Intelligent energy management method, device and equipment and storage medium

Abstract

The invention provides an intelligent energy management method and device, equipment and a storage medium, and the method comprises the steps: collecting historical energy use data through employing a multi-source obtaining mode, carrying out the preprocessing of the historical energy use data, and obtaining a standard data set; a regional change space-time diagram of energy use is constructed, nodes in the regional change space-time diagram represent sub-regions, node features comprise standard data set features and edge representation of an energy transmission relationship between the sub-regions, and a space-time diagram neural network is used to output an energy consumption mode and an energy output prediction amount of each sub-region; acquiring historical energy demand quantity and environmental data as external data, acquiring an energy-related feedback information text through a crawler, inputting the external data and the energy-related feedback information text into the multi-modal time sequence model, and outputting energy demand prediction quantity; and calculating a difference value between the energy output predicted quantity and the energy demand predicted quantity of each sub-region as a governance adjustment quantity, and formulating an energy transmission mode between the sub-regions based on the governance adjustment quantity.

Description

Technical Field

[0001] The present invention relates to the technical field of big data governance, and particularly to an energy intelligent governance method, device, equipment and storage medium. Background Art

[0002] Energy intelligent governance refers to the use of advanced intelligent control technologies to efficiently manage and optimize the production, transmission, distribution and consumption of energy, with the goal of improving the efficiency and reliability of the energy system.

[0003] In related technologies, current energy intelligent prediction mainly relies on statistical methods and machine learning algorithms to output energy production prediction amounts or energy demand prediction amounts. Although statistical methods such as time series models and regression analysis can capture the basic trends and seasonal variations of energy changes, they are unable to handle complex non-linear energy predictions; and existing machine learning algorithms, especially for energy demand prediction tasks, do not consider the influence of subjective dynamic factors such as feedback information, which affects the data processing and analysis capabilities of the model. For example, discussions on social media can reflect the public's attitudes towards related issues such as energy prices, supply stability and environmental protection issues, thereby affecting their energy usage behaviors; in addition, there is no technical means in the field that integrates a wide range of data sources, an efficient and standard data processing and integration process, and an intelligent prediction and governance solution, and continuous improvement and optimization are required.

[0004] Based on the analysis of the development status of this technical field above, the existing technologies lack a solution for intelligent prediction of energy management jointly based on energy production prediction amounts and energy demand prediction amounts, and considering the feedback information characteristics in energy demand prediction. Summary of the Invention

[0005] The purpose of the present invention is to provide an energy intelligent governance method, device, equipment and storage medium, aiming to solve the above problems in the existing technologies.

[0006] According to the first aspect of the embodiment of the present invention, an energy intelligent governance method is provided, including: Collect historical energy usage data by using a multi-source acquisition method, and preprocess the historical energy usage data to obtain a standard data set; Construct a spatio-temporal graph of regional changes in energy usage, where the nodes in the spatio-temporal graph of regional changes represent sub-regions, the node features include the features in the standard data set, the edges represent the energy transmission relationships between sub-regions, and use a spatio-temporal graph neural network to output the energy consumption patterns and energy production prediction amounts of each sub-region; Obtain historical energy demand amounts and environmental data as external data, obtain energy-related feedback information texts through web crawling, and input the external data and energy-related feedback information texts into a multi-modal time series model to output energy demand prediction amounts; Calculate the difference between the predicted energy output and the predicted energy demand for each sub-region as the governance adjustment amount, and formulate the energy transmission method between sub-regions based on the governance adjustment amount.

[0007] According to the second aspect of the embodiments of the present invention, there is provided an energy intelligent governance device, including: An acquisition and preprocessing module, configured to acquire historical energy usage data by means of multi-source acquisition, and preprocess the historical energy usage data to obtain a standard data set; An energy usage prediction module, configured to construct a spatio-temporal graph of regional changes in energy usage. Among them, the nodes in the spatio-temporal graph of regional changes represent sub-regions, the node features include the features in the standard data set, the edges represent the energy transmission relationship between sub-regions, and a spatio-temporal graph neural network is used to output the energy consumption patterns and predicted energy output of each sub-region; An energy demand prediction module, configured to obtain historical energy demand and environmental data as external data, obtain energy-related feedback information text through web crawling, and input the external data and the energy-related feedback information text into a multi-modal time series model to output the predicted energy demand; A governance adjustment module, configured to calculate the difference between the predicted energy output and the predicted energy demand for each sub-region as the governance adjustment amount, and formulate the energy transmission method between sub-regions based on the governance adjustment amount.

[0008] According to the third aspect of the embodiments of the present invention, there is provided an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the steps of the energy intelligent governance method provided in the first aspect of the present disclosure are implemented.

[0009] According to the fourth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, on which an implementation program for information transmission is stored. When the program is executed by the processor, the steps of the energy intelligent governance method provided in the first aspect of the present disclosure are implemented.

[0010] The technical solutions provided by the embodiments of the present invention have the following beneficial effects: The intelligent governance solution is determined from two prediction aspects of energy demand and energy output at the same time, avoiding decision-making biases caused by one-sided reliance on a single factor; When predicting demand, energy-related feedback information text that can reflect the public's emotions and discussions on energy prices, supply stability, and environmental protection issues is considered to fully consider the impact of driving-side change factors on demand and improve prediction accuracy.

[0011] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Description of the Drawings

[0012] To more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0013] Figure 1 is a flowchart of the energy intelligent governance method according to an embodiment of the present invention; Figure 2 is a schematic diagram of the energy intelligent governance device according to an embodiment of the present invention; Figure 3 is a schematic diagram of the electronic device according to an embodiment of the present invention. Detailed implementation manners

[0014] In order to enable those skilled in the art of this technology to better understand the technical solutions in one or more embodiments of this specification, the following will clearly and completely describe the technical solutions in one or more embodiments of this specification in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this document.

[0015] Method embodiments According to an embodiment of the present invention, an energy intelligent governance method is provided. Figure 1 is a flowchart of the energy intelligent governance method according to an embodiment of the present invention. As Figure 1 shown, the energy intelligent governance method according to an embodiment of the present invention specifically includes: In step S110, historical energy usage data is collected by a multi-source acquisition method, and the historical energy usage data is preprocessed to obtain a standard data set, which specifically includes: With the rapid growth and diversification of energy data, the sources of energy data are relatively extensive. Therefore, historical energy usage data is collected from energy equipment, sensor equipment, and smart meters. The historical energy usage data is in a format that has been converted after reception. The historical energy usage data refers to the indicators related to energy usage in a real environment. The specific indicators are not limited in the embodiments of the present invention and include various energy usage amounts, transportation amounts, etc.; The historical energy usage data is cleaned, de-duplicated, and missing values are filled to obtain a standard data set; Preferably, to improve the security performance during model training, the standard dataset is divided into multiple sub-datasets and assigned to multiple participants. Each participant holds a part of the data, and the MPC protocol is used for joint training to ensure that the data is not leaked during the calculation process; or the standard dataset is encrypted using symmetric encryption or asymmetric encryption, and the dataset exists in an encrypted form during storage and transmission. When training subsequently, the key is used to decrypt the data, and the decrypted data only exists in the memory and is not written to the disk.

[0016] In step S120, a spatio-temporal graph of regional changes in energy use is constructed. Among them, the nodes in the spatio-temporal graph of regional changes represent sub-regions, the node features include the features in the standard dataset, and the edges represent the energy transmission relationships between sub-regions. The spatio-temporal graph neural network is used to output the energy consumption patterns and energy output predictions of each sub-region, specifically including: A spatio-temporal graph of regional changes is constructed by introducing a time dimension on the basis of the standard dataset; A spatio-temporal graph neural network including a graph convolutional module GCN and a temporal convolutional module TCN is obtained; The graph convolutional module is used to extract the spatial features in the spatio-temporal graph of regional changes to capture the mutual influence between sub-regions, and the temporal convolutional module is used to extract the temporal features in the spatio-temporal graph of regional changes to capture the temporal evolution law of energy consumption. Among them, the temporal features include periodic laws and seasonal laws, and the spatial features and temporal features are fused to obtain a unified spatio-temporal representation; The energy consumption patterns and energy output predictions of each sub-region are predicted according to the unified spatio-temporal representation; In the embodiments of the present invention, the energy consumption patterns can be divided into industrial, commercial and residential according to industry classification; and can be divided into electricity, fossil fuels and renewable energy according to type.

[0017] In step S130, historical energy demand and environmental data are obtained as external data, and energy-related feedback information text is obtained through web crawling. The external data and the energy-related feedback information text are input into the multi-modal time series model to output the energy demand prediction, specifically including: Meteorological data and economic data are obtained as environmental data; Compared with the energy output prediction, the energy demand prediction needs to pay more attention to the influence of feedback information. Social media feedback information can reflect the public's acceptance of energy regulation. Strong opposition to a certain plan on social media may lead to the postponement or modification of policies, thus affecting energy demand; The content related to energy prices, supply stability and environmental protection issues in the local social forum of the region is extracted through web crawling, the topic model algorithm is used to extract the hot events in the content, and the sentiment classification model is used to identify the emotions reflected in the hot events. The hot events and the corresponding emotions are jointly used as the energy-related feedback information text.

[0018] Obtain a multi-modal time series model including an LSTM module and a Transformer module; Use the LSTM module to extract the first feature corresponding to the external data, use the Transformer module to extract the second feature corresponding to the text of the energy-related feedback information, establish cross-attention between the first feature and the second feature, and calculate the cross-attention using Equation 1: Equation 1; Where, represents the cross-attention, represents the activation function, represents the first feature, represents the transpose of the second feature, represents the feature dimension; the core goal of cross-attention is not to directly adjust the weights of different features, but to explore the interaction relationships between different features; Fuse the first feature, the second feature, and the cross-attention to obtain a unified multi-modal representation, and based on the unified multi-modal representation, predict the energy demand prediction values of each sub-region through the output layer.

[0019] It should be noted that in the embodiment of the present invention, the extraction in step S120 uses the TGN network, while the LSTM network is used to extract the demand features in step S130 because the regional change spatio-temporal graph has a graph structure, and TGN can capture the complex relationship patterns between nodes and allow customized information transmission between nodes; while LSTM is more suitable for ordinary time series prediction.

[0020] In step S140, calculate the difference between the energy output prediction value and the energy demand prediction value of each sub-region as the governance adjustment amount, and formulate the energy transmission method between sub-regions based on the governance adjustment amount, specifically including: Calculating the difference between the energy output prediction value and the energy demand prediction value can grasp the energy gap situation; Maintain the sub-regions with the difference greater than or equal to zero and sort them in descending order of the difference to obtain a positive list, and maintain the sub-regions with the difference less than zero and sort them in descending order of the absolute value of the difference to obtain a negative list; the higher the position in the positive list, the more energy is surplus at the end of the prediction period, and the higher the position in the negative list, the greater the energy gap at the end of the prediction period; Obtain a pre-defined energy transmission rule table, where the energy transmission rule table represents the definitions of which sub-regions can transmit with other sub-regions, because in actual applications, energy transmission is not possible between every two sub-regions, or the types of transmission are restricted; Traverse the sub-regions in the negative list in sequence, and use the sub-region that is ranked first in the positive list and is allowed to transmit energy to this location in the energy transmission rule table as the scheduling point. Adjust the positive list and the negative list in real time. After one traversal, the energy transmission method is obtained; Suppose the negative list is F1 and F2 in sequence; the positive list is Z1, Z2, and Z3 in sequence. First, an energy transmission regulation method needs to be formulated for F1 with the most verified gap. In the energy transmission rule table, it is allowed to transmit between F1 and Z2 and Z3. Therefore, originally, Z1 with the largest surplus should transmit energy to F1, but since the set rule does not allow it, start from Z2 until F1 is adjusted to positive or one traversal ends; Regardless of whether F1 becomes positive, F2 will still be the next to be adjusted because the intelligent governance is based on the predicted value rather than the current value, and not all sub-regions will necessarily have a supply surplus in the end. The energy transmission method does not necessarily need to be executed immediately and can be gradually achieved within the prediction period. The method further includes: In step S150, visualize the energy transmission method on the regional map, and monitor the energy usage of each sub-region and the energy transmission between sub-regions in real time. Specifically, it includes: Visualize and display through creating an interactive dashboard or simulation software. The key lies in displaying key energy indicators and providing an early warning function to send an alarm when a certain sub-region exceeds the set threshold.

[0021] To sum up, in response to the existing problems, the energy intelligent governance method of the present invention determines the intelligent governance solution from two prediction aspects of energy demand and energy output at the same time, avoiding decision-making biases caused by one-sided reliance on a single factor; when predicting demand, it considers the energy-related feedback information text that can reflect the public's emotions and discussions related to energy prices, supply stability, and environmental protection issues to fully consider the impact of driving-side change factors on demand and improve prediction accuracy; when predicting energy demand, it considers the cross-attention between the first feature corresponding to external data and the second feature corresponding to the feedback information text, combines and learns the complex relationships between features across different fields, which helps to reveal potential causal relationships; in the process of formulating the energy transmission method, one round of adjustment can quickly maintain the supply-demand balance to the greatest extent, improving the calculation efficiency of intelligent governance; the overall solution comprehensively collects data, processes it efficiently, analyzes it accurately, and makes intelligent decisions.

[0022] Device Embodiment According to an embodiment of the present invention, an energy intelligent governance device is provided. Figure 2 It is a schematic diagram of the energy intelligent governance device of the embodiment of the present invention, as Figure 2 shown. The device according to the embodiment of the present invention specifically includes: The acquisition and preprocessing module 20 is used to collect historical energy usage data through a multi-source acquisition method, preprocess the historical energy usage data to obtain a standard data set, and is specifically used for: Collect historical energy usage data from energy devices, sensor devices, and smart meters; Clean, deduplicate, and fill in missing values for the historical energy usage data to obtain a standard data set.

[0023] The energy usage prediction module 22 is used to construct a spatio-temporal graph of regional changes in energy usage. Among them, the nodes in the spatio-temporal graph of regional changes represent sub-regions, the node features include the features in the standard data set, and the edges represent the energy transmission relationships between sub-regions. Use a spatio-temporal graph neural network to output the energy consumption patterns and energy output prediction amounts of each sub-region, and is specifically used for: Obtain a spatio-temporal graph neural network including a graph convolution module and a temporal convolution module; Use the graph convolution module to extract the spatial features in the spatio-temporal graph of regional changes, and use the temporal convolution module to extract the temporal features in the spatio-temporal graph of regional changes. Among them, the temporal features include periodic laws and seasonal laws, and fuse the spatial features and temporal features to obtain a unified spatio-temporal representation; Predict the energy consumption patterns and energy output prediction amounts of each sub-region according to the unified spatio-temporal representation.

[0024] The energy demand prediction module 24 is used to obtain historical energy demand and environmental data as external data, obtain energy-related feedback information text through web crawling, and input the external data and energy-related feedback information text into a multi-modal time series model to output the energy demand prediction amount, and is specifically used for: Obtain meteorological data and economic data as environmental data; Extract the content related to energy prices, supply stability, and environmental protection issues in the regional local social forum through web crawling, use the topic model algorithm to extract the hot events in the content, and use the sentiment classification model to identify the emotions reflected in the hot events. Take the hot events and the corresponding emotions together as the energy-related feedback information text.

[0025] Obtain a multi-modal time series model including an LSTM module and a Transformer module; Use the LSTM module to extract the first features corresponding to the external data, use the Transformer module to extract the second features corresponding to the energy-related feedback information text, and establish cross-attention between the first features and the second features; Fuse the first features, second features, and cross-attention to obtain a unified multi-modal representation, and predict the energy demand prediction amounts of each sub-region according to the unified multi-modal representation.

[0026] The governance adjustment module 26 is used to calculate the difference between the predicted energy output and the predicted energy demand of each sub-region as the governance adjustment amount, and formulate the energy transmission method between sub-regions based on the governance adjustment amount. Specifically, it is used for: Maintain the sub-regions with the difference greater than or equal to zero and sort them in descending order of the difference to obtain a positive list. Maintain the sub-regions with the difference less than zero and sort them in descending order of the absolute value of the difference to obtain a negative list; Obtain a pre-defined energy transmission rule table, where the energy transmission rule table represents the definitions of the energy transmission capabilities of each sub-region with other sub-regions; Traverse the sub-regions in the negative list in sequence. Use the sub-region with the highest ranking in the positive list and allowed to transmit to this place in the energy transmission rule table as the scheduling point, and adjust the positive list and the negative list in real time. After one traversal, the energy transmission method is obtained.

[0027] The device further includes: The visualization monitoring module 28 is used to visualize the energy transmission method in the regional map and monitor the energy usage of each sub-region and the energy transmission between sub-regions in real time.

[0028] In summary, in view of the existing problems, the energy intelligent governance device of the present invention determines the intelligent governance solution from two prediction aspects of energy demand and energy output at the same time, avoiding decision-making biases caused by one-sided reliance on a single factor; when predicting demand, it considers the energy-related feedback information text that can reflect the public's emotions and discussions on energy prices, supply stability, and environmental protection issues, so as to fully consider the impact of driving-side change factors on demand and improve prediction accuracy; when predicting energy demand, it considers the cross-attention between the first feature corresponding to the external data and the second feature corresponding to the feedback information text, and combines and learns the complex relationships between features across domains, which helps to reveal potential causal relationships; in the process of formulating the energy transmission method, one-round adjustment can quickly maintain the supply-demand balance to the greatest extent, improving the calculation efficiency of intelligent governance; the overall solution comprehensively collects data, processes it efficiently, analyzes it accurately, and makes intelligent decisions.

[0029] Embodiment of electronic device Figure 3 It is a schematic diagram of the electronic device of the embodiment of the present invention. The electronic device 300 may include at least one processor 310 and a memory 320. The processor 310 may execute instructions stored in the memory 320. The processor 310 is communicatively connected to the memory 320 through a data bus. In addition to the memory 320, the processor 310 may also be communicatively connected to an input device 330, an output device 340, and a communication device 350 through the data bus.

[0030] The processor 310 can be any conventional processor, such as a commercially available CPU. The processor may also include, for example, a Graphic Process Unit (GPU), a Field Programmable Gate Array (FPGA), a System on Chip (SOC), an Application Specific Integrated Circuit (ASIC), or a combination thereof.

[0031] The memory 320 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk.

[0032] In the embodiments of the present disclosure, executable instructions are stored in the memory 320. The processor 310 can read the executable instructions from the memory 320 and execute the instructions to implement all or part of the steps of the energy intelligent governance method in any of the above exemplary embodiments.

[0033] Embodiments of the computer-readable storage medium In addition to the above methods and apparatuses, the exemplary embodiments of the present disclosure may also be a computer program product or a computer-readable storage medium storing the computer program product. The computer product includes computer program instructions that can be executed by a processor to implement all or part of the steps described in the energy intelligent governance method in any of the above exemplary embodiments.

[0034] The computer program product can be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present application. The programming languages include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as the "C" language or similar programming languages, as well as scripting languages (e.g., Python). The programming code can be executed entirely on the user's computing device, partially on the user's device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0035] A computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the readable storage medium include: a static random access memory (SRAM) with one or more electrically connected wires, an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk, or any suitable combination of the above.

[0036] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An energy intelligent governance method, characterized in that, Including: Collect historical energy usage data through a multi-source acquisition method, preprocess the historical energy usage data to obtain a standard data set; Construct a spatio-temporal map of regional changes in energy usage, where nodes in the spatio-temporal map of regional changes represent sub-regions, node features include features in the standard data set, edges represent energy transmission relationships between sub-regions, and use a spatio-temporal graph neural network to output the energy consumption patterns and energy output predictions of each sub-region; Obtain historical energy demand and environmental data as external data, obtain energy-related feedback information text through web crawling, and input the external data and the energy-related feedback information text into a multi-modal time series model to output an energy demand prediction; Calculate the difference between the energy output prediction and the energy demand prediction of each sub-region as a governance adjustment amount, and formulate an energy transmission method between sub-regions based on the governance adjustment amount.

2. The method according to claim 1, characterized in that, The method further includes: Visualize the energy transmission method in a regional map and monitor the energy usage of each sub-region and the energy transmission between sub-regions in real time.

3. The method according to claim 1, characterized in that, The specific steps of collecting historical energy usage data through a multi-source acquisition method and preprocessing the historical energy usage data to obtain a standard data set include: Collect historical energy usage data from energy devices, sensor devices, and smart meters; Clean, deduplicate, and fill in missing values for the historical energy usage data to obtain a standard data set.

4. The method according to claim 1, wherein The specific steps of using a spatio-temporal graph neural network to output the energy consumption patterns and energy output predictions of each sub-region include: Obtain a spatio-temporal graph neural network including a graph convolutional module and a time series convolutional module; Use the graph convolutional module to extract spatial features in the spatio-temporal map of regional changes, use the time series convolutional module to extract time features in the spatio-temporal map of regional changes, where the time features include periodic patterns and seasonal patterns, and fuse the spatial features and time features to obtain a unified spatio-temporal representation; Predict the energy consumption patterns and energy output predictions of each sub-region according to the unified spatio-temporal representation.

5. The method according to claim 1, wherein The specific steps of obtaining historical energy demand and environmental data as external data and obtaining energy-related feedback information text through web crawling include: Obtain meteorological data and economic data as the environmental data; Extract content related to energy prices, supply stability, and environmental protection issues in the local social forum of the region through web crawling, use the topic model algorithm to extract hot events in the content, use the sentiment classification model to identify the emotions reflected in the hot events, and use the hot events and the corresponding emotions together as the energy-related feedback information text.

6. The method according to claim 1, wherein The specific steps of inputting the external data and the energy-related feedback information text into a multi-modal time series model to output an energy demand prediction include: Obtain a multi-modal time series model including an LSTM module and a Transformer module; Use the LSTM module to extract the first feature corresponding to the external data, use the Transformer module to extract the second feature corresponding to the energy-related feedback information text, and establish cross-attention between the first feature and the second feature; Fuse the first feature, the second feature, and the cross-attention to obtain a unified multi-modal representation, and predict the predicted energy demand of each sub-region according to the unified multi-modal representation.

7. The method according to claim 1, characterized in that The formulation of the energy transmission method between sub-regions based on the governance adjustment amount specifically includes: Maintain the sub-regions with the difference greater than or equal to zero and sort them in descending order of the difference to obtain a positive list, maintain the sub-regions with the difference less than zero and sort them in descending order of the absolute value of the difference to obtain a negative list; Obtain a pre-defined energy transmission rule table, where the energy transmission rule table represents the definitions of the energy transmission between each sub-region and other sub-regions; Traverse the sub-regions in the negative list in sequence, use the sub-region that is the first in the positive list and is allowed to transmit to this place in the energy transmission rule table as the scheduling point, and adjust the positive list and the negative list in real time. After one traversal, obtain the energy transmission method.

8. An energy intelligent governance device, characterized in that, It includes: A data acquisition and preprocessing module, which is used to collect historical energy usage data by using a multi-source acquisition method, and preprocess the historical energy usage data to obtain a standard data set; An energy usage prediction module, which is used to construct a spatio-temporal graph of regional changes in energy usage. Among them, the nodes in the spatio-temporal graph of regional changes represent sub-regions, the node features include the features in the standard data set, the edges represent the energy transmission relationship between sub-regions, and use a spatio-temporal graph neural network to output the energy consumption patterns and predicted energy output of each sub-region; An energy demand prediction module, which is used to obtain historical energy demand and environmental data as external data, obtain energy-related feedback information text through web crawling, and input the external data and the energy-related feedback information text into a multi-modal time series model to output the predicted energy demand; A governance adjustment module, which is used to calculate the difference between the predicted energy output and the predicted energy demand of each sub-region as the governance adjustment amount, and formulate the energy transmission method between sub-regions based on the governance adjustment amount.

9. An electronic device, characterized in that, It includes: A memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the energy intelligent governance method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, An information transfer implementation program is stored on the computer-readable storage medium. When the program is executed by the processor, it implements the steps of the energy intelligent governance method according to any one of claims 1 to 7.

Images