A multi-energy coordinated intelligent micro-grid control system

Abstract

This invention relates to the field of energy control, specifically to a multi-energy collaborative intelligent microgrid control system. It includes a management center communicatively connected to a grid acquisition module, a grid analysis module, and a grid control module. The management center acquires historical energy data and historical electricity consumption data, and, combining these data, establishes an energy grid model. It then analyzes the energy grid to obtain energy region data. Based on the energy observation cycle and energy region data, it establishes a two-dimensional grid coordinate system and constructs a time-series prediction model to obtain predicted grid data. Using the predicted grid data, it constructs a predicted grid matrix and uses this matrix to regulate energy in the power region, obtaining pre-regulation strategies and optimal energy distribution points. Finally, it analyzes the pre-regulation strategies based on real-time electricity consumption and real-time power generation to obtain actual regulation strategies. This invention enhances the stability and flexibility of the microgrid.

Description

Technical Field

[0001] This invention relates to the field of energy control, and more specifically to a multi-energy coordinated intelligent microgrid control system. Background Technology

[0002] The increasing prevalence of new energy consumption methods such as distributed energy storage, electric vehicles, micro gas turbines, and fuel cells is driving the evolution of energy systems towards cleaner, more diversified, and distributed solutions. Against this backdrop, microgrids, as a user-centric, self-controllable energy system architecture capable of both independent and grid-connected operation, are gradually becoming an important technological approach for building regional energy autonomy, promoting renewable energy consumption, and improving power supply reliability and resilience. They are particularly well-suited for applications in industrial parks, urban communities, remote areas, and public buildings.

[0003] Chinese Patent Publication No. CN118054569B discloses an intelligent monitoring and control system for power distribution network operation, comprising: a data acquisition module that collects real-time wind direction and real-time wind speed values ​​of the power distribution network operating environment within a preset period; a data processing module that plots a wind direction distribution map based on the real-time wind direction and a wind speed change map based on the real-time wind speed values; an analysis module that determines the actual wind-receiving parameters of each area of ​​the power distribution network based on the wind speed change map, the wind direction distribution map, and the power grid model of the power distribution network, and identifies areas where the actual wind-receiving parameters are greater than the preset wind force as predicted influence areas; and an adjustment module that compares the actual wind-receiving parameters with the predicted wind resistance parameters of the predicted influence areas, determines adjustment parameters based on the comparison results, adjusts the actual number of support points based on the adjustment parameters, and uses the actual wind resistance parameters as the predicted wind resistance parameters for the next period to monitor the operation of the power distribution network in the next period.

[0004] In existing technologies, the instability of multiple energy outputs affects the power supply stability of microgrids, and the centralized control method of microgrids makes it impossible to flexibly control the microgrid according to multiple energy outputs, which has become an urgent problem to be solved. Summary of the Invention

[0005] The purpose of this invention is to address the problems existing in the background technology by proposing a multi-energy coordinated intelligent microgrid control system.

[0006] The technical solution of this invention: A multi-energy coordinated intelligent microgrid control system, comprising a management center, wherein the management center is communicatively connected to a power grid acquisition module, a power grid analysis module, and a power grid control module.

[0007] The power grid acquisition module is used to acquire historical energy data and historical electricity consumption data of the power area, combine the historical energy data and historical electricity consumption data to establish an energy grid model of the power area, analyze the energy grid, and obtain energy area data.

[0008] The power grid analysis module is used to set the daily energy observation cycle, obtain the energy observation cycle by combining the acquired historical environmental data, analyze the energy regional data by combining the energy observation cycle, establish a two-dimensional coordinate system of the power grid, and construct a time series prediction model by combining the two-dimensional coordinate system of the power grid to obtain the predicted power grid data.

[0009] The power grid control module is used to construct a predictive power grid matrix by predicting power grid data, and to regulate the energy in the power area by using the predictive power grid matrix to obtain pre-control strategies and optimal energy distribution points; based on the monitored real-time electricity consumption and real-time power generation, the pre-control strategies are analyzed to obtain the actual control strategies.

[0010] Preferably, the process of acquiring historical energy data and historical electricity consumption data for a power area includes:

[0011] Historical energy data includes historical production capacity time and historical production capacity data; historical production capacity time includes historical photovoltaic time and historical wind power time; historical production capacity data includes historical photovoltaic production capacity data and historical wind power production capacity data; historical photovoltaic production capacity data includes historical photovoltaic power generation and historical equipment status data; historical wind power production capacity data includes historical wind power generation and historical wind turbine equipment status data.

[0012] The historical electricity consumption data includes historical electricity consumption time and historical electricity consumption power.

[0013] Preferably, the process of establishing an energy grid model for a power region by combining historical energy data and historical electricity consumption data includes:

[0014] Based on historical energy production data, construct multiple energy nodes and energy tags, and assign energy tags to the corresponding multiple energy nodes; based on historical electricity consumption data, construct multiple electricity consumption nodes.

[0015] Set up energy distribution points, assign all types of energy tags to different energy distribution points in sequence, obtain the energy management tags of the energy distribution points, and construct the energy transmission link between the energy distribution points of the same type of energy tag and the corresponding type of energy management tag; set up the main power distribution point, construct the power distribution link between all multi-power nodes and the main power distribution point; construct the energy supply link between each energy distribution point and the main power distribution point.

[0016] By connecting multiple energy nodes, energy distribution points, multiple electricity consumption nodes, and the main power distribution point through energy transmission links, power distribution links, and energy supply links, an energy grid model is constructed.

[0017] Preferably, the process of analyzing the energy grid to obtain energy region data is as follows:

[0018] By connecting multiple energy nodes, energy distribution points, multiple electricity consumption nodes, and the main power distribution point through energy transmission links, power distribution links, and energy supply links, an energy grid model is constructed.

[0019] The multiple energy nodes in the energy transmission link and the power areas corresponding to the energy distribution points within the energy grid model are denoted as energy sub-regions. The energy type of the energy sub-region is marked by the energy management label of the energy distribution point to obtain the region label of the energy sub-region. The energy sub-region and the region label are denoted as energy region data.

[0020] Preferably, the process of setting a daily energy observation cycle and obtaining the energy observation cycle by combining the acquired historical environmental data, and then analyzing the energy region data based on the energy observation cycle to establish a two-dimensional coordinate system for the power grid includes:

[0021] By generating historical production capacity data corresponding to historical production capacity time through multiple energy nodes, the daily energy observation cycle is set; historical environmental data corresponding to the daily energy observation cycle is obtained; historical environmental reference data for the daily energy observation cycle is set through daily historical environmental data within the power area each year; a cycle dynamic coefficient is set through historical environmental data and historical environmental reference data; and the cycle dynamic coefficient is multiplied by the daily energy observation cycle to obtain the energy observation cycle.

[0022] By mapping the historical power generation data of all multi-energy nodes in each energy sub-region and the historical power consumption of multi-electricity nodes associated with the total power distribution point to a two-dimensional coordinate system through energy observation cycles, the sum of the area values ​​enclosed by the historical power generation data of all multi-energy nodes and the historical power consumption of all multi-electricity nodes and the x-axis in each energy observation cycle is calculated to obtain the historical power generation of each energy distribution point and the historical power consumption of the total power distribution point. A two-dimensional coordinate system of the power grid is established, and the historical power generation of each energy distribution point, the historical power consumption of the total power distribution point and their corresponding energy observation cycles are mapped to the two-dimensional coordinate system of the power grid.

[0023] Preferably, the process of constructing a time-series prediction model by combining the two-dimensional coordinate system of the power grid to obtain predicted power grid data includes:

[0024] By using energy observation cycles, a predictive input sequence is constructed for historical power generation and historical electricity consumption within the two-dimensional coordinate system of the power grid. A time-series prediction model is then established using this predictive input sequence. Historical power generation and historical electricity consumption corresponding to consecutive energy observation cycles of the same time are used as training and testing sets, respectively. The training and testing sets are then input into the time-series prediction model to train it, thereby obtaining the prediction cycle, predicted power generation, and predicted electricity consumption. The prediction cycle, predicted power generation, and predicted electricity consumption are denoted as the predicted power grid data.

[0025] Preferably, the process of constructing a predictive power grid matrix by predicting power grid data, and then using the predictive power grid matrix to regulate energy in the power region to obtain a pre-regulation strategy includes:

[0026] Real-time energy storage at each energy distribution point is obtained in real time, and a predictive grid matrix is ​​constructed using real-time energy storage and predicted grid data. Where i refers to the prediction period; e refers to the total number of prediction grid data sets corresponding to the prediction period. This refers to the prediction period i corresponding to consecutive times of the same duration. Predict the sub-matrix of the power grid; calculate the difference between the predicted power generation and the predicted power consumption for the predicted period corresponding to the energy distribution point, and denote it as the predicted energy storage. In the predicted power grid submatrix, This indicates the number of energy distribution points corresponding to the forecast period. This represents the real-time and predicted energy storage corresponding to energy distribution points; excluding Predicting the power grid submatrix, In other predicted power grid submatrices, It means The number of energy distribution points corresponding to the prediction period. It means The predicted remaining energy and predicted stored energy corresponding to each energy distribution point in the system;

[0027] The energy distribution points corresponding to the maximum real-time energy storage in each predicted power grid submatrix are marked to obtain prediction point marks. If the real-time energy storage corresponding to the prediction point mark is greater than or equal to the predicted electricity consumption, the corresponding energy distribution point is arranged to pre-transmit the predicted electricity consumption to the total power distribution point, and the predicted power generation of other energy distribution points is pre-stored in each multi-energy node. If the real-time energy storage corresponding to the prediction point mark is less than the predicted electricity consumption, the corresponding energy distribution point is arranged to pre-transmit all the predicted power generation to the total power distribution point, and the maximum predicted power generation among the remaining energy distribution points is pre-transmitted according to the remaining demand of the total power distribution point until the predicted electricity consumption of the total power distribution point is met, thus obtaining the pre-control strategy.

[0028] Preferably, the process of regulating energy in a power region by predicting the power grid matrix to obtain optimal energy distribution points, and analyzing the pre-regulation strategy based on the monitored real-time electricity consumption and real-time power generation to obtain the actual regulation strategy includes:

[0029] Set a threshold for the number of preferred nodes; record the energy distribution points whose number of predicted points for the same energy distribution point in each predicted submatrix of the predicted power grid matrix is ​​greater than or equal to the threshold for the number of preferred nodes as preferred energy distribution points;

[0030] The system monitors the real-time electricity consumption at the main power distribution point and the real-time power generation at the energy distribution points. It compares these figures with the predicted electricity consumption and power generation of the corresponding predicted grid submatrix. The energy distribution points involved in the pre-regulation strategy are given priority in the comparison. The difference between the predicted and real-time electricity consumption is calculated to obtain the regulation energy difference. If the regulation energy difference is greater than 0, it is temporarily stored in the energy distribution point and updated in the next predicted grid submatrix to obtain the actual regulation strategy. If the regulation energy difference is less than 0, the stored energy in the energy distribution point is transferred to the main power distribution point until the sum of the transferred energy and the regulation energy difference equals 0, thus obtaining the actual regulation strategy. If the regulation energy difference is equal to 0, the pre-regulation strategy does not need to be changed, and the main power distribution point distributes the obtained energy to each multi-consumption node as needed.

[0031] Compared with the prior art, the above-mentioned technical solution of the present invention has the following beneficial technical effects: It acquires historical energy data and historical electricity consumption data of the power area; combines the historical energy data and historical electricity consumption data to establish an energy grid model of the power area; analyzes the energy grid to obtain energy area data; it sorts the data within the energy grid model according to energy type, realizing comparability analysis between different energy forms and improving the data analysis capability of the smart microgrid; it sets a daily energy observation cycle and obtains the energy observation cycle by combining the acquired historical environmental data; it helps to dynamically adjust the analysis cycle and improve the accuracy of data prediction; it analyzes the energy area data by combining the energy observation cycle, establishes a two-dimensional coordinate system of the power grid, constructs a time-series prediction model by combining the two-dimensional coordinate system of the power grid, and obtains predicted power grid data; it constructs a predicted power grid matrix by using the predicted power grid data, and regulates the energy of the power area by using the predicted power grid matrix to obtain a pre-regulation strategy; it enhances the stability and flexibility of the microgrid; it obtains optimal energy distribution points, improving the efficiency and stability of energy regulation; and it analyzes the pre-regulation strategy based on the monitored real-time electricity consumption and real-time power generation to obtain the actual regulation strategy. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of one embodiment of the present invention. Detailed Implementation

[0033] Example 1, as Figure 1 As shown, the present invention proposes a multi-energy collaborative intelligent microgrid control system, including a management center, which is communicatively connected to a power grid acquisition module, a power grid analysis module, and a power grid control module.

[0034] The power grid acquisition module is used to acquire historical energy data and historical electricity consumption data of the power area, combine the historical energy data and historical electricity consumption data to establish an energy grid model of the power area, analyze the energy grid, and obtain energy area data.

[0035] The power grid analysis module is used to set the daily energy observation cycle, obtain the energy observation cycle by combining the acquired historical environmental data, analyze the energy regional data by combining the energy observation cycle, establish a two-dimensional coordinate system of the power grid, and construct a time series prediction model by combining the two-dimensional coordinate system of the power grid to obtain the predicted power grid data.

[0036] The power grid control module is used to construct a predictive power grid matrix by predicting power grid data, and to regulate the energy in the power area by using the predictive power grid matrix to obtain pre-control strategies and optimal energy distribution points; based on the monitored real-time electricity consumption and real-time power generation, the pre-control strategies are analyzed to obtain the actual control strategies.

[0037] It should be further explained that, in the specific implementation process, the process of acquiring historical energy data and historical electricity consumption data for the power region, combining this data to establish an energy grid model for the power region, and analyzing the energy grid to obtain energy region data is as follows:

[0038] The historical energy data includes historical production capacity time and historical production capacity data; the historical production capacity time includes historical photovoltaic time and historical wind power time; the historical production capacity data includes historical photovoltaic production capacity data and historical wind power production capacity data; the historical photovoltaic production capacity data includes historical photovoltaic power generation and historical equipment status data; the historical wind power production capacity data includes historical wind power generation and historical wind turbine equipment status data.

[0039] Specifically, the historical equipment status data includes, but is not limited to, inverter operating status, photovoltaic module efficiency change probability, and efficiency tracking curve; the historical wind turbine equipment status data includes, but is not limited to, wind turbine start-up and shutdown times, blade rotation speed, and pitch angle; within the historical production capacity period, the historical equipment status data, the historical wind turbine equipment status data, and the status of other production capacity equipment are all in normal working condition.

[0040] The historical electricity consumption data includes historical electricity consumption time and historical electricity consumption power;

[0041] Based on historical energy production data, construct multiple energy nodes and energy tags. The energy tags refer to the energy types in the historical production data of the multiple energy nodes, and assign energy tags to the corresponding multiple energy nodes; construct multiple electricity consumption nodes based on historical electricity consumption data.

[0042] Set up energy distribution points, assign all types of energy tags to different energy distribution points in sequence, obtain the energy management tags of the energy distribution points, and construct the energy transmission link between the energy distribution points of the same type of energy tag and the corresponding type of energy management tag; set up the main power distribution point, construct the power distribution link between all multi-power nodes and the main power distribution point; construct the energy supply link between each energy distribution point and the main power distribution point.

[0043] It should be noted that in the actual operation of a smart microgrid, there are multiple power transmission circuits and power distribution circuits. The energy transmission link, power distribution link, and energy supply link are the power transmission circuits and power distribution circuits in the actual operation of the smart microgrid.

[0044] By connecting multiple energy nodes, energy distribution points, multiple electricity consumption nodes, and the main power distribution point through energy transmission links, power distribution links, and energy supply links, an energy grid model is constructed.

[0045] The multiple energy nodes in the energy transmission link and the power areas corresponding to the energy distribution points within the energy grid model are denoted as energy sub-regions. The energy type of the energy sub-region is marked by the energy management label of the energy distribution point to obtain the region label of the energy sub-region. The energy sub-region and the region label are denoted as energy region data.

[0046] It should be further explained that, in the specific implementation process, the following steps are taken: A daily energy observation cycle is set, and the energy observation cycle is obtained by combining the acquired historical environmental data; the energy regional data is analyzed based on the energy observation cycle to establish a two-dimensional coordinate system for the power grid; and a time-series prediction model is constructed using this two-dimensional coordinate system to obtain the predicted power grid data.

[0047] By generating historical production capacity data corresponding to historical production capacity time through multiple energy nodes, the daily energy observation cycle is set; historical environmental data corresponding to the daily energy observation cycle is obtained; historical environmental reference data for the daily energy observation cycle is set through daily historical environmental data within the power area each year; a cycle dynamic coefficient is set through historical environmental data and historical environmental reference data; and the cycle dynamic coefficient is multiplied by the daily energy observation cycle to obtain the energy observation cycle.

[0048] Specifically, the energy daily observation cycle refers to the time period from midnight to 12:00 noon each day, and the range of the cycle dynamic coefficient is between 0 and 1.

[0049] By mapping the historical power generation data of all multi-energy nodes in each energy sub-region and the historical power consumption of multi-electricity nodes associated with the total power distribution point to a two-dimensional coordinate system through energy observation cycles, the sum of the area values ​​enclosed by the historical power generation data of all multi-energy nodes and the historical power consumption of all multi-electricity nodes and the x-axis in each energy observation cycle is calculated to obtain the historical power generation of each energy distribution point and the historical power consumption of the total power distribution point. A two-dimensional coordinate system of the power grid is established, and the historical power generation of each energy distribution point, the historical power consumption of the total power distribution point, and their corresponding energy observation cycles are mapped to the two-dimensional coordinate system of the power grid. The x-axis of the two-dimensional coordinate system of the power grid represents the energy observation cycle, and the y-axis represents the historical power generation of each energy distribution point and the historical power consumption of the total power distribution point.

[0050] Set a historical power generation limit threshold; if the historical power generation of each energy distribution point in the grid's two-dimensional coordinate system is lower than the historical power generation limit threshold, then reset the corresponding historical power generation to 0 and mark it synchronously in the grid's two-dimensional coordinate system.

[0051] By using energy observation cycles, a predictive input sequence is constructed for historical power generation and historical electricity consumption within the two-dimensional coordinate system of the power grid. A time-series prediction model is then established based on the predictive input sequence. Historical power generation and historical electricity consumption corresponding to consecutive energy observation cycles of the same time are used as training and testing sets, respectively. The training and testing sets are then input into the time-series prediction model to train it, thereby obtaining the prediction cycle, predicted power generation, and predicted electricity consumption. The prediction cycle, predicted power generation, and predicted electricity consumption are denoted as the predicted power grid data.

[0052] It should be noted that the time-series forecasting model includes a power generation forecasting model and a load forecasting model. The specific process of using historical power generation and historical electricity consumption corresponding to consecutive energy observation cycles of the same time as training and testing sets and inputting the training and testing sets into the time-series forecasting model is as follows: using historical power generation corresponding to consecutive energy observation cycles of the same time as training and testing sets for the power generation forecasting model, the power generation forecasting model is trained to obtain the predicted power generation within the forecasting cycle; using historical electricity consumption corresponding to consecutive energy observation cycles of the same time as training and testing sets for the load forecasting model, the load forecasting model is trained to obtain the predicted electricity consumption within the forecasting cycle.

[0053] It should be further explained that, in the specific implementation process, a predictive power grid matrix is ​​constructed by predicting power grid data. This matrix is ​​then used to regulate energy in the power region, obtaining pre-regulation strategies and optimal energy distribution points. The process of analyzing the pre-regulation strategies based on monitored real-time electricity consumption and real-time power generation to obtain the actual regulation strategies is as follows:

[0054] Real-time energy storage at each energy distribution point is obtained in real time, and a predictive grid matrix is ​​constructed using real-time energy storage and predicted grid data. Where i refers to the prediction period; e refers to the total number of prediction grid data sets corresponding to the prediction period. This refers to the prediction period i corresponding to consecutive times of the same duration. Predict the sub-matrix of the power grid; calculate the difference between the predicted power generation and the predicted power consumption for the predicted period corresponding to the energy distribution point, and denote it as the predicted energy storage. In the predicted power grid submatrix, This indicates the number of energy distribution points corresponding to the forecast period. This represents the real-time and predicted energy storage corresponding to energy distribution points; excluding Predicting the power grid submatrix, In other predicted power grid submatrices, It means The number of energy distribution points corresponding to the prediction period. It means The predicted remaining energy and predicted stored energy corresponding to each energy distribution point in the system;

[0055] The energy distribution points corresponding to the maximum real-time energy storage in each prediction grid submatrix are marked to obtain prediction point marks. If the real-time energy storage corresponding to the prediction point mark is greater than or equal to the predicted electricity consumption, the corresponding energy distribution point is arranged to pre-transmit the predicted electricity consumption to the total power distribution point, and the predicted power generation of other energy distribution points is pre-stored in each multi-energy node. If the real-time energy storage corresponding to the prediction point mark is less than the predicted electricity consumption, the corresponding energy distribution point is arranged to pre-transmit all the predicted power generation to the total power distribution point, and the maximum predicted power generation in the remaining energy distribution points is pre-transmitted according to the remaining demand of the total power distribution point until the predicted electricity consumption of the total power distribution point is met. The pre-control strategy is obtained, the remaining predicted power generation of each energy distribution point is obtained, and the sum of the remaining predicted power generation and the real-time energy storage is calculated, which is the predicted remaining energy. The predicted remaining energy is then updated to the next prediction grid submatrix, which helps to regulate energy in the next prediction cycle.

[0056] Set a threshold for the number of preferred nodes; if the number of predicted point markers for the same energy distribution point in each predicted grid submatrix of the predicted grid matrix is ​​greater than or equal to the threshold for the number of preferred nodes, then the corresponding energy distribution point is recorded as a preferred energy distribution point, and subsequent energy regulation of the smart microgrid is preferentially carried out within the preferred energy distribution point;

[0057] The system monitors the real-time electricity consumption at the main power distribution point and the real-time power generation at the energy distribution points. It compares these figures with the predicted electricity consumption and power generation of the corresponding predicted grid submatrix. The energy distribution points involved in the pre-regulation strategy are given priority in the comparison. The difference between the predicted and real-time electricity consumption is calculated to obtain the regulation energy difference. If the regulation energy difference is greater than 0, it is temporarily stored in the energy distribution point and updated in the next predicted grid submatrix to obtain the actual regulation strategy. If the regulation energy difference is less than 0, the stored energy in the energy distribution point is transferred to the main power distribution point until the sum of the transferred energy and the regulation energy difference equals 0, thus obtaining the actual regulation strategy. If the regulation energy difference is equal to 0, the pre-regulation strategy does not need to be changed, and the main power distribution point distributes the obtained energy to each multi-consumption node as needed.

[0058] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. A multi-energy coordinated intelligent microgrid control system, comprising a management center, characterized in that, The management center is connected to a power grid acquisition module, a power grid analysis module, and a power grid control module. The power grid acquisition module is used to acquire historical energy data and historical electricity consumption data of the power area, combine the historical energy data and historical electricity consumption data to establish an energy grid model of the power area, analyze the energy grid, and obtain energy area data. The power grid analysis module is used to set the daily energy observation cycle, obtain the energy observation cycle by combining the acquired historical environmental data, analyze the energy regional data by combining the energy observation cycle, establish a two-dimensional coordinate system of the power grid, and construct a time series prediction model by combining the two-dimensional coordinate system of the power grid to obtain the predicted power grid data. The power grid control module is used to construct a predictive power grid matrix by predicting power grid data, and to regulate the energy in the power area by using the predictive power grid matrix to obtain pre-control strategies and optimal energy distribution points; based on the monitored real-time electricity consumption and real-time power generation, the pre-control strategies are analyzed to obtain actual control strategies; The process of obtaining historical energy data and historical electricity consumption data for a power area includes: Historical energy data includes historical production capacity time and historical production capacity data; historical production capacity time includes historical photovoltaic time and historical wind power time; historical production capacity data includes historical photovoltaic production capacity data and historical wind power production capacity data; historical photovoltaic production capacity data includes historical photovoltaic power generation and historical equipment status data; historical wind power production capacity data includes historical wind power generation and historical wind turbine equipment status data. The historical electricity consumption data includes historical electricity consumption time and historical electricity consumption power; The process of establishing a regional energy grid model by combining historical energy data and historical electricity consumption data includes: Based on historical energy production data, construct multiple energy nodes and energy tags, and assign energy tags to the corresponding multiple energy nodes; based on historical electricity consumption data, construct multiple electricity consumption nodes. Set up energy distribution points, assign all types of energy tags to different energy distribution points in sequence, obtain the energy management tags of the energy distribution points, and construct the energy transmission link between the energy distribution points of the same type of energy tag and the corresponding type of energy management tag; set up the main power distribution point, construct the power distribution link between all multi-power nodes and the main power distribution point; construct the energy supply link between each energy distribution point and the main power distribution point. By connecting multiple energy nodes, energy distribution points, multiple electricity consumption nodes, and the main power distribution point through energy transmission links, power distribution links, and energy supply links, an energy grid model is constructed. The process of analyzing the energy grid to obtain regional energy data is as follows: By connecting multiple energy nodes, energy distribution points, multiple electricity consumption nodes, and the main power distribution point through energy transmission links, power distribution links, and energy supply links, an energy grid model is constructed. The multiple energy nodes in the energy transmission link and the power areas corresponding to the energy distribution points in the energy grid model are denoted as energy sub-regions. The energy type of the energy sub-region is marked by the energy management label of the energy distribution point to obtain the region label of the energy sub-region. The energy sub-region and the region label are denoted as energy region data. The process of setting a daily energy observation cycle, combining it with acquired historical environmental data to obtain the energy observation cycle, and then analyzing regional energy data based on the energy observation cycle to establish a two-dimensional coordinate system for the power grid includes: By generating historical production capacity data corresponding to historical production capacity time through multiple energy nodes, the daily energy observation cycle is set; historical environmental data corresponding to the daily energy observation cycle is obtained; historical environmental reference data for the daily energy observation cycle is set through daily historical environmental data within the power area each year; a cycle dynamic coefficient is set through historical environmental data and historical environmental reference data; and the cycle dynamic coefficient is multiplied by the daily energy observation cycle to obtain the energy observation cycle. By mapping the historical power generation data of all multi-energy nodes in each energy sub-region and the historical power consumption of multi-electricity nodes associated with the total power distribution point to a two-dimensional coordinate system through energy observation cycles, the sum of the area values ​​enclosed by the historical power generation data of all multi-energy nodes and the historical power consumption of all multi-electricity nodes and the x-axis in each energy observation cycle is calculated to obtain the historical power generation of each energy distribution point and the historical power consumption of the total power distribution point. A two-dimensional coordinate system of the power grid is established, and the historical power generation of each energy distribution point, the historical power consumption of the total power distribution point, and their corresponding energy observation cycles are mapped to the two-dimensional coordinate system of the power grid. The process of constructing a time-series prediction model by combining the two-dimensional coordinate system of the power grid and obtaining predicted power grid data includes: By using energy observation cycles, a predictive input sequence is constructed for historical power generation and historical electricity consumption within the two-dimensional coordinate system of the power grid. A time-series prediction model is then established using this predictive input sequence. Historical power generation and historical electricity consumption corresponding to consecutive energy observation cycles of the same time are used as training and testing sets, respectively. The training and testing sets are then input into the time-series prediction model to train it, thereby obtaining the prediction cycle, predicted power generation, and predicted electricity consumption. The prediction cycle, predicted power generation, and predicted electricity consumption are denoted as the predicted power grid data.

2. The multi-energy coordinated intelligent microgrid control system according to claim 1, characterized in that, The process of constructing a predictive grid matrix by forecasting grid data, and then using this predictive grid matrix to regulate energy in a power region to obtain a pre-regulation strategy includes: Real-time energy storage at each energy distribution point is obtained in real time, and a predictive grid matrix is ​​constructed using real-time energy storage and predicted grid data. Where i refers to the prediction period; e refers to the total number of prediction grid data sets corresponding to the prediction period. This refers to the prediction period i corresponding to consecutive times of the same duration. Predict the sub-matrix of the power grid; calculate the difference between the predicted power generation and the predicted power consumption for the predicted period corresponding to the energy distribution point, and denote it as the predicted energy storage. In the predicted power grid submatrix, This indicates the number of energy distribution points corresponding to the forecast period. This represents the real-time and predicted energy storage corresponding to energy distribution points; excluding Predicting the power grid submatrix, In other predicted power grid submatrices, It means The number of energy distribution points corresponding to the prediction period. It means The predicted remaining energy and predicted stored energy corresponding to each energy distribution point in the system; The energy distribution points corresponding to the maximum real-time energy storage in each predicted power grid submatrix are marked to obtain prediction point marks. If the real-time energy storage corresponding to the prediction point mark is greater than or equal to the predicted electricity consumption, the corresponding energy distribution point is arranged to pre-transmit the predicted electricity consumption to the total power distribution point, and the predicted power generation of other energy distribution points is pre-stored in each multi-energy node. If the real-time energy storage corresponding to the prediction point mark is less than the predicted electricity consumption, the corresponding energy distribution point is arranged to pre-transmit all the predicted power generation to the total power distribution point, and the maximum predicted power generation among the remaining energy distribution points is pre-transmitted according to the remaining demand of the total power distribution point until the predicted electricity consumption of the total power distribution point is met, thus obtaining the pre-control strategy.

3. The multi-energy coordinated intelligent microgrid control system according to claim 2, characterized in that, The process of regulating energy in a power region by predicting the power grid matrix to obtain optimal energy distribution points, and analyzing the pre-regulation strategy based on the monitored real-time electricity consumption and real-time power generation to obtain the actual regulation strategy includes: Set a threshold for the number of preferred nodes; record the energy distribution points whose number of predicted points for the same energy distribution point in each predicted submatrix of the predicted power grid matrix is ​​greater than or equal to the threshold for the number of preferred nodes as preferred energy distribution points; The system monitors the real-time electricity consumption at the main power distribution point and the real-time power generation at the energy distribution points. It compares these figures with the predicted electricity consumption and power generation of the corresponding predicted grid submatrix. The energy distribution points involved in the pre-regulation strategy are given priority in the comparison. The difference between the predicted and real-time electricity consumption is calculated to obtain the regulation energy difference. If the regulation energy difference is greater than 0, it is temporarily stored in the energy distribution point and updated in the next predicted grid submatrix to obtain the actual regulation strategy. If the regulation energy difference is less than 0, the stored energy in the energy distribution point is transferred to the main power distribution point until the sum of the transferred energy and the regulation energy difference equals 0, thus obtaining the actual regulation strategy. If the regulation energy difference is equal to 0, the pre-regulation strategy does not need to be changed, and the main power distribution point distributes the obtained energy to each multi-consumption node as needed.

Images