Micro-grid energy scheduling method and device based on improved difference algorithm, and medium

Abstract

The invention discloses a micro-grid energy scheduling method and device based on an improved difference algorithm and a medium, and the method comprises the steps: predicting photovoltaic output power, load and charging pile demand power based on a pre-constructed algorithm model in combination with historical data, and determining the charging and discharging power of an energy storage device based on a pre-constructed energy storage power model; establishing a dual-objective function, and determining a corresponding constraint condition in combination with the photovoltaic output power, the load and charging pile demand power and the charging and discharging power of the energy storage equipment; dividing a power consumption time period, and checking whether the number of iterations of the algorithm reaches the maximum number of iterations by improving a difference algorithm so as to determine an optimal iteration result; and according to an iterative optimal result, through an energy router and a controller, controlling output of photovoltaic equipment, charging and discharging of energy storage equipment and an electricity purchasing strategy of a main power grid, and adjusting a load demand and the power of a charging pile so as to realize energy scheduling of the micro-grid.

Description

Technical Field

[0001] This application relates to the technical field of energy management, and particularly to a microgrid energy scheduling method, device, and medium based on an improved differential algorithm. Background Art

[0002] With the rapid development of the global energy structure transformation and renewable energy technologies, large-scale distributed resources have gradually been connected to medium and low voltage distribution grids. While promoting the low-carbonization of the energy system, it has also brought a series of challenges to the system, such as voltage over-limit and power flow fluctuations. Facing a large number of controllable resources, it is difficult for the power grid to directly regulate and control. Aggregating and regulating distributed resources relying on a microgrid is an effective solution.

[0003] However, there are still significant defects in the existing microgrid scheduling technologies in practical applications. Renewable energy sources such as photovoltaic and wind power are greatly affected by complex weather conditions, and the prediction accuracy of their power output fluctuates significantly. The existing prediction models lack robustness in variable scenarios, resulting in a decrease in the credibility of the basic data for scheduling optimization. The charge and discharge states of energy storage devices, the regulation requirements of flexible loads, and the operation modes of electric vehicle charging piles have strong time-coupling characteristics. Traditional time-segment independent optimization strategies are difficult to achieve the global optimal solution on the full time scale, while multi-dimensional spatio-temporal correlation modeling leads to a sharp increase in the complexity of the optimization model, and it is difficult for existing algorithms to solve efficiently. For large-scale high-dimensional non-linear optimization problems, the traditional differential evolution algorithm is prone to falling into local optima and has insufficient convergence speed, and it is difficult to meet the timeliness requirements of microgrid real-time scheduling in dynamic time-varying scenarios. Summary of the Invention

[0004] Embodiments of this application provide a microgrid energy scheduling method, device, and medium based on an improved differential algorithm to solve the above technical problems.

[0005] On the one hand, embodiments of this application provide a microgrid energy scheduling method based on an improved differential algorithm, including: Based on a pre-constructed algorithm model and combined with historical data, predicting the photovoltaic output power, load, and charging pile demand power, and determining the charge and discharge power of the energy storage device based on a pre-built energy storage power model; Building a dual-objective function and determining corresponding constraint conditions in combination with the photovoltaic output power, the load, the charging pile demand power, and the charge and discharge power of the energy storage device; Dividing the power consumption period and checking whether the number of algorithm iterations reaches the maximum number of iterations through an improved differential algorithm to determine the iterative optimal result; According to the iterative optimal result, and through an energy router and a controller, controlling the output of photovoltaic devices, the charge and discharge of energy storage devices, and the main grid power purchase strategy, and adjusting the load demand and charging pile power to achieve microgrid energy scheduling.

[0006] In an implementation manner of the present application, before predicting the photovoltaic output power, load, and charging pile demand power based on a pre-constructed algorithm model and combined with historical data, the method further includes: Classify the photovoltaic power generation data through cluster analysis, and extract the photovoltaic power generation characteristics through the Pearson correlation coefficient; Perform dimensionality reduction processing on the high-dimensional photovoltaic power generation data through the principal component analysis method, and analyze multiple influencing factors of photovoltaic power generation prediction based on the dimensionality-reduced photovoltaic power generation data to determine the corresponding main influencing factors; Among them, the main influencing factors include: irradiance, temperature, and weather type, and the weather type includes: sunny, rainy, and complex weather.

[0007] In an implementation manner of the present application, based on a pre-constructed algorithm model and combined with historical data, predict the photovoltaic output power, load, and charging pile demand power, and determine the charging and discharging power of the energy storage device based on a pre-built energy storage power model, specifically including: Construct a fusion prediction model corresponding to various weather types based on the sparrow search algorithm, convolutional neural network, and bidirectional long short-term memory network; For each weather type, output the irradiance prediction value and temperature prediction value corresponding to the weather type through the fusion prediction model, and calculate the photovoltaic output power prediction value corresponding to the weather type according to the irradiance prediction value and the temperature prediction value; Obtain historical data, determine the holiday characteristics corresponding to the historical data, and predict the load and charging pile demand power based on the historical data and the holiday characteristics through a machine learning algorithm; Based on a pre-constructed energy storage device power model, and combined with the energy and efficiency of the energy storage device in the charging and discharging states, calculate the charging and discharging power and remaining capacity of the energy storage device.

[0008] In an implementation manner of the present application, calculate the photovoltaic output power prediction value corresponding to the weather type according to the irradiance prediction value and the temperature prediction value, specifically including: Calculate the photovoltaic output power prediction value through the following formula:

[0009] Among them, represents the predicted output power value of the photovoltaic device, represents the rated output power of the photovoltaic device, represents the irradiance prediction value, represents the maximum irradiance generated by the photovoltaic device under the maximum solar radiation, represents the temperature coefficient, represents the predicted temperature value, represents the standard reference temperature.

[0010] In one implementation of the present application, a dual-objective function is constructed, and in combination with the photovoltaic output power, the load and the charging pile demand power, and the charging and discharging power of the energy storage device, corresponding constraint conditions are determined, specifically including: Construct a dual-objective function, and adjust the weighting coefficient of the dual-objective function according to actual needs to minimize the weighted sum of the economic cost and the carbon emission cost; Determine that the sum of the power generation powers in each time period in the microgrid is equal to the sum of the load demand and the charging and discharging power of the energy storage device; Based on the power model of the energy storage device, determine the maximum capacity of the energy storage device, and according to the maximum capacity of the energy storage device, determine the energy range of the energy storage device in the charging state and the energy range of the energy storage device in the discharging state; Based on the preset maximum power of electricity, determine the power acquisition range of the microgrid; wherein, the maximum power of electricity is determined according to the maximum power obtained from the main power supply at any moment.

[0011] In one implementation of the present application, determining that the sum of the power generation powers in each time period in the microgrid is equal to the sum of the load demand and the charging and discharging power of the energy storage device specifically includes: It is represented by the following formula:

[0012] wherein, represents the load power in the microgrid at time period, represents the line loss power of the electric energy transmitted in the microgrid at time period, represents the charging and discharging power of the energy storage device at time period, represents the active power output by each power generation unit at time period, represents the power obtained from the microgrid at time period.

[0013] In one implementation of the present application, the power consumption time period is divided, and by improving the differential algorithm, it is checked whether the number of algorithm iterations reaches the maximum number of iterations to determine the optimal iteration result, specifically including: Establish a microgrid and a load model, and divide the power consumption time period according to the change of the load demand; wherein, the power consumption time period includes peak time period, normal time period and valley time period; For each power consumption period, by improving the differential algorithm, determine whether the output power of the renewable energy device reaches the consumption power corresponding to the power consumption period.

[0014] In an implementation manner of the present application, for each power consumption period, by improving the differential algorithm, determine whether the output power of the renewable energy device reaches the consumption power corresponding to the power consumption period, specifically including: If not, then supplement the power supply through the main power grid and the energy storage device; If so, store the remaining power output by the renewable energy device in the energy storage device until the maximum number of iterations is reached, and output the corresponding iterative optimal result; Wherein, the remaining power is used to represent the difference between the total output power of the renewable energy device and the power consumption.

[0015] On the other hand, the embodiment of the present application also provides a microgrid energy scheduling device based on the improved differential algorithm, and the device includes: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the microgrid energy scheduling method based on the improved differential algorithm as described above.

[0016] On the other hand, the embodiment of the present application also provides a non-volatile computer storage medium storing computer-executable instructions, and when the computer-executable instructions are executed, the microgrid energy scheduling method based on the improved differential algorithm as described above is implemented.

[0017] The embodiment of the present application provides a microgrid energy scheduling method, device and medium based on the improved differential algorithm, including at least the following beneficial effects: BRIEF DESCRIPTION OF THE DRAWINGS The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation to the present application. In the drawings: Figure 1 It is a flowchart of the microgrid energy scheduling method based on the improved differential algorithm provided by the embodiment of the present application; Figure 2 It is an internal structure diagram of the microgrid energy scheduling device based on the improved differential algorithm provided by the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments of this application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts belong to the scope of protection of this application.

[0019] The following will, in conjunction with the drawings, elaborate on the technical solutions provided by each embodiment of this application.

[0020] Figure 1 It is a schematic flowchart of the microgrid energy scheduling method based on an improved differential algorithm provided by an embodiment of this application.

[0021] The implementation of the analysis method involved in the embodiments of this application can be a terminal device or a server, and this application does not impose special restrictions on this. For the convenience of understanding and description, the following embodiments will be described in detail using a server as an example.

[0022] It should be noted that this server can be a single device or a system composed of multiple devices, that is, a distributed server, and this application does not make specific limitations on this.

[0023] As Figure 1 shown, the microgrid energy scheduling method based on an improved differential algorithm provided by the embodiments of this application includes: 101. Based on a pre-constructed algorithm model and in combination with historical data, predict the photovoltaic output power, load, and charging pile demand power, and determine the charging and discharging power of the energy storage device based on a pre-built energy storage power model.

[0024] Specifically, in an embodiment of this application, first, classify the photovoltaic power generation data through cluster analysis, analyze its important features using the Pearson correlation coefficient, and use principal component analysis (PCA) to reduce the dimension of high-dimensional data, analyze the factors affecting the accuracy of photovoltaic power generation prediction, and obtain the main influencing factors.

[0025] It should be noted that the main influencing factors in the embodiments of this application include irradiance, temperature, and weather type, and the weather type includes sunny days, rainy days, and complex weather.

[0026] In one embodiment, combine the sparrow search algorithm, convolutional neural network, and bidirectional long short-term memory network theory to establish an SSA-CNN-BiLSTM prediction method, and build a fusion prediction model for three weather types: sunny days, rainy days, and complex weather.

[0027] In this way, for each weather type, the irradiance and temperature under the corresponding weather type can be predicted through the fusion prediction model, and then the irradiance and temperature under different weather types can be predicted. Then, according to the predicted irradiance value and temperature prediction value, the predicted photovoltaic output power value corresponding to the weather type is calculated.

[0028] Secondly, based on factors such as historical data and holidays, and combined with machine learning algorithms, the load and the required power of the charging pile are predicted. Moreover, a power model of the energy storage device is constructed. The energy storage device needs to consider the stored energy of the battery and the charge and discharge power constraints. Therefore, based on the pre-constructed power model of the energy storage device, and combined with the energy and efficiency of the energy storage device in the charge and discharge states, the charge and discharge power and the remaining capacity of the energy storage device can be calculated.

[0029] The power model of the energy storage device is represented by the following formula:

[0030] It should be noted that in the embodiments of the present application, SOC(t) represents t the remaining capacity of the energy storage device at time , respectively represent the energies in the charge and discharge states, , respectively represent the efficiencies in the charge and discharge processes.

[0031] In one embodiment, the predicted photovoltaic output power value is calculated by the following formula:

[0032] It should be noted that in the embodiments of the present application, represents the predicted output power value of the photovoltaic device, represents the rated output power of the photovoltaic device, represents the predicted irradiance value, represents the maximum irradiance that the photovoltaic device can generate under the maximum solar radiation, represents the temperature coefficient, represents the predicted temperature value, represents the standard reference temperature.

[0033] 102. Build a dual-objective function, and combine the photovoltaic output power, the load and the required power of the charging pile, and the charge and discharge power of the energy storage device to determine the corresponding constraint conditions.

[0034] Specifically, in an embodiment of the present application, there are the following objective requirements: First, minimize the weighted sum of power generation cost, energy storage cost, electricity purchase cost, charging pile operation cost, charging pile operation revenue, etc. Second, minimize the weighted sum of pollutant emission cost, carbon emission cost, etc. For the dual objectives of economy and environment, according to the different requirements of the park for economy and environmental friendliness, different weighting coefficients are set to balance the relationship between the two. According to actual needs, the weighting coefficients of the dual-objective function are adjusted to minimize the weighted sum of economic cost and carbon emission cost.

[0035] When setting the constraint conditions, it includes power balance constraint, energy storage system state constraint, and maximum demand constraint. The power balance constraint is that the sum of the power generation powers in each time period within the microgrid is equal to the load demand plus the sum of the charging and discharging powers of the energy storage system. The energy storage system state constraint is that the state of charge of the energy storage system is within the specified range, and the charging and discharging powers are also within the specified range. Based on the power model of the energy storage device, the maximum capacity of the energy storage device can be determined. According to the maximum capacity of the energy storage device, the energy range of the energy storage device in the charging state and the energy range of the energy storage device in the discharging state can be determined. , , where 、 respectively represent the energies in the charging and discharging states, SOC max represents the maximum capacity of the energy storage device.

[0036] The maximum demand constraint requires that the power obtained by the microgrid from the main power supply is within the specified range. , where P x-max represents the maximum power of the electricity obtained from the main power supply at any moment set.

[0037] In an embodiment, the power balance constraint is represented by the following formula:

[0038] where represents the load power within the microgrid in the time period, represents the line loss power of the electric energy transmitted within the microgrid in the time period, represents the charging and discharging power of the energy storage device in the time period, represents

[0039] 103. Divide the power consumption periods, and by improving the differential algorithm, check whether the number of algorithm iterations reaches the maximum number of iterations to determine the optimal iterative result.

[0040] Specifically, in an embodiment of the present application, relevant parameters are set for each device in the multi - microgrid system, a microgrid and a load model are established, and according to the change of load data, the power consumption periods are divided into peak periods, normal periods, and valley periods.

[0041] Use the IDE algorithm to optimize the multi - microgrid system. In this process, make full use of renewable energy devices to maximize the advantages of renewable energy devices. For each power consumption period, by improving the differential algorithm, determine whether the output power of the renewable energy device reaches the consumption power corresponding to the power consumption period.

[0042] In an embodiment, due to the uncertainty of renewable energy output, there are two situations: the output power of the renewable energy device is less than the consumption power corresponding to the power consumption period, and the output power of the renewable energy device is greater than the consumption power corresponding to the power consumption period. And any power shortage can be supplemented by the main grid and energy storage devices. When the output power of the renewable energy device is less than the consumption power corresponding to the power consumption period, the main grid and energy storage devices supply power for supplementation. When the output power of the renewable energy device is greater than the consumption power corresponding to the power consumption period, there will be surplus output power of the renewable energy device, and at this time, the surplus power is stored in the energy storage device.

[0043] When the IDE algorithm outputs the optimal result and reaches the maximum number of iterations, output the optimal result. If the IDE algorithm has not reached the maximum number of iterations, continue to optimize the microgrid system until the maximum number of iterations is reached.

[0044] 104. According to the optimal iterative result, and through the energy router and controller, control the output of photovoltaic devices, the charge and discharge of energy storage devices, and the power purchase strategy of the main grid, and adjust the load demand and the power of charging piles to achieve microgrid energy scheduling.

[0045] In an embodiment, according to the predicted load demand and the output of renewable energy devices, control the output of each photovoltaic device to ensure power balance. According to the predicted load demand and renewable energy output, control the charge and discharge of the energy storage system to achieve peak shaving and valley filling and improve the utilization rate of renewable energy.

[0046] According to the predicted load demand and renewable energy output, determine the power purchase strategy for purchasing electricity from the main grid in each period, and when the overall load power of the microgrid system exceeds the maximum demand, stop or reduce the power supply of the charging piles, or reduce the power supply of flexible loads. When implementing the strategy, implement the scheduling strategy into the campus microgrid through the energy router and controller.

[0047] The above are the method embodiments proposed in this application. Based on the same inventive concept, the embodiments of this application also provide a microgrid energy scheduling device based on an improved differential algorithm, and its structure is as Figure 2 shown.

[0048] Figure 2 It is a schematic internal structure diagram of the microgrid energy scheduling device based on the improved differential algorithm provided by the embodiments of this application. As Figure 2 shown, the device includes: At least one processor; And a memory communicatively connected to at least one processor; Wherein, the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor so that at least one processor can: Based on a pre-constructed algorithm model and combined with historical data, predict the photovoltaic output power, load and charging pile demand power, and determine the charging and discharging power of the energy storage device based on a pre-built energy storage power model; Build a dual-objective function, and combine the photovoltaic output power, load, charging pile demand power, and charging and discharging power of the energy storage device to determine the corresponding constraint conditions; Divide the power consumption period, and check whether the number of algorithm iterations reaches the maximum number of iterations through the improved differential algorithm to determine the iterative optimal result; According to the iterative optimal result, and through the energy router and controller, control the output of the photovoltaic device, the charging and discharging of the energy storage device, and the main grid power purchase strategy, and adjust the load demand and charging pile power to achieve microgrid energy scheduling.

[0049] The embodiments of this application also provide a non-volatile computer storage medium storing computer-executable instructions that, when executed, can: Based on a pre-constructed algorithm model and combined with historical data, predict the photovoltaic output power, load and charging pile demand power, and determine the charging and discharging power of the energy storage device based on a pre-built energy storage power model; Build a dual-objective function, and combine the photovoltaic output power, load, charging pile demand power, and charging and discharging power of the energy storage device to determine the corresponding constraint conditions; Divide the power consumption period, and check whether the number of algorithm iterations reaches the maximum number of iterations through the improved differential algorithm to determine the iterative optimal result; According to the iterative optimal result, and through the energy router and controller, control the output of the photovoltaic device, the charging and discharging of the energy storage device, and the main grid power purchase strategy, and adjust the load demand and charging pile power to achieve microgrid energy scheduling.

[0050] The various embodiments in this application are described in a progressive manner. For the same or similar parts among the various embodiments, reference can be made to each other, and the key points of each embodiment are the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiments.

[0051] The devices and media provided in the embodiments of this application correspond one by one to the methods. Therefore, the devices and media also have beneficial technical effects similar to those of their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be elaborated here.

[0052] Those skilled in the art should understand that the embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0053] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0054] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0055] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 steps of the functions specified in one block or multiple blocks.

[0056] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0057] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0058] Computer-readable media includes permanent and non-permanent, removable and non-removable media and can be implemented by any method or technology for information storage. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0059] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, commodity or device comprising the element.

[0060] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A microgrid energy dispatching method based on an improved differential algorithm, characterized in that: The method comprises: Based on the pre-built algorithm model and combined with historical data, the photovoltaic output power, load and charging pile demand power are predicted, and the charging and discharging power of the energy storage equipment is determined based on the pre-built energy storage power model; Construct a dual objective function, and determine the corresponding constraint conditions in combination with the photovoltaic output power, the load and charging pile required power, and the charging and discharging power of the energy storage device; Divide the power consumption period, and check whether the number of algorithm iterations reaches the maximum number of iterations by improving the differential algorithm to determine the optimal iteration result; According to the iterative optimal result, and through the energy router and controller, the output of photovoltaic equipment, the charging and discharging of energy storage equipment and the power purchase strategy of the main power grid are controlled, and the load demand and charging pile power are adjusted to realize the energy dispatch of the microgrid.

2. The microgrid energy dispatching method based on the improved differential algorithm according to claim 1 is characterized in that: Before predicting the photovoltaic output power, load and charging pile required power based on the pre-built algorithm model and in combination with historical data, the method further includes: The photovoltaic power generation data were classified by cluster analysis, and the photovoltaic power generation characteristics were extracted by Pearson correlation coefficient; The high-dimensional photovoltaic power generation data is reduced in dimension by principal component analysis, and multiple influencing factors of photovoltaic power generation prediction are analyzed based on the photovoltaic power generation data after dimension reduction to determine the corresponding main influencing factors; Among them, the main influencing factors include: radiation, temperature and weather type, and the weather type includes: sunny day, rainy day and complex weather.

3. The microgrid energy dispatching method based on the improved differential algorithm according to claim 1 is characterized in that: Based on the pre-built algorithm model and combined with historical data, the photovoltaic output power, load and charging pile demand power are predicted, and the charging and discharging power of the energy storage equipment is determined based on the pre-built energy storage power model, including: Based on the sparrow search algorithm, convolutional neural network and bidirectional long short-term memory network, a fusion prediction model corresponding to various weather types is constructed; For each weather type, outputting the radiation prediction value and the temperature prediction value corresponding to the weather type through the fusion prediction model, and calculating the photovoltaic output power prediction value corresponding to the weather type according to the radiation prediction value and the temperature prediction value; Acquire historical data, determine holiday characteristics corresponding to the historical data, and predict load and charging pile power requirements based on the historical data and the holiday characteristics and through a machine learning algorithm; Based on the pre-built energy storage device power model and combined with the energy and efficiency of the energy storage device in the charging and discharging state, the charging and discharging power and remaining capacity of the energy storage device are calculated.

4. The microgrid energy dispatching method based on the improved differential algorithm according to claim 3 is characterized in that: Calculating the photovoltaic output power prediction value corresponding to the weather type according to the irradiance prediction value and the temperature prediction value, specifically including: The predicted photovoltaic output power is calculated using the following formula: in, represents the predicted output power of the photovoltaic device, Indicates the rated output power of the photovoltaic equipment. represents the predicted value of radiosity, It indicates the maximum irradiance generated by the photovoltaic device under the maximum solar radiation. represents the temperature coefficient, represents the predicted temperature value, Indicates standard reference temperature.

5. The microgrid energy dispatching method based on improved differential algorithm according to claim 1 is characterized in that: A dual objective function is constructed, and corresponding constraints are determined in combination with the photovoltaic output power, the load and charging pile required power, and the charging and discharging power of the energy storage device, including: Constructing a dual objective function, and adjusting the weighted coefficients of the dual objective function according to actual needs, so as to minimize the weighted sum of economic cost and carbon emission cost; Determine that the sum of the power generation in each period of the microgrid is equal to the sum of the load demand and the charging and discharging power of the energy storage device; Based on the power model of the energy storage device, determine the maximum capacity of the energy storage device, and according to the maximum capacity of the energy storage device, determine the energy range of the energy storage device in the charging state and the energy range of the energy storage device in the discharging state; Based on the preset maximum power of the electric power, the power acquisition range of the microgrid is determined; wherein the maximum power of the electric power is determined according to the maximum power obtained from the mains at any time.

6. The microgrid energy dispatching method based on improved differential algorithm according to claim 5 is characterized in that: Determine that the sum of the power generation in each period of the microgrid is equal to the sum of the load demand and the charging and discharging power of the energy storage device, including: It is expressed by the following formula: in, express The load power in the microgrid during the period, express The line loss power of electric energy transmitted in the microgrid during the period, express The charging and discharging power of the time storage device, express The active power output of each power generation unit in the time period, express The power is obtained from the microgrid during the period.

7. The microgrid energy dispatching method based on improved differential algorithm according to claim 1 is characterized in that: Divide the power consumption period, and check whether the number of algorithm iterations reaches the maximum number of iterations by improving the differential algorithm to determine the optimal iteration result, including: Establish a microgrid and load model, and divide the power consumption period according to the load demand change; wherein the power consumption period includes peak period, normal period and valley period; For each power consumption period, it is determined by improving the difference algorithm whether the output power of the renewable energy device reaches the power consumption corresponding to the power consumption period.

8. The microgrid energy dispatching method based on improved differential algorithm according to claim 7 is characterized in that: For each power consumption period, determining whether the output power of the renewable energy device reaches the power consumption corresponding to the power consumption period by improving the differential algorithm specifically includes: If not, the power supply is supplemented by the main power grid and energy storage equipment; If yes, the remaining power output by the renewable energy device is stored in the energy storage device until the maximum number of iterations is reached, and the corresponding optimal result of the iteration is output; The surplus power is used to represent the difference between the total output power and the power consumption of the renewable energy equipment.

9. Microgrid energy dispatching equipment based on improved differential algorithm, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; Wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the microgrid energy scheduling method based on the improved differential algorithm as described in any one of claims 1-8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed, the microgrid energy scheduling method based on the improved differential algorithm as described in any one of claims 1 to 8 is implemented.

Images