Power dispatching method and system based on topology dispatching atlas

Abstract

The invention discloses a power dispatching method and system based on a topology dispatching graph, a storage medium and electronic equipment. The method comprises the following steps: acquiring meteorological data, historical load data and user behavior data; and inputting the meteorological data, the historical load data and the user behavior data into a convolutional neural network for feature extraction and feature fusion to obtain fusion features. Inputting the fusion features into a long-short-term memory network to obtain predicted future load data of the current moment in a period of time in the future; constructing a topological characteristic scheduling graph based on future load data, topological information of the power system and a historical scheduling decision; updating the topological feature scheduling atlas through an adversarial neural network; and decoupling the updated topological feature scheduling atlas to obtain a current scheduling decision. The efficiency of the scheduling strategy calculation process is improved, the topological structure of the power system is effectively fused, and the safety and adequacy of the power system are improved.

Description

Technical Field

[0001] The present application relates to the technical field of power system operation control, and particularly to a power dispatching method, system, storage medium and electronic device based on a topological scheduling map. Background Art

[0002] With the global emphasis on renewable energy, the power system is undergoing profound changes. The large-scale access of renewable energy such as wind energy and solar energy has brought new opportunities for power supply, while also triggering a series of challenges. The security and adequacy dispatching of the power system is an important link to ensure stable operation, meet the social electricity demand, and safeguard economic development and social stability. With the transformation of the energy structure and the large-scale access of renewable energy, the power source structure of the power system has changed significantly, and the intermittency and uncertainty of these energies pose new challenges to the stability and dispatching of the power system.

[0003] Under the background of power market reform, power system dispatching needs to be deeply integrated with market mechanisms, and market means are used to achieve the effective allocation and economic dispatching of power resources. This transformation not only means the transformation of the traditional dispatching mode, but also requires power market participants to play a greater role in aspects such as price formation and supply-demand balance. By establishing a reasonable market mechanism, electricity can be traded at the optimal price at different times and locations, thereby optimizing resource allocation, reducing waste, and improving economic efficiency. At the same time, with the rapid development of advanced technologies such as big data and artificial intelligence, the construction of an intelligent dispatching system has become an important way to improve the intelligent level of power system dispatching. This intelligent dispatching can not only optimize the production and consumption of electricity through real-time data analysis and prediction models, but also achieve more accurate load forecasting and generation dispatching, effectively coping with the fluctuations of power demand. In addition, intelligent dispatching can adapt to the development of new technologies and new business forms such as distributed new energy, new energy storage and virtual power plants, enabling the power system to maintain flexibility and adaptability in the face of a complex market environment, thereby ensuring the safe and stable operation of the power system.

[0004] The existing short-term dispatching technologies for power systems are mainly divided into two categories: model-driven and model-free. Model-driven methods (such as linear programming, nonlinear programming, and mixed integer programming) optimize dispatching by constructing accurate mathematical models, but their computational complexity is high and the time consumption is long, especially difficult to solve quickly in large-scale systems; at the same time, model simplification may lead to results deviating from actual needs, and it is necessary to rely on manual experience for repeated adjustment, with low efficiency. Model-free methods (such as support vector machines and artificial neural networks) directly learn dispatching strategies from data, although the calculation speed is fast, but face challenges such as high data quality requirements and insufficient generalization ability. Traditional machine learning methods (such as random forests and k-nearest neighbors) are effective in simple scenarios, but it is difficult to adapt to the changes in the complex structure of the power grid. Summary of the Invention

[0005] An embodiment of the present application provides a power dispatching method, system, storage medium and electronic device based on a topological scheduling map, which can adapt to the complex topological structure of the power grid and improve the security and adequacy of the power system.

[0006] An embodiment of the present application provides a power dispatching method based on a topological scheduling map, including: Obtain meteorological data, historical load data and user behavior data; Input the meteorological data, the historical load data and the user behavior data into a convolutional neural network for feature extraction and feature fusion to obtain fused features. And input the fused features into a long short-term memory network to obtain predicted future load data for a period of time directly in the future at the current moment; Construct a topological feature scheduling map based on the future load data, the topological information of the power system and historical scheduling decisions; Update the topological feature scheduling map through an adversarial neural network; Decouple the updated topological feature scheduling map to obtain the current scheduling decision.

[0007] As a further improvement of the present invention, in the above power dispatching method based on a topological scheduling map, wherein constructing an initial topological feature scheduling map based on the future load data, the topological information of the power system and historical scheduling decision information includes: Perform normalization processing on the future load data; Convert the normalized future load data into a prediction information layer; Construct two decision information layers based on historical scheduling decision information; Fuse the prediction information layer and the two decision information layers to obtain a scheduling decision image; Construct an initial topological information matrix based on the topological structure of the power system; Use the initial topological information matrix to perform convolution on the scheduling decision image to generate a topological feature scheduling map.

[0008] As a further improvement of the present invention, in the above power dispatching method based on a topological scheduling map, wherein converting the normalized future load data into a prediction information layer includes: Convert the normalized future load data into a matrix, and fill the vacant positions in the matrix with 0 to obtain a prediction information layer.

[0009] As a further improvement of the present invention, in the above power dispatching method based on a topological scheduling map, wherein the adversarial neural network includes a generator and a discriminator; Updating the topological feature scheduling map through the adversarial neural network includes: Randomly initialize the parameters of the generator and the discriminator; The generator receives random noise and the topological feature scheduling map, and generates an updated topological feature scheduling map; The discriminator receives real image data and the updated topological feature scheduling map; Calculate the loss function of the discriminator based on the real image data and the updated topological feature scheduling map, and update the parameters of the discriminator through backpropagation; Repeat the steps of generating the updated topological feature scheduling map, receiving the real image data and the updated topological feature scheduling map, and updating the parameters of the discriminator until an updated topological feature scheduling map that meets the preset requirements is generated.

[0010] As a further improvement of the present invention, in the above power scheduling method based on the topological scheduling map, decoupling the updated topological feature scheduling map to obtain the current scheduling decision includes: Perform deconvolution on the updated topological feature scheduling map and the initial topological information matrix to obtain a scheduling decision image; Decouple the scheduling decision image to obtain two decision information layers, and calculate the mean of the two decision information layers to obtain a decision information matrix; Decouple the decision information matrix to obtain the current scheduling decision.

[0011] As a further improvement of the present invention, in the above power scheduling method based on the topological scheduling map, before the step of inputting the meteorological data, the historical load data, and the user behavior data into the convolutional neural network for feature extraction and feature fusion, it includes: Analyze the distribution characteristics of the meteorological data, the historical load data, and the user behavior data, the pattern of missing data, and the correlation between the data, and use the interpolation method to fill in the missing values of the missing data.

[0012] As a further improvement of the present invention, in the above power scheduling method based on the topological scheduling map, it further includes: Collect the historical load data through a data collector, and collect the user behavior data through SCADA.

[0013] The embodiment of the present application also provides a power scheduling system based on the topological scheduling map, including: An acquisition module for acquiring meteorological data, historical load data, and user behavior data; A prediction module, configured to input the meteorological data, the historical load data, and the user behavior data into a convolutional neural network for feature extraction and feature fusion to obtain fused features, and input the fused features into a long short-term memory network to obtain predicted future load data for the current moment and a period of time in the future; A construction module, configured to construct a topological feature scheduling map based on the future load data, the topological information of the power system, and historical scheduling decisions; An update module, configured to update the topological feature scheduling map through an adversarial neural network; A decoupling module, configured to decouple the updated topological feature scheduling map to obtain the current scheduling decision.

[0014] An embodiment of the present application further provides a computer-readable storage medium, in which multiple instructions are stored, and the instructions are adapted to be loaded by a processor to execute any one of the above power scheduling methods based on a topological scheduling map.

[0015] An embodiment of the present application further provides an electronic device, including a processor and a memory, the processor is electrically connected to the memory, the memory is used to store instructions and data, and the processor is used for the steps in any one of the above power scheduling methods based on a topological scheduling map.

[0016] The power scheduling method, system, storage medium, and electronic device based on a topological scheduling map provided by the present application. The present application uses a device to collect meteorological data, historical load curves, user behavior data, etc., predicts the collected information using CNN-LSTM, constructs a topological feature scheduling map from the obtained prediction data, topological information, and scheduling information, uses a GAN neural network algorithm to generate a topological feature scheduling map by learning the information of the topological feature scheduling map, and decouples the generated topological feature scheduling map to obtain the scheduling information included in the topological feature scheduling map. The present application uses multiple neural networks to assist in prediction, improves the efficiency of the scheduling strategy calculation process, effectively integrates the topological structure of the power system, and improves the security and adequacy of the power system. Description of the Drawings

[0017] The following, by describing in detail the specific embodiments of the present application in conjunction with the drawings, will make the technical solutions and other beneficial effects of the present application obvious.

[0018] Figure 1 It is a flowchart of the power scheduling method based on a topological scheduling map provided by an embodiment of the present application.

[0019] Figure 2 It is a structural diagram of an LSTM provided by an embodiment of the present application.

[0020] Figure 3 Flow chart of generating a topological feature scheduling map provided for this application.

[0021] Figure 4 Structural diagram of the adversarial neural network provided for the embodiments of this application.

[0022] Figure 5 Flow chart of decoupling the topological feature scheduling map provided for the embodiments of this application.

[0023] Figure 6 Schematic structural diagram of a power scheduling system based on a topological scheduling map provided for the embodiments of this application.

[0024] Figure 7 Schematic structural diagram of an electronic device provided for the embodiments of this application. Detailed implementation manners

[0025] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of this application.

[0026] The embodiments of this application provide a power scheduling method, system, storage medium, and electronic device based on a topological scheduling map. A power scheduling system based on a topological scheduling map provided for the embodiments of this application can be integrated in an electronic device, and the electronic device can be a device such as a terminal or a server. Among them, the terminal can include a tablet computer, a notebook computer, a personal computer (PC), a microprocessing box, or other devices, etc.

[0027] Please refer to Figure 1 , Figure 1 which is a flow chart of a power scheduling method based on a topological scheduling map provided for the embodiments of this application. The method is applied to an electronic device. The power scheduling method based on a topological scheduling map includes the following steps: S1. Obtain meteorological data, historical load data, and user behavior data.

[0028] Specifically, meteorological data, including ambient temperature, air quality, humidity, etc., are obtained through weather information released by the Meteorological Bureau. Historical load data, including historical load curves, are collected through smart meters, data collectors and other equipment. The user behavior data is collected through the SCADA (Supervisory Control and Data Acquisition) system, for example, the user's power consumption pattern is recorded by smart meters and sensors, and the user behavior (such as factory production line operation habits, household appliance usage time) is inferred through the equipment start and stop frequency and power change curve. User behavior data includes peak power consumption time, duration (reflecting work and rest rules), sudden start and stop of equipment (possibly related to user operations), load fluctuation variance, average daily power consumption, etc.

[0029] S2, input the meteorological data, historical load data and user behavior data into the convolutional neural network for feature extraction and feature fusion to obtain fusion features. And input the fusion features into the long short-term memory network to obtain the predicted future load data from the current moment to a certain period of time in the future.

[0030] Specifically, the distribution characteristics of meteorological data, historical load data and user behavior data, the pattern of missing data and the correlation between data are first analyzed, and the missing data are filled by interpolation. Then, the meteorological data, historical load data and user behavior data are respectively input into the convolutional neural network (CNN) to extract features through the convolution layer to obtain meteorological data features, historical load data features and user behavior data features, and the meteorological data features, historical load data features and user behavior data features are multi-source feature fusion (for example, they can be weighted fusion through splicing or attention mechanism) to obtain fusion features.

[0031] Figure 2 The structure diagram of the LSTM provided in the embodiment of the present application is as follows: Figure 2 As shown in the figure, the fused features are input into the long short-term memory network (LSTM) to obtain the predicted future load data from the current moment to the future. The LSTM model time series analysis capability is used to deeply explore the patterns and trends in time series data. For example, the data of the past 24 hours can be used to predict the load data of the next 8 hours.

[0032] S3, constructs a topological characteristic dispatch map based on future load data, power system topology information and historical dispatch decisions.

[0033] Figure 3 The flowchart for generating the topological feature scheduling map provided in this application is as follows: Figure 3 As shown, step S3 includes the following steps: S31, normalizing the future load data.

[0034] S32. Convert the normalized future load data into a prediction information layer map.

[0035] Specifically, step S32 includes: Convert the normalized future load data into a matrix, and fill the vacant positions in the matrix with 0 to obtain the prediction information layer map.

[0036] S33. Construct two decision information layer maps based on the historical scheduling decision information.

[0037] S34. Fuse the prediction information layer map and the two decision information layer maps to obtain a scheduling decision image.

[0038] S35. Construct an initial topological information matrix based on the topological structure of the power system.

[0039] Specifically, the initial topological information matrix represents the connection structure of the power system. In the initial topological information matrix, 1 represents connection and 0 represents non-connection.

[0040] S36. Convolve the scheduling decision image with the initial topological information matrix to generate a topological feature scheduling map.

[0041] S4. Update the topological feature scheduling map through an adversarial neural network.

[0042] Figure 4 The structure diagram of the adversarial neural network provided by the embodiment of the present application is as Figure 4 shown. The adversarial neural network includes a generator and a discriminator.

[0043] In one embodiment, step S4 includes the following steps: S41. Randomly initialize the parameters of the generator and the discriminator; S42. The generator receives random noise and the topological feature scheduling map, and generates an updated topological feature scheduling map; S43. The discriminator receives real image data and the updated topological feature scheduling map; S44. Calculate the loss function of the discriminator based on the real image data and the updated topological feature scheduling map, and update the parameters of the discriminator through backpropagation; S45. Repeat the steps of generating the updated topological feature scheduling map, receiving the real image data and the updated topological feature scheduling map, and updating the parameters of the discriminator (i.e., steps S42 - S44) until an updated topological feature scheduling map that meets the preset requirements is generated.

[0044] For example, until the loss value is less than the preset loss threshold, or until the quality of the generated updated topological feature scheduling map reaches the preset clarity.

[0045] S5. Decouple the updated topological feature scheduling graph to obtain the current scheduling decision.

[0046] Figure 5 The flowchart of decoupling the topological feature scheduling graph provided by the embodiment of the present application is as Figure 5 shown. Step S5 includes the following steps: S51. Perform deconvolution on the updated topological feature scheduling graph and the initial topological information matrix to obtain a scheduling decision image; S52. Decouple the scheduling decision image to obtain two decision information layers, and calculate the mean of the two decision information layers to obtain a decision information matrix.

[0047] S53. Decouple the decision information matrix to obtain the current scheduling decision.

[0048] Specifically, the scheduling strategy can be a scheduling plan or a scheduling strategy curve, etc.

[0049] This application uses devices to collect meteorological data, historical load curves, user behavior data, etc., uses CNN-LSTM to predict the collected information, constructs the predicted data, topological information, and scheduling information into a topological feature scheduling graph, uses the GAN neural network algorithm to generate a topological feature scheduling graph by learning the information of the topological feature scheduling graph, decouples the generated topological feature scheduling graph, obtains the scheduling information included in the topological feature scheduling graph, and finally improves the security and adequacy of the power system.

[0050] According to the method described in the above embodiment, this embodiment will further describe from the perspective of a power scheduling system based on a topological scheduling graph. The power scheduling system based on a topological scheduling graph can be specifically implemented as an independent entity or integrated in an electronic device. The electronic device can be a terminal, a server, or other devices. Among them, the terminal can include a tablet computer, a laptop computer, a personal computer (PC), a microprocessing box, or other devices, etc.

[0051] Please refer to Figure 6 , Figure 6 which specifically describes the power scheduling system based on a topological scheduling graph provided by the embodiment of the present application, applied to an electronic device. The power scheduling system based on a topological scheduling graph may include: An acquisition module, configured to acquire meteorological data, historical load data, and user behavior data; A prediction module, configured to input the meteorological data, the historical load data, and the user behavior data into a convolutional neural network for feature extraction and feature fusion to obtain fused features, and input the fused features into a long short-term memory network to obtain predicted future load data for the current moment and a period of time in the future; A construction module, configured to construct a topological feature scheduling map based on the future load data, the topological information of the power system, and historical scheduling decisions; An update module, configured to update the topological feature scheduling map through an adversarial neural network; A decoupling module, configured to decouple the updated topological feature scheduling map to obtain the current scheduling decision.

[0052] In specific implementation, each of the above modules and / or units can be implemented as an independent entity, or can be combined arbitrarily to be implemented as the same or several entities. For the specific implementation of each of the above modules and / or units, reference can be made to the foregoing method embodiments. The specific beneficial effects that can be achieved can also be referred to the beneficial effects in the foregoing method embodiments, which will not be elaborated herein.

[0053] In addition, an embodiment of the present application further provides an electronic device, which may be a device such as a computer or a tablet computer. The electronic device can implement the steps in any of the embodiments of the power scheduling method based on a topological scheduling map provided by the embodiments of the present application. Therefore, the beneficial effects that can be achieved by any of the power scheduling methods based on a topological scheduling map provided by the embodiments of the present invention can be achieved. For details, reference can be made to the foregoing embodiments, which will not be elaborated herein.

[0054] Figure 7 The specific structural block diagram of the electronic device provided by the embodiment of the present invention is shown. The electronic device can be used to implement the power scheduling method based on a topological scheduling map provided in the foregoing embodiments. The electronic device 500 can be a device such as a terminal or a server. Among them, the terminal may include a tablet computer, a notebook computer, a personal computer (PC), a microprocessing box, or other devices, etc.

[0055] The RF circuit 510 is used to receive and transmit electromagnetic waves, realizing the mutual conversion between electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices. The RF circuit 510 may include various existing circuit elements for performing these functions, such as antennas, radio frequency transceivers, digital signal processors, encryption / decryption chips, subscriber identity module (SIM) cards, memories, and so on. The RF circuit 510 can communicate with various networks such as the Internet, enterprise intranets, wireless networks or communicate with other devices through a wireless network. The above-mentioned wireless networks may include cellular phone networks, wireless local area networks or metropolitan area networks. The above-mentioned wireless networks can use various communication standards, protocols and technologies, including but not limited to Global System for Mobile Communication (GSM), Enhanced Data GSM Environment (EDGE), Wideband Code Division Multiple Access (WCDMA), Code Division Access (CDMA), Time Division Multiple Access (TDMA), Wireless Fidelity (Wi-Fi) (such as Institute of Electrical and Electronics Engineers standards IEEE 802.11a, IEEE 802.11b, IEEE 802.11g and / or IEEE 802.11n), Voice over Internet Protocol (VoIP), Worldwide Interoperability for Microwave Access (Wi-Max), other protocols for email, instant messaging and short messages, and any other suitable communication protocols, and may even include those protocols that have not yet been developed currently.

[0056] The memory 520 can be used to store software programs and modules, such as the corresponding program instructions / modules in the above embodiments. The processor 580 executes various functional applications and data processing by running the software programs and modules stored in the memory 520, that is, realizes functions such as taking pictures with the front camera, processing the captured images, and switching the display colors of the display content on the display screen. The memory 520 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 520 may further include a memory remotely disposed relative to the processor 580, and these remote memories can be connected to the electronic device 500 through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0057] The input unit 530 can be used to receive input digital or character information, and generate a keyboard and a mouse related to user settings and function controls. The display unit 540 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces, and these graphical user interfaces can be composed of graphics, text, icons, videos, and any combination thereof. The display unit 540 may include a display panel 541. Optionally, the display panel 541 can be configured in the form of an LCD (Liquid Crystal Display) or an OLED (Organic Light-Emitting Diode).

[0058] The audio circuit 560, the speaker 561, and the microphone 562 can provide an audio interface between the user and the electronic device 500. The audio circuit 560 can transmit the electrical signal converted from the received audio data to the speaker 561, and the speaker 561 converts it into a sound signal for output; on the other hand, the microphone 562 converts the collected sound signal into an electrical signal, which is received by the audio circuit 560 and then converted into audio data. After the audio data is output to the processor 580 for processing, it is sent to another terminal, such as through the RF circuit 510, or the audio data is output to the memory 520 for further processing. The audio circuit 560 may also include an earphone jack to provide communication between the peripheral earphone and the electronic device 500.

[0059] The electronic device 500 can help the user receive requests, send information, etc. through the transmission module 570 (such as a Wi-Fi module), and it provides the user with wireless broadband Internet access. Although the transmission module 570 is shown in the figure, it can be understood that it does not belong to the essential components of the electronic device 500 and can be completely omitted within the scope of not changing the essence of the invention according to needs.

[0060] The processor 580 is the control center of the electronic device 500, connecting various parts of the entire mobile phone through various interfaces and circuits. By running or executing software programs and / or modules stored in the memory 520, and by invoking the data stored in the memory 520, it executes various functions of the electronic device 500 and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 580 may include one or more processing cores; in some embodiments, the processor 580 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor 580 either.

[0061] The electronic device 500 also includes a power supply 590 (such as a battery) for powering each component. In some embodiments, the power supply can be logically connected to the processor 580 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 590 may also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0062] Although not shown, the electronic device 500 also includes a camera (such as a front camera, a rear camera), a Bluetooth module, etc., which will not be elaborated here. Specifically, in this embodiment, the display unit of the electronic device is a touch screen display, and the mobile terminal also includes a memory, and one or more programs, where one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations: Obtain meteorological data, historical load data, and user behavior data; Input the meteorological data, the historical load data, and the user behavior data into a convolutional neural network for feature extraction and feature fusion to obtain fused features. And input the fused features into a long short-term memory network to obtain predicted future load data for the current moment and a period of time in the future; Construct a topological feature scheduling map based on the future load data, the topological information of the power system, and historical scheduling decisions; Update the topological feature scheduling map through an adversarial neural network; Decouple the updated topological feature scheduling map to obtain the current scheduling decision.

[0063] In specific implementation, each of the above modules can be implemented as an independent entity, or can be arbitrarily combined and implemented as the same or several entities. For the specific implementation of each of the above modules, reference can be made to the foregoing method embodiments, which will not be elaborated herein.

[0064] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling related hardware through instructions. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. For this purpose, an embodiment of the present invention provides a storage medium in which multiple instructions are stored, and these instructions can be loaded by a processor to execute the steps of any one of the embodiments of the power dispatching method based on a topological scheduling map provided by the embodiments of the present invention.

[0065] Among them, the computer-readable storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc.

[0066] Since the instructions stored in this storage medium can execute the steps in any one of the embodiments of the power dispatching method based on a topological scheduling map provided by the embodiments of the present invention, the beneficial effects achievable by any of the power dispatching methods based on a topological scheduling map provided by the embodiments of the present invention can be realized. For details, refer to the foregoing embodiments, which will not be elaborated herein.

[0067] The above has introduced in detail a power dispatching method, system, storage medium and electronic device based on a topological scheduling map provided by the embodiments of the present application. Specific examples are used herein to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A power dispatching method based on a topological scheduling map, characterized in that The method includes: Obtaining meteorological data, historical load data, and user behavior data; Inputting the meteorological data, the historical load data, and the user behavior data into a convolutional neural network for feature extraction and feature fusion to obtain fused features, and inputting the fused features into a long short-term memory network to obtain predicted future load data for a period of time from the current moment to the future; Constructing a topological feature scheduling map based on the future load data, the topological information of the power system, and historical scheduling decisions; Updating the topological feature scheduling map through an adversarial neural network; Decoupling the updated topological feature scheduling map to obtain the current scheduling decision.

2. The power dispatching method based on a topological scheduling map according to claim 1, wherein The constructing an initial topological feature scheduling map based on the future load data, the topological information of the power system, and historical scheduling decision information includes: Performing normalization processing on the future load data; Converting the normalized future load data into a prediction information layer; Constructing two decision information layers based on historical scheduling decision information; Fusing the prediction information layer and the two decision information layers to obtain a scheduling decision image; Constructing an initial topological information matrix based on the topological structure of the power system; Convolving the scheduling decision image with the initial topological information matrix to generate a topological feature scheduling map.

3. The power dispatching method based on a topological scheduling map according to claim 2, characterized in that, The converting the normalized future load data into a prediction information layer includes: Converting the normalized future load data into a matrix, filling the vacant positions in the matrix with 0 to obtain a prediction information layer.

4. The power dispatching method based on a topological scheduling map according to claim 1, wherein The adversarial neural network includes a generator and a discriminator; The updating the topological feature scheduling map through an adversarial neural network includes: Randomly initializing the parameters of the generator and the discriminator; The generator receives random noise and the topological feature scheduling map and generates an updated topological feature scheduling map; The discriminator receives real image data and the updated topological feature scheduling map; Calculating the loss function of the discriminator based on the real image data and the updated topological feature scheduling map, and updating the parameters of the discriminator through backpropagation; Repeating the steps of generating the updated topological feature scheduling map, receiving the real image data and the updated topological feature scheduling map, and updating the parameters of the discriminator until an updated topological feature scheduling map that meets the preset requirements is generated.

5. The power dispatching method based on a topological scheduling map according to claim 2, wherein The decoupling the updated topological feature scheduling map to obtain the current scheduling decision includes: Performing deconvolution on the updated topological feature scheduling map and the initial topological information matrix to obtain a scheduling decision image; Decoupling the scheduling decision image to obtain two decision information layers, and taking the mean of the two decision information layers to obtain a decision information matrix; Decoupling the decision information matrix to obtain the current scheduling decision.

6. The power dispatching method based on a topological scheduling map according to claim 1, wherein Before the step of inputting the meteorological data, the historical load data, and the user behavior data into a convolutional neural network for feature extraction and feature fusion, it includes: Analyze the distribution characteristics of the meteorological data, the historical load data, and the user behavior data, the pattern of missing data, and the correlation between the data, and use the interpolation method to fill in the missing values of the missing data.

7. The power dispatch method based on a topological scheduling map according to claim 1, characterized in that It further includes: Collect the historical load data through a data collector, and collect the user behavior data through SCADA.

8. A power dispatching system based on a topological scheduling graph, characterized in that, It includes: An acquisition module for acquiring meteorological data, historical load data, and user behavior data; A prediction module for inputting the meteorological data, the historical load data, and the user behavior data into a convolutional neural network for feature extraction and feature fusion to obtain fused features. And input the fused features into a long short-term memory network to obtain the predicted future load data for the current moment and a period of time in the future; A construction module for constructing a topological feature scheduling map based on the future load data, the topological information of the power system, and the historical scheduling decisions; An update module for updating the topological feature scheduling map through an adversarial neural network; A decoupling module for decoupling the updated topological feature scheduling map to obtain the current scheduling decision.

9. A computer-readable storage medium, characterized in that, Multiple instructions are stored in the computer-readable storage medium, and the instructions are adapted to be loaded by a processor to execute the power scheduling method based on a topological scheduling map according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes a processor and a memory, the processor is electrically connected to the memory, the memory is used to store instructions and data, and the processor is used to execute the steps in the power scheduling method based on a topological scheduling map according to any one of claims 1 to 7.

Images