Converter index evaluation model determination method and device and storage medium

Abstract

The invention provides a method and a device for determining an index evaluation model of a converter and a storage medium. The method comprises the following steps: configuring an executable script file; executing the executable script file to generate at least one group of target control parameter sets, wherein the target control parameter sets comprise control parameters of a plurality of converters; performing a simulation test on each target control parameter set in a target scene to obtain corresponding performance index data, the performance index data being data representing an operation state when the converter operates by using the control parameters in the target control parameter set in the target scene; and training the neural network to be trained by adopting the target control parameter set and the corresponding performance index data to obtain a digital twin model which is used for evaluating the performance index of the converter. According to the method, the influence of the converter control parameters on the performance indexes is quantitatively described with short time consumption and high accuracy by improving the construction method of the relation between the converter control parameters and the performance indexes.

Description

Technical Field

[0001] The present application relates to the field of converter control systems, and in particular, to a method for determining an index evaluation model of a converter, a device for determining an index evaluation model of a converter, a computer-readable storage medium, and an electronic device. Background Art

[0002] With the continuous increase in the scale of renewable energy deployment, energy storage converters are increasingly widely used in AC / DC hybrid power systems. As the degree of power electronics increases, the system regulation capability and response speed are improved, while the inertia and damping of the system are weakened and reduced, which brings great challenges to the stable operation of the system. Therefore, the importance of converter control system design has become increasingly prominent. For traditional energy storage converters, according to different application scenarios, their control systems need to consider goals such as power reference tracking and DC bus voltage control.

[0003] The control parameters and control performance indicators of the converter, especially dynamic performance indicators such as overshoot and rise time, usually do not have a direct linear relationship, and it is difficult to quantitatively characterize them through theoretical research. For this reason, existing solutions mostly use computer software simulation and converter hardware experiments to quantitatively evaluate multiple groups of different control parameters. Due to the need to exhaustively evaluate different control parameters, traditional solutions require a large number of simulations or hardware experimental tests, which is time-consuming and inefficient. Summary of the invention

[0004] The main purpose of the present application is to provide a method for determining an indicator evaluation model of a converter, a device for determining an indicator evaluation model of a converter, a computer-readable storage medium and an electronic device, so as to at least solve the problem that the existing method for determining converter control parameters requires a large amount of simulation or hardware experimental testing, which is time-consuming and inefficient.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for determining an index evaluation model of a converter is provided, comprising: configuring an executable script file; executing the executable script file to generate at least one set of target control parameter sets, wherein the target control parameter set includes multiple control parameters of the converter, and the control parameters are parameters for controlling the operation of the converter; performing simulation tests on each of the target control parameter sets under a target scenario to obtain corresponding performance indicator data, wherein the performance indicator data is data characterizing the operating state of the converter when the converter operates using the control parameters in the target control parameter set under the target scenario; training a neural network to be trained using the target control parameter set and the corresponding performance indicator data to obtain a digital twin model, and the digital twin model is used to evaluate the performance indicators of the converter.

[0006] Optionally, executing the executable script file to generate at least one set of target control parameter sets includes: obtaining a preset parameter scale, the preset parameter scale including: a preset number of control parameter sets and a preset value range of each control parameter; executing the executable script file based on the preset parameter scale to generate an initial control parameter set, the values ​​of the control parameters in the initial control parameter set are all within the corresponding preset value range; determining whether the number of the generated initial control parameter sets reaches the preset number; if the number of the generated initial control parameter sets reaches the preset number, determining all the generated initial control parameter sets as the target control parameter sets; if the number of the generated initial control parameter sets does not reach the preset number, based on the preset parameter scale and the principle of independent and identical distribution, continue to execute the executable script file to generate the initial control parameter set again.

[0007] Optionally, each of the target control parameter sets is subjected to a simulation test under a target scenario to obtain corresponding performance indicator data, including: inputting each of the target control parameter sets into a converter control simulation system in turn for simulation testing; setting the test scenario to the target scenario, and sequentially performing simulation tests on each of the target control parameter sets under the target scenario; obtaining key simulation waveform data obtained by the simulation test of each of the target control parameter sets, the target control parameter sets and the key simulation waveform data corresponding one to one; and processing the key simulation waveform data to obtain performance indicator data corresponding to each of the target control parameter sets.

[0008] Optionally, the key simulation waveform data includes the active power step response waveform file and the reactive power step response waveform file of the converter, and the key simulation waveform data are processed to obtain performance indicator data corresponding to each target control parameter set, including: processing the active power step response waveform file and the reactive power step response waveform file of the converter to obtain the rise time of the active power of the converter, the cumulative integral error of the active power, and the percentage overshoot of the active power, as well as the rise time of the reactive power of the converter, the cumulative integral error of the reactive power, and the percentage overshoot of the reactive power, so as to obtain the performance indicator data.

[0009] Optionally, the target control parameter set and the corresponding performance indicator data are used to train the neural network to be trained to obtain a digital twin model, including: determining the dimension of the data to be fitted according to the number of control parameters in one of the target control parameter sets, and determining the amount of training data according to the data in all the target control parameter sets; determining the structure of the neural network to be trained according to the dimension of the data to be fitted and the amount of training data, the structure of the neural network to be trained including at least the number of neural network layers and the number of neurons in each layer of the neural network; taking all the control parameters in the target control parameter sets as input, and taking the performance indicator data corresponding to each target control parameter set as output, training and fitting the neural network to be trained to obtain the digital twin model.

[0010] Optionally, the control parameters of the converter include: PI parameters of a voltage loop based on dual-loop control and PI parameters of a current loop based on dual-loop control, wherein P is a proportional coefficient and I is an integral coefficient.

[0011] Optionally, after using the target control parameter set and the corresponding performance indicator data to train the neural network to be trained and obtain the digital twin model, the method also includes: obtaining the actual control parameters of the converter at the current moment, the actual control parameters are the control parameters used by the converter in the actual operation process at the current moment; inputting the actual control parameters into the digital twin model to obtain the actual performance indicators of the converter, the actual performance indicators are performance data that characterize the actual operating state of the converter at the current moment; and determining the current operating state of the converter according to the actual performance indicators of the converter.

[0012] According to another aspect of the present application, a device for determining an index evaluation model of a converter is provided, comprising: a first processing unit, for configuring an executable script file, wherein the executable script file is used to generate control parameters of the converter, wherein the control parameters are parameters for controlling the operation of the converter; a second processing unit, for executing the executable script file to generate at least one set of target control parameter sets, wherein the target control parameter set includes a plurality of the control parameters; a third processing unit, for performing simulation tests on each of the target control parameter sets under a target scenario to obtain corresponding performance index data, wherein the performance index data is data characterizing the operating state of the converter under the target scenario when the converter operates with the control parameters in the target control parameter set; and a fourth processing unit, for training a neural network to be trained using the target control parameter set and the corresponding performance index data to obtain a digital twin model, wherein the digital twin model is used to evaluate the performance index of the converter.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods for determining an indicator evaluation model of a converter.

[0014] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for determining an indicator evaluation model for executing any one of the above-mentioned converters.

[0015] Applying the technical solution of the present application, a method for determining an index evaluation model of the above-mentioned converter first configures an executable script file; then executes the executable script file to generate at least one set of target control parameter sets, the target control parameter set including control parameters of multiple converters, the control parameters being parameters for controlling the operation of the converter; then, a simulation test is performed on each target control parameter set under a target scenario to obtain corresponding performance indicator data, the performance indicator data being data characterizing the operating state of the converter when the converter operates using the control parameters in the target control parameter set under the target scenario; finally, the target control parameter set and the corresponding performance indicator data are used to train the neural network to be trained to obtain a digital twin model, which is used to evaluate the performance indicators of the converter. This method improves the method of constructing the relationship between converter control parameters and performance indicators, quantitatively describes the influence of converter control parameters on performance indicators in a short time and with high accuracy, thereby providing guidance and basis for the design of converter control systems. Compared with the traditional exhaustive control parameter performance evaluation method based on a large number of software simulations / experimental tests, it can greatly reduce the required time cost while ensuring accuracy, and can be used for the design of converter control systems in new power systems with a high degree of power electronics, solving the problem that the existing method for determining converter control parameters requires a large number of simulations or hardware experimental tests, which is time-consuming and inefficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for performing a method for determining an indicator evaluation model of a converter provided in an embodiment of the present application is shown;

[0018] Figure 2A schematic flow chart of a method for determining an indicator evaluation model of a converter provided in accordance with an embodiment of the present application is shown;

[0019] Figure 3 A topological structure diagram of an MMC energy storage converter provided according to an embodiment of the present application is shown;

[0020] Figure 4 A control block diagram of an energy storage MMC converter provided according to an embodiment of the present application is shown;

[0021] Figure 5 A neural network structure diagram provided according to an embodiment of the present application is shown;

[0022] Figure 6 A schematic diagram of the accuracy of the cumulative integral error model provided according to an embodiment of the present application is shown;

[0023] Figure 7 A schematic diagram of the accuracy of the overshoot model provided according to an embodiment of the present application is shown;

[0024] Figure 8 A schematic diagram of the accuracy of a rise time model provided according to an embodiment of the present application is shown;

[0025] Fig. 9 A schematic diagram showing the indicators of cumulative integral error, overshoot and rise time fitting provided in an embodiment of the present application is shown;

[0026] Fig.10 A schematic diagram of a system for constructing a digital twin model between converter control parameters and performance indicators provided according to an embodiment of the present application is shown;

[0027] Fig.11 A schematic flow chart of another method for determining an indicator evaluation model of a converter provided in accordance with an embodiment of the present application is shown;

[0028] Fig.12 A structural block diagram of a device for determining an indicator evaluation model of a converter provided according to an embodiment of the present application is shown.

[0029] The above drawings include the following reference numerals:

[0030] 11. Executable script file; 12. Control parameter set generation module; 13. Converter control simulation system; 14. Performance index synthesis module; 15. Neural network trainer; 102. Processor; 104. Memory; 106. Transmission equipment; 108. Input and output equipment. DETAILED DESCRIPTION

[0031] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0032] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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 ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0035] A converter is a power electronic device used to convert one form of electrical energy into another. It plays a key role in modern power electronics and power transmission systems, and can improve energy efficiency, reduce energy consumption, and achieve flexible control and management of electrical energy.

[0036] Digital twin is an advanced digital technology that creates a virtual model of a physical object, system or process, which is a digital copy of the physical entity.

[0037] As introduced in the background technology, the modular multilevel converter (MMC) energy storage inverter is an advanced power electronic device that can efficiently convert between alternating current (AC) and direct current (DC). It plays an important role in energy storage systems. By combining with batteries or supercapacitors, it can store and release energy, provide additional power during peak power demand periods, and store excess power during low periods, thereby balancing the grid load. In addition, MMC energy storage inverters can also support the access of renewable energy, improve grid stability and power quality, and are widely used in modern power systems such as smart grids and microgrids.

[0038] For traditional energy storage converters, according to different application scenarios, their control systems need to consider power reference tracking, DC bus voltage control and other goals. Taking the most common power reference tracking as an example, the converter control system usually uses a dual-loop feedback control method to control the active and reactive power on the AC side, including outer and inner loop control: the outer loop control includes two controllers, usually proportional integral controller (PI), whose inputs are the tracking errors of active and reactive power, and whose outputs are the references of the two components of the converter AC side phase current in the dq (direct-quadrature) coordinate system; the inner loop control is also usually based on the PI controller, tracking the current reference given by the outer loop control, and its output is input to the converter modulation module as a voltage reference signal.

[0039] In addition, in order to improve the operation of the converter and enhance its performance, additional control modules or links are usually introduced into the converter control system. For example, when the active / reactive power reference changes, the converter is prone to overshoot and oscillation in the step transient. To solve this problem, an adaptive power reference module can be introduced to adaptively and dynamically adjust the outer loop active / reactive power reference of the aforementioned dual-loop feedback controller. These newly added control links and modules not only improve the control performance but also introduce additional control parameters.

[0040] In order to solve the problem that the existing method for determining the control parameters of the converter requires a large number of simulations or hardware experimental tests, which is time-consuming and inefficient, the embodiments of the present application provide a method for determining an index evaluation model of the converter, a device for determining the index evaluation model of the converter, a computer-readable storage medium and an electronic device.

[0041] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0042] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of a method for determining an indicator evaluation model of a converter according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0043] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for determining the index evaluation model of the converter in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0044] In this embodiment, a method for determining an indicator evaluation model of a converter running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0045] Figure 2 FIG. 1 is a flow chart of a method for determining an indicator evaluation model of a converter according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0046] Step S201, configuring an executable script file;

[0047] Specifically, the executable file refers to a script file in the real-time simulation software (RTDS) in the field of power systems, which is implemented by a C-like language and is a file in script form.

[0048] The control parameters are generated in the script file, a set of parameters that are within the control parameter range and are obtained by random uniform distribution.

[0049] Step S202, executing the executable script file to generate at least one set of target control parameter sets, wherein the target control parameter set includes a plurality of control parameters of the converter, and the control parameters are parameters for controlling the operation of the converter;

[0050] Specifically, generating multiple sets of target control parameter sets can help optimize the operation of the converter, improve its efficiency and performance, better understand the operating mechanism of the converter, and improve the ability to grasp and adjust its control parameters.

[0051] in, Figure 3 A topological structure diagram of an MMC energy storage converter is shown in FIG. Figure 3 As shown, a modular multilevel converter topology is adopted, with 20 submodules on each bridge arm. The DC power on the submodule is converted into AC power through switching signals and transmitted to the grid.

[0052] Figure 4 Based on Figure 3 The energy storage MMC converter control block diagram is as follows: Figure 4 As shown, the active power and reactive power are calculated by collecting the voltage and current signals on the grid side, which are used as the input signals of the controller. The modulation wave signal is generated by calculating the power outer loop and the current inner loop, and finally converted into the switching signal of the modular multilevel converter through modulation.

[0053] The control parameters of the above converter include: PI parameters of the voltage loop based on dual-loop control and PI parameters of the current loop based on dual-loop control, where P is the proportional coefficient and I is the integral coefficient. The control parameters of the above converter are respectively Figure 4 In kp1, ki1, kp2, ki2, each group of control parameters means a combination of values ​​of four parameters. The value range refers to the value range of various control parameters.

[0054] Specifically, by properly adjusting the PI parameters, the system response speed can be made faster, a faster control response can be achieved, and the overshoot and oscillation of the system can be effectively reduced, thereby improving the stability of the system.

[0055] The execution of the above executable script file to generate at least one set of target control parameter sets includes the following steps:

[0056] Step S301, obtaining a preset parameter scale, the preset parameter scale including: a preset number of control parameter sets and a preset value range of each of the control parameters;

[0057] Step S302, executing the executable script file based on the preset parameter scale to generate an initial control parameter set, wherein the values ​​of the control parameters in the initial control parameter set are all within the corresponding preset value range;

[0058] Step S303, determining whether the number of the generated initial control parameter sets reaches the preset number;

[0059] Step S304, when the number of the generated initial control parameter sets reaches the preset number, all the generated initial control parameter sets are determined as the target control parameter sets;

[0060] Step S305, when the number of the generated initial control parameter sets does not reach the preset number, based on the preset parameter scale and the principle of independent and identical distribution, continue to execute the executable script file to generate the initial control parameter set again.

[0061] Specifically, digital twin technology is used to quantitatively describe and characterize the relationship between converter control parameters and performance indicators, and automatically generate a set of control parameters, reducing the need for manual intervention and improving efficiency. The preset scale is often set based on manual experience.

[0062] The executable file is executed in a loop and stops running after the required number of groups is reached. The performance indicator set is generated in a loop. If there are not enough groups and performance indicators, only the control parameter set needs to be generated.

[0063] Step S203, performing simulation tests on each of the target control parameter sets under a target scenario to obtain corresponding performance indicator data, wherein the performance indicator data is data representing the operating state of the converter under the target scenario when the converter operates with the control parameters in the target control parameter set;

[0064] Specifically, through simulation testing, a large amount of data can be quickly acquired, analyzed and compared, so as to quickly find the optimal control parameters and improve the performance and efficiency of the converter.

[0065] The simulation test is performed on each of the above target control parameter sets under the target scenario to obtain the corresponding performance index data, including the following steps:

[0066] Step S401, inputting each of the above target control parameter sets into a converter control simulation system in sequence for simulation testing;

[0067] Step S402, setting the test scenario to the above target scenario, and sequentially performing simulation tests on each of the above target control parameter sets under the above target scenario;

[0068] Step S403, acquiring key simulation waveform data obtained by performing simulation tests on each of the above target control parameter sets, wherein the above target control parameter sets correspond to the above key simulation waveform data one by one;

[0069] Step S404: Process the above key simulation waveform data to obtain performance indicator data corresponding to each of the above target control parameter sets.

[0070] The above key simulation waveform data include the active power step response waveform file and the reactive power step response waveform file of the above converter. The above key simulation waveform data are processed to obtain the performance index data corresponding to each of the above target control parameter sets, including:

[0071] The active power step response waveform file and the reactive power step response waveform file of the above-mentioned converter are processed to obtain the rise time of the active power, the cumulative integral error of the active power, the percentage overshoot of the active power of the above-mentioned converter, and the rise time of the reactive power, the cumulative integral error of the reactive power, and the percentage overshoot of the reactive power of the above-mentioned converter, so as to obtain the above-mentioned performance indicator data.

[0072] Specifically, by processing the waveform file, the performance index data of the converter can be directly obtained without manual calculation and analysis, which reduces the possibility of human error and improves the accuracy and efficiency of data processing.

[0073] Specifically, by analyzing the performance indicator data, the optimal control parameter set can be found to optimize system performance, and different parameter combinations can be simulated and tested quickly, thereby improving test efficiency.

[0074] Step S204: Use the above-mentioned target control parameter set and the corresponding above-mentioned performance indicator data to train the neural network to be trained to obtain a digital twin model, and the above-mentioned digital twin model is used to evaluate the performance indicators of the above-mentioned converter.

[0075] Specifically, the digital twin model can be trained based on actual data and can more accurately predict the performance indicators of the converter. By continuously optimizing the model, the accuracy of the evaluation results can be improved.

[0076] The target control parameter set and the corresponding performance index data are used to train the neural network to obtain the digital twin model, which includes the following steps:

[0077] Step S501, determining the dimension of the data to be fitted according to the number of the control parameters in one of the target control parameter sets, and determining the amount of training data according to the data in all of the target control parameter sets;

[0078] Step S502, determining the structure of the neural network to be trained according to the dimension of the data to be fitted and the amount of training data, wherein the structure of the neural network to be trained at least includes the number of neural network layers and the number of neurons in each neural network layer;

[0079] Among them, according to Figure 4 and Figure 5 As shown, Figure 5 A neural network structure diagram is shown. The neural network includes an input layer, a hidden layer, and an output layer. Since the input data is four data and the output is a set of indicator data, the dimension of the input layer is four and the dimension of the output layer is one. The data dimension is actually the dimension of the control parameter, that is, the four input parameters, which are Figure 4 kp1, ki1, kp2, ki2, and an output parameter. The amount of data is determined by the retention method, with 20% of the groups being used as validation sets and 80% being used as training sets.

[0080] Step S503, taking all the control parameters in the above-mentioned target control parameter sets as input, and taking the above-mentioned performance indicator data corresponding to each of the above-mentioned target control parameter sets as output, training and fitting the above-mentioned neural network to be trained, and obtaining the above-mentioned digital twin model.

[0081] Specifically, a neural network model is used to fit complex multi-parameter systems to achieve prediction and optimization of system behavior. The trained digital twin model can quickly and accurately simulate and analyze the system, helping to optimize system control parameters.

[0082] Figure 6 A schematic diagram of the accuracy of a cumulative integral error model is shown; Figure 7 A schematic diagram of overshoot model accuracy is shown; Figure 8 A rise time model accuracy diagram is shown.

[0083] In some instances, such as Figure 6 As shown, Figure 6 (a) and Figure 6 (b) The cumulative integrated error response of active power and the cumulative integrated error response of reactive power, respectively. Figure 6 The horizontal axis of (a) is the actual value of the input active power cumulative error integral, and the vertical axis is the predicted value of the output active power cumulative error integral. Figure 6 The horizontal axis of (b) is the actual value of the input reactive power cumulative error integral, and the vertical axis is the predicted value of the output reactive power cumulative error integral. The points falling on the straight line indicate that the prediction result is accurate.

[0084] like Figure 7 As shown, Figure 7 (a) and Figure 7 (b) The overshoot model accuracy responses of active power and reactive power, respectively. Figure 7 The horizontal axis of (a) is the actual value of the input active power percentage overshoot, and the vertical axis is the predicted value of the output active power percentage overshoot. Figure 7 The horizontal axis of (b) is the actual value of the input reactive power percentage overshoot, and the vertical axis is the predicted value of the output reactive power percentage overshoot. The points falling on the straight line indicate that the prediction result is accurate.

[0085] like Figure 8 As shown, Figure 8 (a) and Figure 8 (b) The rise time model accuracy responses of active power and reactive power, respectively. Figure 8 The horizontal axis of (a) is the actual value of the input active power rise time, and the vertical axis is the predicted value of the output active power rise time. Figure 8 The horizontal axis of (b) is the actual value of the input reactive power rise time, and the vertical axis is the predicted value of the output reactive power rise time. The points falling on the straight line indicate that the prediction result is accurate.

[0086] in, Figure 6 , Figure 7 , Figure 8 It is used to illustrate the effect of fitting.

[0087] According to the collected waveform data, the rise time, cumulative integral error, and percentage overshoot are obtained through time domain indicators. Fig. 9 FIG. 1 shows a schematic diagram of an indicator for fitting the cumulative integral error, overshoot and rise time according to an embodiment of the present application. Fig. 9 It is also divided into active index introduction and reactive index introduction, where t1-t0 is the rise time, the shaded area is the cumulative integral error, and a / b is the percentage overshoot.

[0088] Wherein, after the target control parameter set and the corresponding performance indicator data are used to train the neural network to be trained and the digital twin model is obtained, the method further includes the following steps:

[0089] Step S601, obtaining actual control parameters of the converter at the current moment, where the actual control parameters are control parameters used by the converter during actual operation at the current moment;

[0090] Step S602: input the actual control parameters into the digital twin model to obtain the actual performance index of the converter, where the actual performance index is performance data representing the actual operating state of the converter at the current moment;

[0091] Step S603: determining the current operating state of the converter according to the actual performance index of the converter.

[0092] Specifically, the digital twin model simulates and analyzes the actual control parameters of the converter, which can more accurately characterize the actual operating status of the converter, improve the accuracy of judgment, and significantly reduce the time cost while ensuring accuracy.

[0093] The method for determining the index evaluation model of the above-mentioned converter of the present application first configures an executable script file; then executes the executable script file to generate at least one set of target control parameter sets, the target control parameter set includes control parameters of multiple converters, and the control parameters are parameters for controlling the operation of the converter; then, each target control parameter set is subjected to a simulation test under a target scenario to obtain corresponding performance index data, and the performance index data is data characterizing the operating state of the converter when the converter adopts the control parameters in the target control parameter set under the target scenario; finally, the target control parameter set and the corresponding performance index data are used to train the neural network to be trained to obtain a digital twin model, and the digital twin model is used to evaluate the performance index of the converter. This method improves the method of constructing the relationship between converter control parameters and performance indicators, quantitatively describes the influence of converter control parameters on performance indicators in a short time and with high accuracy, thereby providing guidance and basis for the design of converter control systems. Compared with the traditional exhaustive control parameter performance evaluation method based on a large number of software simulations / experimental tests, it can greatly reduce the required time cost while ensuring accuracy, and can be used for the design of converter control systems in new power systems with a high degree of power electronics, solving the problem that the existing method for determining converter control parameters requires a large number of simulations or hardware experimental tests, which is time-consuming and inefficient.

[0094] Fig.10 It is a system for constructing a digital twin model between converter control parameters and performance indicators, such as Fig.10As shown, the system includes an executable script file 11, a control parameter set generation module 12, a converter control simulation system 13, a performance index synthesis module 14, and a neural network trainer 15. By configuring the executable script file 11, the control parameter set generation module 12, the converter control simulation system 13, and the performance index synthesis module 14 are called to obtain the performance index data of the converter controller under specific control parameters. The control parameter set generation module 12 is used to generate specific control parameters to be tested within the specified parameter value range, and then input them to the converter control simulation system 13 for simulation testing under specific scenarios. The key simulation waveform data is output to the performance index synthesis module 14, which is used to extract and calculate the performance index for evaluating the control performance under specific converter control parameters from the key simulation waveform data, and store the results. Then, the neural network trainer 15 uses the control parameter set generated by the control parameter set generation module 12 as input and the corresponding performance index set synthesized and stored by the performance index synthesis module 14 as output to perform neural network fitting.

[0095] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for determining the indicator evaluation model of the converter of the present application will be described in detail below in combination with specific embodiments.

[0096] This embodiment relates to a specific method for determining an indicator evaluation model of a converter, such as Fig.11 As shown, the following steps are included:

[0097] Step S1: Determine the number of control parameter groups to be generated and the value range;

[0098] Step S2: configure the executable script file;

[0099] Step S3: Determine whether the number of generated control parameter groups reaches a preset scale; if so, go to step S8, otherwise go to step S4;

[0100] Step S4: generating a set of new control parameters within the range of converter control parameters preset in step S1 according to the principle of independent and identical distribution;

[0101] Step S5: applying the set of control parameters newly generated in step S4 to the converter control simulation system, and performing simulation testing under a specific performance evaluation scenario;

[0102] Step S6: Obtain key simulation waveform data corresponding to the simulation test in step S5;

[0103] Step S7: Process the waveform data obtained in step S6, calculate and store the performance index, and turn to step S3;

[0104] Step S8: Determine the structure of the neural network to be trained according to the dimension and amount of the data to be fitted, including the number of neural network layers, the number of neurons in each layer of the neural network, etc.;

[0105] Step S9: using the set of all control parameters generated in step S4 and the set of corresponding performance indicators synthesized in step S7 as input and output respectively, training and fitting the neural network of the structure determined in step S8;

[0106] Step S10: generating a digital twin model describing the relationship between the converter control parameters and the performance indicators;

[0107] Step S11: End.

[0108] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0109] The embodiment of the present application also provides a device for determining an index evaluation model of a converter. It should be noted that the device for determining an index evaluation model of a converter in the embodiment of the present application can be used to execute the method for determining an index evaluation model for a converter provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have been described will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0110] The following introduces a device for determining an indicator evaluation model of a converter provided in an embodiment of the present application.

[0111] Fig.12 is a schematic diagram of a device for determining an indicator evaluation model of a converter according to an embodiment of the present application. Fig.12As shown, the device includes: a first processing unit 10, a second processing unit 20, a third processing unit 30 and a fourth processing unit 40, the first processing unit 10 is used to configure an executable script file, the above executable script file is used to generate control parameters of the converter, and the above control parameters are parameters for controlling the operation of the converter; the second processing unit 20 is used to execute the above executable script file to generate at least one set of target control parameter sets, and the above target control parameter set includes multiple control parameters; the third processing unit 30 is used to perform simulation tests on each of the above target control parameter sets under a target scenario to obtain corresponding performance indicator data, and the above performance indicator data is data characterizing the operating state of the above converter when the above control parameters in the above target control parameter set are used to operate under the above target scenario; the fourth processing unit 40 is used to train the neural network to be trained using the above target control parameter set and the corresponding performance indicator data to obtain a digital twin model, and the above digital twin model is used to evaluate the performance indicators of the above converter.

[0112] The device for determining the index evaluation model of the above-mentioned converter of the present application includes: a first processing unit, a second processing unit, a third processing unit and a fourth processing unit, the first processing unit is used to configure an executable script file, the executable script file is used to generate control parameters of the converter, and the control parameters are parameters for controlling the operation of the converter; the second processing unit is used to execute the executable script file to generate at least one set of target control parameter sets, and the target control parameter set includes multiple control parameters; the third processing unit is used to perform simulation tests on each target control parameter set under a target scenario to obtain corresponding performance indicator data, and the performance indicator data is data that characterizes the operating state of the converter when the control parameters in the target control parameter set are used to operate under the target scenario; the fourth processing unit is used to train the neural network to be trained using the target control parameter set and the corresponding performance indicator data to obtain a digital twin model, and the digital twin model is used to evaluate the performance indicators of the converter. The device improves the method of constructing the relationship between converter control parameters and performance indicators, quantitatively describes the influence of converter control parameters on performance indicators in a short time and with high accuracy, thereby providing guidance and basis for the design of converter control systems. Compared with the traditional exhaustive control parameter performance evaluation method based on a large number of software simulations / experimental tests, it can greatly reduce the required time cost while ensuring accuracy. It can be used for the design of converter control systems in new power systems with a high degree of power electronics, and solves the problem that the existing method for determining converter control parameters requires a large number of simulations or hardware experimental tests, which is time-consuming and inefficient.

[0113] In some examples, the second processing unit includes a first acquisition module, a first processing module, a first determination module and a second determination module, the first acquisition module is used to acquire a preset parameter scale, the preset parameter scale includes: a preset number of control parameter sets and a preset value range of each of the control parameters; the first processing module is used to execute the executable script file based on the preset parameter scale to generate an initial control parameter set, the values ​​of the control parameters in the initial control parameter set are all within the corresponding preset value range; the first determination module is used to determine whether the number of the generated initial control parameter sets reaches the preset number; when the number of the generated initial control parameter sets reaches the preset number, all the generated initial control parameter sets are determined as the target control parameter set; the second determination module is used to continue to execute the executable script file to generate the initial control parameter set again based on the preset parameter scale and the principle of independent and identical distribution when the number of the generated initial control parameter sets does not reach the preset number. The quantitative description and characterization of the relationship between the converter control parameters and performance indicators are realized through digital twin technology, and the control parameter set is automatically generated, which reduces the need for manual intervention and improves efficiency.

[0114] In some instances, the third processing unit includes a first test module, a second test module, a second acquisition module, and a second processing module. The first test module is used to input each of the above target control parameter sets into the converter control simulation system in sequence for simulation testing; the second test module is used to set the test scenario as the above target scenario, and perform simulation tests on each of the above target control parameter sets in sequence under the above target scenario; the second acquisition module is used to obtain key simulation waveform data obtained by simulation testing of each of the above target control parameter sets, and the above target control parameter sets and the above key simulation waveform data correspond one to one; the second processing module is used to process the above key simulation waveform data to obtain performance indicator data corresponding to each of the above target control parameter sets. By analyzing the performance indicator data, the optimal control parameter set can be found, thereby optimizing system performance, and simulation tests can be quickly performed on different parameter combinations, thereby improving test efficiency.

[0115] In some examples, the third processing unit includes a third processing module, which is used to process the active power step response waveform file and the reactive power step response waveform file of the above-mentioned converter to obtain the rise time of the active power, the cumulative integral error of the active power, and the percentage overshoot of the active power of the above-mentioned converter, as well as the rise time of the reactive power, the cumulative integral error of the reactive power, and the percentage overshoot of the reactive power of the above-mentioned converter, so as to obtain the above-mentioned performance index data. By processing the waveform file, the performance index data of the converter is directly obtained without manual calculation and analysis, which reduces the possibility of human error and improves the accuracy and efficiency of data processing.

[0116] In some instances, the fourth processing unit includes a third determination module, a fourth determination module, and a fourth processing module. The third determination module is used to determine the dimension of the data to be fitted according to the number of the control parameters in the target control parameter set, and determine the amount of training data according to the data in all the target control parameter sets; the fourth determination module is used to determine the structure of the neural network to be trained according to the dimension of the data to be fitted and the amount of training data, and the structure of the neural network to be trained includes at least the number of neural network layers and the number of neurons in each layer of the neural network; the fourth processing module is used to take the control parameters in all the target control parameter sets as input, and take the performance indicator data corresponding to each target control parameter set as output, train and fit the neural network to be trained, and obtain the digital twin model. The complex multi-parameter system is fitted by the neural network model, so as to realize the prediction and optimization of the system behavior. The digital twin model obtained by training can quickly and accurately simulate and analyze the system, and help optimize the system control parameters.

[0117] In some examples, the first processing unit includes a first control module, and the first control module is used for PI parameters of a voltage loop based on dual-loop control and PI parameters of a current loop based on dual-loop control, where P is a proportional coefficient and I is an integral coefficient. By properly adjusting the PI parameters, the system can respond faster, achieve faster control response, and effectively reduce overshoot and oscillation of the system, thereby improving the stability of the system.

[0118] In some examples, the device further includes a third acquisition module, a fifth processing module and a fourth determination module. The third acquisition module is used to obtain the actual control parameters of the converter at the current moment after the target control parameter set and the corresponding performance index data are used to train the neural network to be trained and obtain the digital twin model. The actual control parameters are the control parameters used by the converter in the actual operation process at the current moment. The fifth processing module is used to input the actual control parameters into the digital twin model to obtain the actual performance index of the converter. The actual performance index is the performance data that characterizes the actual operating state of the converter at the current moment. The fourth determination module is used to determine the current operating state of the converter according to the actual performance index of the converter. The digital twin model simulates and analyzes the actual control parameters of the converter, which can more accurately characterize the actual operating state of the converter, improve the accuracy of the judgment, and greatly reduce the time cost required while ensuring accuracy. It provides an important reference and powerful tool for the design of converter control systems in new power systems with increasing degree of power electronics in the future.

[0119] The device for determining the index evaluation model of the converter includes a processor and a memory. The first processing unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0120] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to solve the problem that the existing method for determining the control parameters of the converter requires a large number of simulations or hardware experimental tests, which is time-consuming and inefficient.

[0121] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0122] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for determining the index evaluation model of the converter.

[0123] Specifically, the method for determining the index evaluation model of the converter includes:

[0124] Step S201, configuring an executable script file;

[0125] Specifically, the executable file refers to a script file in the real-time simulation software (RTDS) in the field of power systems, which is implemented by a C-like language and is a file in script form.

[0126] Step S202, executing the executable script file to generate at least one set of target control parameter sets, wherein the target control parameter set includes a plurality of control parameters of the converter, and the control parameters are parameters for controlling the operation of the converter;

[0127] Specifically, generating multiple sets of target control parameter sets can help optimize the operation of the converter, improve its efficiency and performance, better understand the operating mechanism of the converter, and improve the ability to grasp and adjust its control parameters.

[0128] Step S203, performing simulation tests on each of the target control parameter sets under a target scenario to obtain corresponding performance indicator data, wherein the performance indicator data is data representing the operating state of the converter under the target scenario when the converter operates with the control parameters in the target control parameter set;

[0129] Specifically, through simulation testing, a large amount of data can be quickly acquired, analyzed and compared, so as to quickly find the optimal control parameters and improve the performance and efficiency of the converter.

[0130] Step S204: Use the above-mentioned target control parameter set and the corresponding above-mentioned performance indicator data to train the neural network to be trained to obtain a digital twin model, and the above-mentioned digital twin model is used to evaluate the performance indicators of the above-mentioned converter.

[0131] Specifically, the digital twin model can be trained based on actual data and can more accurately predict the performance indicators of the converter. By continuously optimizing the model, the accuracy of the evaluation results can be improved.

[0132] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the method for determining the index evaluation model of the converter is executed when the program is run.

[0133] Specifically, the method for determining the index evaluation model of the converter includes:

[0134] Step S201, configuring an executable script file;

[0135] Specifically, the executable file refers to a script file in the real-time simulation software (RTDS) in the field of power systems, which is implemented by a C-like language and is a file in script form.

[0136] Step S202, executing the executable script file to generate at least one set of target control parameter sets, wherein the target control parameter set includes a plurality of control parameters of the converter, and the control parameters are parameters for controlling the operation of the converter;

[0137] Specifically, generating multiple sets of target control parameter sets can help optimize the operation of the converter, improve its efficiency and performance, better understand the operating mechanism of the converter, and improve the ability to grasp and adjust its control parameters.

[0138] Step S203, performing simulation tests on each of the target control parameter sets under a target scenario to obtain corresponding performance indicator data, wherein the performance indicator data is data representing the operating state of the converter under the target scenario when the converter operates with the control parameters in the target control parameter set;

[0139] Specifically, through simulation testing, a large amount of data can be quickly acquired, analyzed and compared, so as to quickly find the optimal control parameters and improve the performance and efficiency of the converter.

[0140] Step S204: Use the above-mentioned target control parameter set and the corresponding above-mentioned performance indicator data to train the neural network to be trained to obtain a digital twin model, and the above-mentioned digital twin model is used to evaluate the performance indicators of the above-mentioned converter.

[0141] Specifically, the digital twin model can be trained based on actual data and can more accurately predict the performance indicators of the converter. By continuously optimizing the model, the accuracy of the evaluation results can be improved.

[0142] An embodiment of the present invention provides a device, the device comprising a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:

[0143] Step S201, configuring an executable script file;

[0144] Specifically, the executable file refers to a script file in the real-time simulation software (RTDS) in the field of power systems, which is implemented by a C-like language and is a file in script form.

[0145] Step S202, executing the executable script file to generate at least one set of target control parameter sets, wherein the target control parameter set includes a plurality of control parameters of the converter, and the control parameters are parameters for controlling the operation of the converter;

[0146] Specifically, generating multiple sets of target control parameter sets can help optimize the operation of the converter, improve its efficiency and performance, better understand the operating mechanism of the converter, and improve the ability to grasp and adjust its control parameters.

[0147] Step S203, performing simulation tests on each of the target control parameter sets under a target scenario to obtain corresponding performance indicator data, wherein the performance indicator data is data representing the operating state of the converter under the target scenario when the converter operates with the control parameters in the target control parameter set;

[0148] Specifically, through simulation testing, a large amount of data can be quickly acquired, analyzed and compared, so as to quickly find the optimal control parameters and improve the performance and efficiency of the converter.

[0149] Step S204: Use the above-mentioned target control parameter set and the corresponding above-mentioned performance indicator data to train the neural network to be trained to obtain a digital twin model, and the above-mentioned digital twin model is used to evaluate the performance indicators of the above-mentioned converter.

[0150] Specifically, the digital twin model can be trained based on actual data and can more accurately predict the performance indicators of the converter. By continuously optimizing the model, the accuracy of the evaluation results can be improved.

[0151] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0152] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps: Step S201, configuring an executable script file;

[0153] Specifically, the executable file refers to a script file in the real-time simulation software (RTDS) in the field of power systems, which is implemented by a C-like language and is a file in script form.

[0154] Step S202, executing the executable script file to generate at least one set of target control parameter sets, wherein the target control parameter set includes a plurality of control parameters of the converter, and the control parameters are parameters for controlling the operation of the converter;

[0155] Specifically, generating multiple sets of target control parameter sets can help optimize the operation of the converter, improve its efficiency and performance, better understand the operating mechanism of the converter, and improve the ability to grasp and adjust its control parameters.

[0156] Step S203, performing simulation tests on each of the target control parameter sets under a target scenario to obtain corresponding performance indicator data, wherein the performance indicator data is data representing the operating state of the converter under the target scenario when the converter operates with the control parameters in the target control parameter set;

[0157] Specifically, through simulation testing, a large amount of data can be quickly acquired, analyzed and compared, so as to quickly find the optimal control parameters and improve the performance and efficiency of the converter.

[0158] Step S204: Use the above-mentioned target control parameter set and the corresponding above-mentioned performance indicator data to train the neural network to be trained to obtain a digital twin model, and the above-mentioned digital twin model is used to evaluate the performance indicators of the above-mentioned converter.

[0159] Specifically, the digital twin model can be trained based on actual data and can more accurately predict the performance indicators of the converter. By continuously optimizing the model, the accuracy of the evaluation results can be improved.

[0160] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0161] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0162] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0163] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0164] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0165] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0166] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0167] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0168] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0169] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0170] 1) A method for determining an index evaluation model of the above-mentioned converter of the present application, first configuring an executable script file; then executing the executable script file to generate at least one set of target control parameter sets, the target control parameter set including control parameters of multiple converters, the control parameters being parameters for controlling the operation of the converter; then performing simulation tests on each target control parameter set under a target scenario to obtain corresponding performance index data, the performance index data being data characterizing the operating status of the converter when the converter operates using the control parameters in the target control parameter set under the target scenario; finally, using the target control parameter set and the corresponding performance index data to train the neural network to be trained to obtain a digital twin model, which is used to evaluate the performance index of the converter. This method improves the method of constructing the relationship between converter control parameters and performance indicators, quantitatively describes the influence of converter control parameters on performance indicators in a short time and with high accuracy, thereby providing guidance and basis for the design of converter control systems. Compared with the traditional exhaustive control parameter performance evaluation method based on a large number of software simulations / experimental tests, it can greatly reduce the required time cost while ensuring accuracy, and can be used for the design of converter control systems in new power systems with a high degree of power electronics, solving the problem that the existing method for determining converter control parameters requires a large number of simulations or hardware experimental tests, which is time-consuming and inefficient.

[0171] 2) The device for determining the index evaluation model of the above-mentioned converter of the present application comprises: a first processing unit, a second processing unit, a third processing unit and a fourth processing unit, the first processing unit being used to configure an executable script file, the executable script file being used to generate control parameters of the converter, the control parameters being parameters for controlling the operation of the converter; the second processing unit being used to execute the executable script file to generate at least one set of target control parameter sets, the target control parameter set comprising multiple control parameters; the third processing unit being used to perform simulation tests on each target control parameter set under a target scenario to obtain corresponding performance index data, the performance index data being data characterizing the operating status of the converter when the control parameters in the target control parameter set are used to operate under the target scenario; the fourth processing unit being used to train the neural network to be trained using the target control parameter set and the corresponding performance index data to obtain a digital twin model, the digital twin model being used to evaluate the performance index of the converter. The device improves the method of constructing the relationship between converter control parameters and performance indicators, quantitatively describes the influence of converter control parameters on performance indicators in a short time and with high accuracy, thereby providing guidance and basis for the design of converter control systems. Compared with the traditional exhaustive control parameter performance evaluation method based on a large number of software simulations / experimental tests, it can greatly reduce the required time cost while ensuring accuracy. It can be used for the design of converter control systems in new power systems with a high degree of power electronics, and solves the problem that the existing method for determining converter control parameters requires a large number of simulations or hardware experimental tests, which is time-consuming and inefficient.

[0172] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining an index evaluation model of a converter, characterized in that: include: Configure the executable script file; Executing the executable script file to generate at least one set of target control parameter sets, wherein the target control parameter set includes a plurality of control parameters of the converter, and the control parameters are parameters for controlling the operation of the converter; Performing simulation tests on each of the target control parameter sets under a target scenario to obtain corresponding performance indicator data, wherein the performance indicator data is data characterizing the operating state of the converter under the target scenario when the converter operates with the control parameters in the target control parameter set; The target control parameter set and the corresponding performance indicator data are used to train the neural network to obtain a digital twin model, and the digital twin model is used to evaluate the performance indicators of the converter.

2. The method according to claim 1, characterized in that: Executing the executable script file to generate at least one set of target control parameter sets includes: Acquire a preset parameter scale, wherein the preset parameter scale includes: a preset number of control parameter sets and a preset value range of each control parameter; Executing the executable script file based on the preset parameter scale to generate an initial control parameter set, wherein the values ​​of the control parameters in the initial control parameter set are all within the corresponding preset value range; Determining whether the number of the generated initial control parameter sets reaches the preset number; When the number of the generated initial control parameter sets reaches the preset number, determining all the generated initial control parameter sets as the target control parameter set; When the number of the generated initial control parameter sets does not reach the preset number, based on the preset parameter scale and the principle of independent and identical distribution, the executable script file is continued to be executed to generate the initial control parameter set again.

3. The method according to claim 1, characterized in that Perform simulation tests on each target control parameter set under a target scenario to obtain corresponding performance indicator data, including: Inputting each of the target control parameter sets into the converter control simulation system in sequence for simulation testing; Setting the test scenario as the target scenario, and sequentially performing simulation tests on each of the target control parameter sets under the target scenario; Acquire key simulation waveform data obtained by performing simulation tests on each of the target control parameter sets, wherein the target control parameter sets correspond to the key simulation waveform data in a one-to-one manner; The key simulation waveform data are processed to obtain performance indicator data corresponding to each target control parameter set.

4. The method according to claim 3, characterized in that: The key simulation waveform data includes an active power step response waveform file and a reactive power step response waveform file of the converter. The key simulation waveform data is processed to obtain performance indicator data corresponding to each target control parameter set, including: The active power step response waveform file and the reactive power step response waveform file of the converter are processed to obtain the rise time of the active power, the cumulative integral error of the active power, the percentage overshoot of the active power, and the rise time of the reactive power, the cumulative integral error of the reactive power, and the percentage overshoot of the reactive power of the converter, so as to obtain the performance indicator data.

5. The method according to claim 1, characterized in that: The target control parameter set and the corresponding performance indicator data are used to train the neural network to obtain a digital twin model, including: Determining the dimension of the data to be fitted according to the number of the control parameters in one of the target control parameter sets, and determining the amount of training data according to the data in all of the target control parameter sets; Determine the structure of the neural network to be trained according to the dimension of the data to be fitted and the amount of training data, wherein the structure of the neural network to be trained includes at least the number of neural network layers and the number of neurons in each layer of the neural network; Taking all the control parameters in the target control parameter set as input, and taking the performance indicator data corresponding to each target control parameter set as output, the neural network to be trained is trained and fitted to obtain the digital twin model.

6. The method according to claim 1, characterized in that The control parameters of the converter include: PI parameters of a voltage loop based on dual-loop control and PI parameters of a current loop based on dual-loop control, wherein P is a proportional coefficient and I is an integral coefficient.

7. The method according to claim 1, characterized in that After the target control parameter set and the corresponding performance indicator data are used to train the neural network to be trained to obtain the digital twin model, the method further includes: Acquire actual control parameters of the converter at the current moment, where the actual control parameters are control parameters used by the converter during actual operation at the current moment; Inputting the actual control parameter into the digital twin model to obtain an actual performance index of the converter, wherein the actual performance index is performance data characterizing an actual operating state of the converter at the current moment; The current operating state of the converter is determined according to the actual performance index of the converter.

8. A device for determining an index evaluation model of a converter, characterized in that: include: A first processing unit, configured to configure an executable script file, wherein the executable script file is used to generate control parameters of the converter, wherein the control parameters are parameters for controlling the operation of the converter; A second processing unit, configured to execute the executable script file to generate at least one set of target control parameter sets, wherein the target control parameter set includes a plurality of the control parameters; A third processing unit is used to perform a simulation test on each of the target control parameter sets under a target scenario to obtain corresponding performance indicator data, wherein the performance indicator data is data representing an operating state of the converter when the converter operates with the control parameters in the target control parameter set under the target scenario; The fourth processing unit is used to train the neural network to be trained using the target control parameter set and the corresponding performance indicator data to obtain a digital twin model, and the digital twin model is used to evaluate the performance indicators of the converter.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for determining the indicator evaluation model of the converter according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for determining an indicator evaluation model for executing the converter described in any one of claims 1 to 7.

Images