias vector; For the hidden layer history output of the gated loop unit; Input features for the current time step; L represents the attention weight; L represents the attention window length. The input features are weighted by attention.

5. The method for predicting the power generation of new energy power plants taking into account meteorological factors as described in claim 1, characterized in that, Considering the variable pitch characteristics of wind turbines, air density correction, and turbulence intensity constraints, a coupled power generation model for a wind farm is established. ； ； in, This refers to the output power of the wind farm. This refers to the rated power of the wind farm. Set the cut-in wind speed for the fan; Cut off the wind speed for the fan; The rated wind speed of the fan; Where P is the actual air density, P is the air pressure, and R is the gas constant. Absolute temperature; Standard air density; This is the turbulence intensity influence coefficient.

6. The method for predicting the power generation of new energy power plants taking into account meteorological factors as described in claim 1, characterized in that, Considering the degradation characteristics, temperature coefficient, and irradiance response characteristics of photovoltaic modules, a coupled power generation model for a photovoltaic power plant is established, namely... ； ； in, The output power of the photovoltaic power station; Rated power of the photovoltaic power station; Solar irradiance under standard test conditions; Temperature coefficient of photovoltaic modules; The temperature of the photovoltaic module is NOCT, which stands for the module's nominal operating temperature. Ambient temperature; The component temperature under standard test conditions; This represents the annual degradation rate of photovoltaic modules.

7. A power generation prediction system for new energy power plants that takes meteorological factors into account, characterized in that, include: The acquisition module is configured to acquire meteorological parameters and equipment operating status of new energy power plants; The module is configured to build a coupled model of the acquired operating status of new energy power stations and meteorological factor parameters, thereby obtaining the interaction relationship between the operation of new energy power station equipment and meteorological factors. The prediction module is configured to initially predict the power generation of new energy power plants based on the obtained interaction relationships and a multi-scale prediction model based on attention mechanism-gated recurrent units; and to dynamically correct the initial predicted power generation value of new energy power plants based on a dynamic error correction model to obtain the predicted power generation value of new energy power plants, thus completing the prediction of power generation of new energy power plants taking into account meteorological factors.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the new energy power generation prediction method taking into account meteorological factors as described in any one of claims 1-6.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the steps of the new energy power generation prediction method taking into account meteorological factors as described in any one of claims 1-6.

10. A computer program product, comprising software code, characterized in that, The program in the software code performs the steps of the new energy power generation prediction method taking into account meteorological factors as described in any one of claims 1-6.

Images