A distributed power aggregation modeling method, system, device and medium

Abstract

The application belongs to the technical field of power systems, and discloses a distributed power source aggregation modeling method, system, device and medium. The method comprises the following steps: acquiring a topological structure of a distribution network line, establishing a distribution network topological simulation model according to the external characteristics of the distributed power source based on the topological structure; performing simulation analysis on the distribution network by using the distribution network topological simulation model according to different distributed power source output coefficients and line voltages that are set in advance, to obtain a plurality of line head current-voltage characteristic curve data; taking the obtained plurality of line head current-voltage characteristic curve data as a data set, and training a pre-configured neural network model by using the data set to obtain a distributed power source aggregation model; and performing aggregation analysis on each distributed power source output coefficient by using the distributed power source aggregation model to obtain a line head current-voltage aggregation characteristic curve under each distributed power source output coefficient. The application improves the efficiency, accuracy and flexibility of fault characteristic aggregation equivalence.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and in particular to a distributed power source aggregation modeling method, system, device and medium. Background Technology

[0002] With the rapid development of distributed generation, regional power grids are gradually exhibiting characteristics of high-density and high-penetration power electronics. The widespread application and large-scale integration of distributed generation have significantly altered the fault characteristics of distribution networks, posing new challenges to their stability and protection control. To gain a deeper understanding of the fault characteristics and protection adaptability of regional power grids, aggregate modeling of distributed generation is necessary. However, traditional mechanistic modeling methods require comprehensive consideration of complex power electronic control characteristics, grid topology, line voltage drop, and operating conditions, making the modeling process cumbersome and time-consuming. Furthermore, due to the high nonlinearity and complexity of power electronic devices, mechanistic modeling methods struggle to accurately capture the system's interaction effects, leading to inaccurate modeling results. Summary of the Invention

[0003] This invention provides a distributed power aggregation modeling method, system, device, and medium to solve the aforementioned technical problems in the prior art.

[0004] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or to describe the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0005] According to a first aspect of the present invention, a distributed power aggregation modeling method is provided.

[0006] In one embodiment, the distributed power aggregation modeling method includes:

[0007] Obtain the topology of the distribution network lines, and based on the topology, establish a distribution network topology simulation model according to the external characteristics of distributed generation sources;

[0008] Based on the pre-set output coefficients of different distributed power sources and line voltages, the distribution network topology simulation model is used to perform distribution network simulation analysis and obtain multiple line head-end current and voltage characteristic curve data.

[0009] The obtained current and voltage characteristic curves of multiple line heads are used as a dataset, and the pre-configured neural network model is trained using the dataset to obtain a distributed power source aggregation model.

[0010] Using the distributed power source aggregation model, the output coefficients of each distributed power source are aggregated and analyzed to obtain the line head-end current and voltage aggregation characteristic curves under each distributed power source output coefficient.

[0011] In one embodiment, the distributed power source external characteristics include low-voltage ride-through capability distributed power source external characteristics and non-low-voltage ride-through capability distributed power source external characteristics.

[0012] In one embodiment, the external characteristics of the low-voltage ride-through capability distributed power source are:

[0013]

[0014]

[0015]

[0016]

[0017] In the formula, i q and i d These are the reactive and active current values, U. T P is the per-unit value of the terminal voltage. N and I N These represent the rated capacity and rated current, respectively; OP is the output coefficient; and i is the current amplitude. This represents the current phase.

[0018] In one embodiment, the external characteristics of the non-low voltage ride-through type distributed power source are:

[0019]

[0020]

[0021] In the formula, P N Rated capacity; U T i represents the per-unit value of the terminal voltage; i represents the current amplitude. This represents the current phase.

[0022] In one embodiment, the neural network model is a long short-term memory network model, and the neural network model uses mean squared error as the loss function, and the neural network model updates the neural network model parameters using the Adam stochastic gradient descent method.

[0023] In one embodiment, the distributed power aggregation modeling method further includes:

[0024] The dataset is normalized before it is used to train a pre-configured neural network model.

[0025] In one embodiment, the distributed power aggregation modeling method further includes:

[0026] The aggregation effect of the distributed power aggregation model is evaluated, and the evaluation indicators include: mean absolute error, mean relative error, peak absolute error, and peak relative error.

[0027] According to a second aspect of the present invention, a distributed power aggregation modeling system is provided.

[0028] In one embodiment, the distributed power aggregation modeling system includes:

[0029] The simulation model building module is used to obtain the topology of the distribution network lines and, based on the topology, establish a distribution network topology simulation model according to the external characteristics of distributed power sources.

[0030] The simulation model analysis module is used to perform distribution network simulation analysis based on the pre-set different distributed power output coefficients and line voltages using the distribution network topology simulation model, and obtain multiple line head-end current and voltage characteristic curve data.

[0031] The aggregation model generation module is used to take the obtained current and voltage characteristic curve data of multiple line heads as a dataset, and use the dataset to train a pre-configured neural network model to obtain a distributed power source aggregation model.

[0032] The power aggregation analysis module is used to perform aggregation analysis on the output coefficients of each distributed power source using the distributed power source aggregation model, and obtain the line head-end current and voltage aggregation characteristic curves under each distributed power source output coefficient.

[0033] In one embodiment, the distributed power source external characteristics include low-voltage ride-through capability distributed power source external characteristics and non-low-voltage ride-through capability distributed power source external characteristics.

[0034] In one embodiment, the external characteristics of the low-voltage ride-through capability distributed power source are:

[0035]

[0036]

[0037]

[0038]

[0039] In the formula, i q and i d These are the reactive and active current values, U. TP is the per-unit value of the terminal voltage. N and I N These represent the rated capacity and rated current, respectively; OP is the output coefficient; and i is the current amplitude. This represents the current phase.

[0040] In one embodiment, the external characteristics of the non-low voltage ride-through type distributed power source are:

[0041]

[0042]

[0043] In the formula, P N Rated capacity; U T i represents the per-unit value of the terminal voltage; i represents the current amplitude. This represents the current phase.

[0044] In one embodiment, the neural network model is a long short-term memory network model, and the neural network model uses mean squared error as the loss function, and the neural network model updates the neural network model parameters using the Adam stochastic gradient descent method.

[0045] In one embodiment, the distributed power aggregation modeling system further includes:

[0046] A normalization module is used to normalize the dataset before training a pre-configured neural network model using the dataset.

[0047] In one embodiment, the distributed power aggregation modeling system further includes:

[0048] The aggregation evaluation module is used to evaluate the aggregation effect of the distributed power aggregation model, and the evaluation indicators include: mean absolute error, mean relative error, peak absolute error and peak relative error.

[0049] According to a third aspect of the present invention, a computer device is provided.

[0050] In one embodiment, the computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described above.

[0051] According to a fourth aspect of the present invention, a computer-readable storage medium is provided.

[0052] In one embodiment, a computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the steps of the above method.

[0053] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0054] This invention does not rely on specific physical mechanisms but instead establishes models through a data-driven approach. It utilizes neural networks to capture the nonlinear relationships of complex systems, improving the efficiency, accuracy, and flexibility of fault characteristic aggregation and equivalence modeling. This invention is applicable to distributed power source fault characteristic aggregation modeling at all levels, including lines, buses, and regional power grids, and possesses a certain degree of universality. It can achieve distributed power source aggregation fault characteristic modeling in arbitrary output scenarios, adapting to the real-time modeling needs of fluctuating renewable energy power generation output. It provides accurate and reliable references for relay protection analysis and decision-making, helping to optimize and improve relay protection strategies and enhance the stability and reliability of the power grid.

[0055] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0056] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0057] Figure 1 This is a flowchart illustrating a distributed power aggregation modeling method according to an exemplary embodiment;

[0058] Figure 2 This is a structural block diagram of a distributed power aggregation modeling system according to an exemplary embodiment;

[0059] Figure 3 This is a schematic diagram of the input and output of a neural network according to an exemplary embodiment;

[0060] Figure 4 This is a diagram illustrating the structure of a neural network model according to an exemplary embodiment;

[0061] Figure 5 This is a schematic diagram of the structure of a computer device according to an exemplary embodiment. Detailed Implementation

[0062] The following description and accompanying drawings fully illustrate specific embodiments described herein to enable those skilled in the art to practice them. Some embodiments may include or substitute parts and features of other embodiments. The scope of the embodiments herein encompasses the entire scope of the claims and all available equivalents thereof. Throughout this document, the terms “first,” “second,” etc., are used only to distinguish one element from another without requiring or implying any actual relationship or order between the elements. Indeed, a first element can also be referred to as a second element, and vice versa. Furthermore, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a structure, apparatus, or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a structure, apparatus, or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the structure, apparatus, or device that includes said element. The various embodiments described herein are presented in a progressive manner, with each embodiment focusing on its differences from other embodiments; similar or identical parts between embodiments can be referred to interchangeably.

[0063] The terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer" used in this document to indicate orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings. They are used solely for the convenience of describing the document and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In the description herein, unless otherwise specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly. For example, they can refer to mechanical or electrical connections, or internal connections between two elements; they can be direct connections or indirect connections through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms according to the specific circumstances.

[0064] In this document, unless otherwise stated, the term "multiple" means two or more.

[0065] In this article, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0066] In this article, the term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0067] It should be understood that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order constraint on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the diagram may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0068] The modules in the apparatus or system of this application can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0069] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0070] Figure 1 An embodiment of a distributed power aggregation modeling method of the present invention is shown.

[0071] In this optional embodiment, the distributed power aggregation modeling method includes:

[0072] Step S101: Obtain the topology of the distribution network lines, and based on the topology, establish a distribution network topology simulation model according to the external characteristics of distributed power sources.

[0073] Step S103: Based on the pre-set output coefficients of different distributed power sources and line voltages, the distribution network topology simulation model is used to perform distribution network simulation analysis to obtain multiple line head current and voltage characteristic curve data.

[0074] Step S105: The obtained multiple line head current and voltage characteristic curve data are used as a dataset, and the pre-configured neural network model is trained using the dataset to obtain a distributed power source aggregation model.

[0075] Step S107: Using the distributed power source aggregation model, perform aggregation analysis on the output coefficients of each distributed power source to obtain the line head-end current and voltage aggregation characteristic curves under each distributed power source output coefficient.

[0076] Figure 2 An embodiment of a distributed power aggregation modeling system according to the present invention is shown.

[0077] In this optional embodiment, the distributed power aggregation modeling system includes:

[0078] The simulation model building module 201 is used to obtain the topology of the distribution network lines and, based on the topology, establish a distribution network topology simulation model according to the external characteristics of distributed power sources.

[0079] The simulation model analysis module 203 is used to perform distribution network simulation analysis based on the pre-set different distributed power output coefficients and line voltages using the distribution network topology simulation model, and obtain multiple line head-end current and voltage characteristic curve data.

[0080] The aggregation model generation module 205 is used to take the obtained multiple line head current and voltage characteristic curve data as a dataset, and use the dataset to train a pre-configured neural network model to obtain a distributed power source aggregation model.

[0081] The power aggregation analysis module 207 is used to perform aggregation analysis on the output coefficients of each distributed power source using the distributed power source aggregation model, and obtain the line head-end current and voltage aggregation characteristic curves under each distributed power source output coefficient.

[0082] In practical applications, the external characteristics of distributed generation include low-voltage ride-through (LVR) capability-type distributed generation external characteristics and non-LVR capability-type distributed generation external characteristics. For example, consider 5 distributed generation units, three of which have LVR capability with capacities of 2MW, 4MW, and 6MW, respectively, and two of which do not have LVR capability with capacities of 30kW and 50kW, respectively.

[0083] The external characteristics of the low-voltage ride-through capability distributed power source are as follows:

[0084]

[0085]

[0086]

[0087]

[0088] In the formula, i q and i d These are the reactive and active current values, U. T P is the per-unit value of the terminal voltage. N and I N These represent the rated capacity and rated current, respectively; OP is the output coefficient; and i is the current amplitude. This represents the current phase.

[0089] The external characteristics of the non-low voltage ride-through type distributed power source are as follows:

[0090]

[0091]

[0092] In the formula, P N Rated capacity; U T i represents the per-unit value of the terminal voltage; i represents the current amplitude. This represents the current phase.

[0093] Furthermore, when generating the dataset, the output coefficients of each distributed power source and the line voltage in the simulation model vary within the range of 0-1, and multiple sets of samples are randomly generated. The training set contains 3125 sets of samples, and the test set contains 64 sets of samples. The current-voltage characteristic curves include the RMS current-voltage characteristic curve and the current-phase-voltage characteristic curve. To ensure data accuracy, the dataset can be normalized before training the pre-configured neural network model. The normalization formula is as follows:

[0094]

[0095] In the formula, x and x * These are the values ​​before and after normalization, x. min and x max These are the maximum and minimum values ​​of the sample, respectively.

[0096] Correspondingly, the system includes a normalization processing module (not shown in the figure), which is used to normalize the dataset before training the pre-configured neural network model using the dataset.

[0097] In addition, the neural network model can be a long short-term memory network model, and the neural network model uses mean squared error as the loss function. The neural network model updates the neural network model parameters using the Adam stochastic gradient descent method.

[0098] In use, the neural network model employs a one-dimensional convolutional layer (1D Conv) to extract features from the distributed power source output data of the input model, and outputs sequential data after activation using the Tanh function; a Long Short-Term Memory (LSTM) network is used to process the sequential data; a fully connected layer (FC) is used to map the vectors into a sequence of current and voltage characteristic curves, and the output is obtained after activation using the Sigmoid function. Its loss function is: In the formula, N is the total number of datasets; y n and These are the effective value of the aggregate current or the true value of the phase at the nth data point in the dataset, and the model estimate, respectively.

[0099] like Figure 3 As shown, the input of the neural network model is the photovoltaic power output coefficient sequence, and the output is the current-voltage aggregation characteristic data sequence at the beginning of the line. The first N data points in the current-voltage aggregation characteristic data sequence represent the current phase sequence, and the last N data points represent the current effective value sequence.

[0100] For example Figure 4 As shown, when the neural network model is used, a one-dimensional convolutional layer (1DConv) with 64 channels is used to extract features from the distributed power supply output data of the input model. After activation by the Tanh function, the output sequence data has a size of (B, 64), where B is the batch size. A Long Short-Term Memory (LSTM) network with two hidden layers and 256 and 512 features respectively is used to process the sequence data, and the output vector has a size of (B, 64). A fully connected layer (FC) is used to map the vector into a sequence of current and voltage characteristic curves, and after activation by the Sigmoid function, the output vector has a size of (B, 2*N), where N is the total number of sampling points.

[0101] Furthermore, in specific applications, the aggregation effect of the distributed power aggregation model can be evaluated, and the evaluation metrics can include: Mean Absolute Error (MAE), Mean Relative Error (MRE), Peak Absolute Error (PAE), and Peak Relative Error (PRE).

[0102] Correspondingly, the system includes an aggregation evaluation module (not shown in the figure), which is used to evaluate the aggregation effect of the distributed power aggregation model, and the evaluation indicators include: mean absolute error, mean relative error, peak absolute error and peak relative error.

[0103] In practical use, the calculation formulas for MAE, MRE, PAE, and PRE are as follows:

[0104]

[0105]

[0106]

[0107]

[0108] In the formula, N is the total number of datasets; y n and These are the effective value of the aggregate current or the true value of the phase at the nth data point in the dataset, and the model estimate, respectively.

[0109] Figure 5 An embodiment of a computer device according to the present invention is shown. The computer device may be a server, and includes a processor, memory, and a network interface connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores static and dynamic information data. The network interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps in the above-described method embodiment.

[0110] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device to which the present invention is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0111] In addition, the present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0112] In addition, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0113] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0114] This invention is not limited to the structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this invention is limited only by the appended claims.

Claims

1. A distributed power source aggregation modeling method, characterized in that, include: Obtain the topology of the distribution network lines, and based on the topology, establish a distribution network topology simulation model according to the external characteristics of distributed generation sources; Based on the pre-set output coefficients of different distributed power sources and line voltages, the distribution network topology simulation model is used to perform distribution network simulation analysis and obtain multiple line head-end current and voltage characteristic curve data. The obtained current and voltage characteristic curves of multiple line heads are used as a dataset, and the pre-configured neural network model is trained using the dataset to obtain a distributed power source aggregation model. Using the distributed power source aggregation model, the output coefficients of each distributed power source are aggregated and analyzed to obtain the line head-end current and voltage aggregation characteristic curves under each distributed power source output coefficient.

2. The distributed power source aggregation modeling method according to claim 1, characterized in that, The external characteristics of distributed generation include low-voltage ride-through capability distributed generation external characteristics and non-low-voltage ride-through capability distributed generation external characteristics.

3. The distributed power source aggregation modeling method according to claim 2, characterized in that, The external characteristics of the non-low voltage ride-through type distributed power source are as follows: In the formula, Rated capacity; i represents the per-unit value of the terminal voltage; i represents the current amplitude. This represents the current phase.

4. The distributed power source aggregation modeling method according to claim 1, characterized in that, The neural network model is a long short-term memory network model, and the neural network model uses mean squared error as the loss function. The neural network model updates the neural network model parameters using the Adam stochastic gradient descent method.

5. The distributed power source aggregation modeling method according to claim 1, characterized in that, Also includes: The dataset is normalized before it is used to train a pre-configured neural network model.

6. The distributed power source aggregation modeling method according to claim 1, characterized in that, Also includes: The aggregation effect of the distributed power aggregation model is evaluated, and the evaluation indicators include: mean absolute error, mean relative error, peak absolute error, and peak relative error.

7. A distributed power source aggregation modeling system, characterized in that, include: The simulation model building module is used to obtain the topology of the distribution network lines and, based on the topology, establish a distribution network topology simulation model according to the external characteristics of distributed power sources. The simulation model analysis module is used to perform distribution network simulation analysis based on the pre-set different distributed power output coefficients and line voltages using the distribution network topology simulation model, and obtain multiple line head-end current and voltage characteristic curve data. The aggregation model generation module is used to take the obtained current and voltage characteristic curve data of multiple line heads as a dataset, and use the dataset to train a pre-configured neural network model to obtain a distributed power source aggregation model. The power aggregation analysis module is used to perform aggregation analysis on the output coefficients of each distributed power source using the distributed power source aggregation model, and obtain the line head-end current and voltage aggregation characteristic curves under each distributed power source output coefficient.

8. A distributed power source aggregation modeling system according to claim 7, characterized in that, The external characteristics of distributed generation include low-voltage ride-through capability distributed generation external characteristics and non-low-voltage ride-through capability distributed generation external characteristics.

9. A distributed power aggregation modeling system according to claim 8, characterized in that, The external characteristics of the non-low voltage ride-through type distributed power source are as follows: In the formula, Rated capacity; i represents the per-unit value of the terminal voltage; i represents the current amplitude. This represents the current phase.

10. A distributed power aggregation modeling system according to claim 7, characterized in that, The neural network model is a long short-term memory network model, and the neural network model uses mean squared error as the loss function. The neural network model updates the neural network model parameters using the Adam stochastic gradient descent method.

11. A distributed power aggregation modeling system according to claim 7, characterized in that, Also includes: A normalization module is used to normalize the dataset before training a pre-configured neural network model using the dataset.

12. A distributed power aggregation modeling system according to claim 7, characterized in that, Also includes: The aggregation evaluation module is used to evaluate the aggregation effect of the distributed power aggregation model, and the evaluation indicators include: mean absolute error, mean relative error, peak absolute error and peak relative error.

13. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images