Power generation and supply balance state prediction method and system for power system
By using a trained neural network model to predict the power generation and supply load of the power system, the problem of low accuracy in predicting the balance between power generation and supply in existing technologies is solved, enabling efficient operation and maintenance of power grid dispatch and dynamic dispatch strategy formulation.
Patent Information
- Application Number
- CN202511050116.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-29
- Publication Date
- 2025-11-11
AI Technical Summary
The current power system relies on manual experience to predict the balance between power generation and supply, which has low accuracy and leads to low efficiency in power grid dispatching, affecting residential and industrial electricity use.
The first trained neural network model is used to predict the power generation of the power system, and the second trained neural network model is used to predict the power supply load. The prediction is made by combining meteorological data and feature data, and the prediction accuracy is improved by using LSTM and Transformer models.
It improves the accuracy of power generation and supply balance prediction, provides a reliable reference for power grid dispatch, enhances the work effectiveness of operation and maintenance personnel, and supports multi-dimensional graphical display and dynamic dispatch strategy formulation.
Smart Images
Figure CN120933918A_ABST
Abstract
Description
Technical Field
[0001] This application generally relates to the fields of power grid dispatching and artificial intelligence technology. More specifically, this application relates to a method, system, medium, and device for predicting the power generation and supply balance state of a power system. Background Technology
[0002] Due to the needs of power grid dispatching, it is necessary to periodically predict the power generation and supply balance of the power system. However, with the large-scale grid connection of new energy (wind and solar) power systems, the overall power generation and supply load of the power system are significantly affected by meteorological conditions, exhibiting strong fluctuations and uncertainties. Currently, the power generation and supply balance of the power system is mainly predicted manually based on experience, which has low accuracy. This leads to maintenance personnel being unable to effectively perform grid dispatching work, affecting residential and industrial electricity consumption. Therefore, there is an urgent need for an effective scheme to determine the power generation and supply balance of the power system. Summary of the Invention
[0003] In order to at least solve one or more of the technical problems mentioned above, this application proposes a method, system, medium and equipment for predicting the power generation and supply balance state of a power system in several aspects.
[0004] In the first aspect, the method for predicting the power generation and supply balance state of a power system provided in this application includes the following steps:
[0005] Obtain the first meteorological data at the current moment, and determine the weather category at the current moment based on the first meteorological data. The weather category includes one or more of the following: sunny, cloudy, overcast, high temperature, low temperature, strong wind, dense fog, light rain, and heavy rain.
[0006] Extract first feature data directly related to power generation and second feature data directly related to power supply load from the first meteorological data. The first feature data includes wind speed, wind direction and solar radiation, and the second feature data includes temperature, humidity and air pressure.
[0007] The weather category and the first feature data are input into the trained first neural network model to obtain the power generation capacity of the power system within a future preset time period.
[0008] The current weather category and the second feature data are input into the trained second neural network model to obtain the power supply load of the power system within the preset time period in the future.
[0009] Based on the power generation and supply load of the power system in the future preset time period, predict the power generation and supply balance state of the power system in the future preset time period.
[0010] In some examples, the training process of the first trained neural network model includes:
[0011] Obtain meteorological data for each time of day within a preset historical period and generate secondary meteorological data;
[0012] Extract third characteristic data directly related to power generation from the second meteorological data, wherein the third characteristic data includes wind speed, wind direction and solar radiation.
[0013] Under the third feature data, the weather category and the power generation capacity of the power system at each time point are obtained respectively.
[0014] The third feature data, the weather category corresponding to the second meteorological data, and the power generation power of the power system at each time under the third feature data are input into the neural network model to obtain the first neural network model after training.
[0015] In some examples, the training process of the second neural network model includes:
[0016] Extract a fourth feature data directly related to the power supply load from the second meteorological data, wherein the fourth feature data includes temperature, humidity and air pressure;
[0017] Under the fourth feature data, the power supply load corresponding to each moment of the power system is obtained respectively;
[0018] The fourth feature data, the weather category corresponding to the second meteorological data, and the power supply load corresponding to the power system at each time under the fourth feature data are input into the neural network model to obtain the trained second neural network model.
[0019] In some examples, the first neural network model after training includes both LSTM and Transformer models.
[0020] In some examples, the trained second neural network model includes both LSTM and Transformer models.
[0021] In some examples, the power generation and supply balance of the power system includes a normal state, a slightly unbalanced state, and a severely unbalanced state.
[0022] In some examples, the method further includes:
[0023] It can display the power generation capacity, power supply load, and power generation and supply balance status of the power system in real time within a preset future time period.
[0024] In a second aspect, the power generation and supply balance prediction system for a power system provided in this application includes:
[0025] The acquisition module is configured to acquire the first meteorological data at the current moment, and determine the weather category at the current moment based on the first meteorological data. The weather category includes one or more of the following: sunny, cloudy, overcast, high temperature, low temperature, strong wind, dense fog, light rain, and heavy rain.
[0026] The extraction module is configured to extract first feature data directly related to power generation and second feature data directly related to power supply load from the first meteorological data. The first feature data includes wind speed, wind direction and solar radiation, and the second feature data includes temperature, humidity and air pressure.
[0027] The input module is configured to input the weather category and the first feature data into a trained first neural network model to obtain the power generation capacity of the power system within a future preset time period.
[0028] The input module is further configured to input the current weather category and the second feature data into the trained second neural network model to obtain the power supply load of the power system within the preset time period in the future;
[0029] The prediction module is configured to predict the power generation and supply balance of the power system based on the power generation and supply load of the power system within a preset future time period.
[0030] In a third aspect, the computer-readable storage medium provided in this application includes program instructions that, when executed by a processor, cause the method disclosed in the first aspect to be implemented.
[0031] In the fourth aspect, the electronic device provided in this application includes:
[0032] Processor; and
[0033] A memory storing computer instructions that, when executed by the processor, cause the electronic device to perform the method disclosed in the first aspect.
[0034] The method, system, medium, and equipment for predicting the power generation and supply balance of a power system provided in this application use a trained first neural network model to predict the power generation of the power system and a trained second neural network model to predict the power supply load of the power system. Based on the predicted power generation and power supply load of the power system, the accuracy of the prediction is improved, providing reliable reference information for formulating power grid dispatching strategies and improving the effectiveness of power grid operation and maintenance personnel in performing power grid operation and maintenance work. Attached Figure Description
[0035] The above and other objects, features, and advantages of exemplary embodiments of this application will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of this application are illustrated by way of example and not limitation, and the same or corresponding reference numerals denote the same or corresponding parts, wherein:
[0036] Figure 1 An exemplary flowchart of a power generation and supply balance state prediction method for a power system according to some embodiments of this application is shown;
[0037] Figure 2 An exemplary structural block diagram of a power generation and supply balance prediction system for a power system according to some embodiments of this application is shown;
[0038] Figure 3 An exemplary structural block diagram of an electronic device according to some embodiments of this application is shown. Detailed Implementation
[0039] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0040] It should be understood that the terms "comprising" and "including" used in the specification and claims of this application indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.
[0041] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this specification and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this specification and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.
[0042] As used in this specification and 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 [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."
[0043] The specific embodiments of this application will now be described in detail with reference to the accompanying drawings.
[0044] Example 1
[0045] like Figure 1 As shown in the embodiments of this application, the method for predicting the power generation and supply balance state of a power system includes the following steps:
[0046] S101, Obtain the first meteorological data at the current moment, and determine the weather category at the current moment based on the first meteorological data. The weather category includes one or more of the following: sunny, cloudy, overcast, high temperature, low temperature, strong wind, dense fog, light rain, and heavy rain.
[0047] Specifically, the time is measured in hours, but can also be measured in minutes or seconds. This weather category can also include typhoons, dust storms, hail, light snow, heavy snow, and blizzards.
[0048] S102, extract first characteristic data directly related to power generation and second characteristic data directly related to power supply load from the first meteorological data, wherein the first characteristic data includes wind speed, wind direction and solar radiation, and the second characteristic data includes temperature, humidity and air pressure.
[0049] S103, the weather category and the first feature data are input into the trained first neural network model to obtain the power generation of the power system within a future preset time period. The trained first neural network model can accurately predict the power generation of the power system within the future preset time period.
[0050] Specifically, power generation capacity measures a power plant's ability to supply electrical energy to the grid per unit time, typically measured in megawatts (MW). Higher power generation capacity indicates higher power plant efficiency, allowing it to supply more electrical energy to the grid. Power supply load is the sum of electricity consumption and line losses, reflecting the total demand for power from the power system. Meteorological factors are closely related to the power generation capacity and power supply load of the power system. These factors will be discussed below, including temperature, humidity, air pressure, wind speed, wind direction, and solar radiation.
[0051] (1) Temperature is one of the most important factors affecting the power supply load of the power system. Generally speaking, in hot weather, residents will increase their demand for air conditioning, thereby increasing the power supply load of the power system. In cold weather, residents need to use various heating devices (air conditioners, electric heaters, etc.), which will also increase the power supply load of the power system. In addition, in hot weather, the resistance of the power transmission lines increases, which leads to increased losses in the transmission lines, further increasing the power supply load of the power system.
[0052] (2) Humidity is another crucial factor affecting the power supply load of the power system. Increased humidity leads to increased use of electrical appliances (air conditioners, electric fans, and electric dryers, etc.) by residents, thus increasing the power supply load of the power system. This effect is particularly pronounced during the hot summer months.
[0053] (3) Air pressure is also an important factor affecting the power supply load of the power system. When the air pressure decreases, the density of the air decreases, which leads to a decrease in the insulation capacity of the power transmission lines and also increases the failure rate of the power equipment in the power system, resulting in greater line losses and thus increasing the power supply load of the power system.
[0054] (4) The wind speed and wind direction directly affect the power generation of the power system (wind power station). Generally speaking, the greater the wind speed and the more the wind direction matches the location of the wind power station blades, the greater the power generation of the wind power station.
[0055] (5) The amount of solar radiation directly affects the power generation capacity of the power system (solar power station). The greater the amount of solar radiation, the greater the power generation capacity of the solar power station.
[0056] In some examples, the training process of the first trained neural network model includes:
[0057] Obtain meteorological data for each time of day within a preset historical period and generate secondary meteorological data;
[0058] Extract third characteristic data directly related to power generation from the second meteorological data, wherein the third characteristic data includes wind speed, wind direction and solar radiation.
[0059] Under the third feature data, the weather category and the power generation capacity of the power system at each time point are obtained respectively.
[0060] The third feature data, the weather category corresponding to the second meteorological data, and the power generation power of the power system at each time under the third feature data are input into the neural network model to obtain the first neural network model after training.
[0061] Specifically, the preset historical periods are one month, two months, half a year, one year, two years, etc., with each moment in hours, or in minutes or seconds.
[0062] S104, the current weather category and the second feature data are input into the trained second neural network model to obtain the power supply load of the power system in the future preset time period. The trained second neural network model can accurately predict the power supply load of the power system in the future preset time period.
[0063] In some examples, the training process of the second neural network model includes:
[0064] Extract a fourth feature data directly related to the power supply load from the second meteorological data, wherein the fourth feature data includes temperature, humidity and air pressure;
[0065] Under the fourth feature data, the power supply load corresponding to each moment of the power system is obtained respectively;
[0066] The fourth feature data, the weather category corresponding to the second meteorological data, and the power supply load corresponding to the power system at each time under the fourth feature data are input into the neural network model to obtain the trained second neural network model.
[0067] In some examples, both the trained first and second neural network models include LSTM and Transformer models.
[0068] Specifically:
[0069] The LSTM model has the following advantages:
[0070] (1) It has a simple structure and few parameters, making it suitable for small and medium-sized datasets and resource-limited scenarios;
[0071] (2) It is more efficient at capturing the time dependencies of short sequences (such as n<100);
[0072] (3) It has low computational complexity and is suitable for real-time applications.
[0073] The Transformer model has the following advantages:
[0074] (1) It has strong parallelism and is suitable for large-scale data training and long sequence processing;
[0075] (2) Self-attention mechanism improves long-distance dependency modeling ability and transfer learning effect is good (such as pre-trained model);
[0076] (3) It can be extended to cross-modal tasks (such as text generation and speech recognition).
[0077] Specifically, if the preset time period is not greater than a preset first threshold, the trained first neural network model selects the LTSM model to calculate and continuously output the power generation of the power system within the future time period.
[0078] Specifically, the first threshold is 4 hours. When it is necessary to output the power generation of the power system in the next 4 hours, the trained neural network model selects the LTSM model to calculate and continuously output the power generation of the power system in the future time period.
[0079] Specifically, when the preset time period is longer than a preset first threshold, the trained first neural network model selects the LTSM model to calculate and continuously output the power generation of the power system in the future time period.
[0080] Specifically, the trained first neural network model can predict the power generation capacity of the power system within a preset future time period based on current meteorological data. When it is necessary to output the power supply load of the power system for the next 72 hours, the trained first neural network model selects the Transformer model to calculate and continuously output the power generation capacity of the power system within the specified future time period.
[0081] Specifically, if the preset time period is not greater than a preset second threshold, the trained second neural network model selects the LTSM model to calculate and continuously output the power system supply load within the future time period.
[0082] Specifically, the second threshold is 4 hours. When it is necessary to output the power system supply load for the next 4 hours, the trained second neural network model selects the LTSM model to calculate and continuously output the power system supply load for the next time period.
[0083] Specifically, when the preset time period is longer than a preset first threshold, the trained second neural network model selects the LTSM model to calculate and continuously output the power system supply load for the future time period.
[0084] Specifically, the trained second neural network model can predict the power supply load of the power system within a preset future time period based on current meteorological data. When it is necessary to output the power generation capacity of the power system for the next 72 hours, the trained second neural network model selects the Transformer model to calculate and continuously output the power supply load of the power system within the specified future time period.
[0085] S105, based on the power generation and supply load of the power system in the future preset time period, predicts the power generation and supply balance status of the power system in the future preset time period, providing reliable reference information for formulating scheduling strategies, and can improve the effectiveness of operation and maintenance personnel in performing power grid operation and maintenance work.
[0086] In some examples, the power system's generation and supply balance state includes a normal state, a slightly unbalanced state, and a severely unbalanced state. By accurately predicting the power system's generation and supply balance state,
[0087] Specifically, when the power system's power generation and supply balance is normal, it indicates that supply and demand are matched and redundant capacity is within the safety boundary; when the power system's power generation and supply balance is slightly unbalanced, it can be adjusted through dispatching; when the power system's power generation and supply balance is severely unbalanced, early warning information needs to be issued and emergency dispatching strategies need to be formulated.
[0088] In some examples, the method also includes:
[0089] It can display the power generation capacity, power supply load, and power generation and supply balance status of the power system in real time within a preset future time period.
[0090] Specifically, by employing spatiotemporal fusion visualization technology, the power generation capacity and supply load of the power system are visualized in a multi-dimensional and multi-layered manner, supporting dynamic evolution display under time series, enhancing the power system's operational situation awareness capabilities, and assisting operation and maintenance personnel in quickly grasping the power system's balance status and formulating scheduling strategies. These scheduling strategies can be optimized for resource allocation using optimization algorithms (such as genetic algorithms, particle swarm optimization, and reinforcement learning).
[0091] Specifically, the working principle of the trained first or second neural network model is as follows:
[0092] (1) Construct a causal relationship graph between variables based on causal graph modeling (e.g., PC algorithm, Causal-CNN algorithm);
[0093] (2) Use Bayesian networks or structural equation models to infer risk sources;
[0094] (3) Identify the causal effects of weather factors (such as typhoons and blizzards) on the power generation, power supply load and line failure probability of wind power generation systems.
[0095] Specifically, an online learning mechanism can be established to iteratively update the first and second neural network models after training; expert corrections and scheduling instructions are incorporated to improve the adaptability and robustness of the models.
[0096] Example 2
[0097] like Figure 2 As shown in the embodiment of this application, the power generation and supply balance prediction system for a power system includes:
[0098] The acquisition module is configured to acquire the first meteorological data at the current moment, and determine the weather category at the current moment based on the first meteorological data. The weather category includes one or more of the following: sunny, cloudy, overcast, high temperature, low temperature, strong wind, dense fog, light rain, and heavy rain.
[0099] The extraction module is configured to extract first feature data directly related to power generation and second feature data directly related to power supply load from the first meteorological data. The first feature data includes wind speed, wind direction and solar radiation, and the second feature data includes temperature, humidity and air pressure.
[0100] The input module is configured to input the weather category and the first feature data into a trained first neural network model to obtain the power generation capacity of the power system within a future preset time period.
[0101] The input module is further configured to input the current weather category and the second feature data into the trained second neural network model to obtain the power supply load of the power system within the preset time period in the future;
[0102] The prediction module is configured to predict the power generation and supply balance of the power system based on the power generation and supply load of the power system within a preset future time period.
[0103] Example 3
[0104] On the other hand, embodiments of this application also provide an electronic device, see [link to relevant documentation]. Figure 3 , Figure 3 This is an exemplary structural block diagram of an electronic device according to an embodiment of this application, such as... Figure 3 As shown, the electronic device includes a processor and a memory, the memory storing computer instructions, and the processor executing the computer instructions to perform the method provided in this application.
[0105] Specifically, processor 601 may include a central processing unit (CPU) or a graphics processing unit (GPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application. Memory 602 may include memory for data or instructions. For example, memory 602 may be at least one of the following: a hard disk drive (HDD), read-only memory (ROM), random access memory (RAM), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, Universal Serial Bus (USB) drive, or other physical / tangible memory storage device. Alternatively, memory 602 may include removable or non-removable (or fixed) media. Furthermore, memory 602 may be internal or external to the integrated gateway disaster recovery device. Memory 602 may be non-volatile solid-state memory. In other words, memory 602 typically includes a tangible (non-transitory) computer-readable storage medium (such as a memory device) encoded with executable instructions, wherein the stored executable instructions, when executed by processor 601 (such as by one or more processors), can implement the methods in the embodiments of this application.
[0106] In one example Figure 3 The illustrated electronic device may also include a communication interface 603 and a bus 610. The processor 601, memory 602, and communication interface 603 are connected via bus 610 and communicate with each other. Communication interface 603 is primarily used to enable communication between modules, devices, units, and / or equipment within the electronic device. Bus 610, including hardware, software, or both, couples components of the online data flow metering device together. For example, the bus may include at least one of the following: Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), HyperTransport (HT) interconnect, Industry Standard Architecture (ISA) bus, Infinite Bandwidth Interconnect, Low Pin Count (LPC) bus, memory bus, Microchannel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus, or other suitable buses. Bus 610 may include one or more buses. Although specific buses are described or illustrated in the embodiments of this application, any suitable bus or interconnection method may be considered in the embodiments of this application.
[0107] In another aspect, embodiments of this application also provide a computer-readable storage medium storing computer program instructions that, when executed by a processor, implement the aforementioned method. The computer-readable storage medium may be, for example, a classic computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), disk storage medium, optical storage medium, flash memory, or other electrical, optical, or other physical / tangible memory storage device.
[0108] In another aspect, embodiments of this application also provide a computer program product, which includes computer program instructions that, when executed by a processor, implement the method provided in embodiments of this application. This computer program product may be, for example, a software installation package, a plug-in compatible with a related software system, etc.
[0109] The flowcharts and / or block diagrams of the methods and systems of embodiments of this application have been described above by way of example, and related aspects have been described. It should be understood that each block or combination thereof in the flowcharts and / or block diagrams can be implemented by computer program instructions, by dedicated hardware performing a specified function or action, or by a combination of dedicated hardware and computer instructions. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc.; when implemented in software, it is a program or code segment used to perform the required task. The program or code segment can be stored in memory or transmitted over a transmission medium or communication link via data signals carried in a carrier wave. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.
[0110] While this application has shown and described numerous embodiments, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will arise for those skilled in the art without departing from the spirit and intent of this application. It should be understood that various alternatives to the embodiments of this application described herein may be employed in the practice of this application. The appended claims are intended to define the scope of protection of this application and therefore cover equivalents or alternatives within the scope of these claims.
Claims
1. A method for predicting the power generation and supply balance state of a power system, characterized in that, include: Obtain the first meteorological data at the current moment, and determine the weather category at the current moment based on the first meteorological data. The weather category includes one or more of the following: sunny, cloudy, overcast, high temperature, low temperature, strong wind, dense fog, light rain, and heavy rain. Extract first feature data directly related to power generation and second feature data directly related to power supply load from the first meteorological data. The first feature data includes wind speed, wind direction and solar radiation, and the second feature data includes temperature, humidity and air pressure. The weather category and the first feature data are input into the trained first neural network model to obtain the power generation capacity of the power system within a future preset time period. The current weather category and the second feature data are input into the trained second neural network model to obtain the power supply load of the power system within the preset time period in the future. Based on the power generation and supply load of the power system in the future preset time period, predict the power generation and supply balance state of the power system in the future preset time period.
2. The method for predicting the power generation and supply balance state according to claim 1, characterized in that, The training process of the first neural network model after training includes: Obtain meteorological data for each time of day within a preset historical period and generate secondary meteorological data; Extract third characteristic data directly related to power generation from the second meteorological data, wherein the third characteristic data includes wind speed, wind direction and solar radiation. Under the third feature data, the weather category and the power generation capacity of the power system at each time point are obtained respectively. The third feature data, the weather category corresponding to the second meteorological data, and the power generation power of the power system at each time under the third feature data are input into the neural network model to obtain the first neural network model after training.
3. The method for predicting the power generation and supply balance state according to claim 2, characterized in that, The training process of the second neural network model includes: Extract a fourth feature data directly related to the power supply load from the second meteorological data, wherein the fourth feature data includes temperature, humidity and air pressure; Under the fourth feature data, the power supply load corresponding to each moment of the power system is obtained respectively; The fourth feature data, the weather category corresponding to the second meteorological data, and the power supply load corresponding to the power system at each time under the fourth feature data are input into the neural network model to obtain the trained second neural network model.
4. The method for predicting the power generation and supply balance state according to claim 3, characterized in that: The first neural network model after training includes an LSTM model and a Transformer model.
5. The method for predicting the power generation and supply balance state according to claim 3, characterized in that: The trained second neural network model includes an LSTM model and a Transformer model.
6. The method for predicting the power generation and supply balance state according to claim 1, characterized in that: The power generation and supply balance status of the power system includes a normal state, a slightly unbalanced state, and a severely unbalanced state.
7. The method for predicting the power generation and supply balance state according to claim 6, characterized in that, The method further includes: It can display the power generation capacity, power supply load, and power generation and supply balance status of the power system in real time within a preset future time period.
8. A power generation and supply balance prediction system for a power system, characterized in that, include: The acquisition module is configured to acquire the first meteorological data at the current moment, and determine the weather category at the current moment based on the first meteorological data. The weather category includes one or more of the following: sunny, cloudy, overcast, high temperature, low temperature, strong wind, dense fog, light rain, and heavy rain. The extraction module is configured to extract first feature data directly related to power generation and second feature data directly related to power supply load from the first meteorological data. The first feature data includes wind speed, wind direction and solar radiation, and the second feature data includes temperature, humidity and air pressure. The input module is configured to input the weather category and the first feature data into a trained first neural network model to obtain the power generation capacity of the power system within a future preset time period. The input module is further configured to input the current weather category and the second feature data into the trained second neural network model to obtain the power supply load of the power system within the preset time period in the future; The prediction module is configured to predict the power generation and supply balance of the power system based on the power generation and supply load of the power system within a preset future time period.
9. A computer-readable storage medium, characterized in that, It includes program instructions that, when executed by a processor, cause the method according to any one of claims 1-7 to be implemented.
10. An electronic device, characterized in that, include: processor; as well as A memory storing computer instructions that, when executed by the processor, cause the electronic device to perform the method according to any one of claims 1-7.