Zone area photovoltaic capacity evaluation method, system and device and storage medium

Abstract

The invention discloses a transformer area photovoltaic capacity evaluation method, system and device and a storage medium, and the method comprises the steps: processing obtained target transformer area data through employing a feature extraction model based on a deep learning algorithm, and obtaining a transformer area feature matrix; obtaining voltage quality scenes of different load dimensions on the basis of a result obtained by dividing the transformer area characteristic matrix through a clustering algorithm; generating each sensitivity matrix based on a load flow calculation result in the obtained simulation operation result; performing fitting processing on each sensitivity matrix by using a limit gradient lifting algorithm to obtain a voltage vector and a net load vector; and constructing a photovoltaic capacity evaluation model, and obtaining a photovoltaic capacity evaluation result based on the photovoltaic capacity evaluation model. According to the method provided by the embodiment of the invention, the technical problem that the photovoltaic capacity evaluation result is inaccurate when the distributed photovoltaic is connected to the low-voltage power distribution network can be solved, so that the stability and the safety of a power system are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network planning, and in particular to a method, system, device and storage medium for evaluating photovoltaic capacity in a substation. Background Art

[0002] With the rapid development of distributed photovoltaics, when a large amount of photovoltaic energy is connected to the low-voltage distribution network, in order to ensure the stability and safety of the power system, it is necessary to evaluate the photovoltaic capacity.

[0003] The existing photovoltaic capacity assessment method relies on fixed scenario divisions and ignores the dynamic changes in load and photovoltaic power generation, resulting in large deviations in the assessment results, which in turn affects the stability of the power system.

[0004] It can be seen that how to solve the problem of inaccurate photovoltaic capacity assessment results when distributed photovoltaics are connected to a low-voltage distribution network has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention

[0005] The present invention provides a photovoltaic capacity assessment method, system, device and storage medium for a substation to solve the technical problem of inaccurate photovoltaic capacity assessment results when distributed photovoltaics are connected to a low-voltage distribution network, thereby ensuring the stability and safety of the power system.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a method for evaluating photovoltaic capacity in a metropolitan area, the method comprising: The historical photovoltaic power generation data and load data of the target area are processed using a feature extraction model based on a deep learning algorithm to obtain the area feature matrix; Based on the result of partitioning the substation feature matrix by a clustering algorithm, voltage quality scenarios of different load dimensions are reconstructed; Acquire simulation results of the target substation under each voltage quality scenario, and generate each sensitivity matrix based on power flow calculation results in the simulation results; Using an extreme gradient boosting algorithm to fit each of the sensitivity matrices to obtain a voltage vector and a net load vector; With the goal of maximizing the photovoltaic capacity of the substation and minimizing network losses, a photovoltaic capacity assessment model is constructed; The voltage distribution result obtained by processing the voltage vector using a multivariate normal distribution assumption algorithm is obtained, and the net load distribution result obtained by processing the net load vector using the multivariate normal distribution assumption algorithm is obtained. Under the constraints of the voltage distribution result and the net load distribution result, a photovoltaic capacity assessment result of the target substation is obtained based on the photovoltaic capacity assessment model.

[0007] As one of the preferred solutions, the feature extraction model based on the deep learning algorithm is used to process the historical photovoltaic power generation data and load data of the target area to obtain the area feature matrix, including: Acquire historical photovoltaic power generation data and load data of the target area, and introduce deep learning network parameters, wherein the network parameters include a weight matrix, a bias vector, and an activation function; Constructing a feature extraction model based on the weight matrix, the bias vector and the activation function; The feature extraction model is used to extract features from the historical photovoltaic power generation data and the load data to obtain a station feature matrix.

[0008] As one of the preferred solutions, the voltage quality scenarios of different load dimensions are reconstructed based on the result of partitioning the substation feature matrix by a clustering algorithm, including: A neighborhood radius parameter and a minimum number of sample points in the neighborhood are introduced, and the clustering algorithm is used to divide the station area feature matrix to obtain a clustering result and a neighborhood distance; According to the neighborhood distance, performing robust average calculation on the clustering results to obtain a scale parameter; The scale parameters are used to reconstruct the substation characteristic matrix to obtain voltage quality scenarios of different load dimensions.

[0009] As one of the preferred solutions, the step of obtaining the simulation results of the target substation in each voltage quality scenario and generating each sensitivity matrix based on the power flow calculation results in the simulation results includes: Constructing a power system simulation model of the target substation according to the power grid structure and operating conditions; Based on each of the voltage quality scenarios, obtaining various simulation operation results of the power system simulation model; Performing power flow calculation on each of the simulation operation results using the Gauss-Seidel method to obtain power flow calculation results; Based on the power flow calculation results, a sensitivity matrix is ​​obtained.

[0010] As one of the preferred solutions, after building the photovoltaic capacity assessment model, the photovoltaic capacity assessment method of the substation further includes: Processing the voltage vector and the net load vector to obtain a power flow equation, and iteratively processing the power flow equation to obtain a Jacobian matrix; Expanding the Jacobian matrix to obtain a dynamic sensitivity matrix; Based on the dynamic sensitivity matrix and the sensitivity matrix, a sensitivity matrix deviation is obtained; Based on the sensitivity matrix deviation, the photovoltaic capacity assessment model is optimized.

[0011] As one preferred solution, before obtaining the photovoltaic capacity evaluation result of the target area based on the photovoltaic capacity evaluation model, the photovoltaic capacity evaluation method of the area further includes: Performing sensitivity analysis on the voltage distribution result and the net load distribution result, and calculating the convergence of the photovoltaic capacity evaluation model; Based on the convergence of the photovoltaic capacity evaluation model, the photovoltaic capacity evaluation model is optimized.

[0012] As one of the preferred solutions, after obtaining the photovoltaic capacity assessment result of the target area, the photovoltaic capacity assessment method of the area further includes: The photovoltaic capacity assessment result is processed using a natural language model to generate a natural language report, and the natural language report is sent to a corresponding client terminal for storage.

[0013] Another embodiment of the present invention provides a photovoltaic capacity assessment system for a station area, comprising: A preprocessing module is used to process the historical photovoltaic power generation data and load data of the target area using a feature extraction model based on a deep learning algorithm to obtain an area feature matrix; A reconstruction module, used for reconstructing voltage quality scenarios of different load dimensions based on the result of partitioning the substation feature matrix by a clustering algorithm; An operation module, used for obtaining simulation operation results of the target substation under each voltage quality scenario, and generating each sensitivity matrix based on the power flow calculation results in the simulation operation results; A fitting module, used for fitting each sensitivity matrix using an extreme gradient boosting algorithm to obtain a voltage vector and a net load vector; A construction module is used to construct a photovoltaic capacity assessment model with the goal of maximizing the photovoltaic capacity of the substation and minimizing network losses; A generation module is used to obtain a voltage distribution result obtained by processing the voltage vector using a multivariate normal distribution assumption algorithm, and to obtain a net load distribution result obtained by processing the net load vector using the multivariate normal distribution assumption algorithm, and to obtain a photovoltaic capacity assessment result of the target substation based on the photovoltaic capacity assessment model under the constraints of the voltage distribution result and the net load distribution result.

[0014] Another embodiment of the present invention provides a photovoltaic capacity assessment device for a metropolitan area, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the photovoltaic capacity assessment method for a metropolitan area as described above when executing the computer program.

[0015] Yet another embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the photovoltaic capacity assessment method for the substation as described above is implemented.

[0016] Compared with the prior art, the embodiments of the present invention have the following advantages: The present invention uses a feature extraction model based on a deep learning algorithm to process the historical photovoltaic power generation data and load data of the target substation to obtain a substation feature matrix; based on the result of dividing the substation feature matrix by a clustering algorithm, reconstruct voltage quality scenarios of different load dimensions; obtain the simulation operation results of the target substation under each voltage quality scenario, and generate each sensitivity matrix based on the flow calculation results in the simulation operation results; use an extreme gradient boosting algorithm to fit each sensitivity matrix to obtain a voltage vector and a net load vector; construct a photovoltaic capacity evaluation model with the goal of maximizing the photovoltaic capacity of the substation and minimizing network losses; obtain the voltage distribution result obtained by processing the voltage vector by a multivariate normal distribution assumption algorithm, and obtain the net load distribution result obtained by processing the net load vector by the multivariate normal distribution assumption algorithm, and under the constraints of the voltage distribution result and the net load distribution result, obtain the photovoltaic capacity evaluation result of the target substation based on the photovoltaic capacity evaluation model. Compared with the existing technology, this method combines the dynamic change characteristics of load and photovoltaic power generation, obtains the voltage vector and the net load vector by fitting the sensitivity matrix using the extreme gradient boosting algorithm, and uses the multivariate normal distribution hypothesis algorithm to perform probability calculation on the voltage vector and the net load vector to obtain the distribution result. With the distribution result as a constraint, the constructed photovoltaic capacity assessment model is used to obtain accurate photovoltaic capacity assessment results, thereby ensuring the stability and safety of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the flow of a method for evaluating photovoltaic capacity in a metropolitan area in one embodiment of the present invention; Figure 2 It is a structural schematic diagram of a photovoltaic capacity assessment system for a metropolitan area in one embodiment of the present invention; Figure 3 It is a structural schematic diagram of a photovoltaic capacity assessment device for a metropolitan area in one embodiment of the present invention.

[0018] Reference numerals: Among them, 11, preprocessing module; 12, reconstruction module; 13, operation module; 14, fitting module; 15, construction module; 16, generation module. DETAILED DESCRIPTION

[0019] 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 only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. 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.

[0020] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0021] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0022] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0023] With the rapid development of distributed photovoltaics, when a large amount of photovoltaic energy is connected to the low-voltage distribution network, in order to ensure the stability and safety of the power system, it is necessary to evaluate the photovoltaic capacity.

[0024] The existing photovoltaic capacity assessment method relies on fixed scenario divisions and ignores the dynamic changes in load and photovoltaic power generation, resulting in large deviations in the assessment results, which in turn affects the stability of the power system.

[0025] It can be seen that how to solve the problem of inaccurate photovoltaic capacity assessment results when distributed photovoltaics are connected to a low-voltage distribution network has become a technical problem that technical personnel in this field need to solve urgently.

[0026] In order to solve the above technical problems, an embodiment of the present invention provides a method for evaluating photovoltaic capacity in a metropolitan area. For details, see Figure 1 , Figure 1 The figure shows a flow chart of a method for evaluating photovoltaic capacity in a metropolitan area in one embodiment of the present invention, the method comprising: S1: Use the feature extraction model based on the deep learning algorithm to process the historical photovoltaic power generation data and load data of the target area to obtain the area feature matrix.

[0027] Specifically, the historical photovoltaic power generation data and load data of the target area are obtained, and the deep learning network parameters are introduced, where the network parameters include the weight matrix W, the bias vector b and the activation function , based on the weight matrix W, bias vector b and activation function Build a feature extraction model.

[0028] Preferably, the feature extraction model is constructed by an autoencoder network, and the feature extraction model is used to extract features from the original input data to obtain a station feature matrix, and the formula is as follows: The historical photovoltaic power generation data and load data of the target area are obtained as the original input data X, and Z is the area feature matrix.

[0029] S2: Based on the result of partitioning the substation feature matrix by a clustering algorithm, voltage quality scenarios of different load dimensions are reconstructed.

[0030] Specifically, the neighborhood radius parameter and the minimum number of sample points in the neighborhood parameter are introduced, and the clustering algorithm is used to divide the station area feature matrix to obtain the clustering result and neighborhood distance.

[0031] Preferably, the clustering algorithm is a density-based clustering algorithm (DBSCAN).

[0032] It should be noted that the clustering result refers to the classification of sample points in the station area feature matrix into different categories, while the neighborhood distance refers to the distance between a sample point and its cluster center or other sample points.

[0033] According to the obtained neighborhood distance, the clustering results are robustly averaged to obtain the scale parameter, which is used to measure the compactness and dispersion of the clusters.

[0034] Furthermore, the scale parameters are used to reconstruct the substation characteristic matrix to obtain voltage quality scenarios of different load dimensions, wherein reconstruction refers to adjusting or converting the substation characteristic matrix according to the scale parameters to generate voltage quality scenarios of different load dimensions. Under different load dimensions, the voltage quality scenarios may be different, and the typical voltage quality scenarios divided include high-load high-fluctuation scenarios, low-load low-fluctuation scenarios, PV-intensive scenarios, and heavy-load low-fluctuation scenarios.

[0035] S3: Acquire simulation results of the target substation in each of the voltage quality scenarios, and generate various sensitivity matrices based on power flow calculation results in the simulation results.

[0036] Specifically, a power system simulation model of the target substation is constructed based on the power grid structure and operating conditions. The power grid structure and operating conditions include the topology of the power grid (such as line connection, transformer configuration, etc.), equipment parameters (such as line impedance, transformer ratio, etc.), and operating conditions (such as load level, power generation output, etc.). Based on this information, a detailed simulation model of the target substation is constructed using power system simulation software, which can accurately reflect the actual operating status of the power grid.

[0037] Preferably, the power system simulation software is PSASP, PSCAD, or SimPowerSystems in MATLAB / Simulink.

[0038] Furthermore, based on each voltage quality scenario, each simulation operation result of the power system simulation model is obtained, and the Gauss-Seidel method is used to perform power flow calculation on each of the simulation operation results to obtain power flow calculation results, and based on the power flow calculation results, a sensitivity matrix is ​​obtained.

[0039] It should be noted that the Gauss-Seidel method is a commonly used method for calculating power system flow. It obtains the power flow distribution results of the power grid by iteratively solving a group of nonlinear equations. Based on the power flow calculation results, the sensitivity matrix is ​​calculated by numerical differentiation or perturbation analysis. Specifically, a small disturbance can be made to a certain parameter in the power grid, and then the power flow calculation can be re-performed to compare the changes in the power grid state before and after the disturbance, thereby obtaining the sensitivity of the parameter to the power grid state.

[0040] S4: Using the extreme gradient boosting algorithm to fit each of the sensitivity matrices to obtain a voltage vector and a net load vector.

[0041] Specifically, the sensitivity matrix includes information about the impact of different parameter changes in the power grid on voltage and load. The feature importance evaluation method provided by the extreme gradient boosting algorithm (XGBoost) is used to select the features most relevant to voltage and load changes from the sensitivity matrix. It should be noted that the features need to be scaled to ensure that they are on the same scale.

[0042] Furthermore, the trained XGBoost model is used to fit the sensitivity matrix to obtain the corresponding voltage vector and net load vector.

[0043] S5: Construct a photovoltaic capacity assessment model with the goal of maximizing the photovoltaic capacity in the substation area and minimizing network losses.

[0044] S6: Obtain a voltage distribution result obtained by processing the voltage vector using a multivariate normal distribution assumption algorithm, and obtain a net load distribution result obtained by processing the net load vector using the multivariate normal distribution assumption algorithm, and obtain a photovoltaic capacity assessment result of the target substation based on the photovoltaic capacity assessment model under the constraints of the voltage distribution result and the net load distribution result.

[0045] Furthermore, after constructing the photovoltaic capacity assessment model, the voltage vector and the net load vector are processed to obtain a power flow equation, the power flow equation is iteratively processed to obtain a Jacobian matrix, and the Jacobian matrix is ​​expanded to obtain a dynamic sensitivity matrix.

[0046] Specifically, in the power system, the power flow equation describes the relationship between power flow and voltage and current in the power grid. Using the known voltage vector and net load vector, combined with the network structure of the power system, the power flow equation of the system can be constructed. Since the power flow equation is nonlinear, it is usually necessary to use an iterative method to solve it.

[0047] Preferably, the iterative method is preferably a Newton-Raphson method.

[0048] During the iteration process, it is necessary to calculate the Jacobian matrix of the power flow equation. The Jacobian matrix is ​​a matrix that contains the partial derivatives of the equation with respect to all variables. It plays a key role in iterative methods such as the Newton-Raphson method.

[0049] After obtaining the Jacobian matrix, it can be expanded to take into account the changes in system state over time. This expansion involves performing time derivative operations on the matrix or introducing time-related parameters. The expanded Jacobian matrix is ​​called the dynamic sensitivity matrix, which reflects the dynamic impact of system state changes on voltage and load.

[0050] Based on the dynamic sensitivity matrix and the sensitivity matrix, a sensitivity matrix deviation is obtained, and the deviation reflects the difference between the dynamic characteristics and the static characteristics of the system.

[0051] In order to make the photovoltaic capacity assessment model more accurately reflect the actual operating status of the power system, especially considering the dynamic characteristics of the system, the photovoltaic capacity assessment model is optimized based on the constraint condition of sensitivity matrix deviation.

[0052] Furthermore, the optimization process of the photovoltaic capacity assessment model also includes performing a sensitivity analysis on the voltage distribution result and the net load distribution result, calculating the convergence of the photovoltaic capacity assessment model, and optimizing the photovoltaic capacity assessment model based on the convergence of the photovoltaic capacity assessment model.

[0053] Specifically, model convergence refers to the ability of the model to gradually approach the true solution during the iteration process. By performing a sensitivity analysis on the voltage distribution results and the net load distribution results, the model parameters that have a significant impact on the photovoltaic capacity assessment results are adjusted according to the results of the sensitivity analysis. By adjusting the model parameters that have a significant impact on the photovoltaic capacity assessment results, the convergence of the photovoltaic capacity assessment model is calculated to further improve the accuracy of the model.

[0054] The embodiment of the present invention provides a photovoltaic capacity assessment method for a substation, wherein the method processes the historical photovoltaic power generation data and load data of the target substation obtained by using a feature extraction model based on a deep learning algorithm to obtain a substation feature matrix; based on the result of dividing the substation feature matrix by a clustering algorithm, reconstructs voltage quality scenarios of different load dimensions; obtains simulation operation results of the target substation under each voltage quality scenario, and generates each sensitivity matrix based on the power flow calculation results in the simulation operation results; uses an extreme gradient boosting algorithm to fit each sensitivity matrix to obtain a voltage vector and a net load vector; constructs a photovoltaic capacity assessment model with the goal of maximizing the photovoltaic capacity of the substation and minimizing network loss; obtains a voltage distribution result obtained by processing the voltage vector by a multivariate normal distribution assumption algorithm, and obtains a net load distribution result obtained by processing the net load vector by the multivariate normal distribution assumption algorithm, and obtains a photovoltaic capacity assessment result of the target substation based on the photovoltaic capacity assessment model under the constraints of the voltage distribution result and the net load distribution result. Compared with the existing technology, this method combines the dynamic change characteristics of load and photovoltaic power generation, obtains the voltage vector and the net load vector by fitting the sensitivity matrix using the extreme gradient boosting algorithm, and uses the multivariate normal distribution hypothesis algorithm to perform probability calculation on the voltage vector and the net load vector to obtain the distribution result. With the distribution result as a constraint, the constructed photovoltaic capacity assessment model is used to obtain accurate photovoltaic capacity assessment results, thereby ensuring the stability and safety of the power system.

[0055] In one embodiment, Figure 2 As shown, an embodiment of the present invention provides a photovoltaic capacity assessment system for a metropolitan area, the system comprising: The preprocessing module 11 is used to process the acquired historical photovoltaic power generation data and load data of the target area using a feature extraction model based on a deep learning algorithm to obtain an area feature matrix; A reconstruction module 12, configured to reconstruct voltage quality scenarios of different load dimensions based on the result of partitioning the substation feature matrix by a clustering algorithm; An operation module 13 is used to obtain simulation operation results of the target substation under each voltage quality scenario, and generate each sensitivity matrix based on the power flow calculation results in the simulation operation results; A fitting module 14, configured to perform fitting processing on each of the sensitivity matrices using an extreme gradient boosting algorithm to obtain a voltage vector and a net load vector; A construction module 15 is used to construct a photovoltaic capacity assessment model with the goal of maximizing the photovoltaic capacity of the substation area and minimizing the network loss; The generation module 16 is used to obtain the voltage distribution result obtained by processing the voltage vector using the multivariate normal distribution assumption algorithm, and obtain the net load distribution result obtained by processing the net load vector using the multivariate normal distribution assumption algorithm, and obtain the photovoltaic capacity assessment result of the target substation based on the photovoltaic capacity assessment model under the constraints of the voltage distribution result and the net load distribution result.

[0056] The embodiment of the present invention provides a photovoltaic capacity assessment system for a substation, wherein the system processes the historical photovoltaic power generation data and load data of the target substation obtained by using a feature extraction model based on a deep learning algorithm to obtain a substation feature matrix; based on the result of dividing the substation feature matrix by a clustering algorithm, reconstructs voltage quality scenarios of different load dimensions; obtains simulation operation results of the target substation under each voltage quality scenario, and generates each sensitivity matrix based on the power flow calculation results in the simulation operation results; uses an extreme gradient boosting algorithm to fit each sensitivity matrix to obtain a voltage vector and a net load vector; constructs a photovoltaic capacity assessment model with the goal of maximizing the photovoltaic capacity of the substation and minimizing network loss; obtains a voltage distribution result obtained by processing the voltage vector by a multivariate normal distribution assumption algorithm, and obtains a net load distribution result obtained by processing the net load vector by the multivariate normal distribution assumption algorithm, and obtains a photovoltaic capacity assessment result of the target substation based on the photovoltaic capacity assessment model under the constraints of the voltage distribution result and the net load distribution result. Compared with the existing technology, this system combines the dynamic change characteristics of load and photovoltaic power generation, obtains the voltage vector and net load vector by fitting the sensitivity matrix using the extreme gradient boosting algorithm, and uses the multivariate normal distribution assumption algorithm to perform probability calculation on the voltage vector and the net load vector to obtain the distribution result. With the distribution result as a constraint, the constructed photovoltaic capacity assessment model is used to obtain accurate photovoltaic capacity assessment results, thereby ensuring the stability and safety of the power system.

[0057] See also Figure 3 , which is a structural block diagram of a photovoltaic capacity assessment device for a metropolitan area provided in an embodiment of the present invention. The photovoltaic capacity assessment device 20 for a metropolitan area provided in an embodiment of the present invention comprises a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, the steps in the above-mentioned metropolitan area photovoltaic capacity assessment method embodiment are implemented, for example Figure 1 or, the processor 21 implements the functions of each module in the above-mentioned device embodiments, such as the preprocessing module 11, when executing the computer program.

[0058] Exemplarily, the computer program can be divided into one or more modules, and the one or more modules are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the photovoltaic capacity assessment device 20 of the station area. For example, the computer program can be divided into a pre-processing module 11, a reconstruction module 12, an operation module 13, a fitting module 14, a construction module 15, and a generation module 16. The specific functions of each module are as follows: The preprocessing module 11 is used to process the acquired historical photovoltaic power generation data and load data of the target area using a feature extraction model based on a deep learning algorithm to obtain an area feature matrix; A reconstruction module 12, configured to reconstruct voltage quality scenarios of different load dimensions based on the result of partitioning the substation feature matrix by a clustering algorithm; An operation module 13 is used to obtain simulation operation results of the target substation under each voltage quality scenario, and generate each sensitivity matrix based on the power flow calculation results in the simulation operation results; A fitting module 14, configured to perform fitting processing on each of the sensitivity matrices using an extreme gradient boosting algorithm to obtain a voltage vector and a net load vector; A construction module 15 is used to construct a photovoltaic capacity assessment model with the goal of maximizing the photovoltaic capacity of the substation area and minimizing the network loss; The generation module 16 is used to obtain the voltage distribution result obtained by processing the voltage vector using the multivariate normal distribution assumption algorithm, and obtain the net load distribution result obtained by processing the net load vector using the multivariate normal distribution assumption algorithm, and obtain the photovoltaic capacity assessment result of the target substation based on the photovoltaic capacity assessment model under the constraints of the voltage distribution result and the net load distribution result.

[0059] The photovoltaic capacity assessment device 20 for the substation may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will appreciate that the schematic diagram is merely an example of the photovoltaic capacity assessment device for the substation, and does not constitute a limitation on the photovoltaic capacity assessment device 20 for the substation, and may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, the photovoltaic capacity assessment device 20 for the substation may also include input and output devices, network access devices, buses, and the like.

[0060] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, 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. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the photovoltaic capacity assessment device 20 in the substation, and uses various interfaces and lines to connect various parts of the photovoltaic capacity assessment device 20 in the substation.

[0061] The memory 22 can be used to store the computer program and / or module, and the processor 21 realizes various functions of the photovoltaic capacity assessment device 20 in the metropolitan area by running or executing the computer program and / or module stored in the memory 22, and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0062] Wherein, if the module integrated in the photovoltaic capacity assessment device 20 of the metro area 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 such an 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. Wherein, 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, etc. 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, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0063] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0064] Accordingly, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to perform the steps in the photovoltaic capacity assessment method of the above embodiment, for example Figure 1 Steps S1 to S6 described in .

[0065] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present invention, these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for evaluating photovoltaic capacity in a metropolitan area, characterized in that: include: The historical photovoltaic power generation data and load data of the target area are processed using a feature extraction model based on a deep learning algorithm to obtain the area feature matrix; Based on the result of partitioning the substation feature matrix by a clustering algorithm, voltage quality scenarios of different load dimensions are reconstructed; Acquire simulation results of the target substation under each voltage quality scenario, and generate each sensitivity matrix based on power flow calculation results in the simulation results; Using an extreme gradient boosting algorithm to fit each of the sensitivity matrices to obtain a voltage vector and a net load vector; With the goal of maximizing the photovoltaic capacity of the substation and minimizing network losses, a photovoltaic capacity assessment model is constructed; The voltage distribution result obtained by processing the voltage vector using a multivariate normal distribution assumption algorithm is obtained, and the net load distribution result obtained by processing the net load vector using the multivariate normal distribution assumption algorithm is obtained. Under the constraints of the voltage distribution result and the net load distribution result, a photovoltaic capacity assessment result of the target substation is obtained based on the photovoltaic capacity assessment model.

2. The photovoltaic capacity assessment method of claim 1, wherein: The feature extraction model based on the deep learning algorithm is used to process the historical photovoltaic power generation data and load data of the target area to obtain the area feature matrix, including: Acquire historical photovoltaic power generation data and load data of the target area, and introduce deep learning network parameters, wherein the network parameters include a weight matrix, a bias vector, and an activation function; Constructing a feature extraction model based on the weight matrix, the bias vector and the activation function; The feature extraction model is used to extract features from the historical photovoltaic power generation data and the load data to obtain a station feature matrix.

3. The photovoltaic capacity assessment method of claim 1, wherein: The voltage quality scenarios of different load dimensions are reconstructed based on the result of partitioning the substation feature matrix by a clustering algorithm, including: A neighborhood radius parameter and a minimum number of sample points in the neighborhood are introduced, and the clustering algorithm is used to divide the station area feature matrix to obtain a clustering result and a neighborhood distance; According to the neighborhood distance, performing robust average calculation on the clustering results to obtain a scale parameter; The scale parameters are used to reconstruct the substation characteristic matrix to obtain voltage quality scenarios of different load dimensions.

4. The photovoltaic capacity assessment method of claim 1, wherein: The obtaining of simulation results of the target substation in each voltage quality scenario and generating each sensitivity matrix based on power flow calculation results in the simulation results include: Constructing a power system simulation model of the target substation according to the power grid structure and operating conditions; Based on each of the voltage quality scenarios, obtaining various simulation operation results of the power system simulation model; Performing power flow calculation on each of the simulation operation results using the Gauss-Seidel method to obtain power flow calculation results; Based on the power flow calculation results, a sensitivity matrix is ​​obtained.

5. The photovoltaic capacity assessment method of claim 1, wherein: After the photovoltaic capacity assessment model is constructed, the photovoltaic capacity assessment method for the substation area further includes: Processing the voltage vector and the net load vector to obtain a power flow equation, and iteratively processing the power flow equation to obtain a Jacobian matrix; Expanding the Jacobian matrix to obtain a dynamic sensitivity matrix; Based on the dynamic sensitivity matrix and the sensitivity matrix, a sensitivity matrix deviation is obtained; Based on the sensitivity matrix deviation, the photovoltaic capacity assessment model is optimized.

6. The photovoltaic capacity assessment method of claim 1, wherein: Before obtaining the photovoltaic capacity evaluation result of the target area based on the photovoltaic capacity evaluation model, the photovoltaic capacity evaluation method of the area further includes: Performing sensitivity analysis on the voltage distribution result and the net load distribution result, and calculating the convergence of the photovoltaic capacity evaluation model; Based on the convergence of the photovoltaic capacity evaluation model, the photovoltaic capacity evaluation model is optimized.

7. The photovoltaic capacity assessment method of claim 1, wherein: After obtaining the photovoltaic capacity assessment result of the target area, the photovoltaic capacity assessment method of the area further includes: The photovoltaic capacity assessment result is processed using a natural language model to generate a natural language report, and the natural language report is sent to a corresponding client terminal for storage.

8. A photovoltaic capacity assessment system for a substation, characterized in that: include: A preprocessing module is used to process the historical photovoltaic power generation data and load data of the target area using a feature extraction model based on a deep learning algorithm to obtain an area feature matrix; A reconstruction module, used for reconstructing voltage quality scenarios of different load dimensions based on the result of partitioning the substation feature matrix by a clustering algorithm; An operation module, used for obtaining simulation operation results of the target substation under each voltage quality scenario, and generating each sensitivity matrix based on the power flow calculation results in the simulation operation results; A fitting module, used for fitting each sensitivity matrix using an extreme gradient boosting algorithm to obtain a voltage vector and a net load vector; A construction module is used to construct a photovoltaic capacity assessment model with the goal of maximizing the photovoltaic capacity of the substation and minimizing network losses; A generation module is used to obtain a voltage distribution result obtained by processing the voltage vector using a multivariate normal distribution assumption algorithm, and to obtain a net load distribution result obtained by processing the net load vector using the multivariate normal distribution assumption algorithm, and to obtain a photovoltaic capacity assessment result of the target substation based on the photovoltaic capacity assessment model under the constraints of the voltage distribution result and the net load distribution result.

9. A photovoltaic capacity assessment device for a station area, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the photovoltaic capacity assessment method for a metropolitan area as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the photovoltaic capacity assessment method for a substation as described in any one of claims 1 to 7 is implemented.

Images