Micro-grid scheduling method and system

Abstract

The invention discloses a micro-grid scheduling method and system, and the method comprises the steps: obtaining historical load data and meteorological data in a micro-grid, so as to build a load prediction model, and generating a load prediction value of the micro-grid according to the load prediction model; according to the load prediction value, power generation power distribution of different types of power generation units in the micro-grid is optimized; and generating a scheduling instruction according to the optimized power generation power distribution so as to control the output power of each power generation unit. By utilizing the embodiment of the invention, the power distribution of the power generation units can be optimized, so that a reasonable dispatching instruction is generated, the output power of each power generation unit is efficiently controlled, the operation efficiency and the economical efficiency of the micro-grid can be improved, the adaptability of the micro-grid to emergencies can be enhanced, and a foundation is laid for realizing the target of a smart grid.

Description

Technical Field

[0001] The present invention belongs to the technical field of microgrids, and in particular to a scheduling method and system for microgrids. Background Art

[0002] As the global energy crisis and environmental degradation become increasingly serious, the use of clean energy and the development of microgrid technology have gradually become the key to solving these problems. Microgrids are local power systems composed of multiple distributed energy sources (such as wind energy, solar energy, energy storage equipment, etc.) and loads, which can operate autonomously and interact with the main power grid. Microgrids can not only improve energy utilization efficiency, but also enhance the reliability and flexibility of power systems. However, the current dispatching methods of microgrids still face the following challenges, such as insufficient load forecasting accuracy, unreasonable power distribution, insufficient real-time dispatching decisions, limited ability to integrate renewable energy, etc. This is an urgent problem to be solved. Summary of the invention

[0003] The purpose of the present invention is to provide a microgrid scheduling method and system to solve the deficiencies in the prior art, optimize the power distribution of power generation units, and generate reasonable scheduling instructions to efficiently control the output power of each power generation unit, which can not only improve the operating efficiency and economy of the microgrid, but also enhance its adaptability to emergencies, laying the foundation for achieving the goal of smart grids.

[0004] An embodiment of the present application provides a scheduling method for a microgrid, the method comprising: Acquire historical load data and meteorological data in the microgrid to establish a load forecasting model, and generate a load forecast value of the microgrid according to the load forecasting model; Optimizing the distribution of power generation of different types of power generation units in the microgrid according to the load forecast value; The dispatching instructions are generated according to the optimized power distribution to control the output power of each power generation unit.

[0005] Optionally, the load forecasting model is obtained based on LSTM model training; Generating a load prediction value of a microgrid according to the load prediction model includes: Based on the load forecasting model, the load forecast value at the current time point t is generated using the following formula: Among them, the is the load forecast value of the microgrid at the current time point t, is the weight of the first (tj) time point obtained by learning, is the historical load data of the microgrid at the previous (tj)th time point, is the historical meteorological data of the microgrid at the previous (tj) time point, is the activation function, is the bias term, is the number of time points.

[0006] Optionally, optimizing the power distribution of different types of power generation units in the microgrid according to the load forecast value includes: Multiple individuals are randomly generated to represent different power allocation schemes, where an individual P_t is represented by an array, and each element of the array represents the output power P(k, t) of each power generation unit at time point t. The output power of each power generation unit does not exceed the corresponding maximum power generation power, and the sum of the output power of all power generation units is equal to the sum of the load forecast values ​​of each energy unit. Calculate the fitness of each individual according to the objective function: Among them, the is the cost function of the kth power generation unit, is the environmental impact indicator, is a weight factor used to balance operating costs and environmental costs. is the number of power generation units; According to the fitness of each individual, an individual whose fitness is greater than a preset fitness threshold is selected, and crossover and mutation operations are performed on the selected individuals to obtain new individuals, and the selected individuals and the new individuals are used as the next generation individuals, wherein the output power of each power generation unit in each individual of the next generation individuals does not exceed the corresponding maximum power generation power, and the sum of the output powers of all power generation units is equal to the sum of the load prediction values ​​of each energy unit; Return to the step of calculating the fitness of each individual according to the objective function until the preset number of iterations is reached or the fitness converges, and the final generation of individuals is obtained; The individual with the highest fitness is selected from the final generation of individuals as the optimal power allocation scheme after optimization.

[0007] Optionally, generating a dispatch instruction according to the optimized power distribution to control the output power of each power generation unit includes: According to the optimized best power allocation scheme, a dispatch instruction is generated to indicate the power value that each power generation unit should output at time point t; The dispatching instructions are sent to each power generation unit through the microgrid control unit, so that each power generation unit adjusts the output power according to the corresponding dispatching instructions.

[0008] Another embodiment of the present application provides a microgrid dispatching system, the system comprising: An acquisition module is used to acquire historical load data and meteorological data in the microgrid to establish a load prediction model, and generate a load prediction value of the microgrid according to the load prediction model; An optimization module, used for optimizing the power distribution of various types of power generation units in the microgrid according to the load prediction value; The scheduling module is used to generate scheduling instructions according to the optimized power distribution to control the output power of each power generation unit.

[0009] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when running.

[0010] Yet another embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the methods described above.

[0011] Compared with the prior art, the present invention provides a microgrid scheduling method, which obtains historical load data and meteorological data in the microgrid to establish a load prediction model, and generates a load prediction value of the microgrid according to the load prediction model; optimizes the power distribution of different types of power generation units in the microgrid according to the load prediction value; generates a scheduling instruction according to the optimized power distribution to control the output power of each power generation unit, thereby optimizing the power distribution of the power generation unit, thereby generating reasonable scheduling instructions to efficiently control the output power of each power generation unit, which can not only improve the operating efficiency and economy of the microgrid, but also enhance its adaptability to emergencies, laying the foundation for achieving the goal of smart grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A hardware structure block diagram of a computer terminal for a microgrid scheduling method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a flow chart of a microgrid scheduling method provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a microgrid dispatching system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0013] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but should not be construed as limiting the present invention.

[0014] The embodiment of the present invention first provides a scheduling method for a microgrid, which can be applied to electronic devices such as computer terminals, specifically ordinary computers, etc.

[0015] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal of a microgrid scheduling method provided by an embodiment of the present invention. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0016] The memory 104 can be used to store software programs and modules of application software, such as program instructions / modules corresponding to the dispatching method of the microgrid in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0017] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0018] See also Figure 2 , an embodiment of the present invention provides a scheduling method for a microgrid, which may include the following steps: S201, acquiring historical load data and meteorological data in the microgrid to establish a load prediction model, and generating a load prediction value of the microgrid according to the load prediction model; In this step, the historical load data and meteorological data in the microgrid are first obtained. This process includes extracting the power consumption data (historical load data) at each time point and related meteorological information (such as temperature, humidity, wind speed, etc.) from the monitoring system of the microgrid. Subsequently, a load forecasting model is established based on these data, and by analyzing the rules and trends in the historical data, it is converted into a mathematical model that can be used to predict future loads.

[0019] Next, based on the established load forecasting model, the load forecast value of the microgrid is generated. This means using the model to calculate future loads and predict the power demand at a specific point in time. This forecast value will provide a basis for subsequent power generation scheduling and resource allocation, ensuring that the microgrid can operate efficiently under the condition of supply and demand balance. The implementation of this step is the basis for realizing intelligent scheduling and optimizing resource allocation.

[0020] Specifically, the load prediction model is obtained based on the LSTM model training; the load prediction value of the microgrid is generated according to the load prediction model, and the load prediction value at the current time point t can be generated based on the load prediction model using the following formula: Among them, the is the load forecast value of the microgrid at the current time point t, is the weight of the previous (tj) time point obtained by learning, which represents the influence of historical data on the current prediction. is the historical load data of the microgrid at the previous (tj) time point, reflecting the load situation at the past time point. is the historical meteorological data of the microgrid at the previous (tj)th time point, indicating how weather conditions affect the load. An activation function, such as a Sigmoid function or a hyperbolic tangent (Tanh) function, ensures the nonlinear characteristics of the model to better fit complex data relationships. is the corresponding bias term, which is used to adjust the output of the model. The number of time points defines the backtracking range of historical data.

[0021] The LSTM (Long Short-Term Memory) model has the advantage of processing time series data and can effectively remember information over a long span, thereby achieving efficient pattern recognition and prediction when faced with complex load and meteorological data. The formula is designed to combine historical data (load and meteorological factors) with the learned pattern to output a future load value associated with time, providing a scientific basis for the scheduling and power distribution of microgrids.

[0022] Specifically, we can first collect the historical load data and meteorological data of the microgrid and build a data set. We clean and standardize the collected data to eliminate noise and outliers and ensure the training effect of the model. We use the prepared historical data set to train the LSTM model and optimize the weights and bias terms so that it can effectively fit the load change pattern. We use the trained model to perform real-time load forecasting and calculate the load forecast value at the current time point t through the formula to provide data support for subsequent optimization and scheduling steps.

[0023] S202, optimizing the power distribution of different types of power generation units in the microgrid according to the load prediction value; After obtaining the load forecast value of the microgrid, the power generation of different types of power generation units (such as photovoltaic power generation, wind power generation, diesel power generation, etc.) in the microgrid is optimized and allocated according to these forecast values. This process usually involves comprehensive consideration of factors such as the output capacity, operating cost, and efficiency of each power generation unit to ensure the optimal operation of the system while meeting the load demand. Optimizing the distribution of power generation can effectively improve the overall efficiency of the microgrid, reduce operating costs, and enhance the reliability and flexibility of power supply. This process improves the utilization rate of renewable energy while reducing dependence on fossil fuels, which is conducive to achieving the goal of sustainable development. In addition, it can also improve the response capability of the microgrid under high or low load conditions and ensure the stability of power supply.

[0024] Specifically, multiple individuals can be randomly generated to represent different power allocation schemes, where an individual P_t is represented by an array, each element of the array represents the output power P(k,t) of each power generation unit at time point t, the output power of each power generation unit does not exceed the corresponding maximum power generation power, and the sum of the output powers of all power generation units is equal to the sum of the load forecast values ​​of each energy unit; In this step, multiple individuals are created through a random number generation algorithm, each of which represents a possible power generation allocation scheme. Each individual is represented by an array, where each element of the array corresponds to the output power of a different power generation unit at a specific time point. When generating these individuals, the maximum power generation limit of the power generation unit must be followed, and the sum of all output powers must be equal to the sum of the load forecast values.

[0025] By randomly generating multiple individuals, possible power allocation solutions can be initially explored, providing a variety of options for the subsequent optimization process. This process enables the optimization algorithm to find the best solution from multiple possible solutions and improve search efficiency.

[0026] A random number generation method (such as uniform distribution) can be used to assign initial power values ​​to each power generation unit to ensure that these values ​​are within their respective maximum output ranges, and all output powers can be adjusted through normalization so that their sum is equal to the load forecast value.

[0027] Calculate the fitness of each individual according to the objective function: Among them, the is the cost function of the kth power generation unit, is the environmental impact indicator, is a weight factor used to balance operating costs and environmental costs. is the number of power generation units; In this step, the fitness value of each individual is calculated using the defined objective function. The fitness value reflects the economic and environmental benefits that the individual can bring while meeting the load forecast requirements. The fitness calculation includes the operating costs and environmental impacts of each power generation unit. The higher the fitness of the individual, the better its solution.

[0028] Calculating fitness enables the optimization calculation to distinguish the advantages and disadvantages of different solutions and enhance the basis of algorithm selectivity. This step ensures that the power allocation solution finally selected has the best economic and environmental benefits, reducing operating costs and environmental impact. For each individual, the fitness value is calculated through the formula using the collected power generation unit cost data and environmental indicator data. Ensure that in the calculation of the fitness value, the weight factor Reasonable settings to balance economic and environmental impacts.

[0029] According to the fitness of each individual, an individual whose fitness is greater than a preset fitness threshold is selected, and crossover and mutation operations are performed on the selected individuals to obtain new individuals, and the selected individuals and the new individuals are used as the next generation individuals, wherein the output power of each power generation unit in each individual of the next generation individuals does not exceed the corresponding maximum power generation power, and the sum of the output powers of all power generation units is equal to the sum of the load prediction values ​​of each energy unit; This step includes selecting individuals with fitness higher than a preset threshold and performing crossover and mutation operations in the genetic algorithm to generate new individuals. The generated new individuals will be included in the next round of optimization to maintain the diversity of the genetic algorithm. By selecting individuals with higher fitness for genetic operations, effective solution information can be retained and new potential solutions can be generated. This process helps to accelerate convergence and maintain the diversity of the population, increasing the possibility of finding the optimal solution.

[0030] A fitness threshold can be set to screen out qualified individuals. Then, individuals are selected through a selection algorithm (such as tournament selection), and new individuals are generated using crossover and mutation operations (such as single-point crossover and random mutation) to ensure that the output power requirements of the load forecast are met.

[0031] Return to the step of calculating the fitness of each individual according to the objective function until the preset number of iterations is reached or the fitness converges, and the final generation of individuals is obtained; In this step, we return to the fitness calculation step and continue to perform multiple generations of calculations until the preset number of iterations or fitness value convergence conditions are met. This process will continuously improve the individuals and thus improve the fitness of the entire population. Through multiple rounds of iterations, the quality of the selected power allocation scheme can be effectively improved to ensure that it can continuously approach the optimal solution. This process is the core mechanism of the genetic algorithm, ensuring that the optimal power allocation strategy is found.

[0032] The maximum number of iterations and convergence criteria (such as the fitness change is less than a certain threshold) can be set, and the process of calculating fitness and generating new individuals is repeated in each iteration until the stopping condition is met.

[0033] The individual with the highest fitness is selected from the final generation of individuals as the optimal power allocation scheme after optimization.

[0034] After all iterations are completed, the individual with the highest fitness value is selected from the final population as the final power allocation plan. This individual represents the best solution under the given constraints. This step ensures that the most suitable power allocation plan can be selected, providing the best basis for the dispatch of the microgrid and ensuring both economic and environmental friendliness. The fitness values ​​of all final generation individuals are sorted, and the individual with the highest fitness value is selected as the output optimal power allocation plan, which is recorded and analyzed for subsequent dispatch instruction generation.

[0035] S203, generating a dispatching instruction according to the optimized power distribution to control the output power of each power generation unit.

[0036] Based on the optimized power distribution, dispatch instructions are generated to control the output power of each power generation unit. This process involves converting the optimization results into specific control instructions to ensure that each power generation unit operates according to the predetermined power output. Generating dispatch instructions is a key step in achieving effective operation of the microgrid. By accurately controlling the output power of each power generation unit, it can ensure that the microgrid can optimize operating efficiency, reduce operating costs, and maximize the use of renewable energy while meeting load demand. This process also helps to improve the stability and flexibility of power supply and ensure timely adjustments when load fluctuates.

[0037] Specifically, a dispatch instruction may be generated according to the optimized best power allocation scheme to indicate the power value that each power generation unit should output at time point t; Specific dispatching instructions are formulated using the optimized best power allocation scheme. These instructions include the power value that each power generation unit should output at a specific time point, ensuring a clear control basis for the operation of the microgrid. This step ensures that the microgrid can accurately implement the optimization results and promote the scientificity and rationality of power distribution. Through clear dispatching instructions, each power generation unit can operate in an orderly manner, improve energy utilization efficiency, reduce energy waste, and enhance the overall performance and reliability of the microgrid. The power value of each power generation unit in the optimized power allocation scheme can be extracted to form a dispatching instruction list, which contains the unique identification of each power generation unit and its corresponding power output instruction.

[0038] The dispatching instructions are sent to each power generation unit through the microgrid control unit, so that each power generation unit adjusts the output power according to the corresponding dispatching instructions.

[0039] In this step, the dispatching instructions are sent to each power generation unit through the microgrid control unit to ensure that each power generation unit can receive specific power adjustment instructions and adjust its output power as required. This step is the key to the execution of the dispatching scheme. It converts the results of the optimization calculation into actual operations, ensures that the microgrid can respond to changes in load demand in real time, and improves the flexibility and stability of the overall system. The dispatching instructions can be sent to each power generation unit in a standardized format through the communication module of the microgrid control unit (such as wireless communication, PLC, etc.), ensuring that each power generation unit adjusts its output power according to the received instructions. The system monitoring module provides real-time feedback on the status of each unit to ensure that the instructions are effectively executed.

[0040] It can be seen that historical load data and meteorological data in the microgrid are obtained to establish a load forecasting model, and the load forecast value of the microgrid is generated according to the load forecasting model; according to the load forecast value, the power distribution of different types of power generation units in the microgrid is optimized; according to the optimized power distribution, a dispatching instruction is generated to control the output power of each power generation unit, so as to optimize the power distribution of the power generation unit, thereby generating reasonable dispatching instructions to efficiently control the output power of each power generation unit, which can not only improve the operating efficiency and economy of the microgrid, but also enhance its adaptability to emergencies, laying the foundation for achieving the goal of smart grid.

[0041] Another embodiment of the present invention provides a microgrid dispatching system, see Figure 3 , the system may include: The acquisition module 301 is used to acquire historical load data and meteorological data in the microgrid to establish a load prediction model, and generate a load prediction value of the microgrid according to the load prediction model; An optimization module 302, configured to optimize the power distribution of different types of power generation units in the microgrid according to the load prediction value; The scheduling module 303 is used to generate a scheduling instruction according to the optimized power distribution to control the output power of each power generation unit.

[0042] It can be seen that historical load data and meteorological data in the microgrid are obtained to establish a load forecasting model, and the load forecast value of the microgrid is generated according to the load forecasting model; according to the load forecast value, the power distribution of different types of power generation units in the microgrid is optimized; according to the optimized power distribution, a dispatching instruction is generated to control the output power of each power generation unit, so as to optimize the power distribution of the power generation unit, thereby generating reasonable dispatching instructions to efficiently control the output power of each power generation unit, which can not only improve the operating efficiency and economy of the microgrid, but also enhance its adaptability to emergencies, laying the foundation for achieving the goal of smart grid.

[0043] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0044] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps: S201, acquiring historical load data and meteorological data in the microgrid to establish a load prediction model, and generating a load prediction value of the microgrid according to the load prediction model; S202, optimizing the power distribution of different types of power generation units in the microgrid according to the load prediction value; S203, generating a dispatching instruction according to the optimized power distribution to control the output power of each power generation unit.

[0045] It can be seen that historical load data and meteorological data in the microgrid are obtained to establish a load forecasting model, and the load forecast value of the microgrid is generated according to the load forecasting model; according to the load forecast value, the power distribution of different types of power generation units in the microgrid is optimized; according to the optimized power distribution, a dispatching instruction is generated to control the output power of each power generation unit, so as to optimize the power distribution of the power generation unit, thereby generating reasonable dispatching instructions to efficiently control the output power of each power generation unit, which can not only improve the operating efficiency and economy of the microgrid, but also enhance its adaptability to emergencies, laying the foundation for achieving the goal of smart grid.

[0046] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0047] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0048] Specifically, in this embodiment, the processor may be configured to perform the following steps through a computer program: S201, acquiring historical load data and meteorological data in the microgrid to establish a load prediction model, and generating a load prediction value of the microgrid according to the load prediction model; S202, optimizing the power distribution of different types of power generation units in the microgrid according to the load prediction value; S203, generating a dispatching instruction according to the optimized power distribution to control the output power of each power generation unit.

[0049] It can be seen that historical load data and meteorological data in the microgrid are obtained to establish a load forecasting model, and the load forecast value of the microgrid is generated according to the load forecasting model; according to the load forecast value, the power distribution of different types of power generation units in the microgrid is optimized; according to the optimized power distribution, a dispatching instruction is generated to control the output power of each power generation unit, so as to optimize the power distribution of the power generation unit, thereby generating reasonable dispatching instructions to efficiently control the output power of each power generation unit, which can not only improve the operating efficiency and economy of the microgrid, but also enhance its adaptability to emergencies, laying the foundation for achieving the goal of smart grid.

[0050] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the drawings. Any changes made according to the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the description and drawings, should be within the protection scope of the present invention.

Claims

1. A microgrid dispatching method, characterized in that: The method comprises: Acquire historical load data and meteorological data in the microgrid to establish a load forecasting model, and generate a load forecast value of the microgrid according to the load forecasting model; Optimizing the distribution of power generation of different types of power generation units in the microgrid according to the load forecast value; The dispatching instructions are generated according to the optimized power distribution to control the output power of each power generation unit.

2. The method according to claim 1, characterized in that The load forecasting model is obtained based on LSTM model training; Generating a load prediction value of a microgrid according to the load prediction model includes: Based on the load forecasting model, the load forecast value at the current time point t is generated using the following formula: Among them, the is the load forecast value of the microgrid at the current time point t, is the weight of the first (tj) time point obtained by learning, is the historical load data of the microgrid at the previous (tj)th time point, is the historical meteorological data of the microgrid at the previous (tj) time point, is the activation function, is the bias term, is the number of time points.

3. The method according to claim 2, characterized in that The optimizing the power distribution of different types of power generation units in the microgrid according to the load prediction value includes: Multiple individuals are randomly generated to represent different power allocation schemes, where an individual P_t is represented by an array, and each element of the array represents the output power P(k, t) of each power generation unit at time point t. The output power of each power generation unit does not exceed the corresponding maximum power generation power, and the sum of the output power of all power generation units is equal to the sum of the load forecast values ​​of each energy unit. Calculate the fitness of each individual according to the objective function: Among them, the is the cost function of the kth power generation unit, is the environmental impact indicator, is a weight factor used to balance operating costs and environmental costs. is the number of power generation units; According to the fitness of each individual, an individual whose fitness is greater than a preset fitness threshold is selected, and crossover and mutation operations are performed on the selected individuals to obtain new individuals, and the selected individuals and the new individuals are used as the next generation individuals, wherein the output power of each power generation unit in each individual of the next generation individuals does not exceed the corresponding maximum power generation power, and the sum of the output powers of all power generation units is equal to the sum of the load prediction values ​​of each energy unit; Return to the step of calculating the fitness of each individual according to the objective function until the preset number of iterations is reached or the fitness converges, and the final generation of individuals is obtained; The individual with the highest fitness is selected from the final generation of individuals as the optimal power allocation scheme after optimization.

4. The method according to claim 3, characterized in that Generating a dispatch instruction according to the optimized power distribution to control the output power of each power generation unit includes: According to the optimized best power allocation scheme, a dispatch instruction is generated to indicate the power value that each power generation unit should output at time point t; The dispatching instructions are sent to each power generation unit through the microgrid control unit, so that each power generation unit adjusts the output power according to the corresponding dispatching instructions.

5. A microgrid dispatching system, characterized in that: The system comprises: An acquisition module is used to acquire historical load data and meteorological data in the microgrid to establish a load prediction model, and generate a load prediction value of the microgrid according to the load prediction model; An optimization module, used for optimizing the power distribution of various types of power generation units in the microgrid according to the load prediction value; The scheduling module is used to generate scheduling instructions according to the optimized power distribution to control the output power of each power generation unit.

6. The system according to claim 5, characterized in that The load forecasting model is obtained based on LSTM model training; the acquisition module is specifically used for: Based on the load forecasting model, the load forecast value at the current time point t is generated using the following formula: Among them, the is the load forecast value of the microgrid at the current time point t, is the weight of the first (tj) time point obtained by learning, is the historical load data of the microgrid at the previous (tj)th time point, is the historical meteorological data of the microgrid at the previous (tj) time point, is the activation function, is the bias term, is the number of time points.

7. The system according to claim 6, characterized in that The optimization module is specifically used for: Multiple individuals are randomly generated to represent different power allocation schemes, where an individual P_t is represented by an array, and each element of the array represents the output power P(k, t) of each power generation unit at time point t. The output power of each power generation unit does not exceed the corresponding maximum power generation power, and the sum of the output power of all power generation units is equal to the sum of the load forecast values ​​of each energy unit. Calculate the fitness of each individual according to the objective function: Among them, the is the cost function of the kth power generation unit, is the environmental impact indicator, is a weight factor used to balance operating costs and environmental costs. is the number of power generation units; According to the fitness of each individual, an individual whose fitness is greater than a preset fitness threshold is selected, and crossover and mutation operations are performed on the selected individuals to obtain new individuals, and the selected individuals and the new individuals are used as the next generation individuals, wherein the output power of each power generation unit in each individual of the next generation individuals does not exceed the corresponding maximum power generation power, and the sum of the output powers of all power generation units is equal to the sum of the load prediction values ​​of each energy unit; Return to the step of calculating the fitness of each individual according to the objective function until the preset number of iterations is reached or the fitness converges, and the final generation of individuals is obtained; The individual with the highest fitness is selected from the final generation of individuals as the optimal power allocation scheme after optimization.

8. The system according to claim 7, characterized in that The scheduling module is specifically used for: According to the optimized best power allocation scheme, a dispatch instruction is generated to indicate the power value that each power generation unit should output at time point t; The dispatching instructions are sent to each power generation unit through the microgrid control unit, so that each power generation unit adjusts the output power according to the corresponding dispatching instructions.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 4 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 4.

Images