Micro-grid composite energy storage system monitoring and regulation method and micro-grid composite energy storage system monitoring and regulation system

Abstract

The invention relates to the technical field of micro-grid energy management, in particular to a micro-grid composite energy storage system monitoring and regulation method and system, and the method comprises the steps: carrying out the butt joint of energy supply side and user side energy flow change data predicted by an energy supply side energy prediction model and a user side energy prediction model; the environment data of the energy supply side are analyzed through a machine learning algorithm, an optimization target is set according to an analysis result, and the optimization target comprises the steps that energy provided by the energy supply side is preferentially called, and in the peak period of power grid demand, energy storage electric power is used for balancing supply and demand and reducing power consumption cost; the energy provided by the energy supply side and the carbon emission value of the energy storage electric power used in the peak electricity time period are monitored through the monitoring model, the process of balancing supply and demand by using the energy storage electric power is optimized, and the carbon emission is reduced while the electricity consumption cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of microgrid energy management, and in particular to a monitoring and control method and system for a microgrid composite energy storage system. Background Art

[0002] Energy storage systems are able to perform peak-shaving and valley-filling in a small area, that is, storing energy during low-power consumption and releasing energy during peak power consumption. This mechanism helps to ensure the smooth operation of power loads, thereby reducing problems caused by grid fluctuations. Through rapid response, energy storage systems can quickly adjust power output to ensure the stability of the grid. With the introduction of composite energy storage (solar and wind) systems, microgrids need to develop corresponding monitoring and control capabilities. This includes real-time monitoring of grid status, predicting load changes, and optimizing energy storage resource allocation. Through intelligent control strategies, microgrids can achieve more stable and efficient operation. The application of composite energy storage systems helps to enhance the resilience of microgrids, making them more resistant to external interference and internal failures.

[0003] Therefore, how to improve the robustness of the energy storage system and reduce human intervention is an urgent problem to be solved in the application of existing microgrid energy storage systems. Summary of the invention

[0004] The present invention connects the energy flow change data of the energy supply side and the user side predicted by the energy prediction model on the energy supply side with the energy prediction model on the user side, analyzes the energy flow on the user side and the energy supply side, gives priority to the energy provided by the energy supply side, and uses energy storage power to balance supply and demand during peak grid demand, optimizes the energy supply strategy, reduces power supply costs and optimizes carbon emissions.

[0005] The technical solution proposed by the present invention is: a monitoring and control method for a microgrid composite energy storage system, the method comprising: Connect the energy flow change data of the energy supply side and the user side predicted by the energy prediction model on the energy supply side and the energy prediction model on the user side; The environmental data on the energy supply side is analyzed through machine learning algorithms, and optimization goals are set based on the analysis results. The optimization goals include: giving priority to the energy provided by the energy supply side, using energy storage power to balance supply and demand during peak grid demand periods, and reducing electricity costs; By monitoring the energy provided by the energy supply side and the carbon emission value of the energy storage electricity used during peak power hours through the monitoring model, the process of balancing the supply and demand of energy storage electricity is optimized, thereby reducing carbon emissions while reducing electricity costs.

[0006] Preferably, the step of connecting the energy supply side energy prediction model with the energy supply side and user side energy flow change data predicted by the user side energy prediction model includes: Collect historical energy flow data, including data from the energy supply side and the user side, clean and normalize the historical energy flow data, and form a historical data set for the energy supply side and a historical data set for the user side; Extracting multiple key features from the energy supply side historical data set and the user side historical data set respectively to form an energy supply side feature data set and a user side feature data set, wherein the key features include time series features, seasonal features, and weather features; The energy supply side feature data set is used to train the energy prediction model on the energy supply side, and the energy prediction model on the user side is trained using the feature data set on the user side; Use the DRL model to try to find the optimal strategy through trial and error, optimize the energy prediction model on the energy supply side and the energy prediction model on the user side to minimize the prediction error or maximize the prediction accuracy; Deploy trained energy prediction models on the energy supply side and user side; Obtain energy supply data within a preset time period from each energy supply side of the microgrid at a preset frequency, including power supply current, power supply voltage, and power supply equipment characteristics, to form an energy supply side data set; After feature extraction and preprocessing of the data in the energy supply side data set, the data is input into the energy supply side energy prediction model to predict the energy supply data of each energy supply side in the future. The power consumption data within a preset time period is obtained from each user side of the microgrid at a preset frequency, including the minimum power consumption and the maximum power consumption, to form a user side data set. After feature extraction and preprocessing, the data in the user side data set is input into the user side energy prediction model to predict the energy consumption data of each user side in the future.

[0007] Preferably, the step of connecting the energy supply side energy prediction model with the energy supply side and user side energy flow change data predicted by the user side energy prediction model further includes: Establishing a relationship matrix model of the energy flow from the energy supply side to the energy storage device and the energy flow from the energy storage device to the user side includes the following sub-steps: Establish energy flow to supply lateral energy storage devices: ,in, Represents the energy conversion efficiency matrix from the energy supply side to the energy storage device, represents the power output vector on the energy supply side, ,in, They represent the output power of light energy and wind energy respectively; Establish energy flow from energy storage equipment to the user side: ,in, Represents the energy conversion efficiency matrix from energy storage equipment to the user side, represents the power demand vector at the user side; The expression for the change of charge state of the energy storage device is: ,in, Indicates the maximum capacity of the energy storage device, Indicates the charge state of the energy storage device; Then the relationship matrix of energy flow is: ,in, Represents the identity matrix.

[0008] Preferably, the analyzing of the environmental data on the energy supply side by a machine learning algorithm includes: Constructing environmental factors vector ,in, They represent temperature, global horizontal irradiance, and wind speed respectively; Get the power output vector of the energy supply side ; Then the matrix model of the impact of environmental data on the energy supply side on the energy supply side is: ;in, Indicates the degree of influence of the environment on wind energy supply and light energy supply; Through machine learning algorithms, the relationship between environmental factors and energy supply output is analyzed to determine , to determine the impact of environmental data on the energy supply side on the energy supply side; An independent data set is used to verify the accuracy of the energy supply impact matrix model, and the energy output of the energy supply side under different environmental conditions is predicted by the energy supply impact matrix model.

[0009] Preferably, during the peak period of grid demand, using energy storage power to balance supply and demand and reduce electricity costs includes: Establishing the optimal price balance matrix of energy supply on the energy supply side and energy consumption on the user side includes the following sub-steps: Constructing the optimal price equilibrium matrix model ; in, is the supply and demand matrix, which represents the energy flow from the energy supply side to the user side, that is, the amount of energy provided by each energy supply side to each user side; is the cost-benefit matrix, which represents the cost or benefit of energy transmission from the energy supply side to the user side; represents the adjustment matrix; Analyze the optimal price balance matrix through machine learning models to obtain the optimal cost-benefit matrix ; Considering the power supply characteristics during the peak period of grid demand, an energy balance matrix model is constructed: ,in Represents the dispatch matrix of different energy supply sides and user sides in the power grid, that is, the power grid dispatch matrix; Indicates the energy supply on the energy supply side during peak hours, Indicates the energy demand at the user side during peak hours; Use replace After that, the optimal price equilibrium matrix model during peak hours becomes: ; The optimal price balance matrix during peak hours is analyzed through machine learning models to obtain the corresponding optimal cost-benefit matrix. The element value of .

[0010] Preferably, the process of monitoring the energy provided by the energy supply side and the carbon emission value of the energy storage power used during the peak power period through the monitoring model, and optimizing the use of the energy storage power to balance the supply and demand includes: Constructing the objective function ;in, Indicates different time periods or points in time; Indicates time point The energy balance matrix, Indicates time point The carbon emission factor, Indicates time point electricity price; The optimization algorithm Gurobi is used to solve the objective function and obtain the optimal solution of the objective function, that is, the optimal energy scheduling amount, so that the carbon emissions in the energy scheduling process are minimized.

[0011] Preferably, the prioritizing of energy provided by the energy supply side includes: Obtain wind power supply, photovoltaic power supply, electricity demand, carbon emission factors, power supply cost, and electricity cost at different time points to form a power supply time series; Extract wind power supply data from the power supply time series to form a wind power supply matrix ; Extract photovoltaic power supply data from the power supply time series to form a photovoltaic power supply matrix ; Get the power grid dispatch matrix ; Build a priority scheduling model: ; in, Indicates the demand of the user side at different time points; Carbon emission weight, represents the cost weight; Respectively indicate time points The amount of wind power and photovoltaic power supply at that time; represent the cost of wind power generation and photovoltaic power generation respectively; Indicates different time periods or points in time; They represent the carbon emission costs of wind power generation and photovoltaic power generation respectively; represents the minimum cost; Indicates the maximum capacity of the energy storage device; The optimization algorithm Gurobi is used to solve the priority scheduling model and obtain the wind power supply and photovoltaic scheduling solutions with the best power supply cost and carbon emissions.

[0012] Preferably, the step of preferentially calling the energy provided by the energy supply side further includes: Construct the objective function to minimize the cost: ; in, Indicates time point Wind power generation and photovoltaic power generation; Set the priority constraint: If , , the power supply side of wind power generation will be used first; if , wind power generation is preferred; if , photovoltaic power generation is preferred; Use the optimization algorithm Gurobi to solve the cost minimization objective function and obtain the optimal and .

[0013] The present invention also provides a microgrid composite energy storage system monitoring and control system, and the system is used to execute the microgrid composite energy storage system monitoring and control method.

[0014] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the microgrid composite energy storage system monitoring and control method.

[0015] Beneficial effects of the present invention: 1. The present invention is based on data-driven decision-making. By analyzing the environmental data on the energy supply side, the actual situation of energy supply, including energy type, supply, price fluctuations, etc., is understood. In the optimization goal, it is clearly proposed to give priority to the energy provided by the energy supply side, which helps to reduce dependence on external energy, improve energy self-sufficiency, and reduce losses and costs caused by energy transmission and conversion. During the peak period of grid demand, the use of energy storage power to balance supply and demand is an important means to optimize the operation of the energy system. By shaving the peak and filling the valley, the pressure on the grid can be relieved, the use of high-priced electricity can be reduced, and the cost of electricity can be reduced. It helps to achieve the rational allocation and utilization of energy.

[0016] 2. The present invention realizes the optimal configuration of energy resources by establishing the optimal price balance matrix of energy supply on the energy supply side and energy consumption on the user side. By analyzing the matrix through a machine learning model, the element values ​​in the optimal cost-effectiveness matrix can be obtained, that is, the cost-effectiveness of the optimal configuration of energy resources can be maximized under different supply and demand conditions. By comprehensively considering various factors on the energy supply side and the user side, and using machine learning models for precise analysis, the accuracy and robustness of energy storage system scheduling are improved, and the interference of human factors is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The present invention is a flow chart of a method for monitoring and controlling a microgrid composite energy storage system. DETAILED DESCRIPTION

[0018] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0019] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0020] refer to Figure 1 The technical solution provided by the present invention is: a monitoring and control method for a microgrid composite energy storage system, comprising the following steps: Step 1: Connect the energy flow change data on the energy supply side and the user side predicted by the energy prediction model on the energy supply side and the user side.

[0021] 2. After feature extraction and preprocessing, the data in the energy supply side data set is input into the energy supply side energy prediction model to predict the energy supply data of each energy supply side in the future; after feature extraction and preprocessing, the data in the user side data set is input into the user side energy prediction model to predict the energy consumption data of each user side in the future.

[0022] The specific steps include: Collect historical energy flow data, including data from the energy supply side and the user side, clean and normalize the historical energy flow data, and form a historical data set for the energy supply side and a historical data set for the user side; Extracting multiple key features from the energy supply side historical data set and the user side historical data set respectively to form an energy supply side feature data set and a user side feature data set, wherein the key features include time series features, seasonal features, and weather features; The energy supply side feature data set is used to train the energy prediction model on the energy supply side, and the energy prediction model on the user side is trained using the feature data set on the user side; Use the DRL model to try to find the optimal strategy through trial and error, optimize the energy prediction model on the energy supply side and the energy prediction model on the user side to minimize the prediction error or maximize the prediction accuracy; Deploy trained energy prediction models on the energy supply side and user side; The energy supply data within a preset time period is obtained from each energy supply side of the microgrid at a preset frequency, including the power supply current, power supply voltage, and power supply equipment characteristics to form an energy supply side data set.

[0023] In some preferred embodiments, the method further comprises the following steps: Establishing a relationship matrix model of the energy flow from the energy supply side to the energy storage device and the energy flow from the energy storage device to the user side includes the following sub-steps: Establish energy flow to supply lateral energy storage devices: ,in, Represents the energy conversion efficiency matrix from the energy supply side to the energy storage device, represents the power output vector on the energy supply side, ,in, They represent the output power of light energy and wind energy respectively; Establish energy flow from energy storage equipment to the user side: ,in, Represents the energy conversion efficiency matrix from energy storage equipment to the user side, represents the power demand vector at the user side; The expression for the change of charge state of the energy storage device is: ,in, Indicates the maximum capacity of the energy storage device, Indicates the state of charge of the energy storage device; Then the relationship matrix of energy flow is: ,in, Represents the identity matrix.

[0024] Step 2: Analyze the environmental data on the energy supply side through machine learning algorithms, and set optimization goals based on the analysis results. The optimization goals include: giving priority to the energy provided by the energy supply side, using energy storage power to balance supply and demand during peak grid demand, and reducing electricity costs; Among them, the environmental data on the energy supply side is analyzed through machine learning algorithms, including: Constructing environmental factors vector ,in, They represent temperature, global horizontal irradiance, and wind speed respectively; Get the power output vector of the energy supply side ; Then the matrix model of the impact of environmental data on the energy supply side on the energy supply side is: ;in, Indicates the degree of influence of the environment on wind energy supply and light energy supply; Through machine learning algorithms, the relationship between environmental factors and energy supply output is analyzed to determine , to determine the impact of environmental data on the energy supply side on the energy supply side; An independent data set is used to verify the accuracy of the energy supply impact matrix model, and the energy output of the energy supply side under different environmental conditions is predicted by the energy supply impact matrix model.

[0025] During peak demand periods, energy storage can be used to balance supply and demand and reduce electricity costs, including: Establishing the optimal price balance matrix of energy supply on the energy supply side and energy consumption on the user side includes the following sub-steps: Constructing the optimal price equilibrium matrix model ; in, is the supply and demand matrix, which represents the energy flow from the energy supply side to the user side, that is, the amount of energy provided by each energy supply side to each user side; is the cost-benefit matrix, which represents the cost or benefit of energy transmission from the energy supply side to the user side; represents the adjustment matrix; Analyze the optimal price balance matrix through machine learning models to obtain the element values ​​in the optimal cost-benefit matrix; Considering the power supply characteristics during the peak period of grid demand, an energy balance matrix model is constructed: ,in Represents the dispatch matrix of different energy supply sides and user sides in the power grid, that is, the power grid dispatch matrix; Indicates the energy supply on the energy supply side during peak hours, Indicates the energy demand at the user side during peak hours; Use replace After that, the optimal price equilibrium matrix model during peak hours becomes: ; The optimal price balance matrix during peak hours is analyzed through machine learning models to obtain the corresponding optimal cost-benefit matrix. The element value of .

[0026] Among them, priority is given to the energy provided by the energy supply side, including: Obtain wind power supply, photovoltaic power supply, electricity demand, carbon emission factors, power supply cost, and electricity cost at different time points to form a power supply time series; Extract wind power supply data from the power supply time series to form a wind power supply matrix ; Extract photovoltaic power supply data from the power supply time series to form a photovoltaic power supply matrix ; Get the power grid dispatch matrix ; Build a priority scheduling model: ; in, Indicates the demand of the user side at different time points; Carbon emission weight, represents the cost weight; Respectively indicate time points The amount of wind power and photovoltaic power supply at that time; represent the cost of wind power generation and photovoltaic power generation respectively; Indicates different time periods or points in time; They represent the carbon emission costs of wind power generation and photovoltaic power generation respectively; represents the minimum cost; Indicates the maximum capacity of the energy storage device;

[0027] The optimization algorithm Gurobi is used to solve the priority scheduling model and obtain the wind power supply and photovoltaic scheduling solutions with the best power supply cost and carbon emissions.

[0028] In some preferred embodiments, it also includes: Construct the objective function to minimize the cost: ; in, Indicates time point Wind power generation and photovoltaic power generation; Set the priority constraint: If , , the power supply side of wind power generation will be used first; if , wind power generation is preferred; if , photovoltaic power generation is preferred; Use the optimization algorithm Gurobi to solve the cost minimization objective function and obtain the optimal and .

[0029] For example, if we want to optimize the use of wind energy during peak hours to minimize the difference between wind power generation and user demand, we want to find an energy balance matrix that minimizes the difference between wind power generation and user demand.

[0030] First, construct a wind power generation matrix with a size of ,in is the number of wind turbines, is the number of time periods.

[0031] Construct a user demand matrix of size ,in is the number of users.

[0032] Get the power grid dispatch matrix , the size is , each element in the matrix represents the allocation ratio of each wind turbine to each user, .

[0033] Output bit optimized energy balance matrix: This can be achieved through the following algorithm steps: Create an all-zero matrix as the initial energy balance matrix. Assume that the total demand matrix is ​​directly provided by the user demand matrix.

[0034] The objective function is defined as the sum of squares of the difference between wind power generation and user demand. The objective function is minimized by the gradient descent method and the energy balance matrix is ​​updated.

[0035] When the norm of the gradient is less than the set tolerance, the algorithm is considered to have converged and the energy balance matrix is ​​finally returned. By minimizing the difference between wind power generation and user-side demand, the goal of optimizing wind energy use during peak power consumption periods is achieved.

[0036] Similarly, when it comes to photovoltaic power generation, each element in the constructed grid dispatch matrix can represent the allocation ratio of each photovoltaic power generation device to each user on the electricity consumption side, including the allocation of the number of photovoltaic power generation devices and the allocation of the power generation of each photovoltaic power generation device.

[0037] Step 3: Use the monitoring model to monitor the energy provided by the energy supply side and the carbon emission value of the energy storage power used during the peak power period, optimize the process of using energy storage power to balance supply and demand, and reduce carbon emissions while reducing electricity costs. It includes the following steps: Constructing the objective function ;in, Indicates different time periods or points in time; Indicates time point The energy balance matrix, Indicates time point The carbon emission factor, Indicates time point electricity price; The optimization algorithm Gurobi is used to solve the objective function and obtain the optimal solution of the objective function, that is, the optimal energy scheduling amount, so that the carbon emissions in the energy scheduling process are minimized.

[0038] The present invention also provides a microgrid composite energy storage system monitoring and control system, and the system is used to execute the microgrid composite energy storage system monitoring and control method.

[0039] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the microgrid composite energy storage system monitoring and control method.

[0040] In the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present invention are executed. It should be noted that the above-mentioned computer-readable medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device, or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, device, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless segments, wire segments, optical cables, RF, etc., or any suitable combination of the above.

[0041] The flowchart in the accompanying drawings illustrates the possible architecture, functions and operations of the methods according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in a different order from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0042] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be subject to any changes or modifications.

Claims

1. A method for monitoring and controlling a microgrid composite energy storage system, characterized in that: The method comprises: Connect the energy flow change data of the energy supply side and the user side predicted by the energy prediction model on the energy supply side and the energy prediction model on the user side; The environmental data on the energy supply side is analyzed through machine learning algorithms, and optimization goals are set based on the analysis results. The optimization goals include: giving priority to the energy provided by the energy supply side, using energy storage power to balance supply and demand during peak grid demand periods, and reducing electricity costs; By monitoring the energy provided by the energy supply side and the carbon emission value of the energy storage electricity used during peak power hours through the monitoring model, the process of balancing the supply and demand of energy storage electricity is optimized, thereby reducing carbon emissions while reducing electricity costs.

2. A microgrid composite energy storage system monitoring and control method according to claim 1, characterized in that: The step of connecting the energy supply side energy prediction model with the energy supply side and user side energy flow change data predicted by the user side energy prediction model includes: Collect historical energy flow data, including data from the energy supply side and the user side, clean and normalize the historical energy flow data, and form a historical data set for the energy supply side and a historical data set for the user side; Extracting multiple key features from the energy supply side historical data set and the user side historical data set respectively to form an energy supply side feature data set and a user side feature data set, wherein the key features include time series features, seasonal features, and weather features; The energy supply side feature data set is used to train the energy prediction model on the energy supply side, and the energy prediction model on the user side is trained using the feature data set on the user side; Use the DRL model to try to find the optimal strategy through trial and error, optimize the energy prediction model on the energy supply side and the energy prediction model on the user side to minimize the prediction error or maximize the prediction accuracy; Deploy trained energy prediction models on the energy supply side and user side; Obtain energy supply data within a preset time period from each energy supply side of the microgrid at a preset frequency, including power supply current, power supply voltage, and power supply equipment characteristics, to form an energy supply side data set; After feature extraction and preprocessing of the data in the energy supply side data set, the data is input into the energy supply side energy prediction model to predict the energy supply data of each energy supply side in the future. The power consumption data within a preset time period is obtained from each user side of the microgrid at a preset frequency, including the minimum power consumption and the maximum power consumption, to form a user side data set; the data in the user side data set is feature extracted and preprocessed, and then input into the user side energy prediction model to predict the energy consumption data of each user side in the future.

3. A microgrid composite energy storage system monitoring and control method according to claim 2, characterized in that: The step of connecting the energy supply side energy prediction model with the energy supply side and user side energy flow change data predicted by the user side energy prediction model further includes: Establishing a relationship matrix model of the energy flow from the energy supply side to the energy storage device and the energy flow from the energy storage device to the user side includes the following sub-steps: Establish energy flow to supply lateral energy storage devices: ,in, Represents the energy conversion efficiency matrix from the energy supply side to the energy storage device, represents the power output vector on the energy supply side, ,in, They represent the output power of light energy and wind energy respectively; Establish energy flow from energy storage equipment to the user side: ,in, Represents the energy conversion efficiency matrix from energy storage equipment to the user side, represents the power demand vector at the user side; The expression for the change of charge state of the energy storage device is: ,in, Indicates the maximum capacity of the energy storage device, Indicates the charge state of the energy storage device; Then the relationship matrix of energy flow is: ,in, Represents the identity matrix.

4. A microgrid composite energy storage system monitoring and control method according to claim 3, characterized in that: The environmental data on the energy supply side is analyzed by a machine learning algorithm, including: Constructing environmental factors vector ,in, They represent temperature, global horizontal irradiance, and wind speed respectively; Get the power output vector of the energy supply side ; Then the matrix model of the impact of environmental data on the energy supply side on the energy supply side is: ;in, Indicates the degree of influence of the environment on wind energy supply and light energy supply; represents the energy dispatch amount; Through machine learning algorithms, the relationship between environmental factors and energy supply output is analyzed to determine , to determine the impact of environmental data on the energy supply side on the energy supply side; An independent data set is used to verify the accuracy of the energy supply impact matrix model, and the energy output of the energy supply side under different environmental conditions is predicted by the energy supply impact matrix model.

5. A microgrid composite energy storage system monitoring and control method according to claim 4, characterized in that: During the peak period of grid demand, energy storage is used to balance supply and demand and reduce electricity costs, including: Establishing the optimal price balance matrix of energy supply on the energy supply side and energy consumption on the user side includes the following sub-steps: Constructing the optimal price equilibrium matrix model ; in, is the supply and demand matrix, which represents the energy flow from the energy supply side to the user side, that is, the amount of energy provided by each energy supply side to each user side; is the cost-benefit matrix, which represents the cost or benefit of energy transmission from the energy supply side to the user side; represents the adjustment matrix; Analyze the optimal price balance matrix through machine learning models to obtain the optimal cost-benefit matrix ; Considering the power supply characteristics during the peak period of grid demand, an energy balance matrix model is constructed: ,in Represents the dispatch matrix of different energy supply sides and user sides in the power grid, that is, the power grid dispatch matrix; Indicates the energy supply on the energy supply side during peak hours, Indicates the energy demand at the user side during peak hours; Use replace After that, the optimal price equilibrium matrix model during peak hours becomes: ; The optimal price balance matrix during peak hours is analyzed through machine learning models to obtain the corresponding optimal cost-benefit matrix. The element value of .

6. A microgrid composite energy storage system monitoring and control method according to claim 5, characterized in that: The process of monitoring the energy provided by the energy supply side and the carbon emission value of the energy storage power used during the peak power period through the monitoring model, and optimizing the use of energy storage power to balance supply and demand, includes: Constructing the objective function ;in, Indicates different time periods or points in time; Indicates time point The energy balance matrix, Indicates time point The carbon emission factor, Indicates time point electricity price; The optimization algorithm Gurobi is used to solve the objective function and obtain the optimal solution of the objective function, that is, the optimal energy scheduling amount, so that the carbon emissions in the energy scheduling process are minimized.

7. A microgrid composite energy storage system monitoring and control method according to claim 6, characterized in that: The priority calling of energy provided by the energy supply side includes: Obtain wind power supply, photovoltaic power supply, electricity demand, carbon emission factors, power supply cost, and electricity cost at different time points to form a power supply time series; Extract wind power supply data from the power supply time series to form a wind power supply matrix ; Extract photovoltaic power supply data from the power supply time series to form a photovoltaic power supply matrix ; Get the power grid dispatch matrix ; Build a priority scheduling model: ； in, Indicates the demand of the user side at different time points; Carbon emission weight, represents the cost weight; Respectively indicate time points The amount of wind power and photovoltaic power supply at that time; represent the cost of wind power generation and photovoltaic power generation respectively; Indicates different time periods or points in time; They represent the carbon emission costs of wind power generation and photovoltaic power generation respectively; represents the minimum cost; Indicates the maximum capacity of the energy storage device; The optimization algorithm Gurobi is used to solve the priority scheduling model and obtain the wind power supply and photovoltaic scheduling solutions with the best power supply cost and carbon emissions.

8. A microgrid composite energy storage system monitoring and control method according to claim 7, characterized in that: The prioritization of energy provided by the energy supply side also includes: Construct the objective function to minimize the cost: ; in, Indicates time point Wind power generation and photovoltaic power generation; Set the priority constraint: If , , the power supply side of wind power generation will be used first; if , wind power generation is preferred; if , photovoltaic power generation is preferred; Use the optimization algorithm Gurobi to solve the cost minimization objective function and obtain the optimal and .

9. A microgrid composite energy storage system monitoring and control system, characterized in that: The system is used to execute a microgrid composite energy storage system monitoring and control method as described in any one of claims 1 to 8 above.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a microgrid composite energy storage system monitoring and control method as described in any one of claims 1 to 8.

Images