A method and system for real-time assessment of new energy voltage support strength
By constructing an equivalent impedance matrix of the AC power grid and a hierarchical extraction network, the voltage support strength of new energy sources can be evaluated in real time. This solves the problem of large calculation error in the critical short-circuit ratio in existing technologies and achieves efficient and accurate voltage support strength evaluation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD
- Filing Date
- 2023-03-09
- Publication Date
- 2026-05-15
AI Technical Summary
Existing technologies for assessing the voltage support strength of new energy sources rely on critical short-circuit ratio calculation methods that are difficult to adapt to complex scenarios, resulting in large errors, low practicality, and difficulty in applying them to the high-order characteristic equations of actual power grids, leading to insufficient assessment accuracy.
By acquiring measurement data from multiple new energy power plants, an equivalent impedance matrix of the AC power grid is constructed, the short-circuit ratio is calculated, and a critical short-circuit ratio dataset is established. A hierarchical extraction network is used to train a prediction model, and target measurement data is acquired in real time to assess voltage support strength.
It enables efficient and accurate assessment of the voltage support strength of new energy sources under real-time conditions, has good applicability, is suitable for large-scale new energy grid-connected systems, and has engineering application value.
Smart Images
Figure CN116523367B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of large power grid stability analysis and control application technology, and more specifically, to a method and system for real-time evaluation of the voltage support strength of new energy sources. Background Technology
[0002] With the continuous increase in the installed capacity of new energy units such as wind power and photovoltaic power in my country, the voltage support capacity of the AC main grid for new energy grid connection points has significantly weakened. This has resulted in limitations on the energy transmission scale of large-scale new energy bases, and voltage stability issues are prone to occur at the grid connection points during faults. Therefore, an accurate voltage support strength assessment method is of great significance for ensuring the stable operation of the power system and solving the problem of limited new energy transmission scale.
[0003] Voltage support strength is typically assessed using quantitative indicators and stability criteria. Among numerous quantitative indicators, the short-circuit ratio is widely used due to its clear physical meaning and simple calculation method. This indicator uses the critical short-circuit ratio as a stability criterion to complete the voltage support strength assessment. Based on different calculation methods for the critical short-circuit ratio, short-circuit ratios applicable to assessing the scale of new energy grid integration are divided into two categories: 1) setting empirical values as the critical short-circuit ratio based on engineering experience; 2) constructing short-circuit ratios with clearly defined thresholds based on voltage stability conditions, thereby providing a theoretically grounded calculation method.
[0004] However, setting a fixed critical short-circuit ratio based on engineering experience is difficult to adapt to complex scenarios, while theoretically based calculation methods rely on numerous assumptions. Once these assumptions are removed, the practicality of these methods may decrease. Furthermore, these calculation methods are difficult to apply to the high-order characteristic equations of actual power grids, easily leading to the "curse of dimensionality." Therefore, errors in the calculation of the critical short-circuit ratio will result in low assessment accuracy, necessitating the development of an intelligent enhancement method to improve the accuracy of the voltage support strength index. Summary of the Invention
[0005] To address the above problems, this invention proposes a method for real-time evaluation of the voltage support strength of new energy sources, comprising:
[0006] Acquire measurement data of multiple new energy power plants, construct an equivalent impedance matrix of the AC power grid connected to the grid from the multiple new energy power plants based on the measurement data, and calculate the short-circuit ratio of the multiple new energy power plants based on the equivalent impedance matrix of the AC power grid.
[0007] Based on the calculated short-circuit ratio of multiple new energy power stations, the critical short-circuit ratio of multiple new energy power stations is determined, and a dataset of the critical short-circuit ratio of multiple new energy power stations is established.
[0008] The dataset is divided into a training set and a test set according to a preset ratio, and then input into a pre-built hierarchical extraction network for training to obtain a prediction model.
[0009] Real-time target measurement data of multiple new energy power stations is acquired, and the target measurement data is input into a prediction model for calculation to obtain the real-time critical short-circuit ratio of the multiple new energy power stations. The real-time short-circuit ratio of the target measurement data is also acquired. Based on the difference between the real-time short-circuit ratio and the real-time critical short-circuit ratio, the voltage support strength of the new energy is evaluated in real time.
[0010] Optional measurement data and target measurement data include: the current injected into the AC system at the busbar of the new energy multi-site grid connection point and the busbar node voltage at the grid connection point.
[0011] Optionally, the formula for calculating the short-circuit ratio of multiple new energy power stations is as follows:
[0012]
[0013] Among them, MRSCR i For the short-circuit ratio of multiple new energy power stations, Let be the nominal voltage of the i-th grid-connected bus node. Let be the voltage generated by the new energy source at the i-th node. The apparent power injected into the bus node of the i-th renewable energy grid connection point. and are the conjugate values of the operating voltages of the bus nodes at the i-th and j-th grid connection points, respectively, where n is the number of grid connection points. The element in the i-th row and i-th column of the equivalent impedance matrix of an AC power grid is... is the element in the i-th row and j-th column of the equivalent impedance matrix of the AC power grid.
[0014] Optionally, determining the critical short-circuit ratio of multiple renewable energy power plants includes: randomly dividing the active power of multiple power plants according to the total power of renewable energy to obtain the initial power flow state; tracking the power / voltage curve based on the initial power flow state to obtain the maximum transmittable power at the grid connection point of the multiple renewable energy power plants; and determining the critical short-circuit ratio of the multiple renewable energy power plants based on the maximum transmittable power and the multiple renewable energy power plants.
[0015] Optionally, the dataset is divided into a training set and a test set according to a preset ratio, and input into a pre-built hierarchical extraction network for training to obtain a prediction model, including:
[0016] The training set is input into a pre-constructed hierarchical extraction network to extract electrical features and construct a mapping relationship between electrical features and critical short-circuit ratio to build an initial prediction model. The test set is input into the initial prediction model for testing, and the hyperparameters of the initial prediction model are adjusted based on the test results to obtain the prediction model.
[0017] Furthermore, this invention also proposes a system for real-time evaluation of the voltage support strength of new energy sources, comprising:
[0018] The measurement unit is used to acquire measurement data of multiple new energy power plants, construct the equivalent impedance matrix of the AC power grid connected to the grid of the multiple new energy power plants based on the measurement data, and calculate the short-circuit ratio of the multiple new energy power plants based on the equivalent impedance matrix of the AC power grid.
[0019] The calculation unit is used to determine the critical short-circuit ratio of the new energy multi-power station based on the calculated short-circuit ratio, and to establish a dataset of the critical short-circuit ratio of the new energy multi-power station.
[0020] The training unit is used to divide the dataset into a training set and a test set according to a preset ratio, and input them into a pre-built hierarchical extraction network for training to obtain a prediction model.
[0021] The evaluation unit is used to acquire target measurement data of multiple new energy power stations in real time, input the target measurement data into the prediction model for calculation to obtain the real-time critical short-circuit ratio of the multiple new energy power stations, and acquire the real-time short-circuit ratio of the target measurement data. Based on the difference between the real-time short-circuit ratio and the real-time critical short-circuit ratio, the voltage support strength of the new energy is evaluated in real time.
[0022] Optional measurement data and target measurement data include: the current injected into the AC system at the busbar of the new energy multi-site grid connection point and the busbar node voltage at the grid connection point.
[0023] Optionally, the formula for calculating the short-circuit ratio of multiple new energy power stations is as follows:
[0024]
[0025] Among them, MRSCR i For the short-circuit ratio of multiple new energy power stations, Let be the nominal voltage of the i-th grid-connected bus node. Let be the voltage generated by the new energy source at the i-th node. The apparent power injected into the bus node of the i-th renewable energy grid connection point. and are the conjugate values of the operating voltages of the bus nodes at the i-th and j-th grid connection points, respectively, where n is the number of grid connection points. The element in the i-th row and i-th column of the equivalent impedance matrix of an AC power grid is... is the element in the i-th row and j-th column of the equivalent impedance matrix of the AC power grid.
[0026] Optionally, determining the critical short-circuit ratio of multiple renewable energy power plants includes: randomly dividing the active power of multiple power plants according to the total power of renewable energy to obtain the initial power flow state; tracking the power / voltage curve based on the initial power flow state to obtain the maximum transmittable power at the grid connection point of the multiple renewable energy power plants; and determining the critical short-circuit ratio of the multiple renewable energy power plants based on the maximum transmittable power and the multiple renewable energy power plants.
[0027] Optionally, the dataset is divided into a training set and a test set according to a preset ratio, and input into a pre-built hierarchical extraction network for training to obtain a prediction model, including:
[0028] The training set is input into a pre-constructed hierarchical extraction network to extract electrical features and construct a mapping relationship between electrical features and critical short-circuit ratio to build an initial prediction model. The test set is input into the initial prediction model for testing, and the hyperparameters of the initial prediction model are adjusted based on the test results to obtain the prediction model.
[0029] In another aspect, the present invention also provides a computing device, comprising: one or more processors;
[0030] A processor is used to execute one or more programs;
[0031] When the one or more programs are executed by the one or more processors, the method described above is implemented.
[0032] In another aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the method described above.
[0033] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0034] This invention provides a method for real-time assessment of the voltage support strength of renewable energy sources, comprising: acquiring measurement data of multiple renewable energy power stations; constructing an equivalent impedance matrix of the AC power grid output from the renewable energy power stations based on the measurement data; calculating the short-circuit ratio of the renewable energy power stations based on the equivalent impedance matrix of the AC power grid; determining the critical short-circuit ratio of the renewable energy power stations based on the calculated short-circuit ratio, and establishing a dataset of the critical short-circuit ratio of the renewable energy power stations; dividing the dataset into a training set and a test set according to a preset ratio, and inputting them into a pre-constructed hierarchical extraction network for training to obtain a prediction model; acquiring target measurement data of the renewable energy power stations in real time, inputting the target measurement data into the prediction model for calculation to obtain the real-time critical short-circuit ratio of the renewable energy power stations, and acquiring the real-time short-circuit ratio of the target measurement data; and assessing the voltage support strength of renewable energy sources in real time based on the difference between the real-time short-circuit ratio and the real-time critical short-circuit ratio. This invention only requires real-time measurement of real-time data from multiple renewable energy power stations to assess the voltage support strength of renewable energy sources in real time, has good applicability, and has engineering application value. Attached Figure Description
[0035] Figure 1 This is a flowchart of the method of the present invention;
[0036] Figure 2 This is a structural diagram of the system of the present invention. Detailed Implementation
[0037] Exemplary embodiments of the invention will now be described with reference to the accompanying drawings. However, the invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to fully and completely disclose the invention and to fully convey its scope to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the drawings is not intended to limit the invention. In the drawings, the same units / elements are referred to by the same reference numerals.
[0038] Unless otherwise stated, the terms used herein (including technical terms) have their common meaning as understood by one of ordinary skill in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have a meaning consistent with the context of their relevant field, and not to be interpreted as having an idealized or overly formal meaning.
[0039] Example 1:
[0040] This invention proposes a method for real-time evaluation of the voltage support strength of new energy sources, such as... Figure 1 As shown, it includes:
[0041] Step 1: Obtain measurement data of multiple new energy power plants, construct the equivalent impedance matrix of the AC power grid connected to the grid of the multiple new energy power plants based on the measurement data, and calculate the short-circuit ratio of the multiple new energy power plants based on the equivalent impedance matrix of the AC power grid.
[0042] Step 2: Based on the calculated short-circuit ratio of the new energy multi-power station, determine the critical short-circuit ratio of the new energy multi-power station and establish a dataset of the critical short-circuit ratio of the new energy multi-power station.
[0043] Step 3: Divide the dataset into training and testing sets according to a preset ratio, and input them into a pre-built hierarchical extraction network for training to obtain a prediction model;
[0044] Step 4: Acquire target measurement data of multiple new energy power stations in real time, input the target measurement data into the prediction model for calculation to obtain the real-time critical short-circuit ratio of the multiple new energy power stations, and obtain the real-time short-circuit ratio of the target measurement data. Based on the difference between the real-time short-circuit ratio and the real-time critical short-circuit ratio, evaluate the voltage support strength of the new energy in real time.
[0045] Optional measurement data and target measurement data include: the current injected into the AC system at the busbar of the new energy multi-site grid connection point and the busbar node voltage at the grid connection point.
[0046] Optionally, the formula for calculating the short-circuit ratio of multiple new energy power stations is as follows:
[0047]
[0048] Among them, MRSCR i For the short-circuit ratio of multiple new energy power stations, Let be the nominal voltage of the i-th grid-connected bus node. Let be the voltage generated by the new energy source at the i-th node. The apparent power injected into the bus node of the i-th renewable energy grid connection point. and are the conjugate values of the operating voltages of the bus nodes at the i-th and j-th grid connection points, respectively, where n is the number of grid connection points. The element in the i-th row and i-th column of the equivalent impedance matrix of an AC power grid is... is the element in the i-th row and j-th column of the equivalent impedance matrix of the AC power grid.
[0049] Optionally, determining the critical short-circuit ratio of multiple renewable energy power plants includes: randomly dividing the active power of multiple power plants according to the total power of renewable energy to obtain the initial power flow state; tracking the power / voltage curve based on the initial power flow state to obtain the maximum transmittable power at the grid connection point of the multiple renewable energy power plants; and determining the critical short-circuit ratio of the multiple renewable energy power plants based on the maximum transmittable power and the multiple renewable energy power plants.
[0050] Optionally, the dataset is divided into a training set and a test set according to a preset ratio, and input into a pre-built hierarchical extraction network for training to obtain a prediction model, including:
[0051] The training set is input into a pre-constructed hierarchical extraction network to extract electrical features and construct a mapping relationship between electrical features and critical short-circuit ratio to build an initial prediction model. The test set is input into the initial prediction model for testing, and the hyperparameters of the initial prediction model are adjusted based on the test results to obtain the prediction model.
[0052] The invention will be further described below with reference to specific implementations:
[0053] Step 1: Calculation of the short-circuit ratio of multiple new energy power stations;
[0054] Let the current injected into the AC system by the busbars of each new energy grid connection point be respectively The bus node voltages at each grid connection point can be expressed as:
[0055]
[0056] In equation (1), Let be the element in the i-th row and j-th column of the AC grid equivalent impedance matrix at the point of renewable energy grid connection.
[0057]
[0058] In equation (2), The nominal voltage of the i-th grid-connected bus node; Let be the voltage generated by the new energy source at the i-th node; Apparent power injected into the bus node of the i-th renewable energy grid connection point.
[0059] The voltage amplitude and phase angle, active power and reactive power of the new energy power generation equipment access point / grid connection point of the whole network are obtained by using the measuring device, and the short circuit ratio and critical short circuit ratio of the new energy multi-site are calculated in real time according to the formula (2).
[0060] Step 2: Constructing the critical short-circuit ratio dataset;
[0061] The steps for constructing the critical short-circuit ratio dataset are as follows: 1) Randomly divide the active power of each power station according to the total power of new energy sources to obtain the initial power flow state of the system; 2) To obtain the maximum transmittable power at the grid connection point, repeatedly use the continuous power flow method to track the power-voltage curve. First, select a certain new energy power station and make its active power grow according to a constant power factor, where the surplus power is absorbed by the generators of the balancing node. Then, track the steady-state behavior of the system under power change conditions until it approaches the maximum transmittable power of the corresponding grid connection point; 3) Calculate the critical short-circuit ratio of each grid connection point as a prediction label according to the calculation formula of the maximum transmittable power and the short-circuit ratio of multiple new energy power stations, and extract the electrical features under the current initial power flow state as input features; 4) Repeat steps 1-3 according to the required number of samples to obtain a large number of static voltage stability critical point sets. The point sets constitute the static voltage stability domain boundary of each grid connection point. To facilitate the storage of the dataset, the input features and prediction labels of all samples are merged into a two-dimensional array.
[0062] Considering the complex and diverse ways in which the active power of multiple renewable energy power plants can increase simultaneously, step 2 obtains a relatively conservative critical short-circuit ratio by simulating the active power growth of a single power plant.
[0063] Step 3: Construction of the progressive hierarchical extraction network;
[0064] Progressive layered extraction (PLE) is a multi-task model based on a hard parameter sharing mechanism, consisting of a bottom-level sharing network, an expert network, a gating network, and a tower network. The construction steps of this network are as follows:
[0065] 1) Construct an extraction network layer consisting of a shared network and different expert networks based on the number of network connection points. Both the shared network and the expert networks consist of multiple sub-networks. By setting up a multi-layer extraction network, deeper feature extraction can be achieved.
[0066] 2) Input features are first extracted by a shared network and an expert network. Then, a gated network selectively fuses the extracted features. The gated network is a single-layer feedforward network, where V represents the input vector. The output formula of the gated network for task k is:
[0067] g k (x)=w k (x)S k (x) (3)
[0068] Where x is the input, w k (x) is the weighting function for the k-th task:
[0069]
[0070] in, Let S be the parameter matrix. k (x) is a selected matrix consisting of the outputs of the shared network and the expert network for task k:
[0071]
[0072] 3) The output of the gating network enters each tower network to obtain the predicted output of each grid connection point. The calculation method of the tower network is as follows:
[0073] y k (x)=t k (g k (x)) (6)
[0074] Where t k For task k, there is a tower network.
[0075] This invention uses the CEPRI-102 node system as the test system, which has 6 wind farms and 6 photovoltaic farms, denoted as Wi and Pi respectively. A critical short-circuit ratio dataset containing 10,000 samples is constructed, and the distribution of the labels is statistically analyzed.
[0076] To verify the effectiveness of PLE, this invention selects single-task learning (STL), bottom-shared, one-gate mixture-of-experts (OMOE), and multi-gate mixture-of-experts (MMOE) as comparison models. STL uses a deep neural network as its base model. Bottom-Shared is a traditional MTL model, consisting of a shared network and a tower network. Based on bottom-shared, OMOE and MMOE transform the shared network into multiple expert networks and introduce gating units to capture task differences. The network structure of the basic STL model is 512-256-128-64-1.
[0077] To comprehensively evaluate the predictive performance of each model, mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and the coefficient of fit (R-squared, R²) were selected as error metrics. The formulas for calculating these metrics are as follows:
[0078]
[0079]
[0080]
[0081]
[0082] Among them, y i For the true value, For predicted values, For y i The average value.
[0083] The critical short-circuit ratio dataset was divided into a training set (80%) and a test set (20%). The average of 20 experimental results was used as the final result. The final result showed that PLE had better balance among grid-connected points, and all error indicators were at a high level, verifying the effectiveness of the invention. To verify the advantages of the invention in terms of time cost, the time costs of each method were statistically analyzed, as shown in Table 1. In Table 1, offline simulation requires repeated calls to the continuous power flow method, making it difficult to meet the real-time evaluation requirements. STL, on the other hand, relies on an accumulating model, resulting in heavy training costs. Especially when the scale of new energy sources in the system continues to expand, the time costs of both methods will further increase. Obviously, MTL has significantly better time costs in model training and prediction than STL and offline simulation, verifying the effectiveness of the invention.
[0084] Table 1 Comparison of Time Costs of the Models
[0085]
[0086] Example 2:
[0087] This invention also proposes a system 200 for real-time evaluation of the voltage support strength of new energy sources, such as... Figure 2 As shown, it includes:
[0088] Measurement unit 201 is used to acquire measurement data of multiple new energy power plants, construct an equivalent impedance matrix of the AC power grid connected to the grid of the multiple new energy power plants based on the measurement data, and calculate the short-circuit ratio of the multiple new energy power plants based on the equivalent impedance matrix of the AC power grid.
[0089] The calculation unit 202 is used to determine the critical short-circuit ratio of the new energy multi-power station based on the calculated short-circuit ratio, and to establish a dataset of the critical short-circuit ratio of the new energy multi-power station.
[0090] Training unit 203 is used to divide the dataset into training set and test set according to a preset ratio, and input them into a pre-built hierarchical extraction network for training to obtain a prediction model;
[0091] The evaluation unit 204 is used to acquire target measurement data of multiple new energy power stations in real time, input the target measurement data into the prediction model for calculation to obtain the real-time critical short-circuit ratio of the multiple new energy power stations, and acquire the real-time short-circuit ratio of the target measurement data. Based on the difference between the real-time short-circuit ratio and the real-time critical short-circuit ratio, the voltage support strength of the new energy is evaluated in real time.
[0092] Among them, the measurement data and target measurement data include: the current injected into the AC system by the busbar at the grid connection point of the new energy multi-site grid connection point and the busbar node voltage at the grid connection point.
[0093] The formula for calculating the short-circuit ratio of multiple new energy power stations is as follows:
[0094]
[0095] Among them, MRSCR i For the short-circuit ratio of multiple new energy power stations, Let be the nominal voltage of the i-th grid-connected bus node. Let be the voltage generated by the new energy source at the i-th node. The apparent power injected into the bus node of the i-th renewable energy grid connection point. and are the conjugate values of the operating voltages of the bus nodes at the i-th and j-th grid connection points, respectively, where n is the number of grid connection points. The element in the i-th row and i-th column of the equivalent impedance matrix of an AC power grid is... is the element in the i-th row and j-th column of the equivalent impedance matrix of the AC power grid.
[0096] The determination of the critical short-circuit ratio of multiple renewable energy power plants includes: randomly dividing the active power of multiple power plants according to the total power of renewable energy to obtain the initial power flow state; tracking the power / voltage curve based on the initial power flow state to obtain the maximum transmittable power at the grid connection point of the multiple renewable energy power plants; and determining the critical short-circuit ratio of the multiple renewable energy power plants based on the maximum transmittable power and the multiple renewable energy power plants.
[0097] The dataset is divided into training and testing sets according to a preset ratio, and then input into a pre-constructed hierarchical extraction network for training to obtain a prediction model, including:
[0098] The training set is input into a pre-constructed hierarchical extraction network to extract electrical features and construct a mapping relationship between electrical features and critical short-circuit ratio to build an initial prediction model. The test set is input into the initial prediction model for testing, and the hyperparameters of the initial prediction model are adjusted based on the test results to obtain the prediction model.
[0099] Example 3:
[0100] Based on the same inventive concept, this invention also provides a computer device, which includes a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, 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. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to implement corresponding method flows or corresponding functions, thereby implementing the steps of the methods in the above embodiments.
[0101] Example 4:
[0102] Based on the same inventive concept, this invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of the method in the above embodiments.
[0103] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.
[0104] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0106] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0107] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.
[0108] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.
Claims
1. A method for real-time evaluation of the voltage support strength of new energy sources, characterized in that, The method includes: Acquire measurement data of multiple new energy power plants, construct an equivalent impedance matrix of the AC power grid connected to the grid from the multiple new energy power plants based on the measurement data, and calculate the short-circuit ratio of the multiple new energy power plants based on the equivalent impedance matrix of the AC power grid. Based on the calculated short-circuit ratio of multiple new energy power stations, the critical short-circuit ratio of multiple new energy power stations is determined, and a dataset of the critical short-circuit ratio of multiple new energy power stations is established. The dataset is divided into a training set and a test set according to a preset ratio, and then input into a pre-built hierarchical extraction network for training to obtain a prediction model. Real-time target measurement data of multiple new energy power stations is acquired, and the target measurement data is input into the prediction model for calculation to obtain the real-time critical short-circuit ratio of the multiple new energy power stations. The real-time short-circuit ratio of the target measurement data is also acquired. Based on the difference between the real-time short-circuit ratio and the real-time critical short-circuit ratio, the voltage support strength of the new energy is evaluated in real time. The formula for calculating the short-circuit ratio of multiple new energy power stations is as follows: in, For the short-circuit ratio of multiple new energy power stations, For the first The nominal voltage of each grid-connected bus node For new energy in the first The voltage generated at each node For the first Apparent power injected into the bus node of each new energy grid connection point and The first The and the first The conjugate value of the operating voltage of each grid-connected bus node. For the number of grid connection points, The first is the equivalent impedance matrix of the AC power grid. OK, Column elements, The first is the equivalent impedance matrix of the AC power grid. OK, Column elements; The determination of the critical short-circuit ratio of multiple new energy power plants includes: randomly dividing the active power of multiple power plants according to the total power of new energy to obtain the initial power flow state; tracking the power / voltage curve based on the initial power flow state to obtain the maximum transmittable power at the grid connection point of the multiple new energy power plants; and determining the critical short-circuit ratio of the multiple new energy power plants based on the maximum transmittable power and the multiple new energy power plants. The dataset is divided into training and testing sets according to a preset ratio, and then input into a pre-built hierarchical extraction network for training to obtain a prediction model, including: The training set is input into a pre-constructed hierarchical extraction network to extract electrical features and construct a mapping relationship between electrical features and critical short-circuit ratio to build an initial prediction model. The test set is input into the initial prediction model for testing, and the hyperparameters of the initial prediction model are adjusted based on the test results to obtain the prediction model.
2. The method according to claim 1, characterized in that, The measurement data and target measurement data include: the current injected into the AC system at the busbar of the new energy multi-site grid connection point and the busbar node voltage at the grid connection point.
3. A system for real-time assessment of the voltage support strength of new energy sources, characterized in that, The system includes: The measurement unit is used to acquire measurement data of multiple new energy power plants, construct the equivalent impedance matrix of the AC power grid connected to the grid of the multiple new energy power plants based on the measurement data, and calculate the short-circuit ratio of the multiple new energy power plants based on the equivalent impedance matrix of the AC power grid. The calculation unit is used to determine the critical short-circuit ratio of the new energy multi-power station based on the calculated short-circuit ratio, and to establish a dataset of the critical short-circuit ratio of the new energy multi-power station. The training unit is used to divide the dataset into a training set and a test set according to a preset ratio, and input them into a pre-built hierarchical extraction network for training to obtain a prediction model. The evaluation unit is used to acquire target measurement data of multiple new energy power stations in real time, input the target measurement data into the prediction model for calculation to obtain the real-time critical short-circuit ratio of the multiple new energy power stations, and acquire the real-time short-circuit ratio of the target measurement data. Based on the difference between the real-time short-circuit ratio and the real-time critical short-circuit ratio, the voltage support strength of the new energy is evaluated in real time. The formula for calculating the short-circuit ratio of multiple new energy power stations is as follows: in, For the short-circuit ratio of multiple new energy power stations, For the first The nominal voltage of each grid-connected bus node For new energy in the first The voltage generated at each node For the first Apparent power injected into the bus node of each new energy grid connection point and The first The and the first The conjugate value of the operating voltage of each grid-connected bus node. For the number of grid connection points, The first is the equivalent impedance matrix of the AC power grid. OK, Column elements, The first is the equivalent impedance matrix of the AC power grid. OK, Column elements; The determination of the critical short-circuit ratio of multiple new energy power plants includes: randomly dividing the active power of multiple power plants according to the total power of new energy to obtain the initial power flow state; tracking the power / voltage curve based on the initial power flow state to obtain the maximum transmittable power at the grid connection point of the multiple new energy power plants; and determining the critical short-circuit ratio of the multiple new energy power plants based on the maximum transmittable power and the multiple new energy power plants. The dataset is divided into training and testing sets according to a preset ratio, and then input into a pre-built hierarchical extraction network for training to obtain a prediction model, including: The training set is input into a pre-constructed hierarchical extraction network to extract electrical features and construct a mapping relationship between electrical features and critical short-circuit ratio to build an initial prediction model. The test set is input into the initial prediction model for testing, and the hyperparameters of the initial prediction model are adjusted based on the test results to obtain the prediction model.
4. The system according to claim 3, characterized in that, The measurement data and target measurement data include: the current injected into the AC system at the busbar of the new energy multi-site grid connection point and the busbar node voltage at the grid connection point.
5. A computer device, characterized in that, include: One or more processors; A processor is used to execute one or more programs; When the one or more programs are executed by the one or more processors, the method described in any one of claims 1-2 is implemented.
6. A computer-readable storage medium, characterized in that, It contains a computer program, which, when executed, implements the method as described in any one of claims 1-2.