A data set generation method and system for converter harmonic coupling feature learning

Abstract

The application discloses a kind of data set generation method and system for harmonic coupling characteristics learning of converter, determine the access capacity and position of power electronic converter in power distribution network, randomly generate multiple frequency harmonic voltage under the amplitude limit of m group, define the distance between two groups of harmonic voltage;The distance matrix between all harmonic voltage data is calculated, according to the traversal rule, sequentially carry out small signal superposition of m group data;Get steady-state equation coefficient matrix;The harmonic voltage at the converter is divided into multiple stages as a large disturbance, calculate the small disturbance response of each state variable under the harmonic voltage disturbance of each stage small signal equation;The small disturbance response of each state variable solved in this stage is superimposed into its steady-state component, and the small signal equation set of the system is updated;Superimpose the disturbance of next stage, repeat until the amplitude of harmonic voltage disturbance and the set target are the same, finally obtain the harmonic coupling characteristics of converter under m group random harmonic voltage data.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power quality and harmonic calculation, and particularly relates to a data set generation method and system for converter harmonic coupling characteristic learning. BACKGROUND

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

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

[0004] However, traditional harmonic power flow calculation methods mainly focus on the influence of linear loads, ignoring the nonlinear characteristics of power electronic devices. This leads to an increasing error of traditional calculation methods in the case of large-scale power electronic devices connected to the grid, which cannot meet the demand of modern distribution network for harmonic analysis. SUMMARY

[0005] The technical problem to be solved by the present application is to provide a data set generation method and system for converter harmonic coupling characteristic learning to solve the limitations of traditional iterative methods in analyzing harmonic coupling characteristics and the low efficiency of collecting data sets using traditional simulation.

[0006] The application adopts the following technical solutions:

[0007] A data set generation method for converter harmonic coupling characteristic learning, comprising the following steps:

[0008] S1, determine the access capacity and position of power electronic converters in the distribution network, and obtain the filter parameters and control methods thereof;

[0009] S2, select the frequency to be calculated, randomly generate m sets of multi-frequency harmonic voltages under amplitude limitation, and define the distance between the two sets of harmonic voltages;

[0010] S3, based on the distance between the two sets of harmonic voltages obtained in step S2, calculate the distance matrix between all harmonic voltage data, and sequentially perform small signal superposition on the m sets of data according to the traversal rule;

[0011] S4, for the harmonic voltage randomly distributed in step S2, only the fundamental grid voltage 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;

[0012] S5, based on the steady-state quantity in step S4, the harmonic voltage at the power electronic converter is divided into multiple stages as a large disturbance, and the disturbance is increased in stages, and the disturbance size of each stage meets the requirements of small signal equation calculation;

[0013] S6, based on the steady-state quantity in step S4, the small signal equation obtained in step S5 is calculated to obtain the small disturbance response of each state variable at each harmonic voltage disturbance stage; the small disturbance response of each state variable at this stage is superimposed on the steady-state component to update the small signal equation set of the system;

[0014] 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 m groups of random harmonic voltage data.

[0015] Preferably, the power electronic converter is a frequency coupling model based on harmonic transfer function.

[0016] Preferably, in step S2, the distance between the two groups of harmonic voltages is as follows:

[0017]

[0018] wherein, and respectively represent two groups of multi-frequency harmonic voltages, is the selected frequency number, and respectively represent the th data in the two groups of multi-frequency harmonic voltages.

[0019] Preferably, the multi-frequency harmonic voltage is specifically:

[0020]

[0021]

[0022] The distance between the corresponding values in each group of harmonic voltages is defined as:

[0023]

[0024] wherein, and respectively represent the real part of the harmonic voltage at the corresponding position of the two groups of data, and ​Im (Vh) represents the imaginary part of the harmonic voltage at the corresponding position of the two groups of data respectively.

[0025] Preferably, in step S3, the traversal rule is divided into a traversal method and a calculation rule;

[0026] The traversal method sequentially finds an uncalculated point of the shortest distance from the origin as a harmonic voltage to be calculated in the next stage;

[0027] The calculation rule is that each stage finds a point with the shortest distance from the calculated point as the basis for small signal superposition.

[0028] Preferably, in step S5, the harmonic voltage disturbance is added step by step, and a plurality of stages of small signal linearization are adopted, each stage updates the small signal equation, i.e., the coefficient matrix, according to the calculation result of the previous stage, and calculates the steady-state result under large disturbance.

[0029] Preferably, the harmonic coupling characteristics of the converter under m groups of random harmonic voltage data are as follows:

[0030]

[0031] wherein, is the multi-frequency harmonic voltage at the converter.

[0032] In a second aspect, an embodiment of the present application provides a data set generation system for learning harmonic coupling characteristics of a converter, comprising:

[0033] A distance module determines the access capacity and position of the power electronic converter in the power distribution network, obtains the filter parameters and control method thereof, selects a to-be-calculated frequency, randomly generates m groups of multi-frequency harmonic voltages under amplitude limitation, and defines the distance between the two groups of harmonic voltages.

[0034] A matrix module calculates the distance matrix between all harmonic voltage data based on the distance between the two groups of harmonic voltages, and sequentially performs small signal superposition on the m groups of data according to the traversal rule; for each group of harmonic voltage, only the fundamental grid voltage is used as the initial state of the system to solve the initial steady-state quantity, and the steady-state equation coefficient matrix is obtained.

[0035] A disturbance module divides the harmonic voltage at the converter as a large disturbance into a plurality of stages, and increases the disturbance in stages, and the disturbance size of each stage meets the requirement of small signal calculation.

[0036] An update module calculates the small disturbance response of each state variable under the harmonic voltage disturbance of each stage; adds the small disturbance response of each state variable solved in the stage to the steady-state component of the state variable, and updates the small signal equation group of the system.

[0037] ​An 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 down converter under m groups of random harmonic voltage data.

[0038] In a third aspect, a computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the data set generation method for learning harmonic coupling characteristics of a converter when executing the computer program.

[0039] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium including a computer program, and the computer program implements the steps of the data set generation method for learning harmonic coupling characteristics of a converter when executed by a processor.

[0040] In a fifth aspect, a chip includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the data set generation method for learning harmonic coupling characteristics of a converter when executing the computer program.

[0041] In a sixth aspect, an embodiment of the present application provides an electronic device including a computer program, and the computer program implements the steps of the data set generation method for learning harmonic coupling characteristics of a converter when executed by the electronic device.

[0042] Compared with the prior art, the present application has at least the following beneficial effects:

[0043] A data set generation method for learning harmonic coupling characteristics of a converter, for a new power distribution network system with multiple power electronic devices, taking into account the characteristics of power electronic devices, using a deep learning method to learn the complex relationship of the coupling harmonic current generated by the converter under harmonic voltage disturbance, which can simplify the difficulty of coupling feature analysis. Simulation models are difficult to obtain a large amount of data under random scenarios, so that the feature learning of harmonic coupling cannot be performed. Based on small signal superposition calculation and traversal rules, a large number of random data sets for feature analysis can be quickly generated, the generalization ability of the deep learning model is improved, and the coupling relationship under harmonic disturbance is more accurately learned.

[0044] Further, by setting the power electronic converter as a frequency coupling model based on the harmonic transfer function, the small signal relationship between the port voltage and current of the power electronic device is described, which can accurately capture the harmonic interaction behavior and provide a basis for subsequent analysis of the frequency domain coupling characteristics.

[0045] Further, by dividing the traversal rule into traversal method and calculation rule, on the one hand, the traversal method is set to find the nearest uncalculated point as the calculation data in the next stage, so as to ensure global traversal of the data points; on the other hand, the calculation rule is set to find the nearest calculated point as the superposition reference, so as to improve the calculation speed and stepping accuracy.

[0046] Further, for each group of data points, different stepping lengths are set based on the superposition reference, so that the large disturbance is divided into multiple stages of small disturbance superposition, and the small disturbance is repeatedly superimposed to ensure the accuracy of linearization based on the steady-state quantity, and to provide accurate and reliable voltage and current data for subsequent analysis of frequency domain coupling characteristics.

[0047] It can be understood that the beneficial effects of the above-mentioned second aspect to the fourth aspect can be referred to the related description in the first aspect, which will not be repeated here.

[0048] In summary, the method has high calculation accuracy, wide applicability, can adapt to various power distribution network structures, and has relatively practical engineering application value.

[0049] The technical solutions of the present application will be further described in detail below with the help of the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 is a flowchart of the method of the present application;

[0051] Figure 2 is a schematic diagram of the traversal rule of the present application;

[0052] Figure 3 is the data and related simulation results of the method of the present application, wherein (a) is the real part value and imaginary part value of the randomly generated multi-frequency harmonic voltage, (b) is the target voltage of the randomly grouped 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 groups of data sets are input into the LSTM neural network;

[0053] Figure 4 is a schematic diagram of the computer device provided by an embodiment of the present application;

[0054] Figure 5 is a block diagram of a chip provided by an embodiment of the present application. DETAILED DESCRIPTION

[0055] Clearly, the embodiments described are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort are within the protection scope of the present application.

[0056] In the description of the present application, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0057] It should also be understood that the terms used in the specification of the present application are only for the purpose of describing the specific embodiments and are not intended to limit the present application. As used in the specification and the appended claims of the present application, the singular forms "a", "an" and "the" are intended to include the plural forms, unless the context clearly indicates otherwise.

[0058] It should be further understood that the term "and / or" used in the specification and the appended claims of the present application means 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 the three cases of A alone, A and B together, and B alone. In addition, the character " / " in the present application generally represents an "or" relationship between the front and rear associated objects.

[0059] It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present application to describe preset ranges, etc., these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from each other. For example, the first preset range can also be referred to as the second preset range, and similarly, the second preset range can also be referred to as the first preset range, without departing from the scope of the embodiments of the present application.

[0060] Depending on the context, the word "if" as used herein can be interpreted as meaning "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (a stated condition or event)" can be interpreted as meaning "when determined" or "in response to determining" or "when detecting (a stated condition or event)" or "in response to detecting (a stated condition or event)".

[0061] Various structural diagrams according to the disclosed embodiments of the present application are shown in the drawings. These diagrams are not drawn to scale, in which certain details are exaggerated for clarity of presentation and may be omitted. The shapes of various regions, layers shown in the drawings and their relative sizes and positional relationships are merely exemplary, and in actuality may deviate due to manufacturing tolerances or technical limitations, and regions / layers with different shapes, sizes, relative positions can be additionally designed according to actual needs by those skilled in the art.

[0062] The application provides a data set generation method for converter harmonic coupling feature learning, which is based on a method of superimposing nonlinear characteristics on traditional harmonic power flow calculation and considers learning of complex coupling relationship between harmonic voltage and coupled harmonic current by using deep learning. In order to obtain a large amount of data sets under multiple scenarios for harmonic coupling feature learning, the application obtains multi-frequency harmonic currents under a large amount of random multi-frequency harmonic voltages based on a small signal step method and a traversal rule.

[0063] For single-group multi-frequency harmonic voltage calculation, the small signal step method does not need to consider the operation time, while a large amount of data needs to consider improving the calculation rate of the traditional small signal superposition method under the premise of ensuring the calculation accuracy. For the calculation of multiple groups of data, the application considers both the speed of generating data sets and the accuracy of the small signal superposition result. The traversal rule considering step accuracy is designed based on the small signal superposition method, the "distance" between each group of data is transparentized in this process, and the defined distance is sequentially traversed. The superposition calculation of the current traversal data is based on the calculated data under the minimum distance, which effectively improves the speed and accuracy of the calculation of multiple groups of random harmonic data.

[0064] Referring to Figure 1 The application is a data set generation method for converter harmonic coupling feature learning, which comprises the following steps:

[0065] S1, determining the access capacity and position of the power electronic converter model in the power distribution network, obtaining the filter parameters and control method thereof;

[0066] The power electronic converter model is a frequency coupling model based on a harmonic transfer function, which obtains the small signal relationship of the port voltage and current of the converter device, and provides a theoretical basis for the small signal superposition calculation in the subsequent steps.

[0067] S2, selecting a to-be-calculated frequency, randomly generating 1000 groups of multi-frequency harmonic voltages with amplitude limitation, and defining the distance between two groups of harmonic voltages;

[0068] The specific expression of the multi-frequency harmonic voltage is:

[0069]

[0070]

[0071] And the distance between the corresponding values in each group of harmonic voltages is defined as:

[0072]

[0073] Wherein, And Respectively represent the real part of the harmonic voltage at the corresponding position of the two groups of data, And Respectively represent the imaginary part of the harmonic voltage at the corresponding position of the two groups of data.

[0074] The distance between the two groups of harmonic voltages is as follows:

[0075]

[0076] Wherein, And Respectively represent the two groups of multi-frequency harmonic voltages, Is the selected frequency number, And Respectively represent the first Data in the two groups of multi-frequency harmonic voltages.

[0077] 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 carried out in turn according to the following steps;

[0078] The traversal rule mainly includes two parts, based on the defined voltage distance. One part is the traversal method, which starts from the origin and sequentially finds the shortest distance point that has not been calculated as the harmonic voltage that needs to be calculated in the next stage. The other part is the calculation rule, and the point found in each stage is based on the shortest calculated point to carry out small signal superposition.

[0079] S4, for the randomly distributed harmonic voltages in step S2, only the fundamental grid voltage is taken as the initial state of the system, and the initial steady-state quantity is solved to obtain the steady-state equation coefficient matrix;

[0080] The steady-state equation coefficient matrix in step S4 mainly describes the frequency domain characteristics of the converter and the dynamic relationship of the controller. Based on the system frequency, device parameters, and converter controller characteristics, the steady-state voltages and currents of the direct current and alternating current are calculated, which provides a linearization basis for subsequent small signal disturbance analysis.

[0081] S5, based on the steady-state quantity in step S4, the harmonic voltage at the converter is divided into multiple stages as a large disturbance, and the disturbance is increased in stages, and the disturbance size of each stage meets the requirements of small signal equation calculation;

[0082] Harmonic voltage disturbances are superimposed in steps, and small-signal linearization is performed in multiple stages. Each stage updates the small-signal equation, i.e., the coefficient matrix, based on the calculation results of the previous stage, and then calculates the steady-state result under large disturbances. When the disturbance step size of each frequency in each stage is less than 0.005 of the target voltage, it can be considered a small disturbance, which satisfies the requirements of small-signal calculation.

[0083] S6. Based on the steady-state quantities in step S4, calculate the small disturbance response of each state variable under each harmonic voltage disturbance stage by the small-signal equations obtained in step S5; superimpose the small disturbance responses of each state variable obtained in this stage onto its steady-state components, and update the small-signal equations of the system.

[0084] The small-signal equations of the converter are defined as follows:

[0085]

[0086] in, , as well as , All represent coefficient matrices, which are continuously updated as perturbations are superimposed; and These represent the harmonic voltage matrix and harmonic current matrix of the transformer under different conditions; * phase represents the frequency coupling phase.

[0087] S7. Superimpose the disturbance from the next stage, and repeat step S6 until the amplitude of the harmonic voltage disturbance is the same as the set target. Finally, obtain the converter harmonic coupling characteristics under 1000 sets of random harmonic voltage data. .

[0088] Harmonic Coupling Characteristics of Converter under 1000 Sets of Random Harmonic Voltage Data for:

[0089]

[0090] in, This refers to the multi-frequency harmonic voltage at the converter. Those skilled in the art will understand that various aspects of this invention can be implemented as a system, method, or program product. Therefore, various aspects of this invention can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "platform."

[0091] In still another embodiment of the present application, a data set generation system for learning harmonic coupling characteristics of a converter is provided, which can be used to implement the above-mentioned method for generating a data set for learning harmonic coupling characteristics of a converter. Specifically, the data set generation system for learning harmonic coupling characteristics of a converter comprises a distance module, a matrix module, a perturbation module, an update module, and an output module.

[0092] The distance module determines the access capacity and position of a power electronic converter in a power distribution network, obtains filter parameters and control methods thereof, selects a to-be-calculated frequency, randomly generates m sets of multi-frequency harmonic voltages under amplitude limitation, and defines a distance between two sets of harmonic voltages.

[0093] The matrix module calculates a distance matrix between all harmonic voltage data based on the distance between the two sets of harmonic voltages, sequentially performs small signal superposition on the m sets of data according to a traversal rule, and obtains a steady-state equation coefficient matrix by solving initial steady-state quantities with only a fundamental grid voltage as a system initial state for each set of harmonic voltage.

[0094] The perturbation module divides the harmonic voltage at the converter as a large disturbance into multiple stages, and increases the disturbance in stages, with the disturbance size of each stage meeting the requirements of small signal calculation.

[0095] The update module calculates small disturbance responses of each state variable under harmonic voltage disturbance in each stage, superimposes the small disturbance responses of each state variable solved in the stage into a steady-state component, and updates a small signal equation set of the system.

[0096] The output module superimposes the disturbance of the next stage, and repeats until the amplitude of the harmonic voltage disturbance is the same as a set target, and finally obtains harmonic coupling characteristics of the converter under the m sets of random harmonic voltage data.

[0097] In another embodiment of the present application, a terminal device is provided, which comprises a processor and a memory, the memory being configured to store a computer program, the computer program comprising program instructions, and the processor being configured to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, graphics processing units (GPUs), tensor processing units (TPUs), digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) 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, and are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions to implement a corresponding method flow or a corresponding function; the processor in the embodiments of the present application can be used for the operation of the data set generation method for harmonic coupling characteristics learning of a power electronic converter, including:

[0098] The access capacity and position of the power electronic converter in the power distribution network are determined, the filter parameters and the control method thereof are obtained, a to-be-calculated frequency is selected, a plurality of harmonic voltages with a random frequency under amplitude limitation are generated, and the distance between two groups of harmonic voltages is defined; based on the distance between the two groups of harmonic voltages, a distance matrix between all harmonic voltage data is calculated, and small-signal superposition is sequentially performed on m groups of data according to a traversal rule; for each group of harmonic voltages, only the fundamental grid voltage is taken as the initial state of the system, the initial steady-state quantity is solved, and a steady-state equation coefficient matrix is obtained; the harmonic voltage at the converter is taken as a large disturbance and is divided into a plurality of stages, and the disturbance is increased in stages, and the disturbance size of each stage meets the requirement of small-signal calculation; the small-signal equation is calculated to obtain the small disturbance response of each state variable under the harmonic voltage disturbance of each stage; the small disturbance response of each state variable solved in this stage is superimposed on the steady-state component, and the small-signal equation set of the system is updated; the disturbance of the next stage is superimposed, and the process is repeated until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally the harmonic coupling characteristics of the converter under m groups of random harmonic voltage data are obtained.

[0099] Please refer to Figure 4, the terminal device is a computer device, 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, and the computer program 63, when executed by the processor 61, implements the data set generation method for converter harmonic coupling feature learning in the embodiment. To avoid repetition, details are not described here. Alternatively, the computer program 63, when executed by the processor 61, implements the functions of each model / unit in the data set generation system for converter harmonic coupling feature learning in the embodiment. To avoid repetition, details are not described here.

[0100] The computer device 60 can be a desktop computer, a notebook, a palm computer, and a cloud server, etc. The computer device 60 can include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art can understand that the computer device 60 can include more or fewer components, or combine certain components, or different components, for example, the computer device can also include an input / output device, a network access device, a bus, etc. Figure 4 The computer device 60 is only an example and does not constitute a limitation on the computer device 60, and can include more or fewer components than the illustration, or combine certain components, or different components, for example, the computer device can also include an input / output device, a network access device, a bus, etc.

[0101] The processor 61 can be a central processing unit (CPU), and can also be other general-purpose processors, graphics processing units (GPUs), tensor processing units (TPUs), digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0102] The memory 62 can be an internal storage unit of the computer device 60, such as a hard disk or a memory of the computer device 60. The memory 62 can 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.

[0103] Further, the memory 62 can 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 can also be used to temporarily store data that has been output or will be output.

[0104] Referring to Figure 5 The terminal device is a chip, and the chip 600 of the embodiment includes one or more processors 622 and a memory 632 for storing computer programs executable by the processor 622. The computer programs stored in the memory 632 can include one or more modules each corresponding to a set of instructions. In addition, the processor 622 can be configured to execute the computer programs to perform the data set generation method for transformer harmonic coupling feature learning described above.

[0105] In addition, the chip 600 can further include a power supply component 626 configured to perform power management of the chip 600 and a communication component 650 configured to implement communication of the chip 600, such as wired or wireless communication. In addition, the chip 600 can further include an input / output interface 658. The chip 600 can operate based on an operating system stored in the memory 632.

[0106] In another embodiment of the present application, the present application also provides a storage medium, specifically a computer readable storage medium, which is a memory device in the terminal device and is used to store programs and data. It can be understood that the computer readable storage medium herein can include an internal storage medium of the terminal device, and of course can also include an expansion storage medium supported by the terminal device. The computer readable storage medium provides a storage space, and the storage space stores an 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 the instructions can be one or more computer programs. It should be noted that the computer readable storage medium herein can be a high-speed RAM memory or a non-volatile memory such as at least one disk memory.

[0107] The one or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the data set generation method for transformer harmonic coupling feature learning in the above embodiments; the one or more instructions stored in the computer readable storage medium are loaded and executed by the processor as follows:

[0108] The access capacity and position of a power electronic converter in a power distribution network are determined, filter parameters thereof are obtained, and a control method thereof is selected; a to-be-calculated frequency is selected, a plurality of frequency harmonic voltages under amplitude limitation are randomly generated, and a distance between two groups of harmonic voltages is defined; a distance matrix between all harmonic voltage data is calculated based on the distance between the two groups of harmonic voltages, and small-signal superposition is sequentially performed on the m groups of data according to a traversal rule; for each group of harmonic voltages, only a fundamental grid voltage is taken as a system initial state to solve initial steady-state quantities and obtain a steady-state equation coefficient matrix; the harmonic voltage at the converter is taken as a large disturbance and is divided into a plurality of stages, and the disturbance is increased in stages, and the disturbance size of each stage meets the requirement of small-signal calculation; small disturbance responses of each state variable under the harmonic voltage disturbance of each stage are calculated; the small disturbance responses of each state variable solved in this stage are superimposed on the steady-state component to update the small-signal equation set of the system; the disturbance of the next stage is superimposed, and the process is repeated until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally the harmonic coupling characteristics of the converter under the m groups of random harmonic voltage data are obtained.

[0109] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will be a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0110] Referring to Figure 1 , the flow of the method of the present application is:

[0111] First, select the calculation frequency, and select -5, 7, -11, and 13 harmonics for calculation in simulation verification;

[0112] Then, randomly generate 1000 groups of multi-frequency voltage data that meet the limit value size, and calculate the "distance" between the data;

[0113] Start to find the calculation points of each stage and the superposition starting point, and calculate the corresponding multi-frequency harmonic current by using the small-signal superposition method;

[0114] Based on the data amount, all data points are traversed, and finally the multi-frequency harmonic current corresponding to all groups of data is obtained.

[0115] Referring to Figure 2, the schematic diagram of the traversal rule. All generated random harmonic voltages are regarded as points in the plane, from the origin, according to the defined shortest distance, along the blue solid line and the red solid line to find to point ③, taking point ③ as an example, point ②-point ③ is the shortest distance from point ② to find the surrounding uncalculated point; Point ③ finds the shortest distance to the surrounding calculated point as the superposition starting point, as shown by the yellow solid line; And find the shortest distance to the surrounding uncalculated point as the next stage to be calculated point. Therefore, taking point ④ as an example, the red solid line is the path of finding ④, the yellow solid line represents the calculation starting point of point ④, and the blue solid line is the next stage to be calculated position; And point ⑥ as the last traversal point will no longer appear blue solid line.

[0116] Please refer to Figure 3, the method data and related simulation results of the application; Figure 3(a) is the real part value and the imaginary part value of the randomly generated multi-frequency harmonic voltage, both of which are kept within a certain limit; Figure 3(b) is 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) is the multi-frequency harmonic current calculated from the harmonic voltage in Figure 3(b); Table 1 shows the code running effect, as follows:

[0117] Table 1

[0118]

[0119] According to the running result, the average running time of 1000 groups of random data is 150s, the operation time of a single group of data is improved by 20 times, and a high-precision result with basically no error is obtained;

[0120] Figure 3(d) is the learning effect of 1000 groups of data set input LSTM neural network, the proportion of training set and test set is kept at 9:1, and the early stopping callback function under Keras framework is used to prevent model overfitting. From the loss function curve, it can be seen that the model reaches stability at about 260 rounds, and the learning effect is good.

[0121] In summary, the data set generation method and system for harmonic coupling feature learning of a converter consider using deep learning to learn the complex coupling relationship between harmonic voltage and coupled harmonic current. To obtain a large number of data sets for harmonic coupling feature learning under multiple scenarios, the present application first obtains the multi-frequency harmonic current under the corresponding multi-frequency harmonic voltage signal based on the small signal step method and the traversal rule. Specifically, when using the small signal step method to calculate a single set of data, the calculation time does not need to be considered, but when calculating a large number of data at the same time, the calculation rate of the traditional small signal superposition method needs to be improved under the premise of ensuring the calculation accuracy. For the calculation of multiple sets of data, the present application designs a traversal rule considering the calculation accuracy. In this process, the "distance" between each set of data is transparentized, and the traversal is performed one by one based on the defined distance. The superposition calculation of the current traversal data is based on the calculated data under the minimum distance, effectively improving the speed and accuracy of the calculation of multiple sets of data. Therefore, the calculation method proposed by the present application generates a large number of random and accurate coupling data, improves the generalization ability of the analysis using deep learning, and has important theoretical value and practical application prospect.

[0122] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware or software function unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, which will not be described here.

[0123] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0124] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0125] In the embodiments of the present application, it should be understood that the disclosed apparatus / terminal and method can be implemented in other manners. For example, the apparatus / terminal embodiments described above are merely schematic, and the division of the modules or units is merely logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0126] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments.

[0127] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can be a physically independent unit, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0128] The integrated module / unit, if implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the computer readable medium can include or exclude contents according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0129] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in one or more flow or blocks

[0130] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in one or more flow or blocks

[0131] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in one or more flow or blocks

[0132] The above merely provides the technical idea of the present application, and cannot be used to limit the protection scope of the present application. Any modification made according to the technical idea of the present application, on the basis of the technical solutions, falls within the protection scope of the claims of the present application.

Claims

1. A data set generation method for converter harmonic coupling feature learning, characterized by, The method comprises the following steps: S1, determining the access capacity and position of the power electronic converter in the power distribution network, obtaining the filter parameters and control method thereof; S2, selecting a to-be-calculated frequency, randomly generating m sets of multi-frequency harmonic voltages under amplitude limitation, and defining the distance between two sets of harmonic voltages; S3, based on the distance between the two sets of harmonic voltages obtained in step S2, a distance matrix between all harmonic voltage data is calculated, and small signal superposition is sequentially performed on the m sets of data according to the traversal rule; S4, for the randomly distributed harmonic voltages in step S2, only the fundamental grid voltage is taken as the initial state of the system, the initial steady-state quantity is solved, and a steady-state equation coefficient matrix is obtained; S5, based on the steady-state quantity in step S4, the harmonic voltage at the power electronic converter is taken as a large disturbance and is divided into multiple stages, and the disturbance is increased in stages, and the disturbance size of each stage meets the requirement 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 through the small signal equation obtained in step S5; the small disturbance response of each state variable in this stage is superimposed on the steady-state component, and the small signal equation set of the system is updated; S7, the disturbance of the next stage is superimposed, and step S6 is repeated until the amplitude of the harmonic voltage disturbance is the same as the set target, and finally the harmonic coupling characteristics of the converter under m sets of random harmonic voltage data are obtained.

2. The data set generation method for learning a harmonic coupling characteristic of a converter according to claim 1, characterized by, The power electronic converter is a frequency coupling model based on a harmonic transfer function.

3. The data set generation method for learning a harmonic coupling characteristic of a converter according to claim 1, characterized by, In step S2, the distance between the two sets of harmonic voltages is as follows: wherein, and denote two sets of multi-frequency harmonic voltages, is the selected frequency number, and denote the i-th data in the two sets of multi-frequency harmonic voltages, respectively.

4. The data set generation method for learning a harmonic coupling characteristic of a converter according to claim 3, characterized by, The multi-frequency harmonic voltage is specifically: The distance between the corresponding values in each set of harmonic voltages is defined as: wherein, and Rei and Re2 respectively represent the real part of the harmonic voltage at the corresponding position of the two sets of data, and Imi and Im2 respectively represent the imaginary part of the harmonic voltage at the corresponding position of the two sets of data.

5. The data set generation method for learning a harmonic coupling characteristic of a converter according to claim 1, characterized by, In step S3, the traversal rule is divided into a traversal method and a calculation rule; The traversal method sequentially finds the shortest distance point that has not been calculated as the harmonic voltage that needs to be calculated in the next stage from the origin; The calculation rule is that each stage finds a point based on the shortest calculated point.

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

7. The data set generation method for learning a harmonic coupling characteristic of a converter according to claim 1, characterized by, m set random harmonic voltage data downconverter harmonic coupling characteristics is: wherein is the multi-frequency harmonic voltage at the converter.

8. A data set generation system for converter harmonic coupling feature learning, characterized by, It comprises: A distance module for determining the access capacity and position of the power electronic converter in the power distribution network, obtaining the filter parameters and control method thereof; Selecting a to-be-calculated frequency, randomly generating m sets of multi-frequency harmonic voltages under amplitude limitation, and defining the distance between two sets of harmonic voltages; A matrix module for calculating a distance matrix between all harmonic voltage data based on the distance between the two sets of harmonic voltages, and sequentially performing small signal superposition on the m sets of data according to the traversal rule; for each set of harmonic voltage, only the fundamental grid voltage is taken as the initial state of the system, the initial steady-state quantity is solved, and a steady-state equation coefficient matrix is obtained; A disturbance module for taking the harmonic voltage at the power electronic converter as a large disturbance and dividing it into multiple stages, increasing the disturbance in stages, and meeting the requirement of small signal calculation in each stage; an updating module, which calculates the small perturbation response of each state variable under the harmonic voltage disturbance of each stage small signal equation, and adds the small perturbation response of each state variable solved in this stage to the steady-state component to update the small signal equation set of the system; an output module, which adds 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, the one or more programs comprising instructions for: The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform the method of any one of claims 1-7.

10. A computing device, comprising: comprise: 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 performing the method of any one of claims 1-7.

Images