End-to-end scheduling method and device of power system, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an end-to-end scheduling method and device of a power system, electronic equipment and a storage medium, a scheduling instruction can be obtained by inputting the first environment data and the current environment data into the pre-trained scheduling model, the conditions of relatively large information transmission loss and relatively large accumulative error can be avoided, and the scheduling efficiency of the power system is improved. And the dispatching effect of the power system can be improved.

Description

End-to-end dispatching methods, devices, electronic equipment and storage media for power systems Technical Field

[0001] This application relates to the field of computer technology, and in particular to an end-to-end scheduling method, apparatus, electronic device, and storage medium for a power system. Background Technology

[0002] The power system operating mode of source-grid-load-storage (SPES) is a new type of power system operation that uses digital technology to coordinate and optimize the four components of power generation, grid, load, and energy storage, thereby achieving dynamic balance between power supply and demand and efficient energy utilization. The power source can include renewable energy power supply equipment, such as wind power or solar power equipment.

[0003] Because renewable energy power supply is significantly intermittent and volatile, in order to balance the power output of the power system with the power demand of load equipment and avoid situations such as wasted or insufficient power output, it is necessary to predict the output power value of renewable energy power supply equipment, and then dispatch various parts of the power source, grid, load, and storage system based on the predicted output power value. However, this method suffers from drawbacks such as significant information transmission losses and large cumulative errors, resulting in poor dispatching performance of the power system.

[0004] Improving the dispatching efficiency of the power system has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides an end-to-end scheduling method, apparatus, electronic device, and storage medium for a power system, which can improve the scheduling effect of the power system.

[0006] In a first aspect, embodiments of this application provide an end-to-end scheduling method for a power system, the power system including new energy power supply equipment, the method comprising: acquiring first environmental data and current environmental data; the first environmental data being environmental data at a first moment, the current environmental data being environmental data at the current moment, the first moment being prior to the current moment, and the environmental data being data that can affect the output power value of the new energy power supply equipment; inputting the first environmental data and the current environmental data into a pre-trained scheduling model to obtain a scheduling instruction; and controlling the power system to execute the scheduling instruction.

[0007] Optionally, before acquiring the first environmental data and the current environmental data, the method further includes: acquiring first historical environmental data and second historical environmental data; determining the change of the second historical environmental data relative to the first historical environmental data; acquiring historical scheduling instructions that match the change; and training an initial scheduling model using the first historical environmental data, the second historical environmental data, and the historical scheduling instructions to obtain a trained scheduling model.

[0008] Optionally, obtaining the first historical environmental data and the second historical environmental data includes: obtaining the first historical environmental data and the second historical environmental data from the target database; obtaining the historical scheduling instructions that match the changes includes: filtering the historical scheduling instructions that match the changes from the target database.

[0009] Optionally, the historical dispatch instructions are obtained by inputting the first historical environmental data and the second historical environmental data into a preset power system dispatch simulation model for processing.

[0010] Optionally, the scheduling model is a hybrid neural network model.

[0011] Optionally, before controlling the power system to execute the scheduling instruction, the method further includes: inputting the first environmental data, the current environmental data, and the scheduling instruction into a large language model to determine whether the scheduling instruction needs to be modified, and modifying the scheduling instruction if modification is required; controlling the power system to execute the scheduling instruction includes: controlling the power system to execute the modified scheduling instruction if modification is required; and controlling the power system to execute the scheduling instruction if no modification is required.

[0012] Optionally, the new energy power supply equipment includes solar power supply equipment and / or wind power supply equipment.

[0013] Secondly, embodiments of this application provide an end-to-end dispatching device for a power system, the power system including new energy power supply equipment, the end-to-end dispatching device for the power system including: an acquisition module, used to acquire first environmental data and current environmental data; the first environmental data is environmental data at a first moment, the current environmental data is environmental data at the current moment, the first moment is before the current moment, and the environmental data is data that can affect the output power value of the new energy power supply equipment; an input module, used to input the first environmental data and the current environmental data into a pre-trained dispatching model to obtain dispatching instructions; and a control module, used to control the power system to execute the dispatching instructions.

[0014] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements any of the methods described in the first aspect.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any of the methods described in the first aspect.

[0016] This application provides an end-to-end scheduling method, apparatus, electronic device, and storage medium for a power system. By inputting first environmental data and current environmental data into a pre-trained scheduling model, scheduling instructions can be obtained, avoiding situations where information transmission loss is large and cumulative errors are large, thereby improving the scheduling effect of the power system. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 is a schematic flowchart of an end-to-end scheduling method for a power system provided in an embodiment of this application; Figure 2 is another schematic flowchart of an end-to-end scheduling method for a power system provided in an embodiment of this application; Figure 3 is a schematic structural diagram of an end-to-end scheduling device for a power system provided in an embodiment of this application; Figure 4 is a schematic structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] In this article, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The symbol " / " in this article indicates that the related objects are in an "or" relationship; for example, A / B means A or B.

[0020] The terms "first" and "second," etc., used in the specification and claims herein are used to distinguish different objects, not to describe a specific order of objects. For example, "first response message" and "second response message," etc., are used to distinguish different response messages, not to describe a specific order of response messages.

[0021] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0022] In the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more, for example, multiple processors means two or more processors, multiple elements means two or more elements, etc.

[0023] This application provides an end-to-end scheduling method, apparatus, electronic device, and storage medium for a power system, which can improve the scheduling effect of the power system.

[0024] As shown in Figure 1, this application embodiment provides an end-to-end scheduling method for a power system. This scheduling method can be executed by an electronic device, such as a smart interactive flat panel, laptop computer, desktop computer, mobile phone, tablet computer, or server, etc., and this application embodiment is not limited thereto. The scheduling method may specifically include the following steps: S11, acquiring first environmental data and current environmental data.

[0025] In this step, environmental data refers to data that can affect the output power value of the new energy power supply equipment. The first environmental data is the environmental data at the first moment, and the current environmental data is the environmental data at the current moment. The first moment is prior to the current moment. For example, if the current moment is 10:05, the first moment could be 10:03.

[0026] In practical applications, electronic devices can continuously acquire environmental data at preset time intervals (e.g., two minutes). For example, if the current time is 9:00, the first time interval could be 8:58. If the current time is 8:58, the first time interval could be 8:56. If the current time is 8:56, the first time interval could be 8:54.

[0027] The types of environmental data vary depending on the type of renewable energy power supply equipment. In one example, the renewable energy power supply equipment could be a wind power supply equipment, and the environmental data could include one or more of the following: satellite cloud images, monitoring images generated by sky imagers, detection data from weather radar, and wind speed data measured by anemometers.

[0028] In another example, the new energy power supply equipment can be solar power equipment, and the current environmental data can include one or more of the following: satellite cloud images, monitoring images generated by sky imagers, and detection data from weather radar.

[0029] In addition, new energy power supply equipment may include both solar power supply equipment and wind power supply equipment. Current environmental data may include one or more of the following: satellite cloud images, monitoring images generated by sky imagers, detection data from meteorological radar, and wind speed data measured by anemometers.

[0030] The sampling frequencies of the various environmental data mentioned above can be different, thus forming a complementary relationship in the time dimension.

[0031] S12, input the first environmental data and the current environmental data into the pre-trained scheduling model to obtain scheduling instructions.

[0032] S13, control the power system to execute the dispatching command.

[0033] In the above steps, the user can input the aforementioned first environmental data and current environmental data into a pre-trained scheduling model. This allows the pre-trained model to process the data and obtain scheduling instructions that match the current situation. Then, the electronic device can control the power system to execute these scheduling instructions, thereby balancing the power system's output power and power demand. This embodiment of the application utilizes a scheduling model that can directly obtain corresponding scheduling instructions based on the first environmental data and current environmental data. Therefore, it avoids significant information transmission losses and large accumulated errors, thereby improving the scheduling effect of the power system.

[0034] More specifically, compared to the existing technology that uses multiple modules (such as prediction and scheduling modules) to work together, the end-to-end scheduling method for power systems in this application embodiment directly converts the collected environmental data into scheduling instructions through a unified scheduling model, realizing full-process automation from environmental perception to decision execution. This avoids the problem of information loss when different modules transmit information, and also avoids the problem of upstream module errors being transmitted to downstream, resulting in large cumulative errors. Therefore, it can improve the scheduling effect of the power system.

[0035] To provide a clearer explanation of the embodiments of this application, specific examples are used below. In one example, the power system includes four parts: power source, power grid, load, and energy storage. The power source includes new energy power supply equipment, which includes wind power supply equipment and solar power supply equipment. Continuing with the previous example, the current time is 10:05, and the current environmental data is that the weather is cloudy and the wind speed is 4 m / s. The first time could be 10:03, and the first environmental data would be that the weather is sunny and the wind speed is 5 m / s. The environmental data here can include one or more of the following: satellite cloud images, monitoring images generated by sky imagers, detection data from weather radar, and wind speed data measured by an anemometer.

[0036] After inputting the current environmental data and the initial environmental data into a pre-trained scheduling model, the model outputs scheduling instructions to increase the output power of energy storage devices and reduce the power demand (i.e., rated power) of load devices. Thus, in the event of a decrease in the output power of solar power equipment (due to weather changes) or wind power equipment (due to decreased wind speed), executing the scheduling instructions can increase the output power of energy storage devices to compensate for the decrease in the output power of renewable energy equipment and reduce the power demand of load devices. This allows the power supply and demand of the power system to be balanced, avoiding situations such as wasted or insufficient output power, thereby achieving good scheduling results.

[0037] The above content describes the process of using a pre-trained scheduling model. Before using the scheduling model, it is necessary to train it first. The following content will introduce the training process of the scheduling model in detail.

[0038] In some embodiments of this application, as shown in FIG2, before step S11, the end-to-end scheduling method of the power system provided in the embodiments of this application may further include the following steps: S14, obtaining first historical environmental data and second historical environmental data.

[0039] In this step, the first historical environmental data and the second historical environmental data are environmental data from different historical moments. It can be understood that a historical moment is a moment prior to the current moment.

[0040] Specifically, the first and second historical environmental data can be environmental data from two adjacent moments preceding the current moment. In the first example, the first historical environmental data is the environmental data at 9:00 AM on October 5, 2024. Specifically, the first historical environmental data could be: sunny weather, wind speed 8 m / s. The second historical environmental data is the environmental data at 9:02 AM on October 5, 2024. Specifically, the second historical environmental data could be: cloudy weather, wind speed 8 m / s.

[0041] In the second example, the first historical environmental data is the environmental data at 9:30 AM on October 5, 2024. Specifically, the first historical environmental data could be environmental data under the condition of clear weather and a wind speed of 8 m / s. The second historical environmental data is the environmental data at 9:32 AM on October 5, 2024. Specifically, the second historical environmental data could be environmental data under the condition of clear weather and a wind speed of 12 m / s. The environmental data here can include one or more of the following: satellite cloud images, monitoring images generated by sky imagers, detection data from weather radar, and wind speed data measured by an anemometer.

[0042] S15, determine the changes in the second historical environmental data relative to the first historical environmental data.

[0043] In this step, continuing with the previous example, since the weather and wind speed corresponding to the first historical environmental data are different from those corresponding to the second historical environmental data, there must be differences between the first and second historical environmental data. Therefore, we can determine the changes in one or more of the following at 9:02 AM on October 5, 2024: satellite cloud imagery, monitoring images generated by the sky imager, detection data from weather radar, and wind speed data measured by an anemometer, relative to the time of 9:00 AM on October 5, 2024. Similarly, we can also determine the changes in one or more of the following at 9:32 AM on October 5, 2024: satellite cloud imagery, monitoring images generated by the sky imager, detection data from weather radar, and wind speed data measured by an anemometer, relative to the time of 9:30 AM on October 5, 2024.

[0044] S16, Obtain historical scheduling instructions that match the changes.

[0045] In this step, the historical scheduling instructions are those prior to the current moment. In this embodiment, a manual screening method can be used to select historical scheduling instructions that match the aforementioned changes, and these instructions can be input into the electronic device. Specifically, in the first example, the historical scheduling instructions could be to increase the output power of the energy storage device and / or decrease the power demand of the load device. In the second example, the historical scheduling instructions could be to decrease the output power of the energy storage device and / or increase the power demand of the load device.

[0046] In one specific implementation, when using existing prediction and scheduling methods to schedule the power system, a large amount of historical environmental data and scheduling instructions are generated. For example, during the 100-day period last year, existing technology can determine the predicted output power of new energy power supply equipment based on environmental data, and then calculate the corresponding scheduling instructions based on this predicted power value. All of this data can be stored in a designated database (i.e., the target database). In step S15, based on possible environmental change scenarios in reality, first historical environmental data and second historical environmental data can be selected from the target database.

[0047] Because historical dispatch instructions generated using existing technologies may not match changes in environmental data, step S16 requires filtering the historical dispatch instructions in the target database to exclude those that do not match environmental data changes and accurately select those that do match. Specifically, historical dispatch instructions that match environmental data changes are those that can achieve a balance between power system supply and demand, while those that cannot achieve a balance between power system supply and demand are those that do not.

[0048] In practical applications, the aforementioned first historical environmental data, second historical environmental data, and historical scheduling instructions can be preprocessed by segmentation, cleaning, transformation, enhancement, etc., to improve the accuracy of these data.

[0049] S17, using the first historical environment data, the second historical environment data, and the historical scheduling instructions, the initial scheduling model is trained to obtain a trained scheduling model.

[0050] In this step, the aforementioned first historical environment data, second historical environment data, and historical scheduling instructions can be used as training samples and input into the initial scheduling model for training until the model converges, thus obtaining a trained scheduling model. Specifically, scheduling model convergence refers to the state where, during the training process, after continuous adjustments to its parameters (such as weights and biases), the value of the loss function gradually decreases and tends to stabilize, while the model's performance indicators (specifically, the matching degree of scheduling instructions) no longer significantly improve. This is a key indicator that the scheduling model training has reached a stable and reliable state.

[0051] In the specific implementation of creating training samples, corresponding labels can be created for the first historical environment data, the second historical environment data, and the corresponding scheduling instructions. Then, the first historical environment data, the second historical environment data, and the corresponding scheduling instructions can be labeled accordingly so that the scheduling model can identify them.

[0052] The preceding description only exemplifies two scenarios of change for the first and second historical environmental data. In actual implementation, the quantity and types of the first and second historical environmental data should be sufficiently large to cover various environmental changes in reality, thereby adequately training the scheduling model and enabling it to converge.

[0053] In another implementation, the first and second historical environmental data can be input into a pre-defined power system dispatch simulation model for processing, thereby obtaining corresponding dispatch instructions. These instructions are then stored in a target database. The power system dispatch simulation model is a core tool for power system planning, design, operation, and control. By establishing an accurate mathematical model and using computer technology for simulation analysis, it evaluates system performance, predicts operating conditions, and optimizes operating strategies. Based on the first and second historical environmental data, matching dispatch instructions can be generated. When using this implementation method, the quantity and types of the first and second historical environmental data should be sufficiently large to cover various real-world environmental changes, facilitating thorough training of the dispatch model and ensuring its convergence.

[0054] Alternatively, environmental data for various scenarios can be generated manually and processed using a power system dispatch simulation model to obtain corresponding dispatch instructions. This data can then be used as training samples to train the dispatch model, enabling it to converge.

[0055] In one specific implementation, the scheduling model can be a hybrid neural network model. Specifically, a hybrid neural network model is a technique that improves model performance by fusing multiple neural network structures or mechanisms. The core idea is to achieve more efficient data processing and decision-making capabilities by combining the advantages of different models. In this embodiment, the environmental data may include image data. The image processing part of the scheduling model can use a convolutional neural network (CNN) structure, the time series processing part uses a long short-term memory (LSM) network structure, and data transfer within the scheduling model employs a transformer structure to achieve higher accuracy, lower cost, and stronger adaptability.

[0056] In some embodiments of this application, after step S13, the electronic device may further input the first environmental data, the current environmental data, and the scheduling instruction into the large language model to determine whether the scheduling instruction is reasonable, that is, whether the scheduling instruction matches the changes in the environmental data.

[0057] If the conditions are reasonable, no modification to the dispatch instructions is needed; the electronic equipment will continue to control the power system to execute the aforementioned dispatch instructions. If the conditions are unreasonable, the dispatch instructions will be modified to match changes in environmental data. The electronic equipment can then control the power system to execute the modified dispatch instructions, thereby further improving dispatch efficiency.

[0058] Furthermore, in some emergency scenarios, the predictability of environmental data for sudden events remains poor. For example, it is difficult to predict sudden wind gusts based on environmental data. As a result, when encountering emergencies, dispatch instructions obtained from environmental data using the aforementioned dispatch model may fail to achieve a balance between power supply and demand, leading to wasted or insufficient output power.

[0059] To avoid the aforementioned situations, the observation instructions from the field dispatcher can be quickly input into the large language model to rapidly generate corresponding dispatch instructions. In one example, when a sudden windstorm occurs, the dispatcher can input the observation instructions into the large language model to generate corresponding dispatch instructions, enabling the power system to respond quickly to the sudden windstorm and rapidly achieve a state of supply and demand balance, thus compensating for the shortcomings of the dispatch model.

[0060] As shown in Figure 3, this application embodiment provides an end-to-end dispatching device for a power system, comprising: a first acquisition module, used to acquire first environmental data and current environmental data; the first environmental data is environmental data at a first moment, the current environmental data is environmental data at the current moment, the first moment is prior to the current moment, and the environmental data is data that can affect the output power value of the new energy power supply equipment; an input module, used to input the first environmental data and the current environmental data into a pre-trained dispatching model to obtain dispatching instructions; and a control module, used to control the power system to execute the dispatching instructions.

[0061] Optionally, the end-to-end dispatching device of the power system further includes: a second acquisition module for acquiring first historical environmental data and second historical environmental data; a determination module for determining the change of the second historical environmental data relative to the first historical environmental data; a third acquisition module for acquiring historical dispatching instructions that match the change; and a training module for training an initial dispatching model using the first historical environmental data, the second historical environmental data, and the historical dispatching instructions to obtain a trained dispatching model.

[0062] Optionally, the second acquisition module is specifically used to acquire first historical environmental data and second historical environmental data from the target database; the third acquisition module is specifically used to filter historical scheduling instructions that match the changes from the target database.

[0063] Optionally, the historical dispatch instructions are obtained by inputting the first historical environmental data and the second historical environmental data into a preset power system dispatch simulation model for processing.

[0064] Optionally, the scheduling model is a hybrid neural network model.

[0065] Optionally, the end-to-end dispatching device of the power system further includes: a modification module, used to input the first environmental data, the current environmental data, and the dispatching instruction into a large language model to determine whether the dispatching instruction needs to be modified, and to modify the dispatching instruction if modification is required; the control module is specifically used to control the power system to execute the modified dispatching instruction if modification is required, and to control the power system to execute the dispatching instruction if no modification is required.

[0066] Optionally, the new energy power supply equipment includes solar power supply equipment and / or wind power supply equipment.

[0067] The end-to-end dispatching device for the power system provided in this application embodiment can execute the method executed by the electronic device in the above embodiment. Its implementation principle and technical effect are similar, and will not be repeated here.

[0068] As shown in Figure 4, this application embodiment also provides an electronic device, which includes a memory and a processor. The memory is used to store a computer program. When the computer program is executed by the processor, the scheduling method described above can be implemented. For details, please refer to the description of the foregoing embodiments.

[0069] Specifically, at the hardware level, the electronic device may include a processor, an internal bus, and memory. The memory may include main memory and non-volatile memory. The processor reads the corresponding computer program from the non-volatile memory into main memory and then runs it. Those skilled in the art will understand that the structure shown in Figure 4 is merely illustrative and does not limit the structure of the aforementioned electronic device. For example, the electronic device may include more or fewer components than shown in Figure 4, such as other processing hardware, like a GPU (Graphics Processing Unit), or external communication ports. Of course, besides software implementations, this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software.

[0070] In this embodiment, the processor may include a central processing unit (CPU) or a graphics processing unit (GPU), and may also include other microcontrollers, logic gates, integrated circuits, or appropriate combinations thereof with logic processing capabilities. The memory described in this embodiment can be a storage device for storing information. In digital systems, a device capable of storing binary data can be a memory; in integrated circuits, a circuit without physical form but with storage function can also be a memory, such as RAM or FIFO; in a system, a storage device with physical form can also be called a memory. In implementation, this memory can also be implemented using a cloud storage method; the specific implementation method is not limited in this specification.

[0071] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the end-to-end scheduling method for a power system as described above.

[0072] This application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the end-to-end scheduling method for a power system as described above.

[0073] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0074] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An end-to-end dispatching method for a power system, characterized in that, The power system includes new energy power supply equipment. The method includes: acquiring first environmental data and current environmental data; the first environmental data is environmental data at a first moment, the current environmental data is environmental data at the current moment, the first moment is before the current moment, and the environmental data is data that can affect the output power value of the new energy power supply equipment; inputting the first environmental data and the current environmental data into a pre-trained scheduling model to obtain scheduling instructions; and controlling the power system to execute the scheduling instructions.

2. The end-to-end dispatching method for a power system according to claim 1, characterized in that, Before acquiring the first environmental data and the current environmental data, the method further includes: acquiring first historical environmental data and second historical environmental data; determining the change of the second historical environmental data relative to the first historical environmental data; acquiring historical scheduling instructions that match the change; and training an initial scheduling model using the first historical environmental data, the second historical environmental data, and the historical scheduling instructions to obtain a trained scheduling model.

3. The end-to-end dispatching method for a power system according to claim 2, characterized in that, The step of obtaining the first historical environmental data and the second historical environmental data includes: obtaining the first historical environmental data and the second historical environmental data from the target database; the step of obtaining historical scheduling instructions that match the changes includes: filtering historical scheduling instructions that match the changes from the target database.

4. The end-to-end dispatching method for a power system according to claim 3, characterized in that, The historical dispatch instructions are obtained by inputting the first historical environmental data and the second historical environmental data into a preset power system dispatch simulation model for processing.

5. The end-to-end dispatching method for a power system according to claim 1, characterized in that, The scheduling model is a hybrid neural network model.

6. The end-to-end dispatching method for a power system according to claim 1, characterized in that, Before controlling the power system to execute the scheduling instruction, the method further includes: inputting the first environmental data, the current environmental data, and the scheduling instruction into a large language model to determine whether the scheduling instruction needs to be modified, and modifying the scheduling instruction if modification is required; controlling the power system to execute the scheduling instruction includes: controlling the power system to execute the modified scheduling instruction if modification is required; and controlling the power system to execute the scheduling instruction if no modification is required.

7. The end-to-end dispatching method for a power system according to claim 1, characterized in that, The new energy power supply equipment includes solar power supply equipment and / or wind power supply equipment.

8. An end-to-end dispatching device for a power system, characterized in that, The power system includes new energy power supply equipment. The end-to-end dispatching device of the power system includes: an acquisition module for acquiring first environmental data and current environmental data; the first environmental data is environmental data at a first moment, and the current environmental data is environmental data at the current moment, wherein the first moment is prior to the current moment, and the environmental data is data that can affect the output power value of the new energy power supply equipment; an input module for inputting the first environmental data and the current environmental data into a pre-trained dispatching model to obtain dispatching instructions; and a control module for controlling the power system to execute the dispatching instructions.

9. An electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it causes the electronic device to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images