Energy storage system simulation method and device based on agent model, equipment and medium

Abstract

The application relates to the field of simulation technology, and discloses a method and device for simulating an energy storage system based on an agent model, equipment and a medium. The method comprises the following steps: connecting a battery agent model, an energy storage converter agent model, a filter agent model and a transformer agent model according to a topological structure in a topological graph to obtain a simulation model of the energy storage system; inputting a current direct-current voltage signal into the energy storage converter agent model, processing the current direct-current voltage signal through the energy storage converter agent model to obtain a current alternating-current voltage signal, inputting the current alternating-current voltage signal into the filter agent model, processing the current alternating-current voltage signal through the filter agent model to obtain a filtered current alternating-current voltage signal, a current amplitude-frequency value and a current phase offset value; and taking the efficiency of the transformer, the current amplitude-frequency value and the current phase offset value as performance indexes of the energy storage system. The application is beneficial to improving the simulation efficiency of the energy storage system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of simulation, in particular to a method and device for simulating an energy storage system based on a proxy model, and a medium. BACKGROUND

[0002] With the widespread use of renewable energy, the demand for energy storage in power systems is increasing. As an important means of regulating grid fluctuations and optimizing energy, the simulation analysis of energy storage systems is crucial.

[0003] However, the prior art mainly adopts an artificial construction method to construct a simulation model of an energy storage system, and the artificial construction method consumes a large amount of human and time resources, increases the construction time of the simulation model of the energy storage system, and is not conducive to improving the construction efficiency of the simulation model of the energy storage system. Therefore, how to construct the simulation model of the energy storage system and how to call the simulation model of the energy storage system are technical problems that need to be solved. SUMMARY

[0004] The embodiments of the present application provide a method and device for simulating an energy storage system based on a proxy model, and a medium, to solve the technical problems of how to construct the simulation model of the energy storage system and how to call the simulation model of the energy storage system.

[0005] In a first aspect, the embodiments of the present application provide a method for simulating an energy storage system based on a proxy model, applied to an electronic device, and the method comprises:

[0006] selecting a trained first deep learning model as a battery proxy model, a trained second deep learning model as an energy storage converter proxy model, a trained third deep learning model as a filter proxy model, and a trained fourth deep learning model as a transformer proxy model;

[0007] connecting the battery proxy model, the energy storage converter proxy model, the filter proxy model, and the transformer proxy model according to the topological structure in the topological graph to obtain a simulation model of the energy storage system;

[0008] obtaining an initial current signal and an initial voltage signal of the simulation model, processing the initial current signal and the initial voltage signal through the battery proxy model to obtain a current DC voltage signal, inputting the current DC voltage signal into the energy storage converter proxy model, processing the current DC voltage signal through the energy storage converter proxy model to obtain a current AC voltage signal, inputting the current AC voltage signal into the filter proxy model, and processing the current AC voltage signal through the filter proxy model to obtain a filtered current AC voltage signal, a current amplitude value, and a current phase shift value;

[0009] input the filtered current alternating voltage signal into the transformer proxy model, process the filtered current alternating voltage signal through the transformer proxy model, and obtain a transformed current direct voltage signal;

[0010] obtain an output voltage from the current direct voltage signal, obtain an output current of the transformer proxy model, multiply the output voltage and the output current to obtain an output power, divide the output power by the input power to obtain an efficiency of the transformer, and take the efficiency of the transformer, the current amplitude-frequency value, and the current phase shift value as performance indicators of the energy storage system.

[0011] In a possible implementation manner of the first aspect, the trained first deep learning model is selected as the battery proxy model, the trained second deep learning model is selected as the energy storage converter proxy model, the trained third deep learning model is selected as the filter proxy model, and the trained fourth deep learning model is selected as the transformer proxy model, and the method comprises the following steps.

[0012] obtain a first output variable corresponding to a preset first input variable, compose a battery data sample by using the preset first input variable and the first output variable, compose a first data set by using different battery data samples, train the first deep learning model by using the first data set, obtain a trained first deep learning model, select the trained first deep learning model as the battery proxy model, the preset first input variable comprises a preset current signal and a preset voltage signal of the battery, and the first output variable comprises a direct voltage signal;

[0013] obtain a second input variable and a second output variable, compose a voltage data sample by using the second input variable and the second output variable, compose a second data set by using different voltage data samples, train the second deep learning model by using the second data set, and select the trained second deep learning model as the energy storage converter proxy model, the second input variable comprises a preset direct voltage signal, and the second output variable comprises a preset alternating voltage signal;

[0014] obtain a third input variable and a third output variable, compose a filter data sample by using the third input variable and the third output variable, compose a third data set by using different filter data samples, train the third deep learning model by using the third data set, obtain a trained third deep learning model, and select the trained third deep learning model as the filter proxy model, the third input variable comprises a preset alternating voltage signal, and the third output variable comprises a filtered preset alternating voltage signal, a preset amplitude-frequency value, and a preset phase shift value;

[0015] The fourth input variable and the fourth output variable are obtained, the fourth input variable and the fourth output variable are combined to form a transformer data sample, different transformer data samples are combined to form a fourth data set, the fourth data set is used to train a fourth deep learning model, a trained fourth deep learning model is obtained, the trained fourth deep learning model is selected as a transformer proxy model, the fourth input variable includes a filtered preset alternating current side voltage signal, and the fourth output variable includes a transformed preset alternating current side voltage signal.

[0016] In a possible implementation manner of the first aspect, the battery proxy model, the energy storage converter proxy model, the filter proxy model and the transformer proxy model are connected according to the topological structure in the topological graph to obtain the simulation model of the energy storage system, and the simulation model of the energy storage system includes:

[0017] The topological graph corresponding to the power system is obtained, and the battery proxy model, the energy storage converter proxy model, the filter proxy model and the transformer proxy model are connected according to the topological structure in the topological graph to obtain the simulation model of the energy storage system.

[0018] In a possible implementation manner of the first aspect, the output voltage is obtained from the current direct current voltage signal, the output current of the transformer proxy model is obtained, the output voltage and the output current are multiplied to obtain the output power, the output power is divided by the input power to obtain the efficiency of the transformer, and the efficiency of the transformer, the current amplitude-frequency value and the current phase offset value are taken as the performance indicators of the energy storage system.

[0019] The output voltage is obtained from the current direct current voltage signal, the output current of the transformer proxy model is obtained, the output voltage and the output current are multiplied to obtain the output power, and the output power is divided by the input power to obtain the efficiency of the transformer.

[0020] The health state value of the battery and the internal impedance of the battery are obtained, the total harmonic distortion value of the converter and the energy conversion efficiency of the converter are obtained, the efficiency of the transformer, the core loss of the transformer and the winding loss of the transformer are obtained, and the health state value of the battery, the internal impedance of the battery, the total harmonic distortion value of the converter, the energy conversion efficiency of the converter, the efficiency of the transformer, the core loss of the transformer, the winding loss of the transformer, the current amplitude-frequency value and the current phase offset value are taken as the performance indicators of the energy storage system.

[0021] In a possible implementation manner of the first aspect, after the output voltage is obtained from the current direct current voltage signal, the output current of the transformer proxy model is obtained, the output voltage and the output current are multiplied to obtain the output power, the output power is divided by the input power to obtain the efficiency of the transformer, and the efficiency of the transformer, the current amplitude-frequency value and the current phase offset value are taken as the performance indicators of the energy storage system, the energy storage system simulation method includes:

[0022] A display window is created, and the performance indicators of the energy storage system are displayed through the display window.

[0023] In a possible implementation manner of the first aspect, after the output voltage is obtained from the current direct-current voltage signal, the output current of the transformer proxy model is obtained, the output voltage and the output current are multiplied to obtain the output power, the output power is divided by the input power to obtain the efficiency of the transformer, and the efficiency of the transformer, the current amplitude-frequency value and the current phase offset value are taken as the performance indicators of the energy storage system, the energy storage system simulation method comprises:

[0024] The simulation platform of the power system is connected, and the performance indicators of the energy storage system are sent to the simulation platform.

[0025] In a possible implementation manner of the first aspect, the first deep learning model adopts a short-term memory network or a gated recurrent unit structure, the second deep learning model adopts a multi-layer perception or a one-dimensional convolutional neural network; the third deep learning model adopts a one-dimensional convolutional neural network or a hybrid neural network; and the fourth deep learning model adopts a one-dimensional convolutional neural network or a hybrid neural network.

[0026] In a second aspect, an embodiment of the present application provides an energy storage system simulation device based on a proxy model, applied to an electronic device, comprising:

[0027] The selecting module is configured to select the trained first deep learning model as a battery proxy model, select the trained second deep learning model as an energy storage converter proxy model, select the trained third deep learning model as a filter proxy model, and select the trained fourth deep learning model as a transformer proxy model.

[0028] The connecting module is configured to connect the battery proxy model, the energy storage converter proxy model, the filter proxy model and the transformer proxy model according to the topological structure in the topological graph to obtain a simulation model of the energy storage system.

[0029] The input module is configured to obtain an initial current signal and an initial voltage signal of the simulation model, process the initial current signal and the initial voltage signal through the battery proxy model to obtain a current direct-current voltage signal, input the current direct-current voltage signal into the energy storage converter proxy model, process the current direct-current voltage signal through the energy storage converter proxy model to obtain a current alternating-current voltage signal, input the current alternating-current voltage signal into the filter proxy model, and process the current alternating-current voltage signal through the filter proxy model to obtain a filtered current alternating-current voltage signal, a current amplitude-frequency value and a current phase offset value.

[0030] The transformation module is configured to input the filtered current alternating voltage signal into a transformer proxy model when the current amplitude-frequency value is less than a first preset value and the current offset value is less than a second preset value, process the filtered current alternating voltage signal through the transformer proxy model, and obtain a transformed current direct voltage signal.

[0031] The composition module is configured to obtain an output voltage from the current direct voltage signal, obtain an output current of the transformer proxy model, multiply the output voltage and the output current to obtain an output power, divide the output power by the input power to obtain an efficiency of the transformer, and take the efficiency of the transformer, the current amplitude-frequency value, and the current phase offset value as the performance indicators of the energy storage system.

[0032] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the energy storage system simulation method of any one of the first aspect when executing the computer program.

[0033] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program is executable on a processor to implement the energy storage system simulation method of any one of the first aspect.

[0034] In a fifth aspect, a computer program product is provided, which, when executed on an electronic device, causes the electronic device to perform the energy storage system simulation method of any one of the first aspect.

[0035] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0036] The embodiment of the present application has three advantages. First, according to the topological structure in the topological graph, the battery agent model, the energy storage converter agent model, the filter agent model and the transformer agent model are connected to obtain a simulation model of the energy storage system, thereby solving the problem of how to construct the simulation model of the energy storage system and facilitating reduction of simulation time of the energy storage system and improvement of simulation efficiency of the energy storage system. Second, the output voltage is obtained from the current DC voltage signal, the output current of the transformer agent model is obtained, the output voltage and the output current are multiplied to obtain the output power, the output power is divided by the input power to obtain the efficiency of the transformer, and the efficiency of the transformer, the current amplitude-frequency value and the current phase shift value are taken as performance indicators of the energy storage system, thereby solving the technical problem of how to call the simulation model of the energy storage system and facilitating improvement of calling efficiency of the simulation model of the energy storage system. Third, the battery agent model, the energy storage converter agent model, the filter agent model and the transformer agent model in the simulation model of the energy storage system are different deep learning models, the simulation model of the energy storage system uses the battery agent model, the energy storage converter agent model, the filter agent model and the transformer agent model to replace complex physical equations, thereby reducing data processing time and facilitating improvement of data processing speed of the simulation model of the energy storage system. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0038] Figure 1 A structural diagram of the simulation model of the energy storage system provided by the embodiment of the present application is shown in FIG. 1.

[0039] Figure 2 A flowchart of the energy storage system simulation method provided by the embodiment of the present application is shown in FIG. 2.

[0040] Figure 3 A flowchart of obtaining performance indicators provided by the embodiment of the present application is shown in FIG. 3.

[0041] Figure 4 A schematic block diagram of the energy storage system simulation device provided by the embodiment of the present application is shown in FIG. 4.

[0042] Figure 5 A structural diagram of the electronic device provided by the embodiment of the present application is shown in FIG. 5. DETAILED DESCRIPTION

[0043] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0044] The energy storage system simulation method provided by the embodiments of the present application can be applied to electronic devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, notebook computers, personal computers, and netbooks. The embodiments of the present application do not make any limitation on the specific type of electronic device.

[0045] Referring to Figure 1 , Figure 1 The structural diagram of the simulation model of the energy storage system provided by the embodiments of the present application is described as follows:

[0046] The structural diagram includes a battery agent model, an energy storage converter agent model, a filter agent model, and a transformer agent model.

[0047] In the embodiments of the present application, the battery agent model, the energy storage converter agent model, the filter agent model, and the transformer agent model are connected in series to obtain the simulation model of the energy storage system.

[0048] Referring to Figure 2 , Figure 2 The flowchart of the energy storage system simulation method provided by the embodiments of the present application is shown in the figure, and the method can be applied to an electronic device.

[0049] As Figure 2 shown, the energy storage system simulation method provided by the embodiments of the present application includes the following steps, which are described in detail as follows:

[0050] S201, selecting a trained first deep learning model as a battery agent model, selecting a trained second deep learning model as an energy storage converter agent model, selecting a trained third deep learning model as a filter agent model, and selecting a trained fourth deep learning model as a transformer agent model;

[0051] Among them, selecting a trained first deep learning model as a battery agent model, selecting a trained second deep learning model as an energy storage converter agent model, selecting a trained third deep learning model as a filter agent model, and selecting a trained fourth deep learning model as a transformer agent model include:

[0052] The first output variable corresponding to the preset first input variable is obtained, the preset first input variable and the first output variable are combined to form a battery data sample, different battery data samples are combined to form a first data set, the first data set is used to train a first deep learning model, a trained first deep learning model is obtained, the trained first deep learning model is selected as a battery proxy model, the preset first input variable includes a preset current signal and a preset voltage signal of the battery, and the first output variable includes a direct current voltage signal;

[0053] The second input variable and the second output variable are obtained, the second input variable and the second output variable are combined to form a voltage data sample, different voltage data samples are combined to form a second data set, the second data set is used to train a second deep learning model, and a trained second deep learning model is selected as a storage converter proxy model, the second input variable includes a preset direct current voltage signal, and the second output variable includes a preset alternating current side voltage signal;

[0054] The third input variable and the third output variable are obtained, the third input variable and the third output variable are combined to form a filter data sample, different filter data samples are combined to form a third data set, the third data set is used to train a third deep learning model, a trained third deep learning model is obtained, and the trained third deep learning model is selected as a filter proxy model, the third input variable includes a preset alternating current side voltage signal, and the third output variable includes a filtered preset alternating current side voltage signal, a preset amplitude frequency value, and a preset phase offset value;

[0055] The fourth input variable and the fourth output variable are obtained, the fourth input variable and the fourth output variable are combined to form a transformer data sample, different transformer data samples are combined to form a fourth data set, the fourth data set is used to train a fourth deep learning model, a trained fourth deep learning model is obtained, and the trained fourth deep learning model is selected as a transformer proxy model, the fourth input variable includes a filtered preset alternating current side voltage signal, and the fourth output variable includes a transformed preset alternating current side voltage signal.

[0056] Exemplarily, the trained first deep learning model is selected as the battery proxy model, the trained second deep learning model is selected as the storage converter proxy model, the trained third deep learning model is selected as the filter proxy model, and the trained fourth deep learning model is selected as the transformer proxy model, including:

[0057] obtaining a first output variable corresponding to a preset first input variable, grouping the preset first input variable and the first output variable to form a battery data sample, grouping different battery data samples to form a first data set, dividing the first data set into a first training set and a first test set, training a first deep learning model using the first training set, obtaining a trained first deep learning model, obtaining a mean absolute error of the trained first deep learning model on the first test set, selecting the trained first deep learning model as a battery proxy model when the mean absolute error of the trained first deep learning model on the first test set is less than a preset value, the preset first input variable including a preset current signal and a preset voltage signal of the battery, and the first output variable including a direct current voltage signal;

[0058] obtaining a second input variable and a second output variable, grouping the second input variable and the second output variable to form a voltage data sample, grouping different voltage data samples to form a second data set, dividing the second data set into a second training set and a second test set, training a second deep learning model using the second training set, obtaining a trained second deep learning model, obtaining a mean absolute error of the trained second deep learning model on the second test set, and selecting the trained second deep learning model as a voltage proxy model when the mean absolute error of the trained second deep learning model on the second test set is less than a preset value, the second input variable including a preset direct current voltage signal, and the second output variable including a preset alternating current side voltage signal;

[0059] obtaining a third input variable and a third output variable, grouping the third input variable and the third output variable to form a filter data sample, grouping different filter data samples to form a third data set, dividing the third data set into a third training set and a third test set, training a third deep learning model using the third training set, obtaining a trained third deep learning model, and obtaining a mean absolute error of the trained third deep learning model on the third test set, and selecting the trained third deep learning model as a filter proxy model when the mean absolute error of the trained third deep learning model on the third test set is less than a preset value,

[0060] selecting the trained third deep learning model as a filter proxy model, the third input variable including a preset alternating current side voltage signal, and the third output variable including a filtered preset alternating current side voltage signal, a preset amplitude frequency value, and a preset phase shift value;

[0061] obtaining a fourth input variable and a fourth output variable, grouping the fourth input variable and the fourth output variable to form a transformer data sample, grouping different transformer data samples to form a fourth data set, dividing the fourth data set into a fourth training set and a fourth test set, training a fourth deep learning model using the fourth training set, obtaining a trained fourth deep learning model, obtaining a mean absolute error of the trained fourth deep learning model on the fourth test set, and selecting the trained fourth deep learning model as a transformer proxy model when the mean absolute error of the trained fourth deep learning model on the fourth test set is less than a preset value,

[0062] The fourth deep learning model after training is selected as a transformer proxy model, the fourth input variable includes the filtered preset alternating current side voltage signal, and the fourth output variable includes the transformed preset alternating current side voltage signal.

[0063] Optionally, the preset first input variable further includes a preset temperature value of the battery, a first state of charge of the battery, and a time sequence.

[0064] Optionally, the first output variable further includes a second state of charge of the battery.

[0065] Optionally, the second input variable further includes a current signal of the energy storage converter and a modulation signal of the energy storage converter.

[0066] Optionally, the second output variable further includes an amplitude of a harmonic component in the current signal of the energy storage converter.

[0067] Optionally, the third input variable further includes a voltage signal across the filter and a current signal across the filter.

[0068] Optionally, the fourth output variable further includes a voltage gain value corresponding to the frequency point.

[0069] The battery proxy model is a proxy model of the battery.

[0070] The energy storage converter proxy model is a proxy model of the energy storage converter.

[0071] The filter proxy model is a proxy model of the filter.

[0072] The transformer proxy model is a proxy model of the transformer.

[0073] S202, according to the topological structure in the topological graph, the battery proxy model, the energy storage converter proxy model, the filter proxy model and the transformer proxy model are connected to obtain a simulation model of the energy storage system.

[0074] The battery proxy model, the energy storage converter proxy model, the filter proxy model and the transformer proxy model are connected according to the topological structure in the topological graph to obtain a simulation model of the energy storage system.

[0075] A topological graph corresponding to a power system is obtained, and the battery proxy model, the energy storage converter proxy model, the filter proxy model and the transformer proxy model are connected according to the topological structure in the topological graph to obtain a simulation model of the energy storage system.

[0076] Optionally, a topology graph corresponding to the power system is acquired, and the battery agent model, the energy storage converter agent model, the filter agent model and the transformer agent model are connected in series according to a topology structure in the topology graph to obtain a simulation model of the energy storage system.

[0077] The simulation model of the energy storage system can quickly construct virtual prototypes of different topology structures and control strategies, verify key performance indicators such as charging and discharging efficiency and cycle life through parameterized analysis, shorten the development cycle compared with physical prototype testing, and reduce the research and development cost. In the grid-connected verification link, the simulation model of the energy storage system can simulate complex working conditions such as power grid faults and frequency fluctuations, accurately predict the dynamic response characteristics of the energy storage system, ensure that the grid-connected performance meets the standard requirements, and avoid compatibility problems in actual grid connection.

[0078] In S203, an initial current signal and an initial voltage signal of the simulation model are acquired, the initial current signal and the initial voltage signal are processed by the battery agent model to obtain a current direct-current voltage signal, the current direct-current voltage signal is input into the energy storage converter agent model, the current direct-current voltage signal is processed by the energy storage converter agent model to obtain a current alternating-current voltage signal, the current alternating-current voltage signal is input into the filter agent model, and the current alternating-current voltage signal is processed by the filter agent model to obtain a filtered current alternating-current voltage signal, a current amplitude-frequency value and a current phase shift value.

[0079] The waveform of the filtered current alternating-current voltage signal is smoother, which can avoid numerical oscillation or convergence difficulty problems caused by signal mutation or harmonic distortion in the simulation process, and improve the simulation efficiency.

[0080] In S204, when the current amplitude-frequency value is less than a first preset value and the current phase shift value is less than a second preset value, the filtered current alternating-current voltage signal is input into the transformer agent model, and the filtered current alternating-current voltage signal is processed by the transformer agent model to obtain a transformed current direct-current voltage signal.

[0081] The current amplitude-frequency value being less than the first preset value can effectively avoid the interference of high-frequency noise or resonance components on the simulation model, ensure that the system dynamic characteristics are mainly dominated by the fundamental wave or key frequency band, and thus more truly reflect the actual working condition.

[0082] The current phase shift value being less than the second preset value can suppress the influence of direct-current components or low-frequency drift, and prevent numerical instability or convergence difficulty problems caused by signal baseline shift in the simulation process.

[0083] The current amplitude-frequency value being less than the first preset value and the current phase shift value being less than the second preset value not only make the simulation result closer to the actual behavior of the physical system, but also reduce the consumption of computing resources.

[0084] S205, obtaining an output voltage from the current direct current voltage signal, obtaining an output current of the transformer proxy model, multiplying the output voltage and the output current to obtain an output power, dividing the output power by the input power to obtain an efficiency of the transformer, and taking the efficiency of the transformer, the current amplitude-frequency value and the current phase offset value as the performance indicators of the energy storage system.

[0085] The efficiency of the transformer is directly related to energy loss, and the improvement of the efficiency of the transformer directly reduces the energy loss of the energy storage system in the charging and discharging process, so that the energy storage system can more accurately follow the grid demand in the charging and discharging process, effectively suppresses the renewable energy fluctuation, and improves the grid accommodation capacity of new energy.

[0086] The current amplitude-frequency value reflects the transmission characteristics of the transformer to different frequency signals, and the current amplitude-frequency value is included in the performance indicators, which is beneficial to evaluate the stability of the energy storage system under dynamic working conditions.

[0087] The current phase offset value reflects the difference in synchronization of voltage and current waveforms, and by accurately monitoring and dynamically compensating the current phase offset value, the power factor of the energy storage system can be optimized, the reactive power loss can be reduced, and the energy conversion efficiency can be improved and the operation cost can be reduced.

[0088] The efficiency of the transformer, the current amplitude-frequency value and the current phase offset value are taken as the performance indicators of the energy storage system, which not only strengthens the adaptability of the energy storage system to complex power environment, but also provides a more comprehensive quantitative basis for the operation optimization of the energy storage system.

[0089] The efficiency of the transformer is directly related to energy loss, and the improvement of the efficiency of the transformer directly reduces the energy loss of the energy storage system in the charging and discharging process, so that the energy storage system can more accurately follow the grid demand in the charging and discharging process, effectively suppresses the renewable energy fluctuation, and improves the grid accommodation capacity of new energy.

[0090] After S205, the energy storage system simulation method comprises:

[0091] Step A, creating a display window, and displaying the performance indicators of the energy storage system through the display window.

[0092] After S205, the energy storage system simulation method comprises:

[0093] Step B, connecting a simulation platform of a power system, and sending the performance indicators of the energy storage system to the simulation platform.

[0094] Step A can be executed simultaneously with step B, or step A can be executed before or after step B. The specific execution order is not limited herein.

[0095] The first deep learning model uses a short-term memory network or a gated recurrent unit structure; the second deep learning model uses a multilayer perceptron or a one-dimensional convolutional neural network; the third deep learning model uses a one-dimensional convolutional neural network or a hybrid neural network; and the fourth deep learning model uses a one-dimensional convolutional neural network or a hybrid neural network.

[0096] Please see Figure 3 , Figure 3 The flowchart for obtaining performance metrics provided in the embodiments of this application is described in detail below:

[0097] S301: Obtain the output voltage from the current DC voltage signal, obtain the output current of the transformer proxy model, multiply the output voltage and output current to obtain the output power, and divide the output power by the input power to obtain the transformer efficiency.

[0098] S302 acquires the battery's state of health value and internal impedance, acquires the converter's total harmonic distortion value and energy conversion efficiency, acquires the transformer's efficiency, core loss, and winding loss, and uses the battery's state of health value, internal impedance, total harmonic distortion value, energy conversion efficiency, transformer efficiency, core loss, winding loss, current amplitude-frequency value, and current phase offset value as performance indicators of the energy storage system.

[0099] Among them, the battery's state of health value is a key indicator for assessing the degree of battery performance degradation, and is usually used to quantify the degree of degradation of the battery's current capacity or performance relative to its initial state.

[0100] In this embodiment of the application, the simulation model of the energy storage system can simulate various operating conditions at a low cost. The performance indicators of the energy storage system can be determined based on the simulation model, which can avoid the high cost and potential safety hazards of physical testing and improve the efficiency of obtaining the performance indicators of the energy storage system.

[0101] For the energy storage system simulation method described in the above embodiments, please refer to [link / reference]. Figure 4 , Figure 4 This is a schematic block diagram of an energy storage system simulation device provided in an embodiment of this application. Figure 4 The energy storage system simulation device 400 shown can be applied to, for example... Figure 1 The application scenario diagram shows electronic devices. The following section uses electronic devices as an example to illustrate this. Figure 4 The energy storage system simulation device 400 shown will be described in detail. The energy storage system simulation device 400 may include a selection module 401, a connection module 402, an input module 403, a transformation module 404, and a composition module 405.

[0102] The selecting module 401 is configured to select the trained first deep learning model as a battery agent model, select the trained second deep learning model as a storage converter agent model, select the trained third deep learning model as a filter agent model, and select the trained fourth deep learning model as a transformer agent model.

[0103] The connecting module 402 is configured to connect the battery agent model, the storage converter agent model, the filter agent model, and the transformer agent model according to a topological structure in the topological graph to obtain a simulation model of the energy storage system.

[0104] The input module 403 is configured to obtain an initial current signal and an initial voltage signal of the simulation model, process the initial current signal and the initial voltage signal through the battery agent model to obtain a current direct-current voltage signal, input the current direct-current voltage signal into the storage converter agent model, process the current direct-current voltage signal through the storage converter agent model to obtain a current alternating-current voltage signal, input the current alternating-current voltage signal into the filter agent model, process the current alternating-current voltage signal through the filter agent model to obtain a filtered current alternating-current voltage signal, a current amplitude-frequency value, and a current phase offset value.

[0105] The transforming module 404 is configured to input the filtered current alternating-current voltage signal into the transformer agent model when the current amplitude-frequency value is less than a first preset value and the current offset value is less than a second preset value, process the filtered current alternating-current voltage signal through the transformer agent model to obtain a transformed current direct-current voltage signal.

[0106] The composing module 405 is configured to obtain an output voltage from the current direct-current voltage signal, obtain an output current of the transformer agent model, multiply the output voltage and the output current to obtain an output power, divide the output power by an input power to obtain an efficiency of the transformer, and take the efficiency of the transformer, the current amplitude-frequency value, and the current phase offset value as performance indicators of the energy storage system.

[0107] It should be noted that each of the embodiments in the present specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other.

[0108] Please refer to Figure 5 , Figure 5 The structural schematic diagram of an electronic device provided by the embodiment of the present application is shown in FIG. 1.

[0109] As Figure 5 shown, Figure 5The electronic device 2 comprises at least one processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20, wherein the processor 20 implements the steps in any of the method embodiments described above when executing the computer program 22.

[0110] The electronic device 2 can comprise, but is not limited to, the processor 20 and the memory 21. Those skilled in the art can understand that the electronic device 2 can further comprise other components, such as an input / output device, a network access device, etc. Figure 5 The electronic device 2 is merely an example and does not constitute a limitation on the electronic device 2, and can comprise more or fewer components than shown, or combine certain components, or comprise different components, for example, can further comprise an input / output device, a network access device, etc.

[0111] The processor 20 is configured to execute the computer program 22 stored in the memory 21.

[0112] The processor 20 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits, field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor.

[0113] The memory 21 can be an internal storage unit of the electronic device 2 in some embodiments, for example, a hard disk or a memory of the electronic device 2. The memory 21 can also be an external storage device of the electronic device 2 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 21 can comprise both an internal storage unit and an external storage device of the electronic device 2. The memory 21 is configured to store an operating system, an application program, a boot loader, data, and other programs, for example, program codes of the computer program, etc. The memory 21 can also be configured to temporarily store data that has been output or will be output.

[0114] It should be noted that the information interaction and execution process between the above-described apparatuses / units, since based on the same concept as the method embodiments, the specific functions and the technical effects brought by the same can be referred to the method embodiments part, and will not be described here.

[0115] The embodiment of the present application provides a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program is executed by a processor to realize the steps in each method embodiment.

[0116] The embodiment of the present application provides a computer program product, when the computer program product runs on the electronic device, makes the electronic device execute the energy storage system simulation method.

[0117] In the above embodiment, the description of each embodiment has its own emphasis, and the part not described or recorded in a certain embodiment can be referred to the related description of other embodiments.

[0118] The above is only the preferred embodiment of the present application, and does not limit the patent range of the present application, and any equivalent structure or equivalent flow transformation using the content of the specification and the drawings of the present application, or directly or indirectly applied in other related technical fields, are also included in the patent protection range of the present application.

Claims

1. A method for simulation of an energy storage system based on a proxy model, characterized in that, The energy storage system simulation method is applied to an electronic device and comprises the following steps: The trained first deep learning model is selected as the battery agent model, the trained second deep learning model is selected as the energy storage converter agent model, the trained third deep learning model is selected as the filter agent model, and the trained fourth deep learning model is selected as the transformer agent model; According to the topological structure in the topological graph, the battery agent model, the energy storage converter agent model, the filter agent model, and the transformer agent model are connected to obtain a simulation model of the energy storage system; The initial current signal and the initial voltage signal of the simulation model are obtained, the initial current signal and the initial voltage signal are processed by the battery agent model to obtain a current direct-current voltage signal, the current direct-current voltage signal is input into the energy storage converter agent model, the current direct-current voltage signal is processed by the energy storage converter agent model to obtain a current alternating-current voltage signal, the current alternating-current voltage signal is input into the filter agent model, the current alternating-current voltage signal is processed by the filter agent model to obtain a filtered current alternating-current voltage signal, a current amplitude-frequency value, and a current phase offset value; When the current amplitude-frequency value is less than a first preset value and the current offset value is less than a second preset value, the filtered current alternating-current voltage signal is input into the transformer agent model, the filtered current alternating-current voltage signal is processed by the transformer agent model to obtain a transformed current direct-current voltage signal; An output voltage is obtained from the current direct-current voltage signal, an output current of the transformer agent model is obtained, the output voltage and the output current are multiplied to obtain an output power, the output power is divided by an input power to obtain an efficiency of the transformer, and the efficiency of the transformer, the current amplitude-frequency value, and the current phase offset value are taken as performance indicators of the energy storage system.

2. The energy storage system simulation method of claim 1, wherein, The trained first deep learning model is selected as the battery agent model, the trained second deep learning model is selected as the energy storage converter agent model, the trained third deep learning model is selected as the filter agent model, and the trained fourth deep learning model is selected as the transformer agent model, which comprises the following steps: A first output variable corresponding to a preset first input variable is obtained, the preset first input variable and the first output variable are combined to form a battery data sample, different battery data samples are combined to form a first data set, the first deep learning model is trained using the first data set to obtain a trained first deep learning model, and the trained first deep learning model is selected as the battery agent model, the preset first input variable includes a preset current signal and a preset voltage signal of the battery, and the first output variable includes a direct-current voltage signal; A second input variable and a second output variable are obtained, the second input variable and the second output variable are combined to form a voltage data sample, different voltage data samples are combined to form a second data set, the second deep learning model is trained using the second data set, and the trained second deep learning model is selected as the energy storage converter agent model, the second input variable includes a preset direct-current voltage signal, and the second output variable includes a preset alternating-current side voltage signal; The third input variable and the third output variable are obtained, the third input variable and the third output variable are combined to form a filter data sample, different filter data samples are combined to form a third data set, the third data set is used to train a third deep learning model, and a trained third deep learning model is obtained; the trained third deep learning model is selected as a filter proxy model; the third input variable includes a preset alternating current side voltage signal; and the third output variable includes a filtered preset alternating current side voltage signal, a preset amplitude-frequency value, and a preset phase shift value. The fourth input variable and the fourth output variable are obtained, the fourth input variable and the fourth output variable are combined to form a transformer data sample, different transformer data samples are combined to form a fourth data set, the fourth data set is used to train a fourth deep learning model, and a trained fourth deep learning model is obtained; the trained fourth deep learning model is selected as a transformer proxy model; the fourth input variable includes a filtered preset alternating current side voltage signal; and the fourth output variable includes a transformed preset alternating current side voltage signal.

3. The energy storage system simulation method of claim 1, wherein, The battery proxy model, the energy storage converter proxy model, the filter proxy model, and the transformer proxy model are connected according to the topological structure in the topological graph to obtain a simulation model of the energy storage system. The topological graph corresponding to the power system is obtained, and the battery proxy model, the energy storage converter proxy model, the filter proxy model, and the transformer proxy model are connected according to the topological structure in the topological graph to obtain a simulation model of the energy storage system.

4. The energy storage system simulation method of claim 1, wherein, The output voltage is obtained from the current direct current voltage signal, the output current of the transformer proxy model is obtained, the output voltage and the output current are multiplied to obtain the output power, the output power is divided by the input power to obtain the efficiency of the transformer, and the efficiency of the transformer, the current amplitude-frequency value, and the current phase shift value are taken as performance indicators of the energy storage system. The output voltage is obtained from the current direct current voltage signal, the output current of the transformer proxy model is obtained, the output voltage and the output current are multiplied to obtain the output power, the output power is divided by the input power to obtain the efficiency of the transformer. The health state value of the battery, the internal impedance of the battery, the total harmonic distortion value of the converter, the energy conversion efficiency of the converter, the efficiency of the transformer, the core loss of the transformer, and the winding loss of the transformer are obtained, and the health state value of the battery, the internal impedance of the battery, the total harmonic distortion value of the converter, the energy conversion efficiency of the converter, the efficiency of the transformer, the core loss of the transformer, the winding loss of the transformer, the current amplitude-frequency value, and the current phase shift value are taken as performance indicators of the energy storage system.

5. The energy storage system simulation method of claim 1, wherein, After the output voltage is obtained from the current direct current voltage signal, the output current of the transformer proxy model is obtained, the output voltage and the output current are multiplied to obtain the output power, the output power is divided by the input power to obtain the efficiency of the transformer, and the efficiency of the transformer, the current amplitude-frequency value, and the current phase shift value are taken as performance indicators of the energy storage system, the energy storage system simulation method comprises: A display window is created, and the performance indicators of the energy storage system are displayed through the display window.

6. The energy storage system simulation method of claim 1, wherein, After obtaining the output voltage from the current direct-current voltage signal, obtaining the output current of the transformer agent model, multiplying the output voltage and the output current to obtain the output power, dividing the output power by the input power to obtain the efficiency of the transformer, and taking the efficiency of the transformer, the current amplitude-frequency value and the current phase offset value as the performance indicators of the energy storage system, the energy storage system simulation method comprises: A simulation platform connected to the power system, and sending the performance indicators of the energy storage system to the simulation platform.

7. The energy storage system simulation method of claim 2, wherein, The first deep learning model adopts a short-term memory network or a gated recurrent unit structure, the second deep learning model adopts a multi-layer perceptron or a one-dimensional convolutional neural network; the third deep learning model adopts a one-dimensional convolutional neural network or a hybrid neural network; and the fourth deep learning model adopts a one-dimensional convolutional neural network or a hybrid neural network.

8. A storage system simulation device for implementing the storage system simulation method according to claim 1, characterized by, Applied to an electronic device, comprising: A selection module for selecting the trained first deep learning model as a battery agent model, selecting the trained second deep learning model as an energy storage converter agent model, selecting the trained third deep learning model as a filter agent model, and selecting the trained fourth deep learning model as a transformer agent model; A connection module for connecting the battery agent model, the energy storage converter agent model, the filter agent model and the transformer agent model according to the topological structure in the topological graph to obtain a simulation model of the energy storage system; An input module for obtaining an initial current signal and an initial voltage signal of the simulation model, processing the initial current signal and the initial voltage signal through the battery agent model to obtain a current direct-current voltage signal, inputting the current direct-current voltage signal into the energy storage converter agent model, processing the current direct-current voltage signal through the energy storage converter agent model to obtain a current alternating-current voltage signal, inputting the current alternating-current voltage signal into the filter agent model, and processing the current alternating-current voltage signal through the filter agent model to obtain a filtered current alternating-current voltage signal, a current amplitude-frequency value and a current phase offset value; A transformation module for inputting the filtered current alternating-current voltage signal into the transformer agent model when the current amplitude-frequency value is less than a first preset value and the current offset value is less than a second preset value, processing the filtered current alternating-current voltage signal through the transformer agent model to obtain a transformed current direct-current voltage signal; A composition module for obtaining an output voltage from the current direct-current voltage signal, obtaining an output current of the transformer agent model, multiplying the output voltage and the output current to obtain an output power, dividing the output power by the input power to obtain the efficiency of the transformer, and taking the efficiency of the transformer, the current amplitude-frequency value and the current phase offset value as the performance indicators of the energy storage system.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the energy storage system simulation method of any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to realize the energy storage system simulation method of any one of claims 1 to 7.

Images