Control method and related device of DC microgrid system

Abstract

The embodiment of the present application relates to the field of artificial intelligence, and provides a control method and related device of a DC microgrid system. The control method of the DC microgrid system includes: constructing a target Lyapunov function; calculating N global asymptotic stability domains; determining the stability domain fluctuation parameters of M first grid parameters based on the N global asymptotic stability domains; determining the P first grid parameters that are ranked top in order from large to small as P second grid parameters; constructing a training set based on the P second grid parameters; training a target stability classification neural network model based on the training set; inputting the P parameter values ​​to be predicted of the P second grid parameters input by the user into the target stability classification neural network model; when the stability prediction result is a system stability type, determining the P parameter values ​​to be predicted corresponding to the stability prediction result as the parameter values ​​of the DC microgrid system and running the DC microgrid system. The present application can improve the stability of the DC microgrid system.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of artificial intelligence, and more specifically to a control method and related devices for a DC microgrid system. Background Art

[0002] With the development of new energy technology and distributed power generation technology, microgrids have been widely used as a new energy supply and management model. Microgrid technology is a technology that is very suitable for the grid layout of distribution networks. It has an independent source of electricity and can supply users with island operation needs when the large power grid fails. It can also supply electricity to the large power grid when there is a surplus of power generation, reducing the power supply pressure of the large power grid. Microgrids can collect clean energy such as wind energy and solar energy around users, produce electricity for users, and supply electricity to the large power grid when there is a surplus of power generation. The stability of the microgrid system is very important, but the existing technology cannot accurately predict the stability of the microgrid system, resulting in failures of the microgrid system. Summary of the invention

[0003] The embodiments of the present application provide a control method and related devices for a DC microgrid system, which can improve the stability of the microgrid system.

[0004] In a first aspect, an embodiment of the present application provides a control method for a DC microgrid system, wherein the DC microgrid system includes a control loop, a main circuit, and a bus, wherein the main circuit includes a first inductor and a first capacitor, and the control method for the DC microgrid system includes:

[0005] Acquire M first grid parameters of the DC microgrid system, a maximum output voltage deviation of the first capacitor, a minimum output voltage deviation of the first capacitor, and a constant load power of the bus, where M is an integer greater than 1;

[0006] Determine a first parameter matrix based on the output voltage deviation minimum value, the constant load power and M first grid parameters;

[0007] Determine a second parameter matrix based on the maximum output voltage deviation, the constant load power and M first grid parameters;

[0008] Determining a target positive definite matrix based on the first parameter matrix and the second parameter matrix, wherein the target positive definite matrix enables the DC microgrid system to satisfy global asymptotic stability;

[0009] constructing a target Lyapunov function based on an output voltage deviation of the first capacitor, a current deviation of the first inductor, and the target positive definite matrix;

[0010] Determining a global asymptotic stability domain of the target Lyapunov function, wherein the global stability domain includes a plurality of stability domain parameters, and the stability domain parameters include an output voltage deviation and a through current deviation;

[0011] Determine one of the first power grid parameters as the target power grid parameter and determine the remaining (M-1) first power grid parameters as reference power grid parameters, assign values ​​to the M first power grid parameters N times, and calculate the global asymptotic stability domain N times to obtain N global asymptotic stability domains, wherein the values ​​of the target power grid parameters assigned N times are different, the values ​​of the reference power grid parameters assigned N times are the same, and N is an integer greater than 1;

[0012] Determine the stable domain fluctuation parameter of the target power grid parameter based on the N global asymptotic stable domains, and obtain the stable domain fluctuation parameters of the M first power grid parameters;

[0013] Determine the P first power grid parameters that are ranked first in descending order of the stable domain fluctuation parameters as the P second power grid parameters;

[0014] Constructing a training set based on the P second power grid parameters, the training set comprising training samples and corresponding classification labels, the training samples comprising generated values ​​of the P second power grid parameters, the classification labels being a system stability type or a system instability type;

[0015] Training the target stable classification neural network model based on the training set until a preset stopping condition is met;

[0016] Inputting the P parameter values ​​to be predicted of the P second power grid parameters input by the user into the target stability classification neural network model, and obtaining a stability prediction result output by the target stability classification neural network model, wherein the stability prediction result is a system stability type or a system instability type;

[0017] When the stability prediction result is a system stability type, the P to-be-predicted parameter values ​​corresponding to the stability prediction result are determined as parameter values ​​of the DC microgrid system and the DC microgrid system is operated.

[0018] In a second aspect, the present application provides a control device for a DC microgrid system, wherein the DC microgrid system includes a control loop, a main circuit, and a bus, wherein the main circuit includes a first inductor and a first capacitor, and wherein the control device for the DC microgrid system includes:

[0019] an acquisition module, used to acquire M first grid parameters of the DC microgrid system, a maximum output voltage deviation of the first capacitor, a minimum output voltage deviation of the first capacitor, and a constant load power of the bus, where M is an integer greater than 1;

[0020] A first determination module, configured to determine a first parameter matrix based on the output voltage deviation minimum value, the constant load power and M first grid parameters;

[0021] A second determination module, configured to determine a second parameter matrix based on the maximum output voltage deviation, the constant load power and M first grid parameters;

[0022] A third determination module is used to determine a target positive definite matrix based on the first parameter matrix and the second parameter matrix, wherein the target positive definite matrix enables the DC microgrid system to satisfy global asymptotic stability;

[0023] A function construction module, configured to construct a target Lyapunov function based on an output voltage deviation of the first capacitor, a current deviation of the first inductor, and the target positive definite matrix;

[0024] A fourth determination module is used to determine a global asymptotic stability domain of the target Lyapunov function, wherein the global stability domain includes a plurality of stability domain parameters, and the stability domain parameters include an output voltage deviation and a flow current deviation;

[0025] A calculation module, used for respectively determining one of the first power grid parameters as a target power grid parameter and determining the remaining (M-1) first power grid parameters as reference power grid parameters, assigning values ​​to the M first power grid parameters N times, and calculating the global asymptotic stability domains N times to obtain N global asymptotic stability domains, wherein the values ​​of the target power grid parameters assigned N times are different, the values ​​of the reference power grid parameters assigned N times are the same, and N is an integer greater than 1;

[0026] A fifth determination module, configured to determine the stable domain fluctuation parameter of the target power grid parameter based on the N global asymptotic stability domains, and obtain the stable domain fluctuation parameters of the M first power grid parameters;

[0027] A sixth determination module, configured to determine the P first power grid parameters that are ranked top in descending order of the stable domain fluctuation parameters as the P second power grid parameters;

[0028] A sample construction module, configured to construct a training set based on P second power grid parameters, wherein the training set includes training samples and corresponding classification labels, wherein the training samples include generated values ​​of the P second power grid parameters, and the classification labels are system stability type or system instability type;

[0029] A training module, used for training a target stable classification neural network model based on the training set until a preset stop condition is met;

[0030] A prediction module, used for inputting the P to-be-predicted parameter values ​​of the P second power grid parameters input by the user into the target stability classification neural network model, and obtaining a stability prediction result output by the target stability classification neural network model, wherein the stability prediction result is a system stability type or a system instability type;

[0031] An operation module is used to determine the P to-be-predicted parameter values ​​corresponding to the stability prediction result as parameter values ​​of the DC microgrid system and operate the DC microgrid system when the stability prediction result is a system stability type.

[0032] In a third aspect, the electronic device provided in the present application includes a memory and a processor, the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the control method of the DC microgrid system provided in the present application.

[0033] In a fourth aspect, the computer-readable storage medium provided in the present application stores a plurality of instructions, which are suitable for loading by a processor to implement the steps in the control method of the DC microgrid system provided in the present application.

[0034] In a fifth aspect, the computer program product provided in the present application includes a computer program or instructions, which, when executed by a processor, implement the steps in the control method of the DC microgrid system provided in the present application.

[0035] In the present application, compared with the related art, M first grid parameters of the DC microgrid system, the maximum output voltage deviation of the first capacitor, the minimum output voltage deviation of the first capacitor and the constant load power of the bus are obtained, where M is an integer greater than 1; a first parameter matrix is ​​determined based on the minimum output voltage deviation, the constant load power and the M first grid parameters; a second parameter matrix is ​​determined based on the maximum output voltage deviation, the constant load power and the M first grid parameters; a target positive definite matrix is ​​determined based on the first parameter matrix and the second parameter matrix, wherein the target positive definite matrix enables the DC microgrid system to satisfy global asymptotic stability; a target Lyapunov function is constructed based on the output voltage deviation of the first capacitor, the current deviation of the first inductor and the target positive definite matrix; a global asymptotic stability domain of the target Lyapunov function is determined, wherein the global stability domain includes multiple stability domain parameters, and the stability domain parameters include the output voltage deviation and the current deviation; one of the first grid parameters is determined as the target grid parameter and the remaining (M-1) first grid parameters are determined as reference grid parameters, the M first grid parameters are assigned N times, and the global asymptotic stability domain is calculated N times to obtain N A global asymptotic stability domain, wherein the values ​​of the target grid parameter assigned N times are different, the values ​​of the reference grid parameter assigned N times are the same, and N is an integer greater than 1; based on the N global asymptotic stability domains, the stable domain fluctuation parameters of the target grid parameter are determined to obtain the stable domain fluctuation parameters of the M first grid parameters; the P first grid parameters whose stable domain fluctuation parameters are ranked from large to small are determined as the P second grid parameters; a training set is constructed based on the P second grid parameters, the training set includes training samples and corresponding classification labels, the training samples include the generated values ​​of the P second grid parameters, and the classification labels are system stability type or system instability type; a target stable classification neural network model is trained based on the training set until a preset stop condition is met; the P parameter values ​​to be predicted of the P second grid parameters input by the user are input into the target stable classification neural network model to obtain a stable prediction result output by the target stable classification neural network model, wherein the stable prediction result is a system stability type or a system instability type; when the stable prediction result is a system stability type, the P parameter values ​​to be predicted corresponding to the stable prediction result are determined as parameter values ​​of the DC microgrid system and the DC microgrid system is operated. The present application constructs a target Lyapunov function, determines the global asymptotic stability domain of the target Lyapunov function, and then selects P second power grid parameters with larger stability domain fluctuations from M first power grid parameters according to the stability domain fluctuation parameters of the global asymptotic stability domain, constructs a training set to train a neural network model using the P second power grid parameters with larger stability domain fluctuations, and uses the neural network model to predict P parameter values ​​to be predicted input by a user, determines the P parameter values ​​to be predicted that can stabilize the system as parameter values ​​of a DC microgrid system, and runs the DC microgrid system, thereby avoiding failures of the DC microgrid system, and thus improving the stability of the DC microgrid system. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] By reading the detailed description of the embodiments of the present application with reference to the accompanying drawings, the objectives, features and advantages of the embodiments of the present application will become easy to understand. Among them:

[0037] Figure 1 A schematic diagram of a control system of a DC microgrid system according to a control method of a DC microgrid system in an embodiment of the present application;

[0038] Figure 2 A schematic structural diagram of a DC microgrid system according to a control method of a DC microgrid system in an embodiment of the present application;

[0039] Figure 3 A schematic flow chart of a control method for a DC microgrid system provided in an embodiment of the present application;

[0040] Figure 4 A schematic diagram of a global asymptotic stability region in a control method for a DC microgrid system provided in an embodiment of the present application;

[0041] Figure 5 It is a structural schematic diagram of an embodiment of a control device for a DC microgrid system provided in an embodiment of the present application;

[0042] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0043] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0044] It should be noted that the principles of the present application are illustrated by implementing them in an appropriate computing environment. The following description is based on the illustrated specific embodiments of the present application and should not be considered as limiting other specific embodiments of the present application that are not described in detail herein.

[0045] In the following description of the present application, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0046] In the following description of the present application, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0048] In order to improve the control effect of a DC microgrid system, the embodiments of the present application provide a control method of a DC microgrid system, a control device of a DC microgrid system, an electronic device, a computer-readable storage medium, and a computer program product. The control method of a DC microgrid system can be executed by the control device of the DC microgrid system, or by an electronic device integrated with the control device of the DC microgrid system.

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0050] Please refer to Figure 1 , the present application also provides a control system for a DC microgrid system, such as Figure 1 As shown, the control system of the DC microgrid system includes a DC microgrid system 200 and an electronic device 100 .

[0051] Among them, the electronic device 100 can be any device equipped with a processor and has processing capabilities, such as mobile electronic devices with processors such as smart phones, tablet computers, PDAs, laptops, smart speakers, or fixed electronic devices with processors such as desktop computers, televisions, servers, industrial equipment, etc.

[0052] like Figure 2 As shown, the DC microgrid system 200 includes a control loop, a main circuit, a bus and a plurality of energy storage units. The control loop is connected to the main circuit, and the plurality of energy storage units and the main circuit are connected to the bus. The bus is used to transmit constant load power to the outside. The main circuit includes a first inductor, a first capacitor, a converter, a first resistor, and the converter includes a second capacitor. The control loop includes a first controller, a droop resistor and a second controller.

[0053] In addition, if Figure 1 As shown, the control system of the DC microgrid system may also include a memory for storing original data, intermediate data and result data.

[0054] In the embodiment of the present application, the memory may be a cloud memory. Cloud storage is a new concept extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as the storage system) refers to a storage system that uses cluster applications, grid technology, and distributed storage file systems to bring together a large number of storage devices of various types (storage devices are also called storage nodes) in the network through application software or application interfaces to work together and provide external data storage and business access functions.

[0055] At present, the storage method of the storage system is: create a logical volume, and when creating a logical volume, allocate physical storage space for each logical volume, and the physical storage space may be composed of disks of a storage device or several storage devices. The client stores data on a logical volume, that is, stores the data on the file system. The file system divides the data into many parts, each of which is an object. The object contains not only data but also additional information such as data identification (ID, ID entity). The file system writes each object into the physical storage space of the logical volume, and the file system records the storage location information of each object, so that when the client requests to access the data, the file system can allow the client to access the data according to the storage location information of each object.

[0056] The process of the storage system allocating physical storage space to a logical volume is as follows: based on the estimated capacity of the objects stored in the logical volume (this estimate often has a large margin relative to the actual capacity of the objects to be stored) and the grouping of independent redundant disk arrays (RAID, Redundant Array of Independent Disks), the physical storage space is divided into stripes in advance. A logical volume can be understood as a stripe, thereby allocating physical storage space to the logical volume.

[0057] It should be noted that Figure 1 The scenario diagram of the control system of the DC microgrid system shown is only an example. The control system and scenario of the DC microgrid system described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of the control system of the DC microgrid system and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.

[0058] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0059] Please refer to Figure 3 , Figure 3FIG. 1 is a flow chart of an embodiment of a control method for a DC microgrid system provided in an embodiment of the present application. Figure 3 As shown, the process of the control method of the DC microgrid system provided by the present application is as follows:

[0060] 201. Obtain M first grid parameters of a DC microgrid system, a maximum output voltage deviation of a first capacitor, a minimum output voltage deviation of the first capacitor, and a constant load power of a bus.

[0061] In the embodiment of the present application, the DC microgrid system includes a control loop, a main circuit and a bus. The control loop includes a first controller, a droop resistor and a second controller, the main circuit includes a converter, a first capacitor, a first resistor and a first inductor, the converter includes a second capacitor, and the M first grid parameters include a first output capacitance value of the first capacitor. , the first resistance value of the first resistor , the first inductance value of the first inductor , the second output capacitance value of the second capacitor , droop coefficient of droop resistor , the control parameters of the first controller , the control parameters of the second controller and M is an integer greater than 1. The constant load power of the bus is , determined by the specific load.

[0062] Specifically, the output voltage of the first capacitor is , the steady-state value of the output voltage of the first capacitor is The output voltage deviation of the first capacitor is recorded as , the output voltage deviation of the first capacitor is the difference between the output voltage of the first capacitor and the steady-state value of the output voltage of the first capacitor. The maximum value of the output voltage deviation of the first capacitor is The minimum output voltage deviation of the first capacitor is .

[0063] 202. Determine a first parameter matrix based on a minimum output voltage deviation, a constant load power, and M first grid parameters.

[0064] Among them, the first parameter matrix Satisfies the following formula,

[0065] ,

[0066] in, is the first output capacitance value of the first capacitor, is the first resistance value of the first resistor, is the first inductance value of the first inductor, is the second output capacitance value of the second capacitor, is the droop coefficient of the droop resistor, is the constant load power of the bus, is the control parameter of the first controller, and is the control parameter of the second controller, is the minimum output voltage deviation of the first capacitor.

[0067] 203. Determine a second parameter matrix based on the maximum output voltage deviation, the constant load power, and M first grid parameters.

[0068] Specifically, the second parameter matrix Satisfies the following formula,

[0069]

[0070] in, is the first output capacitance value of the first capacitor, is the first resistance value of the first resistor, is the first inductance value of the first inductor, is the second output capacitance value of the second capacitor, is the droop coefficient of the droop resistor, Constant load power for the main circuit, is the control parameter of the first controller, and is the control parameter of the second controller, is the maximum output voltage deviation of the first capacitor.

[0071] 204. Determine a target positive definite matrix based on the first parameter matrix and the second parameter matrix.

[0072] Among them, the target positive definite matrix makes the DC microgrid system meet the global asymptotic stability.

[0073] In the embodiment of the present application, the target positive definite matrix satisfies the following formula:

[0074] ,

[0075] 205. Construct a target Lyapunov function based on an output voltage deviation of the first capacitor, a current deviation of the first inductor, and a target positive definite matrix.

[0076] In the embodiment of the present application, the target Lyapunov function Satisfies the following formula,

[0077] ,

[0078] Among them, the output voltage deviation of the first capacitor is recorded as , the steady-state value of the output voltage deviation of the first capacitor is The output voltage deviation of the first capacitor is recorded as The current deviation of the first inductor is .

[0079] Specifically, the current flowing through the first inductor is , the steady-state value of the current flowing through the first inductor is The current deviation of the first inductor is the difference between the current of the first inductor and the steady-state value of the current of the first inductor, which is expressed as .

[0080] 206. Determine the global asymptotic stability region of the target Lyapunov function.

[0081] The global stability domain includes a plurality of stability domain parameters, and the stability domain parameters include output voltage deviation and flow current deviation.

[0082] Among them, the global stability domain includes multiple stability domain parameters, which can be expressed as (output voltage deviation , the current deviation ).

[0083] 207. Determine one of the first power grid parameters as the target power grid parameter and determine the remaining (M-1) first power grid parameters as reference power grid parameters, assign values ​​to the M first power grid parameters N times, and calculate the global asymptotic stability domain N times to obtain N global asymptotic stability domains.

[0084] The values ​​of the target grid parameter assigned N times are different, the values ​​of the reference grid parameter assigned N times are the same, and N is an integer greater than 1.

[0085] Global asymptotic stability refers to the asymptotic stability of a class of systems where the entire phase space is an attractive region. For a linear system, if a linear system is globally asymptotically stable, then it must be asymptotically stable.

[0086] In the embodiment of the present application, when assigning values ​​N times, the reference grid parameters are kept unchanged, and only the parameters of the target grid parameters are changed. N is an integer greater than 1.

[0087] For example, N=3, the target grid parameter is the first output capacitance value of the first capacitor , is the first output capacitor value Assign different values ​​to each of them and get three global asymptotically stable regions.

[0088] like Figure 4 As shown, Figure 4 The area enclosed by the three global asymptotic stability regions is shown in Figure 1. The three global asymptotic stability regions are the first output capacitance value The global asymptotic stability domain generated when different values ​​are assigned three times.

[0089] 208. Determine a stable domain fluctuation parameter of a target power grid parameter based on the N global asymptotic stable domains, and obtain M stable domain fluctuation parameters of a first power grid parameter.

[0090] In the embodiment of the present application, the stable domain fluctuation parameters of the target power grid parameters are determined based on N global asymptotic stable domains, and the stable domain fluctuation parameters of the target power grid parameters are obtained, including:

[0091] (1) The output voltage deviation and the current deviation in each stability domain parameter in the global asymptotic stability domain are respectively determined as the horizontal coordinate and the vertical coordinate on the preset plane coordinate system, and multiple projection two-dimensional points of multiple stability domain parameters in the global asymptotic stability domain on the preset plane coordinate system are obtained.

[0092] (2) The region enclosed by multiple projected two-dimensional points is determined as the stable enclosed region corresponding to the global asymptotic stability domain.

[0093] like Figure 4 As shown, Figure 4 The area enclosed by the three global asymptotic stability regions is shown in Figure 1. The three global asymptotic stability regions are the first output capacitance value The global asymptotic stability domain generated when different values ​​are assigned three times.

[0094] (3) Calculate the centroid positions and area sizes of N stable enclosed regions.

[0095] (4) Determine a stable domain fluctuation parameter of a target power grid parameter based on a centroid position variance of the regional centroid positions of the N stable enclosed regions and a first area size variance of the regional area sizes of the N stable enclosed regions.

[0096] In a specific embodiment, the centroid position variance and the first area size variance are weighted and summed based on the first weight coefficient and the second weight coefficient to obtain the stable domain fluctuation parameter of the target power grid parameter. The first weight coefficient and the second weight coefficient can be set according to specific circumstances.

[0097] In another specific embodiment, determining the stable domain fluctuation parameter of the target power grid parameter based on the centroid position variance of the regional centroid positions of the N stable enclosed areas and the first area size variance of the regional area sizes of the N stable enclosed areas includes:

[0098] (1) A plurality of rays are generated starting from the centroid position of the stable enclosed area, and the stable enclosed area is divided into a plurality of enclosed sub-areas, wherein the angles between two adjacent rays in the plurality of rays are the same.

[0099] (2) Calculate the second area size variance of the area sizes of multiple enclosed sub-regions in the stable enclosed region to obtain the second area size variance corresponding to the stable enclosed region.

[0100] (3) Determine the stable domain fluctuation parameter of the target power grid parameter based on the average value of the second area size variances corresponding to the N stable enclosed areas, the centroid position variances of the area centroid positions of the N stable enclosed areas, and the first area size variances of the area sizes of the N stable enclosed areas.

[0101] Specifically, based on the first weight coefficient, the second weight coefficient and the third weight coefficient, the average values ​​of the centroid position variance, the first area size variance and the second area size variance are weighted and summed to obtain the stable domain fluctuation parameter of the target power grid parameter. The first weight coefficient, the second weight coefficient and the third weight coefficient can be set according to specific circumstances.

[0102] 209. Determine the P first power grid parameters that are ranked highest in descending order of the stable domain fluctuation parameters as the P second power grid parameters.

[0103] Among them, P is less than M. When the stable domain fluctuation parameter is small, it indicates that the parameter has little effect on the result. Not using this parameter when training the model can improve the model training efficiency.

[0104] 210. Construct a training set based on P second power grid parameters.

[0105] The training set includes training samples and corresponding classification labels. The training samples include P generated values ​​of the second power grid parameters. The classification labels are system stability type or system instability type.

[0106] In the embodiment of the present application, a training set is constructed based on P second power grid parameters, including:

[0107] (1) Obtain multiple historical values ​​of a second power grid parameter within a preset historical time period.

[0108] In the embodiment of the present application, multiple historical values ​​of the second power grid parameter within a preset historical time period can be obtained through historical records.

[0109] (2) Determine a parameter probability distribution function of a second power grid parameter based on a plurality of historical values ​​within a preset historical time period.

[0110] In the embodiments of the present application, the parameter probability distribution function may be a normal distribution or other distribution functions, which is not limited in the present application.

[0111] (3) Generate multiple different generated values ​​of the second power grid parameter based on the parameter probability distribution function to obtain multiple generated values ​​of each second power grid parameter.

[0112] Specifically, a parameter range of the second power grid parameter is acquired, and a plurality of different generated values ​​of the second power grid parameter that are within the parameter range are generated based on a parameter probability distribution function to obtain a plurality of generated values ​​of each second power grid parameter.

[0113] The distribution of the multiple generated values ​​of the second power grid parameter satisfies the parameter probability distribution function of the second power grid parameter and is located within the parameter range of the second power grid parameter. Different second power grid parameters have different parameter ranges.

[0114] For example, the target grid parameter is the first output capacitance value of the first capacitor , the first output capacitor value The parameter range is 1.5mF-2mF.

[0115] (4) Combining the P generated values ​​corresponding to the P second power grid parameters into one training sample to obtain a plurality of training samples of the training set.

[0116] Specifically, a production value is obtained from each second power grid parameter, P production values ​​are obtained, and a training sample is obtained.

[0117] (5) The P second grid parameters in the DC microgrid system are adjusted to the P generated values ​​of the training samples to obtain the voltage variance of the bus DC voltage when the DC microgrid system is operating within a preset time period.

[0118] The preset time period can be 1 minute after the current time or other values, which can be set according to the specific situation. The bus DC voltage is the DC voltage on the bus.

[0119] (6) When the voltage variance is not greater than the preset value, the classification label of the training sample is determined to be a system stable type; when the voltage variance is greater than the preset value, the classification label of the training sample is determined to be a system unstable type.

[0120] Among them, the preset value can be set according to the specific situation, and this application does not limit this.

[0121] 211. Based on the training set, the target classification neural network model is trained to be stable until the preset stopping condition is met.

[0122] Among them, the target stable classification neural network model can be an LSTM model.

[0123] Specifically, the preset stopping condition may be that the loss value calculated by the target stable classification neural network model is less than a preset loss value.

[0124] 212. Input the P to-be-predicted parameter values ​​of the P second power grid parameters input by the user into the target stability classification neural network model to obtain a stability prediction result output by the target stability classification neural network model.

[0125] The stability prediction result is a system stability type or a system instability type.

[0126] The P parameter values ​​to be predicted can be the specific values ​​of the P second power grid parameters input by the user. The user can input according to the specific situation, and then the target stability classification neural network model makes a stable prediction result for the input parameter value. The stable prediction result is a system stability type or a system instability type. The user can predict his own system to determine whether the system is stable.

[0127] 213. When the stability prediction result is a system stability type, the P parameter values ​​to be predicted corresponding to the stability prediction result are determined as parameter values ​​of the DC microgrid system and the DC microgrid system is operated.

[0128] In the embodiment of the present application, when the stable prediction result is a system stable type, the P parameter values ​​to be predicted corresponding to the stable prediction result are determined as the parameter values ​​of the DC microgrid system and the DC microgrid system is operated. When the stable prediction result is a system unstable type, the P parameter values ​​to be predicted of the P second grid parameters are updated until a stable prediction result belonging to the system stable type is obtained, and the updated P parameter values ​​to be predicted are determined as the parameter values ​​of the DC microgrid system and the DC microgrid system is operated.

[0129] In an embodiment of the present application, a DC microgrid system includes multiple energy storage units, and a control method of the DC microgrid system includes:

[0130] (1) When the stability prediction result is a system stability type, determine whether the current bus DC voltage of the bus is within a preset voltage range.

[0131] In the embodiment of the present application, the preset voltage range is ,in, is the maximum value of the range voltage, is the minimum value of the range voltage.

[0132] (2) If the current bus DC voltage of the bus does not fall within the preset voltage range, the remaining power of the multiple energy storage units is obtained.

[0133] If the current bus DC voltage of the bus does not fall within the preset voltage range, the bus DC voltage needs to be adjusted.

[0134] In the embodiment of the present application, the remaining power of the i-th energy storage unit is recorded as The range of remaining power is [0, 1].

[0135] (3) Based on the remaining power of the multiple energy storage units, the remaining power of each energy storage unit is mapped to a preset power range to obtain the remaining power mapping values ​​of the multiple energy storage units, wherein the remaining power mapping value corresponding to the minimum remaining power is the minimum value of the preset power range, and the remaining power mapping value corresponding to the maximum remaining power is the maximum value of the preset power range.

[0136] In the embodiment of the present application, the preset power range is [1, -1], and the remaining power mapping value and the remaining power of multiple energy storage units satisfy the following relationship:

[0137] ,

[0138] in, is the remaining power mapping value of the i-th energy storage unit, is the maximum value of the remaining power of multiple energy storage units, is the minimum value of the remaining power of multiple energy storage units, is the remaining power of the i-th energy storage unit.

[0139] (4) Selecting a preset number of target energy storage units from the plurality of energy storage units.

[0140] In the embodiment of the present application, a preset number of target energy storage units are selected from a plurality of energy storage units, including:

[0141] First, the number of times each energy storage unit has been charged and discharged, the time interval since the last charge and discharge, and the remaining power are obtained.

[0142] Then, the candidate priority is determined based on the number of times the energy storage unit has been charged and discharged, the time interval since the last charge and discharge, and the remaining power.

[0143] Among them, the number of times the energy storage unit has been charged and discharged, the time interval since the last charge and discharge, and the remaining power are normalized respectively to obtain the normalized value of the number of charge and discharge times, the normalized value of the time interval, and the normalized value of the remaining power. The candidate priority a is determined based on the normalized value c of the number of charge and discharge times, the normalized value t of the time interval, and the normalized value s of the remaining power.

[0144] Specifically, the calculation formula of candidate priority a is as follows:

[0145]

[0146] Finally, a preset number of energy storage units ranked higher in the candidate priority order from high to low are determined as a preset number of target energy storage units. The preset number is less than the total number of energy storage units.

[0147] (5) Obtain a preset voltage value within a preset voltage range.

[0148] The preset voltage value is u. The preset voltage value belongs to the preset voltage range, and the preset voltage range is .

[0149] (6) Determine the adjustment mapping value of the energy storage unit based on the maximum value of the range voltage, the minimum value of the range voltage, the bus rated voltage of the bus, and the preset voltage value of the preset voltage range.

[0150] Among them, the relationship between the maximum value of the range voltage, the minimum value of the range voltage, the bus rated voltage of the bus, the preset voltage value, and the adjustment mapping value satisfies the following formula:

[0151] ,

[0152] in, is the adjustment mapping value of the i-th energy storage unit, u is the preset voltage value, is the maximum value of the range voltage, is the minimum value of the range voltage, is the rated voltage of the busbar.

[0153] (7) Charging or discharging a preset number of target energy storage units until the remaining power mapping value of each target energy storage unit reaches the adjusted mapping value.

[0154] In the embodiment of the present application, the target energy storage unit whose remaining power mapping value is less than the adjusted mapping value is charged until the remaining power mapping value of the target energy storage unit reaches the adjusted mapping value; the target energy storage unit whose remaining power mapping value is greater than the adjusted mapping value is discharged until the remaining power mapping value of the target energy storage unit reaches the adjusted mapping value.

[0155] In order to facilitate better implementation of the control method of the DC microgrid system provided in the embodiment of the present application, the embodiment of the present application also provides a control device of the DC microgrid system based on the control method of the DC microgrid system. The meanings of the terms are the same as those in the control method of the DC microgrid system. For specific implementation details, please refer to the description in the above method embodiment.

[0156] Please refer to Figure 5 , Figure 5 A schematic diagram of the structure of a control device for a DC microgrid system provided in an embodiment of the present application, wherein the control device for the DC microgrid system may include:

[0157] An acquisition module 701 is used to acquire M first grid parameters of a DC microgrid system, a maximum output voltage deviation of a first capacitor, a minimum output voltage deviation of the first capacitor, and a constant load power of a bus, where M is an integer greater than 1;

[0158] A first determination module 702, configured to determine a first parameter matrix based on a minimum output voltage deviation, a constant load power, and M first grid parameters;

[0159] A second determination module 703, configured to determine a second parameter matrix based on the maximum output voltage deviation, the constant load power and the M first grid parameters;

[0160] A third determination module 704 is used to determine a target positive definite matrix based on the first parameter matrix and the second parameter matrix, wherein the target positive definite matrix enables the DC microgrid system to satisfy global asymptotic stability;

[0161] A function construction module 705 is used to construct a target Lyapunov function based on an output voltage deviation of the first capacitor, a current deviation of the first inductor, and a target positive definite matrix;

[0162] A fourth determination module 706 is used to determine a global asymptotic stability domain of the target Lyapunov function, wherein the global stability domain includes a plurality of stability domain parameters, and the stability domain parameters include an output voltage deviation and a flow current deviation;

[0163] A calculation module 707 is used to respectively determine one of the first power grid parameters as a target power grid parameter and determine the remaining (M-1) first power grid parameters as reference power grid parameters, assign values ​​to the M first power grid parameters N times, and calculate the global asymptotic stability domain N times to obtain N global asymptotic stability domains, wherein the values ​​of the target power grid parameters assigned N times are different, the values ​​of the reference power grid parameters assigned N times are the same, and N is an integer greater than 1;

[0164] A fifth determination module 708 is configured to determine a stable domain fluctuation parameter of a target power grid parameter based on the N global asymptotic stable domains, and obtain M stable domain fluctuation parameters of the first power grid parameter;

[0165] A sixth determining module 709 is configured to determine the P first power grid parameters that are ranked top in descending order of the stable domain fluctuation parameters as the P second power grid parameters;

[0166] A sample construction module 710 is used to construct a training set based on P second power grid parameters, the training set including training samples and corresponding classification labels, the training samples including generated values ​​of the P second power grid parameters, and the classification labels are system stability type or system instability type;

[0167] A training module 711 is used to train a target stable classification neural network model based on a training set until a preset stop condition is met;

[0168] A prediction module 712 is used to input the P to-be-predicted parameter values ​​of the P second power grid parameters input by the user into the target stability classification neural network model to obtain a stability prediction result output by the target stability classification neural network model, wherein the stability prediction result is a system stability type or a system instability type;

[0169] The operation module 713 is used to determine the P to-be-predicted parameter values ​​corresponding to the stability prediction result as parameter values ​​of the DC microgrid system and operate the DC microgrid system when the stability prediction result is a system stability type.

[0170] The specific implementation of each of the above modules can be found in the previous embodiments and will not be described in detail here.

[0171] An embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the processor is used to execute the steps in the control method of the DC microgrid system provided in this embodiment by calling a computer program stored in the memory.

[0172] Please refer to Figure 6 , Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0173] The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0174] The processor 101 is the control center of the electronic device, which uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 102, and calling data stored in the memory 102. Optionally, the processor 101 may include one or more processing cores; optionally, the processor 101 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 101.

[0175] The memory 102 can be used to store software programs and modules. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 102. The memory 102 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 102 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 102 may also include a memory controller to provide the processor 101 with access to the memory 102.

[0176] The electronic device also includes a power supply 103 for supplying power to each component. Optionally, the power supply 103 can be logically connected to the processor 101 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 103 can also include any components such as one or more DC or AC power supplies, recharging systems, power anomaly detection circuits, power converters or inverters, and power status indicators.

[0177] The electronic device may further include an input unit 104, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0178] Although not shown, the electronic device may also include a display unit, an image acquisition component, etc., which will not be described in detail here. Specifically in this embodiment, the processor 101 in the electronic device will load the executable code corresponding to one or more computer programs into the memory 102 according to the following instructions, and the processor 101 will execute the steps in the control method of the DC microgrid system provided in this application, such as:

[0179] Obtain M first grid parameters of the DC microgrid system, a maximum output voltage deviation of the first capacitor, a minimum output voltage deviation of the first capacitor, and a constant load power of the bus, where M is an integer greater than 1;

[0180] Determine a first parameter matrix based on the minimum output voltage deviation, the constant load power, and M first grid parameters;

[0181] Determine a second parameter matrix based on the maximum output voltage deviation, the constant load power, and the M first grid parameters;

[0182] Determine a target positive definite matrix based on the first parameter matrix and the second parameter matrix, wherein the target positive definite matrix enables the DC microgrid system to satisfy global asymptotic stability;

[0183] constructing a target Lyapunov function based on an output voltage deviation of the first capacitor, a current deviation of the first inductor, and a target positive definite matrix;

[0184] Determine a global asymptotic stability domain of the target Lyapunov function, wherein the global stability domain includes a plurality of stability domain parameters, and the stability domain parameters include an output voltage deviation and a flow current deviation;

[0185] Determine one of the first power grid parameters as the target power grid parameter and determine the remaining (M-1) first power grid parameters as reference power grid parameters, assign values ​​to the M first power grid parameters N times, and calculate the global asymptotic stability domain N times to obtain N global asymptotic stability domains, wherein the values ​​of the target power grid parameters assigned N times are different, the values ​​of the reference power grid parameters assigned N times are the same, and N is an integer greater than 1;

[0186] Determine the stable domain fluctuation parameter of the target power grid parameter based on N global asymptotic stable domains, and obtain the stable domain fluctuation parameters of M first power grid parameters;

[0187] Determine the P first power grid parameters that are ranked first in descending order of the stable domain fluctuation parameters as the P second power grid parameters;

[0188] Constructing a training set based on the P second power grid parameters, the training set including training samples and corresponding classification labels, the training samples including generated values ​​of the P second power grid parameters, and the classification labels being a system stability type or a system instability type;

[0189] Based on the training set, the target classification neural network model is trained to be stable until the preset stop condition is met;

[0190] Inputting P parameter values ​​to be predicted of the P second power grid parameters input by the user into the target stability classification neural network model, and obtaining a stability prediction result output by the target stability classification neural network model, wherein the stability prediction result is a system stability type or a system instability type;

[0191] When the stability prediction result is a system stability type, the P to-be-predicted parameter values ​​corresponding to the stability prediction result are determined as parameter values ​​of the DC microgrid system and the DC microgrid system is operated.

[0192] It should be noted that the electronic device provided in the embodiment of the present application and the control method of the DC microgrid system in the above embodiment belong to the same concept, and its specific implementation process is detailed in the above related embodiments and will not be repeated here.

[0193] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program stored therein is executed on the processor of the electronic device provided in the embodiment of the present application, the processor of the electronic device executes the steps in the control method of the DC microgrid system provided in the present application. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0194] The present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes various optional implementations of the control method of the DC microgrid system.

[0195] The above is a detailed introduction to the control method and device of a DC microgrid system provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0196] It should be noted that when the above embodiments of the present application are applied to specific products or technologies, the relevant data of the user is involved, and the user's permission or consent is required, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

Claims

1. A control method for a DC microgrid system, characterized in that: The DC microgrid system includes a control loop, a main circuit and a bus, the main circuit includes a first inductor and a first capacitor, and the control method of the DC microgrid system includes: Acquire M first grid parameters of the DC microgrid system, a maximum output voltage deviation of the first capacitor, a minimum output voltage deviation of the first capacitor, and a constant load power of the bus, where M is an integer greater than 1; Determine a first parameter matrix based on the output voltage deviation minimum value, the constant load power and M first grid parameters; Determine a second parameter matrix based on the maximum output voltage deviation, the constant load power and M first grid parameters; Determining a target positive definite matrix based on the first parameter matrix and the second parameter matrix, wherein the target positive definite matrix enables the DC microgrid system to satisfy global asymptotic stability; constructing a target Lyapunov function based on an output voltage deviation of the first capacitor, a current deviation of the first inductor, and the target positive definite matrix; Determining a global asymptotic stability domain of the target Lyapunov function, wherein the global asymptotic stability domain includes a plurality of stability domain parameters, and the stability domain parameters include an output voltage deviation and a flow current deviation; Determine one of the first power grid parameters as the target power grid parameter and determine the remaining (M-1) first power grid parameters as reference power grid parameters, assign values ​​to the M first power grid parameters N times, and calculate the global asymptotic stability domain N times to obtain N global asymptotic stability domains, wherein the values ​​of the target power grid parameters assigned N times are different, the values ​​of the reference power grid parameters assigned N times are the same, and N is an integer greater than 1; Determine the stable domain fluctuation parameter of the target power grid parameter based on the N global asymptotic stable domains, and obtain the stable domain fluctuation parameters of the M first power grid parameters; Determine the P first power grid parameters that are ranked first in descending order of the stable domain fluctuation parameters as the P second power grid parameters; Constructing a training set based on the P second power grid parameters, the training set comprising training samples and corresponding classification labels, the training samples comprising generated values ​​of the P second power grid parameters, the classification labels being a system stability type or a system instability type; Training the target stable classification neural network model based on the training set until a preset stop condition is met; Inputting the P parameter values ​​to be predicted of the P second power grid parameters input by the user into the target stability classification neural network model, and obtaining a stability prediction result output by the target stability classification neural network model, wherein the stability prediction result is a system stability type or a system instability type; When the stability prediction result is a system stability type, the P to-be-predicted parameter values ​​corresponding to the stability prediction result are determined as parameter values ​​of the DC microgrid system and the DC microgrid system is operated.

2. The control method of the DC microgrid system according to claim 1, characterized in that: The step of determining the stable domain fluctuation parameter of the target power grid parameter based on the N global asymptotic stable domains to obtain the stable domain fluctuation parameters of the M first power grid parameters includes: Determine the output voltage deviation and the current deviation in each stability domain parameter in the global asymptotic stability domain as the abscissa and ordinate on a preset plane coordinate system, respectively, and obtain a plurality of projection two-dimensional points of the plurality of stability domain parameters in the global asymptotic stability domain on the preset plane coordinate system; Determine the region enclosed by the plurality of projected two-dimensional points as a stable enclosed region corresponding to the global asymptotically stable region; Calculating the centroid positions and area sizes of the N stable enclosed areas; The stable domain fluctuation parameter of the target power grid parameter is determined based on the centroid position variance of the area centroid positions of the N stable enclosed areas and the first area size variance of the area sizes of the N stable enclosed areas.

3. The control method of the DC microgrid system according to claim 2, characterized in that: The determining of the stable domain fluctuation parameter of the target power grid parameter based on the centroid position variance of the area centroid positions of the N stable enclosed areas and the first area size variance of the area sizes of the N stable enclosed areas comprises: Generate multiple rays starting from the centroid position of the stable enclosed area, and divide the stable enclosed area into multiple enclosed sub-areas, wherein the angles between two adjacent rays in the multiple rays are the same; Calculate the second area size variance of the area sizes of the plurality of enclosed sub-regions in the stable enclosed region to obtain the second area size variance corresponding to the stable enclosed region; The stable domain fluctuation parameter of the target power grid parameter is determined based on the average value of the second area size variances corresponding to the N stable enclosed areas, the centroid position variances of the area centroid positions of the N stable enclosed areas, and the first area size variances of the area sizes of the N stable enclosed areas.

4. The control method of the DC microgrid system according to claim 1, characterized in that: The constructing a training set based on P second power grid parameters comprises: Acquire multiple historical values ​​of the second power grid parameter within a preset historical time period; Determine a parameter probability distribution function of the second power grid parameter based on a plurality of historical values ​​within the preset historical time period; generating a plurality of different generated values ​​of the second power grid parameter based on the parameter probability distribution function, to obtain a plurality of generated values ​​of each of the second power grid parameters; Combining P generated values ​​corresponding to P second power grid parameters into one training sample to obtain a plurality of the training samples of the training set; Adjusting P second grid parameters in the DC microgrid system to P generated values ​​of the training samples to obtain a voltage variance of a bus DC voltage when the DC microgrid system is running within a preset time period; When the voltage variance is not greater than a preset value, the classification label of the training sample is determined to be a system stable type; when the voltage variance is greater than a preset value, the classification label of the training sample is determined to be a system unstable type.

5. The control method of the DC microgrid system according to claim 1, characterized in that: The control loop includes a first controller, a droop resistor and a second controller, the main circuit also includes a converter and a first resistor, the converter includes a second capacitor, the M first power grid parameters include a first output capacitance value of the first capacitor, a first resistance value of the first resistor, a first inductance value of the first inductor, a second output capacitance value of the second capacitor, a droop coefficient of the droop resistor, control parameters of the first controller, and control parameters of the second controller.

6. The control method of the DC microgrid system according to claim 1, characterized in that: The DC microgrid system includes a plurality of energy storage units, and the control method of the DC microgrid system includes: When the stability prediction result is a system stability type, determining whether the current bus DC voltage of the bus belongs to a preset voltage range; If the current bus DC voltage of the bus does not fall within the preset voltage range, obtaining the remaining power of the plurality of energy storage units; Based on the remaining power of the multiple energy storage units, the remaining power of each energy storage unit is mapped to a preset power range to obtain the remaining power mapping values ​​of the multiple energy storage units, wherein the remaining power mapping value corresponding to the minimum remaining power is the minimum value of the preset power range, and the remaining power mapping value corresponding to the maximum remaining power is the maximum value of the preset power range; Selecting a preset number of target energy storage units from the plurality of energy storage units; Obtaining a preset voltage value within a preset voltage range; Determine the adjustment mapping value of the energy storage unit based on the maximum value of the range voltage, the minimum value of the range voltage, the bus rated voltage of the bus and the preset voltage value of the preset voltage range; A preset number of the target energy storage units are charged or discharged until the remaining power mapping value of each of the target energy storage units reaches the adjusted mapping value.

7. The control method of the DC microgrid system according to claim 6, characterized in that: The preset power range is [1, -1], and the remaining power mapping value and the remaining power of multiple energy storage units satisfy the following relationship: ， in, is the remaining power mapping value of the i-th energy storage unit, is the maximum value of the remaining power of multiple energy storage units, is the minimum value of the remaining power of multiple energy storage units, is the remaining power of the i-th energy storage unit; The relationship between the maximum value of the range voltage, the minimum value of the range voltage, the bus rated voltage, the preset voltage value and the adjustment mapping value satisfies the following formula: ， in, is the adjustment mapping value of the i-th energy storage unit, u is the preset voltage value, is the maximum value of the range voltage, is the minimum value of the range voltage, is the rated voltage of the bus.

8. A control device for a DC microgrid system, characterized in that: The DC microgrid system includes a control loop, a main circuit and a bus, the main circuit includes a first inductor and a first capacitor, and the control device of the DC microgrid system includes: an acquisition module, used to acquire M first grid parameters of the DC microgrid system, a maximum output voltage deviation of the first capacitor, a minimum output voltage deviation of the first capacitor, and a constant load power of the bus, where M is an integer greater than 1; A first determination module, configured to determine a first parameter matrix based on the output voltage deviation minimum value, the constant load power and M first grid parameters; A second determination module, configured to determine a second parameter matrix based on the maximum output voltage deviation, the constant load power and M first grid parameters; A third determination module is used to determine a target positive definite matrix based on the first parameter matrix and the second parameter matrix, wherein the target positive definite matrix enables the DC microgrid system to satisfy global asymptotic stability; A function construction module, configured to construct a target Lyapunov function based on an output voltage deviation of the first capacitor, a current deviation of the first inductor, and the target positive definite matrix; A fourth determination module is used to determine a global asymptotic stability domain of the target Lyapunov function, wherein the global asymptotic stability domain includes a plurality of stability domain parameters, and the stability domain parameters include an output voltage deviation and a flow current deviation; A calculation module, used for respectively determining one of the first power grid parameters as a target power grid parameter and determining the remaining (M-1) first power grid parameters as reference power grid parameters, assigning values ​​to the M first power grid parameters N times, and calculating the global asymptotic stability domains N times to obtain N global asymptotic stability domains, wherein the values ​​of the target power grid parameters assigned N times are different, the values ​​of the reference power grid parameters assigned N times are the same, and N is an integer greater than 1; A fifth determination module, configured to determine the stable domain fluctuation parameter of the target power grid parameter based on the N global asymptotic stability domains, and obtain the stable domain fluctuation parameters of the M first power grid parameters; A sixth determination module, configured to determine the P first power grid parameters that are ranked top in descending order of the stable domain fluctuation parameters as the P second power grid parameters; A sample construction module, configured to construct a training set based on P second power grid parameters, wherein the training set includes training samples and corresponding classification labels, wherein the training samples include generated values ​​of the P second power grid parameters, and the classification labels are system stability type or system instability type; A training module, used for training a target stable classification neural network model based on the training set until a preset stop condition is met; A prediction module, used for inputting the P to-be-predicted parameter values ​​of the P second power grid parameters input by the user into the target stability classification neural network model, and obtaining a stability prediction result output by the target stability classification neural network model, wherein the stability prediction result is a system stability type or a system instability type; An operation module is used to determine the P to-be-predicted parameter values ​​corresponding to the stability prediction result as parameter values ​​of the DC microgrid system and operate the DC microgrid system when the stability prediction result is a system stability type.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the steps in the control method of the DC microgrid system according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the control method of a DC microgrid system according to any one of claims 1 to 7.

Images