Data set generation method and system for converter harmonic coupling feature learning

Abstract

The invention discloses a data set generation method and system for converter harmonic coupling feature learning, and the method comprises the steps: determining the access capacity and position of a power electronic converter in a power distribution network, randomly generating m groups of multi-frequency harmonic voltages under the amplitude limitation, and defining the distance between two groups of harmonic voltages; calculating to obtain a distance matrix among all harmonic voltage data, and according to a traversal rule, carrying out small signal superposition on m groups of data in sequence; obtaining a steady-state equation coefficient matrix; dividing the harmonic voltage at the converter as large disturbance into a plurality of stages, and calculating the small disturbance response of each state variable of the small signal equation under the harmonic voltage disturbance at each stage; superposing the small disturbance response of each state variable solved in the stage into a steady-state component of the state variable, and updating a small signal equation set of the system; and superposing the disturbance of the next stage, repeating until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally obtaining the harmonic coupling characteristics of the converter under m groups of random harmonic voltage data.

Description

Technical Field

[0001] The present invention belongs to the technical field of power quality and harmonic calculation, and in particular relates to a method and system for generating a data set for learning harmonic coupling characteristics of a converter. Background Art

[0002] With the transformation of energy structure and the popularization of intelligent distribution network, distribution network is undergoing significant changes. These changes are mainly reflected in two aspects: high penetration rate and high power electronics. High penetration rate means that more and more distributed energy (such as solar energy, wind energy, etc.) are connected to the distribution network, while high power electronics is due to the widespread application of power electronic equipment (such as rectifiers, inverters, etc.) in the distribution network.

[0003] Power electronic devices have nonlinear load characteristics, which causes them to produce some special phenomena when subjected to harmonic voltage disturbances, such as frequency coupling. Frequency coupling refers to the interaction between harmonics of different frequencies, which may make the propagation and distribution of harmonics more complicated. In addition, the nonlinear characteristics of power electronic devices may also cause the generation and amplification of harmonics, further exacerbating the harmonic problem.

[0004] However, the traditional harmonic flow calculation method mainly focuses on the impact of linear loads and ignores the nonlinear characteristics of power electronic equipment. This leads to the gradual increase of errors in traditional calculation methods when large-scale power electronic devices are connected to the grid, and it cannot meet the harmonic analysis requirements of modern distribution networks. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method and system for generating a data set for learning the harmonic coupling characteristics of a converter in view of the deficiencies in the above-mentioned prior art, so as to solve the limitations of traditional iterative methods for analyzing harmonic coupling characteristics and the technical problem of low efficiency in collecting data sets using traditional simulation.

[0006] The present invention adopts the following technical solutions: A method for generating a data set for learning harmonic coupling features of a converter comprises the following steps: S1. Determine the access capacity and location of the power electronic converter in the distribution network, and obtain its filter parameters and control method; S2, select the frequency to be calculated, randomly generate m groups of multi-frequency harmonic voltages under amplitude restrictions, and define the distance between two groups of harmonic voltages; S3, based on the distance between the two groups of harmonic voltages obtained in step S2, calculate the distance matrix between all harmonic voltage data, and perform small signal superposition of m groups of data in sequence according to the traversal rule; S4, for the randomly distributed harmonic voltage in step S2, taking the grid voltage containing only the fundamental wave as the initial state of the system, solving the initial steady-state quantity, and obtaining the steady-state equation coefficient matrix; S5, performing small disturbance linearization based on the steady-state quantity in step S4, dividing the harmonic voltage at the power electronic converter into multiple stages as a large disturbance, increasing the disturbance in stages, and the disturbance size in each stage meets the requirements of small signal equation calculation; S6, based on the steady-state quantity in step S4, the small disturbance response of each state variable in each harmonic voltage disturbance stage is calculated by the small signal equation obtained in step S5; the small disturbance response of each state variable obtained in this stage is superimposed on its steady-state component, and the small signal equation group of the system is updated; S7, superimposing the disturbance of the next stage, repeating step S6, until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally obtaining the harmonic coupling characteristics of the converter under m groups of random harmonic voltage data.

[0007] Preferably, the power electronic converter is a frequency coupling model based on a harmonic transfer function.

[0008] Preferably, in step S2, the distance between the two groups of harmonic voltages is as follows:

[0009] in, and Respectively represent two groups of multi-frequency harmonic voltages, is the number of selected frequencies, and Respectively represent the first data.

[0010] Preferably, the multi-frequency harmonic voltage is specifically:

[0011]

[0012] The distance between corresponding values ​​in each group of harmonic voltages is defined as:

[0013] in, and Respectively represent the real part of the harmonic voltage at the corresponding position of the two sets of data, and They respectively represent the imaginary part of the harmonic voltage at the corresponding positions of the two sets of data.

[0014] Preferably, in step S3, the traversal rules are divided into traversal methods and calculation rules; The traversal method starts from the origin and sequentially searches for the shortest distance point that has not been calculated as the harmonic voltage to be calculated in the next stage; Calculation rules: the points to be found in each stage are based on the small signal superposition of the calculated points with the shortest distance to them.

[0015] Preferably, in step S5, the harmonic voltage disturbance is superimposed in steps, and small signal linearization is performed in multiple stages. In each stage, the small signal equation, i.e., the coefficient matrix, is updated according to the calculation result of the previous stage to calculate the steady-state result under large disturbance.

[0016] Preferably, the harmonic coupling characteristics of the converter under m groups of random harmonic voltage data are for:

[0017] in, is the multi-frequency harmonic voltage at the converter.

[0018] In a second aspect, an embodiment of the present invention provides a data set generation system for learning harmonic coupling features of a converter, comprising: The distance module determines the access capacity and location of the power electronic converter in the distribution network, obtains its filter parameters and its control method; selects the frequency to be calculated, randomly generates m groups of multi-frequency harmonic voltages under amplitude restrictions, and defines the distance between two groups of harmonic voltages; The matrix module calculates the distance matrix between all harmonic voltage data based on the distance between two groups of harmonic voltages, and performs small signal superposition of m groups of data in sequence according to the traversal rules; for each group of harmonic voltages, the grid voltage containing only the fundamental wave is taken as the initial state of the system, the initial steady-state quantity is solved, and the steady-state equation coefficient matrix is ​​obtained; The disturbance module divides the harmonic voltage at the converter into multiple stages as a large disturbance, and increases the disturbance in stages. The disturbance size in each stage meets the requirements of small signal calculation. The updating module calculates the small disturbance response of each state variable under the harmonic voltage disturbance of each stage of the small signal equation; superimposes the small disturbance response of each state variable solved in this stage into its steady-state component, and updates the small signal equation group of the system; The output module superimposes the disturbance of the next stage and repeats until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally obtains the harmonic coupling characteristics of the converter under m groups of random harmonic voltage data.

[0019] In a third aspect, a computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the data set generation method for learning harmonic coupling features of the converter when executing the computer program.

[0020] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for generating a data set for learning harmonic coupling features of a converter.

[0021] In a fifth aspect, a chip comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the data set generation method for learning harmonic coupling features of the above-mentioned converter when executing the computer program.

[0022] In a sixth aspect, an embodiment of the present invention provides an electronic device, including a computer program, which, when executed by the electronic device, implements the steps of the data set generation method for learning the harmonic coupling characteristics of the converter.

[0023] Compared with the prior art, the present invention has at least the following beneficial effects: A method for generating a data set for learning the harmonic coupling characteristics of converters is proposed. It takes into account the characteristics of power electronic equipment and uses deep learning methods to learn the complex relationship between coupled harmonic currents generated when the converter is disturbed by harmonic voltage. This method can simplify the difficulty of coupling characteristic analysis. It is difficult for simulation models to obtain a large amount of data in random scenarios, making it impossible to learn the characteristics of harmonic coupling. Based on small signal superposition calculation and traversal rules, a large number of random data sets for feature analysis can be quickly generated, which improves the generalization ability of deep learning models and allows more accurate learning of coupling relationships under harmonic disturbances.

[0024] Furthermore, by setting the power electronic converter as a frequency coupling model based on the harmonic transfer function and describing the small signal relationship between the voltage and current at the power electronic device port, the harmonic interaction behavior can be accurately captured, providing a basis for the subsequent analysis of the frequency domain coupling characteristics.

[0025] Furthermore, by dividing the traversal rules into two parts, the traversal method and the calculation rules, on the one hand, the traversal method is set to find the nearest uncalculated point as the calculation data for the next stage to ensure global traversal of the data points; on the other hand, the calculation rules are set to find the nearest calculated point as the superposition benchmark to improve the calculation speed and step accuracy.

[0026] Furthermore, for each group of data points, different step lengths are set based on the superposition benchmark, and the large disturbance is divided into multiple stages of small disturbance superposition. The small disturbance is repeatedly superimposed to ensure the accuracy of linearization based on steady-state quantities, providing accurate and reliable voltage and current data for the subsequent analysis of frequency domain coupling characteristics.

[0027] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0028] In summary, the method of the present invention has high calculation accuracy, wide applicability, can adapt to various distribution network structures, and has relatively practical engineering application value.

[0029] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a flow chart of the method of the present invention; Figure 2 A schematic diagram of the traversal rules of the present invention; Fig. 3 shows the data of the method of the present invention and the related simulation results, wherein (a) is the real value and imaginary value of the randomly generated multi-frequency harmonic voltage, (b) is the target voltage of the randomly generated multi-frequency harmonic voltage and the error between the superimposed voltage and the target voltage, (c) is the multi-frequency harmonic current calculated from the harmonic voltage in (b), and (d) is the learning effect after 1000 sets of data sets are input into the LSTM neural network; Figure 4 A schematic diagram of a computer device provided by an embodiment of the present invention; Figure 5 The block diagram of a chip provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] In the description of the present invention, it should be understood that the terms “include” and “comprises” indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0033] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include plural forms unless the context clearly indicates otherwise.

[0034] It should be further understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects are in an "or" relationship.

[0035] It should be understood that, although the terms first, second, third, etc. may be used to describe preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0036] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0037] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0038] The present invention provides a method for generating a data set for learning harmonic coupling features of a converter. Based on the traditional method of calculating the superimposed nonlinear characteristics of harmonic power flow, deep learning is considered to learn the complex coupling relationship between harmonic voltage and coupled harmonic current. In order to obtain a large number of data sets in multiple scenarios for harmonic coupling feature learning, the present invention obtains multi-frequency harmonic currents under a large number of random multi-frequency harmonic voltage signals based on the small signal stepping method and the traversal rule.

[0039] For the calculation of a single group of multi-frequency harmonic voltages, the calculation time does not need to be considered when using the small signal stepping method. When calculating a large amount of data at the same time, it is necessary to consider improving the calculation rate of the traditional small signal superposition method while ensuring the calculation accuracy. For the calculation of multiple groups of data, the present invention not only considers the speed of generating data sets, but also in order to ensure the accuracy of the small signal superposition results, a traversal rule considering the stepping accuracy is designed based on the small signal superposition method. In this process, the "distance" between each group of data is made transparent, and traversal is performed in sequence based on the defined distance. The superposition calculation of the current traversal data is based on the calculated data at the minimum distance, which effectively improves the speed and accuracy of the calculation of multiple groups of random harmonic data.

[0040] See also Figure 1 The present invention provides a method for generating a data set for learning harmonic coupling characteristics of a converter, comprising the following steps: S1. Determine the access capacity and location of the power electronic converter model in the distribution network, and obtain its filter parameters and control method; The power electronic converter model is a frequency coupling model based on the harmonic transfer function. It is obtained by describing the small signal relationship between the voltage and current at the converter device port, providing a theoretical basis for the small signal superposition calculation in the subsequent steps.

[0041] S2. Select the frequency to be calculated, randomly generate 1000 groups of multi-frequency harmonic voltages under amplitude restrictions, and define the distance between two groups of harmonic voltages; The specific expression of multi-frequency harmonic voltage is:

[0042]

[0043] And the distance between corresponding values ​​in each group of harmonic voltages is specifically defined as:

[0044] in, and Respectively represent the real part of the harmonic voltage at the corresponding position of the two sets of data, and They respectively represent the imaginary part of the harmonic voltage at the corresponding positions of the two sets of data.

[0045] The distance between the two groups of harmonic voltages is as follows:

[0046] in, and Respectively represent two groups of multi-frequency harmonic voltages, is the number of selected frequencies, and Respectively represent the first data.

[0047] S3. Based on the distance between the two groups of harmonic voltages defined in step S2, the distance matrix between all harmonic voltage data is calculated, and according to the traversal rule, the small signal superposition of 1000 groups of data is performed in sequence according to the following steps; The traversal rules are mainly divided into two parts, based on the defined voltage distance. One part is the traversal method, starting from the origin, sequentially looking for the uncalculated shortest distance point as the harmonic voltage to be calculated in the next stage; the other part is the calculation rule, and the points found in each stage are based on the shortest calculated point for small signal superposition.

[0048] S4, for the randomly distributed harmonic voltage in step S2, taking the grid voltage containing only the fundamental wave as the initial state of the system, solving the initial steady-state quantity, and obtaining the steady-state equation coefficient matrix; The steady-state equation coefficient matrix in step S4 mainly describes the frequency domain characteristics of the converter and the dynamic relationship between the controller. Based on the system frequency, equipment parameters, and converter controller characteristics, the DC and AC steady-state voltages and currents are calculated, providing a linearization basis for subsequent small signal disturbance analysis.

[0049] S5, performing small disturbance linearization based on the steady-state quantity in step S4, dividing the harmonic voltage at the converter as a large disturbance into multiple stages, increasing the disturbance in stages, and the disturbance size in each stage meets the requirements of small signal equation calculation; The harmonic voltage disturbance is superimposed in steps, and small signal linearization is adopted in multiple stages. In each stage, the small signal equation, i.e., the coefficient matrix, is updated according to the calculation results of the previous stage, and then the steady-state results under large disturbances are calculated. When the disturbance step size of each frequency in each stage is less than 0.005 of the target voltage, it can be regarded as a small disturbance, which can meet the small signal calculation requirements.

[0050] S6, based on the steady-state quantity in step S4, the small disturbance response of each state variable in each harmonic voltage disturbance stage is calculated by the small signal equation obtained in step S5; the small disturbance response of each state variable obtained in this stage is superimposed on its steady-state component, and the small signal equation group of the system is updated; The converter small signal equations are defined as:

[0051] in, , as well as , Both represent coefficient matrices, which are continuously updated as disturbances are superimposed; and They respectively represent the harmonic voltage matrix and harmonic current matrix of the transformer in different states; *phase represents the frequency coupling phase.

[0052] S7, superimpose the disturbance of the next stage, repeat step S6 until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally obtain the harmonic coupling characteristics of the converter under 1000 sets of random harmonic voltage data .

[0053] Harmonic coupling characteristics of converters under 1000 sets of random harmonic voltage data for:

[0054] in, is the multi-frequency harmonic voltage at the converter. It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0055] In yet another embodiment of the present invention, a system for generating a data set for learning harmonic coupling features of a converter is provided. The system can be used to implement the above-mentioned method for generating a data set for learning harmonic coupling features of a converter. Specifically, the system for generating a data set for learning harmonic coupling features of a converter includes a distance module, a matrix module, a disturbance module, an update module and an output module.

[0056] Among them, the distance module determines the access capacity and location of the power electronic converter in the distribution network, obtains its filter parameters and its control method; selects the frequency to be calculated, randomly generates m groups of multi-frequency harmonic voltages under amplitude restrictions, and defines the distance between two groups of harmonic voltages; The matrix module calculates the distance matrix between all harmonic voltage data based on the distance between two groups of harmonic voltages, and performs small signal superposition of m groups of data in sequence according to the traversal rules; for each group of harmonic voltages, the grid voltage containing only the fundamental wave is taken as the initial state of the system, the initial steady-state quantity is solved, and the steady-state equation coefficient matrix is ​​obtained; The disturbance module divides the harmonic voltage at the converter into multiple stages as a large disturbance, and increases the disturbance in stages. The disturbance size in each stage meets the requirements of small signal calculation. The updating module calculates the small disturbance response of each state variable under the harmonic voltage disturbance of each stage of the small signal equation; superimposes the small disturbance response of each state variable solved in this stage into its steady-state component, and updates the small signal equation group of the system; The output module superimposes the disturbance of the next stage and repeats until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally obtains the harmonic coupling characteristics of the converter under m groups of random harmonic voltage data.

[0057] In another embodiment of the present invention, a terminal device is provided, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, graphics processors (GPU), tensor processors (TPU), digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding functions; the processor described in the embodiment of the present invention can be used for the operation of the data set generation method for harmonic coupling feature learning of converters, including: Determine the access capacity and location of the power electronic converter in the distribution network, obtain its filter parameters and control methods; select the frequency to be calculated, randomly generate m groups of multi-frequency harmonic voltages under amplitude restrictions, and define the distance between two groups of harmonic voltages; based on the distance between the two groups of harmonic voltages, calculate the distance matrix between all harmonic voltage data, and according to the traversal rules, perform small signal superposition of m groups of data in sequence; for each group of harmonic voltages, take the grid voltage containing only the fundamental wave as the initial state of the system, solve the initial steady-state quantity, and obtain the steady-state equation coefficient matrix; divide the harmonic voltage at the converter as a large disturbance into multiple stages, increase the disturbance in batches, and the disturbance size of each stage meets the requirements of small signal calculation; calculate the small disturbance response of each state variable under the harmonic voltage disturbance in each stage of the small signal equation; superimpose the small disturbance response of each state variable solved in this stage into its steady-state component, and update the small signal equation group of the system; superimpose the disturbance of the next stage, repeat until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally obtain the harmonic coupling characteristics of the converter under m groups of random harmonic voltage data.

[0058] See also Figure 4, the terminal device is a computer device, and the computer device 60 of this embodiment includes: a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61. When the computer program 63 is executed by the processor 61, the method for generating a data set for learning harmonic coupling characteristics of the converter in the embodiment is implemented. To avoid repetition, it is not described one by one here. Alternatively, when the computer program 63 is executed by the processor 61, the functions of each model / unit in the system for generating a data set for learning harmonic coupling characteristics of the converter in the embodiment are implemented. To avoid repetition, it is not described one by one here.

[0059] The computer device 60 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art will appreciate that Figure 4 This is only an example of the computer device 60 and does not constitute a limitation of the computer device 60. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0060] The processor 61 may be a central processing unit (CPU), or other general-purpose processors, graphics processing units (GPU), tensor processing units (TPU), digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0061] The memory 62 may be an internal storage unit of the computer device 60, such as a hard disk or memory of the computer device 60. The memory 62 may also be an external storage device of the computer device 60, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the computer device 60.

[0062] Furthermore, the memory 62 may include both an internal storage unit of the computer device 60 and an external storage device. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 may also be used to temporarily store data that has been output or is to be output.

[0063] See also Figure 5 The terminal device is a chip, and the chip 600 of this embodiment includes a processor 622, which may be one or more, and a memory 632 for storing a computer program executable by the processor 622. The computer program stored in the memory 632 may include one or more modules, each corresponding to a set of instructions. In addition, the processor 622 may be configured to execute the computer program to execute the above-mentioned method for generating a data set for learning harmonic coupling features of a converter.

[0064] In addition, the chip 600 may further include a power supply component 626 and a communication component 650, wherein the power supply component 626 may be configured to perform power management of the chip 600, and the communication component 650 may be configured to implement communication, for example, wired or wireless communication, of the chip 600. In addition, the chip 600 may further include an input / output interface 658. The chip 600 may operate based on an operating system stored in the memory 632.

[0065] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium, which is a memory device in a terminal device for storing programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs. It should be noted that the computer-readable storage medium here can be a high-speed RAM memory, or a non-volatile memory (Non-VolatileMemory), such as at least one disk memory.

[0066] One or more instructions stored in a computer-readable storage medium may be loaded and executed by a processor to implement the corresponding steps of the method for generating a data set for learning harmonic coupling characteristics of a converter in the above embodiment; one or more instructions in the computer-readable storage medium may be loaded and executed by a processor as follows: Determine the access capacity and location of the power electronic converter in the distribution network, obtain its filter parameters and control methods; select the frequency to be calculated, randomly generate m groups of multi-frequency harmonic voltages under amplitude restrictions, and define the distance between two groups of harmonic voltages; based on the distance between the two groups of harmonic voltages, calculate the distance matrix between all harmonic voltage data, and according to the traversal rules, perform small signal superposition of m groups of data in sequence; for each group of harmonic voltages, take the grid voltage containing only the fundamental wave as the initial state of the system, solve the initial steady-state quantity, and obtain the steady-state equation coefficient matrix; divide the harmonic voltage at the converter as a large disturbance into multiple stages, increase the disturbance in batches, and the disturbance size of each stage meets the requirements of small signal calculation; calculate the small disturbance response of each state variable under the harmonic voltage disturbance in each stage of the small signal equation; superimpose the small disturbance response of each state variable solved in this stage into its steady-state component, and update the small signal equation group of the system; superimpose the disturbance of the next stage, repeat until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally obtain the harmonic coupling characteristics of the converter under m groups of random harmonic voltage data.

[0067] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention described and shown in the drawings here can usually be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0068] See also Figure 1 , the process of the method of the present invention is: First, select the calculation frequency, and select -5, 7, -11, and 13 harmonics for calculation in the simulation verification; Then, 1000 sets of multi-frequency voltage data meeting the limit values ​​are randomly generated, and the “distance” between the data is calculated; Start to find the calculation points and superposition starting points of each stage, and use the small signal superposition method to calculate the corresponding multi-frequency harmonic currents; Based on the data volume, all data points are traversed, and finally the multi-frequency harmonic currents corresponding to all groups of data are obtained.

[0069] See also Figure 2, a schematic diagram of the traversal rules of the present invention. All generated random harmonic voltages are regarded as points in the plane, starting from the origin, and according to the defined shortest distance, searching for point ③ along the blue solid line and the red solid line. Taking point ③ as an example, point ②-point ③ is to find the uncalculated point with the shortest surrounding distance on the basis of point ②; point ③ searches for the calculated point with the shortest surrounding distance as the starting point of superposition, as shown by the yellow solid line; and searches for the uncalculated point with the shortest surrounding distance as the point to be calculated in the next stage. Therefore, taking point ④ as an example, the red solid line is the path to find ④, the yellow solid line indicates the calculation starting point of point ④, and the blue solid line is the position to be calculated in the next stage; and point ⑥, as the last traversed point, will no longer have a blue solid line.

[0070] Please refer to Figure 3, the data of the method of the present invention and the related simulation results; Figure 3 (a) shows the real and imaginary values ​​of the randomly generated multi-frequency harmonic voltage, both of which are kept within certain limits; Figure 3 (b) shows the target voltage of the randomly generated multi-frequency harmonic voltage and the error between the superimposed voltage and the target voltage; Figure 3 (c) shows the multi-frequency harmonic current calculated from the harmonic voltage in Figure 3 (b); Table 1 shows the code running effect, as follows: Table 1

[0071] According to the running results, the average running time for 1,000 sets of random data is 150 seconds, the operation time for a single set of data is increased by 20 times, and a high-precision result with basically no error is obtained; Figure 3 (d) shows the learning effect after 1000 sets of data sets are input into the LSTM neural network. The ratio of training set to test set is maintained at 9:1, and the early stopping callback function under the Keras framework is used to prevent the model from overfitting. From the loss function curve, it can be seen that the model reaches stability after running for about 260 rounds, and the learning effect is good.

[0072] In summary, the present invention provides a data set generation method and system for harmonic coupling feature learning of a converter, and considers using deep learning to learn the complex coupling relationship between harmonic voltage and coupled harmonic current. In order to obtain a large number of data sets in multiple scenarios for harmonic coupling feature learning, the present invention first obtains the multi-frequency harmonic current corresponding to the multi-frequency harmonic voltage signal based on the small signal stepping method and the traversal rule. Specifically, when using the small signal stepping method to calculate a single set of data, it is not necessary to consider the operation time, but when calculating a large amount of data at the same time, it is necessary to consider improving the calculation rate of the traditional small signal superposition method under the premise of ensuring the calculation accuracy. The present invention designs a traversal rule that considers the calculation accuracy for the calculation of multiple sets of data. In this process, the "distance" between each set of data is transparent, and the traversal is performed in sequence based on the defined distance. The superposition calculation of the current traversal data is based on the calculated data at the minimum distance, which effectively improves the speed and accuracy of the calculation of multiple sets of data. Therefore, the calculation method proposed in the present invention generates a large amount of random and accurate coupling data, improves the generalization ability of deep learning for analysis, and has important theoretical value and practical application prospects.

[0073] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0074] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0075] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0076] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0077] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0079] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0080] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices, and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to 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.

[0081] 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 including 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.

[0082] 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.

[0083] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for generating a data set for learning converter harmonic coupling features, characterized in that: The following steps are involved: S1. Determine the access capacity and location of the power electronic converter in the distribution network, and obtain its filter parameters and control method; S2, select the frequency to be calculated, randomly generate m groups of multi-frequency harmonic voltages under amplitude restrictions, and define the distance between two groups of harmonic voltages; S3, based on the distance between the two groups of harmonic voltages obtained in step S2, calculate the distance matrix between all harmonic voltage data, and perform small signal superposition of m groups of data in sequence according to the traversal rule; S4, for the randomly distributed harmonic voltage in step S2, taking the grid voltage containing only the fundamental wave as the initial state of the system, solving the initial steady-state quantity, and obtaining the steady-state equation coefficient matrix; S5, performing small disturbance linearization based on the steady-state quantity in step S4, dividing the harmonic voltage at the power electronic converter as a large disturbance into multiple stages, increasing the disturbance in stages, and the disturbance size in each stage meets the requirements of small signal equation calculation; S6, based on the steady-state quantity in step S4, the small disturbance response of each state variable in each harmonic voltage disturbance stage is calculated by the small signal equation obtained in step S5; the small disturbance response of each state variable obtained in this stage is superimposed on its steady-state component, and the small signal equation group of the system is updated; S7, superimposing the disturbance of the next stage, repeating step S6, until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally obtaining the harmonic coupling characteristics of the converter under m groups of random harmonic voltage data.

2. The method for generating a data set for learning converter harmonic coupling features according to claim 1, characterized in that: The power electronic converter is a frequency coupled model based on the harmonic transfer function.

3. The method for generating a data set for learning converter harmonic coupling features according to claim 1, characterized in that: In step S2, the distance between the two groups of harmonic voltages is as follows: in, and Respectively represent two groups of multi-frequency harmonic voltages, is the number of selected frequencies, and Respectively represent the first data.

4. The method for generating a data set for learning converter harmonic coupling features according to claim 3, characterized in that: The multi-frequency harmonic voltage is specifically: The distance between corresponding values ​​in each group of harmonic voltages is defined as: in, and Respectively represent the real part of the harmonic voltage at the corresponding position of the two sets of data, and They respectively represent the imaginary part of the harmonic voltage at the corresponding positions of the two sets of data.

5. The method for generating a data set for learning converter harmonic coupling features according to claim 1, characterized in that: In step S3, the traversal rules are divided into traversal methods and calculation rules; The traversal method starts from the origin and sequentially searches for the shortest distance point that has not been calculated as the harmonic voltage to be calculated in the next stage; Calculation rules: the points to be found in each stage are based on the small signal superposition of the calculated points with the shortest distance to them.

6. The method for generating a data set for learning converter harmonic coupling features according to claim 1, characterized in that: In step S5, the harmonic voltage disturbance is superimposed step by step, and small signal linearization is performed in multiple stages. In each stage, the small signal equation, i.e., the coefficient matrix, is updated according to the calculation result of the previous stage to calculate the steady-state result under large disturbance.

7. The method for generating a data set for learning converter harmonic coupling features according to claim 1, characterized in that: Harmonic coupling characteristics of converter under m groups of random harmonic voltage data for: in, is the multi-frequency harmonic voltage at the converter.

8. A data set generation system for converter harmonic coupling feature learning, characterized in that: include: The distance module determines the access capacity and location of the power electronic converter in the distribution network, obtains its filter parameters and its control method; Select the frequency to be calculated, randomly generate m groups of multi-frequency harmonic voltages under amplitude restrictions, and define the distance between two groups of harmonic voltages; The matrix module calculates the distance matrix between all harmonic voltage data based on the distance between two groups of harmonic voltages, and performs small signal superposition of m groups of data in sequence according to the traversal rules; for each group of harmonic voltages, the grid voltage containing only the fundamental wave is taken as the initial state of the system, the initial steady-state quantity is solved, and the steady-state equation coefficient matrix is ​​obtained; The disturbance module divides the harmonic voltage at the power electronic converter into multiple stages as a large disturbance, and increases the disturbance in stages. The disturbance size in each stage meets the requirements of small signal calculation. The updating module calculates the small disturbance response of each state variable under the harmonic voltage disturbance of each stage of the small signal equation; superimposes the small disturbance response of each state variable solved in this stage into its steady-state component, and updates the small signal equation group of the system; The output module superimposes the disturbance of the next stage and repeats until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally obtains the harmonic coupling characteristics of the converter under m groups of random harmonic voltage data.

9. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions, which, when executed by a computing device, cause the computing device to perform the method of any one of claims 1 to 7.

10. A computing 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 configured to be executed by the one or more processors, and the one or more programs include steps for executing the method described in any one of claims 1 to 7.

Images