A photovoltaic power station ultra-short-term power prediction method, system, device and medium
By acquiring and processing historical data from photovoltaic power plants, and combining mesoscale weather forecasting models and ultra-short-term power forecasting models, the problem of low accuracy in ultra-short-term power forecasting for photovoltaic power plants has been solved, achieving higher forecast accuracy and improving grid stability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 华能(嘉峪关)新能源有限公司
- Filing Date
- 2024-11-28
- Publication Date
- 2026-06-02
AI Technical Summary
The accuracy of ultra-short-term power prediction for photovoltaic power plants in existing technologies is relatively low, which affects the stability and frequency quality of the power grid.
By acquiring historical meteorological data and geographical information of the target photovoltaic power station, data preprocessing and feature extraction are performed. Combined with mesoscale weather prediction models and ultra-short-term power prediction models, linear regression, support vector regression, random forest or long short-term memory networks are used for training and prediction to improve prediction accuracy.
It improves the accuracy of ultra-short-term power prediction for photovoltaic power plants, and enhances the stability and frequency quality of the power grid.
Abstract
Description
Technical Field
[0001] This invention belongs to the field of photovoltaic power generation, specifically relating to a method, system, equipment, and medium for ultra-short-term power prediction of photovoltaic power plants. Background Technology
[0002] Solar energy is a clean energy source with randomness and volatility, so the output power of photovoltaic power generation will vary due to factors such as weather conditions, seasonal changes, and cloud cover. This randomness and volatility can lead to insufficient ability of photovoltaic power plants to respond to grid frequency regulation commands, thereby affecting the stability and frequency quality of the grid.
[0003] Existing technologies rely on weather forecast data to establish corresponding algorithm models for predicting wind power in the ultra-short term. The accuracy is evaluated based on the accuracy over a day or a period of time. However, the accuracy is low at finer time granularities such as hours and minutes. Furthermore, no further processing is done to improve the accuracy of the ultra-short term power prediction results, resulting in low precision of the ultra-short term power prediction data. Summary of the Invention
[0004] The purpose of this invention is to provide a method, system, equipment and medium for ultra-short-term power prediction of photovoltaic power plants, which solves the problem of low accuracy in existing ultra-short-term power prediction.
[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: This invention provides a method for predicting ultra-short-term power output of a photovoltaic power plant, comprising the following steps: Step 1: Obtain historical meteorological data and geographic information for the area where the target photovoltaic power station is located, as well as historical operating data for each photovoltaic power station; Step 2: Perform data preprocessing on the acquired historical meteorological data, geographic information, and historical operation data of each photovoltaic power station to obtain preprocessed historical meteorological data, geographic information, and historical operation data; Step 3: Extract and select features from the preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values; Step 4: Train the constructed ultra-short-term power prediction model using multiple feature values to obtain the trained ultra-short-term power prediction model. Step 5: Use the preset mesoscale weather prediction model to predict the future meteorological data of the area where the target power station is located, and combine the obtained future meteorological data with the trained ultra-short-term power prediction model to predict the ultra-short-term power of the target power station.
[0006] Preferably, in step 1, the historical meteorological data is obtained by assimilating data from a collection of multiple data sources obtained from numerical weather prediction and historical measured meteorological data from various stations.
[0007] Preferably, in step 3, feature extraction and selection are performed on the preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values. The specific method is as follows: Key features were extracted from the preprocessed historical meteorological data, geographic information, and historical operational data. From the multiple key features obtained by correlation analysis or principal component analysis, features with importance greater than a set threshold are selected to obtain multiple feature values.
[0008] Preferably, in step 5, the method for constructing the preset mesoscale weather prediction model is as follows: Establish an initial mesoscale weather prediction model that assimilates multi-source data and covers a specified cluster; The initial mesoscale weather prediction model was downscaled and parameterized to obtain the preset mesoscale weather prediction model.
[0009] Preferably, the obtained multi-source historical meteorological data are assimilated using methods such as stepwise correction, optimal interpolation, three-dimensional variational, four-dimensional variational, or Kalman filtering.
[0010] Preferably, in step 4, an ultra-short-term power prediction model is constructed using a linear regression model, support vector regression, random forest, or long short-term memory network.
[0011] A photovoltaic power plant ultra-short-term power prediction system includes: The data acquisition unit is used to acquire historical meteorological data and geographic information corresponding to the area where the target photovoltaic power station is located, as well as historical operating data of each photovoltaic power station; The data preprocessing unit is used to preprocess the acquired historical meteorological data, geographic information and historical operation data of each photovoltaic power station to obtain preprocessed historical meteorological data, geographic information and historical operation data. The feature extraction unit is used to extract and select features from preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values. The model training unit is used to train the constructed ultra-short-term power prediction model using multiple feature values to obtain the trained ultra-short-term power prediction model. The power prediction unit is used to predict future meteorological data of the area where the target power plant is located using a preset mesoscale weather prediction model, and then combine the obtained future meteorological data with the trained ultra-short-term power prediction model to predict the ultra-short-term power of the target power plant.
[0012] A computer device, comprising: A processor is used to execute computer programs; A computer-readable storage medium storing a computer program that, when executed by the processor, performs the method.
[0013] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method.
[0014] A computer program product comprising a computer program that, when executed by a processor, implements the method.
[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention provides a method for predicting the ultra-short-term power of a photovoltaic power plant. It uses a mesoscale weather forecasting model to predict future meteorological data to improve the accuracy of meteorological forecasts. The predicted meteorological data is then used to predict the ultra-short-term power of the target power plant, thereby improving the accuracy of ultra-short-term power prediction for photovoltaic power plants. Detailed Implementation
[0016] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.
[0017] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.
[0018] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0019] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."
[0020] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0021] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.
[0022] Example 1 This embodiment provides a method for ultra-short-term power prediction of photovoltaic power plants. It employs a combination of multiple data sources, including numerical weather forecast data, historical measured meteorological data from various power plants, and historical output power data. This is combined with information such as the topography of the area where the power plant is located and the operating conditions of the power plant. A medium- and short-term prediction model for the region / section and the power plant is established using a combination of physical and statistical methods. The main input data for the short-term prediction model is the numerical weather forecast data for the next day and the measured meteorological data for the current day. The model continuously predicts the power generation data of the region and the power plant for the next four hours every 15 minutes (time resolution 15 minutes). Specifically, the method includes the following steps: Step 1: Obtain historical meteorological data and geographic information for the area where the target photovoltaic power station is located, as well as historical operating data for each photovoltaic power station.
[0023] The historical meteorological data is obtained by assimilating aggregated data from multiple data sources obtained from numerical weather prediction (NWP) and historical measured meteorological data from various stations. The aggregated data includes temperature, humidity, wind speed, wind direction, and air pressure; the historical measured meteorological data includes wind speed, wind direction, temperature, and humidity.
[0024] The geographic information includes altitude and terrain slope.
[0025] The historical operating data includes historical output power data and operating conditions, wherein the operating conditions include power-on / power-off status and maintenance plan.
[0026] Step 2: Perform data preprocessing on the acquired historical meteorological data, geographic information, and historical operation data of each photovoltaic power station to obtain preprocessed historical meteorological data, geographic information, and historical operation data.
[0027] The preprocessing includes cleaning the data, removing outliers and missing values, and normalizing or standardizing the data.
[0028] Step 3: Use a pre-set mesoscale weather forecasting model to predict future meteorological data for the area where the target power station is located.
[0029] The pre-defined method for constructing a mesoscale weather prediction model is as follows: Establish an initial mesoscale weather prediction model that assimilates multi-source data and covers a specified cluster; The initial mesoscale weather prediction model was downscaled and parameterized to obtain the preset mesoscale weather prediction model.
[0030] In this embodiment, the preprocessed historical meteorological data is assimilated using a combination of stepwise correction, optimal interpolation, three-dimensional variational analysis, four-dimensional variational analysis, Kalman filtering, and hybrid assimilation.
[0031] Step 4: Extract and select features from the preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values.
[0032] Key features, including but not limited to timestamps, geographical locations, weather parameters, and historical output power, are extracted from the preprocessed historical meteorological data, geographic information, and historical operational data.
[0033] Use feature selection methods (such as correlation analysis or principal component analysis) to filter features whose importance is higher than a set threshold, and obtain multiple feature values.
[0034] Step 5: Construct an ultra-short-term power prediction model.
[0035] Ultra-short-term power prediction models are constructed using linear regression models, support vector regression, random forests, or long short-term memory networks.
[0036] Step 6: Use the obtained multiple feature values to train the ultra-short-term power prediction model to obtain the trained ultra-short-term power prediction model.
[0037] Step 7: Using the predicted future meteorological data of the area where the target power station is located, and combining it with the trained ultra-short-term power prediction model, the ultra-short-term power of the target power station is predicted.
[0038] Example 2 This embodiment provides a photovoltaic power plant ultra-short-term power prediction system, including: The data acquisition unit is used to acquire historical meteorological data and geographic information corresponding to the area where the target photovoltaic power station is located, as well as historical operating data of each photovoltaic power station; The data preprocessing unit is used to preprocess the acquired historical meteorological data, geographic information and historical operation data of each photovoltaic power station to obtain preprocessed historical meteorological data, geographic information and historical operation data. The feature extraction unit is used to extract and select features from preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values. The model training unit is used to train the constructed ultra-short-term power prediction model using multiple feature values to obtain the trained ultra-short-term power prediction model. The power prediction unit is used to predict future meteorological data of the area where the target power plant is located using a preset mesoscale weather prediction model, and then combine the obtained future meteorological data with the trained ultra-short-term power prediction model to predict the ultra-short-term power of the target power plant.
[0039] Example 3 This embodiment 3 provides a computer device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of a computer method.
[0040] When the processor executes the computer program, it implements the steps of the above-described computer method.
[0041] For example, a method for predicting the ultra-short-term power output of a photovoltaic power plant includes the following steps: Step 1: Obtain historical meteorological data and geographic information for the area where the target photovoltaic power station is located, as well as historical operating data for each photovoltaic power station; Step 2: Perform data preprocessing on the acquired historical meteorological data, geographic information, and historical operation data of each photovoltaic power station to obtain preprocessed historical meteorological data, geographic information, and historical operation data; Step 3: Extract and select features from the preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values; Step 4: Train the constructed ultra-short-term power prediction model using multiple feature values to obtain the trained ultra-short-term power prediction model. Step 5: Use the preset mesoscale weather prediction model to predict the future meteorological data of the area where the target power station is located, and combine the obtained future meteorological data with the trained ultra-short-term power prediction model to predict the ultra-short-term power of the target power station.
[0042] Alternatively, when the processor executes the computer program, it implements the functions of each module in the above system, such as: The data acquisition unit is used to acquire historical meteorological data and geographic information corresponding to the area where the target photovoltaic power station is located, as well as historical operating data of each photovoltaic power station; The data preprocessing unit is used to preprocess the acquired historical meteorological data, geographic information and historical operation data of each photovoltaic power station to obtain preprocessed historical meteorological data, geographic information and historical operation data. The feature extraction unit is used to extract and select features from preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values. The model training unit is used to train the constructed ultra-short-term power prediction model using multiple feature values to obtain the trained ultra-short-term power prediction model. The power prediction unit is used to predict future meteorological data of the area where the target power plant is located using a preset mesoscale weather prediction model, and then combine the obtained future meteorological data with the trained ultra-short-term power prediction model to predict the ultra-short-term power of the target power plant.
[0043] The computer device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above are examples of computer devices and do not constitute a limitation on the computer device; it may include more components than described above, or combine certain components, or different components. For example, the computer device may also include input / output devices, network access devices, buses, etc.
[0044] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor, or any conventional processor, etc. The processor is the control center of the computer device, connecting various parts of the computer device through various interfaces and lines.
[0045] The memory can be used to store the computer program and / or module, and the processor implements various functions of the computer device by running or executing the computer program and / or module stored in the memory, and by calling the data stored in the memory.
[0046] The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function (such as sound playback, image playback, etc.); the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, SmartMediaCards (SMC), Secure Digital (SD) cards, FlashCards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.
[0047] Example 4 This embodiment 4 also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described.
[0048] For example, a method for predicting the ultra-short-term power output of a photovoltaic power plant includes the following steps: Step 1: Obtain historical meteorological data and geographic information for the area where the target photovoltaic power station is located, as well as historical operating data for each photovoltaic power station; Step 2: Perform data preprocessing on the acquired historical meteorological data, geographic information, and historical operation data of each photovoltaic power station to obtain preprocessed historical meteorological data, geographic information, and historical operation data; Step 3: Extract and select features from the preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values; Step 4: Train the constructed ultra-short-term power prediction model using multiple feature values to obtain the trained ultra-short-term power prediction model. Step 5: Use the preset mesoscale weather prediction model to predict the future meteorological data of the area where the target power station is located, and combine the obtained future meteorological data with the trained ultra-short-term power prediction model to predict the ultra-short-term power of the target power station.
[0049] If the modules / units integrated in the computer system are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.
[0050] Based on this understanding, all or part of the processes in the above-described method can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-described computer method. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or a preset intermediate form, etc.
[0051] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.
[0052] It should be noted that the content contained in the computer-readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.
[0053] Example 5 This embodiment 5 provides a computer product, which includes a computer program stored in a computer-readable storage medium. The processor of the computer device reads the computer program from the computer-readable storage medium and executes the computer program, enabling the computer device to perform the method in embodiment 1. Specifically: A method for predicting ultra-short-term power output of a photovoltaic power plant includes the following steps: Step 1: Obtain historical meteorological data and geographic information for the area where the target photovoltaic power station is located, as well as historical operating data for each photovoltaic power station; Step 2: Perform data preprocessing on the acquired historical meteorological data, geographic information, and historical operation data of each photovoltaic power station to obtain preprocessed historical meteorological data, geographic information, and historical operation data; Step 3: Extract and select features from the preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values; Step 4: Train the constructed ultra-short-term power prediction model using multiple feature values to obtain the trained ultra-short-term power prediction model. Step 5: Use the preset mesoscale weather prediction model to predict the future meteorological data of the area where the target power station is located, and combine the obtained future meteorological data with the trained ultra-short-term power prediction model to predict the ultra-short-term power of the target power station.
[0054] It should be noted that those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods.
[0055] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A method for ultra-short-term power prediction of a photovoltaic power plant, characterized in that, Includes the following steps: Step 1: Obtain historical meteorological data and geographic information for the area where the target photovoltaic power station is located, as well as historical operating data for each photovoltaic power station; Step 2: Perform data preprocessing on the acquired historical meteorological data, geographic information, and historical operation data of each photovoltaic power station to obtain preprocessed historical meteorological data, geographic information, and historical operation data; Step 3: Extract and select features from the preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values; Step 4: Train the constructed ultra-short-term power prediction model using multiple feature values to obtain the trained ultra-short-term power prediction model. Step 5: Use the preset mesoscale weather prediction model to predict the future meteorological data of the area where the target power station is located, and combine the obtained future meteorological data with the trained ultra-short-term power prediction model to predict the ultra-short-term power of the target power station.
2. The method according to claim 1, wherein, In step 1, the historical meteorological data is obtained by assimilating data from multiple data sources obtained from numerical weather prediction and historical measured meteorological data from various stations.
3. The method according to claim 1, wherein, In step 3, feature extraction and selection are performed on the preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values. The specific method is as follows: Key features were extracted from the preprocessed historical meteorological data, geographic information, and historical operational data. From the multiple key features obtained by correlation analysis or principal component analysis, features with importance greater than a set threshold are selected to obtain multiple feature values.
4. The method according to claim 1, wherein, In step 5, the method for constructing the pre-defined mesoscale weather prediction model is as follows: Establish an initial mesoscale weather prediction model that assimilates multi-source data and covers a specified cluster; The initial mesoscale weather prediction model was downscaled and parameterized to obtain the preset mesoscale weather prediction model.
5. The method according to claim 4, wherein, The multi-source historical meteorological data were assimilated using stepwise correction, optimal interpolation, three-dimensional variational, four-dimensional variational, or Kalman filtering methods.
6. The method of claim 1, wherein the method further comprises: In step 4, an ultra-short-term power prediction model is constructed using a linear regression model, support vector regression, random forest, or long short-term memory network.
7. A photovoltaic power plant ultra-short term power prediction system, characterized by, include: The data acquisition unit is used to acquire historical meteorological data and geographic information corresponding to the area where the target photovoltaic power station is located, as well as historical operating data of each photovoltaic power station; The data preprocessing unit is used to preprocess the acquired historical meteorological data, geographic information and historical operation data of each photovoltaic power station to obtain preprocessed historical meteorological data, geographic information and historical operation data. The feature extraction unit is used to extract and select features from preprocessed historical meteorological data, geographic information, and historical operational data to obtain multiple feature values. The model training unit is used to train the constructed ultra-short-term power prediction model using multiple feature values to obtain the trained ultra-short-term power prediction model. The power prediction unit is used to predict future meteorological data of the area where the target power plant is located using a preset mesoscale weather prediction model, and then combine the obtained future meteorological data with the trained ultra-short-term power prediction model to predict the ultra-short-term power of the target power plant.
8. A computer device, comprising: include: A processor is used to execute computer programs; A computer-readable storage medium storing a computer program that, when executed by the processor, performs the method as described in any one of claims 1-6.
9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.
10. A computer program product, characterised in that, The computer program product includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1-6.