Power grid adaptability test method and system for wind power storage station

Abstract

The embodiment of the invention discloses a wind power storage station power grid adaptability test method and system, and the method comprises the following steps: building an initial test model of a wind power storage station, carrying out the power grid adaptability test of the initial test model, and obtaining first model index data; parameters of the initial test model are adjusted until simulation index data obtained according to the current test model meet preset conditions, and a finally adjusted target test model is obtained; for the target test model, obtaining second model index data; and mapping the second model index data, and inputting the mapped data into a quantum support vector machine algorithm model to obtain a classification result of the power grid adaptability of the wind power storage station, the classification result being one of excellent, good, qualified and unqualified. According to the method, the influence of inaccurate parameters on the credibility of a simulation result when a simulation model is directly adopted to carry out a power grid adaptability test is avoided, and the credibility of the simulation result is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of grid adaptability testing, and in particular, to a method and system for testing the grid adaptability of a wind power storage power station. Background Art

[0002] With the continuous increase in the demand for energy in modern society, wind power generation in China is in a rapid development stage. Most of the already built or under-construction ten-million-kilowatt-level wind power bases are located at the end of the power grid. The grid structure is not strong enough and the power source structure is relatively single. The large-scale access of wind power and the volatility of the wind bring great pressure to the stable operation of the power grid in these areas. As the scale of the wind farm expands, the requirements for wind turbines to adapt to the grid fluctuations are getting higher and higher. Therefore, it is necessary to accurately test the grid adaptability. Grid adaptability testing is to simulate the grid environment from aspects such as voltage, frequency, and flicker, and analyze the performance of the wind power storage power station's adaptability to it to determine whether the wind power storage power station can complete an important link in the grid connection test.

[0003] The grid adaptability of traditional wind turbines usually only conducts modeling and simulation for the power grid system, without comprehensively considering the influence of the wind power part of the wind power storage power station; moreover, when using a simulation model for grid adaptability testing, there are errors or uncertainties in obtaining some parameters in the model, such as parameter changes caused by equipment aging, some parameters that are difficult to accurately measure, etc., which inaccurately affect the credibility of the simulation results. Summary of the Invention

[0004] In order to overcome the deficiencies of the prior art, the purpose of the embodiments of the present invention is to provide a method and system for testing the grid adaptability of a wind power storage power station, an electronic device, and a storage medium, which avoid the influence of errors or uncertainties in obtaining some parameters in the model on the credibility of the simulation results when directly using a simulation model for grid adaptability testing, and can more efficiently complete grid adaptability classification.

[0005] To solve the above problems, the first aspect of the embodiments of the present invention discloses a method for testing the grid adaptability of a wind power storage power station, which includes the following steps: Establish an initial test model of the wind power storage power station, conduct grid adaptability testing on the initial test model, and obtain first model index data; the initial test model includes a wind power model, an energy storage model, and a power grid model; Adjust the parameters of the initial test model according to the first simulation index data until the simulation index data obtained according to the current test model meets the preset conditions, and obtain the finally adjusted target test model; Conduct grid adaptability testing on the target test model to obtain second model index data; Map the second model index data, and input the mapped data into the quantum support vector machine algorithm model to obtain the classification result of the grid adaptability of the wind power storage power station. The classification result is one of excellent, good, qualified, and unqualified.

[0006] Further, adjusting the parameters of the initial test model according to the first simulation index data until the simulation index data obtained according to the current test model meets the preset conditions includes: The preset condition is that the average difference between the first set of eigenvalue corresponding to the simulation index data and the second set of eigenvalue corresponding to the actual index data is less than or equal to the difference threshold; Obtain the actual index data of the on-site test of the wind power storage power station to be measured, extract the third set of eigenvalue of the first model index data and the second set of eigenvalue of the actual test index data respectively according to the preset algorithm, compare the average difference between the third set of eigenvalue and the second set of eigenvalue. If the average difference is greater than the difference threshold, perform multiple iterative processes on the parameters of the test model until the simulation index data obtained according to the current test model meets the preset conditions.

[0007] Further, extracting the third set of eigenvalue of the first model index data and the second set of eigenvalue of the actual test index data respectively according to the preset algorithm, and comparing the average difference between the third set of eigenvalue and the second set of eigenvalue includes: Use the RBM algorithm to extract the third set of eigenvalue of the first model index data to obtain the first eigenvector , , use the RBM algorithm to extract the second set of eigenvalue of the actual test index data to obtain the second eigenvector , , calculate the mean vector of the two sets of eigenvectors in each dimension and , and take the Euclidean distance between the mean vectors and as the average difference between the third set of eigenvalue and the second set of eigenvalue. The average difference D satisfies the following formula ; ; ; where is the mean of the first eigenvector in the k-th dimension, is the mean of the second eigenvector in the k-th dimension, and d, k, n, and m are all natural numbers.

[0008] Further, establishing the initial test model of the wind power storage power station includes: Establish a wind power model according to the type of wind turbine; establish an energy storage model according to the energy storage device of the wind power storage power station; establish a power grid model according to the topological structure, line parameters, and transformer parameters of the power grid.

[0009] Furthermore, the first model index data includes power-related index data, voltage-related index data, frequency-related index data, and power quality index data; the power grid adaptability test includes voltage fluctuation test, frequency change test, fault ride-through test, power regulation test, and energy management test.

[0010] Furthermore, mapping the second model index data, and inputting the mapped data into the quantum support vector machine algorithm model to obtain the classification result of the wind power storage power station's power grid adaptability, including: Map the second model index data into a quantum state through quantum coding; Use the actual test index data as training sample data, train the quantum support vector machine through the training sample data, construct a Lagrangian function, and determine the optimal separation hyperplane in the feature space; Calculate the kernel matrix between the second model index data and the sample data using the quantum kernel function, and each element in the kernel matrix represents the similarity of the corresponding data under the quantum kernel function; Input the kernel matrix into the quantum support vector machine for classification to obtain the classification result of the wind power storage power station's power grid adaptability.

[0011] Furthermore, mapping the second model index data into a quantum state through quantum coding includes: performing normalization processing on the second model index data, encoding the normalized data using amplitude coding to construct a quantum state, and the quantum state , where is a quantum state composed of quantum bits, , is the i-th data in the second model index data, 1 < i < m, both i and m are natural numbers, and the quantum kernel function uses a Gaussian kernel function. is the i-th data in the second model index data, 1 < i < m, both i and m are natural numbers, and the quantum kernel function uses a Gaussian kernel function.

[0012] The second aspect of the embodiments of the present invention discloses a wind power storage power station power grid adaptability test system, and the system includes: Initial model acquisition unit: used to establish an initial test model of the wind power storage power station, perform a power grid adaptability test on the initial test model, and obtain the first model index data; the initial test model includes a wind power model, an energy storage model, and a power grid model; An adjustment unit for adjusting the parameters of the initial test model according to the first simulation index data until the simulation index data obtained from the current test model meets the preset conditions, and obtaining the target test model after final adjustment; A target data acquisition unit for performing a grid adaptability test on the target test model to obtain second model index data; A classification unit for mapping the second model index data, inputting the mapped data into a quantum support vector machine algorithm model, and obtaining a classification result of the grid adaptability of the wind power storage power station, where the classification result is one of excellent, good, qualified, and unqualified.

[0013] A third aspect of the embodiments of the present invention discloses an electronic device, which includes: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the wind power storage power station grid adaptability test method disclosed in the first aspect of the embodiments of the present invention.

[0014] A fourth aspect of the embodiments of the present invention discloses a computer-readable storage medium storing a computer program, where the computer program causes a computer to execute the wind power storage power station grid adaptability test method disclosed in the first aspect of the embodiments of the present invention.

[0015] Compared with the prior art, the beneficial effects of the embodiments of the present invention are as follows: The method of the present invention establishes a wind power model, a energy storage model, and grid model data for the wind power storage power station grid. After adjusting the established wind power model, energy storage model, and grid model data, the adjusted wind power model, energy storage model, and grid model are used as adaptability test data, and the adaptability test data is input into a quantum support vector machine algorithm model to obtain a classification result of the grid adaptability of the wind power storage power station. The present invention performs a grid adaptability test through a target test model. Compared with directly using on-site grid adaptability tests where the on-site environment is complex and changeable and factors such as wind speed, temperature, and humidity cannot be precisely controlled and adjusted, precise control and adjustment can be performed, and at the same time, it avoids the situation where when directly using a simulation model for grid adaptability tests, some parameters in the model have errors or uncertainties, such as parameter changes caused by equipment aging and some parameters that are difficult to accurately measure, which affect the credibility of the simulation results. This improves the credibility of the simulation results. At the same time, using a quantum support vector machine algorithm model for grid adaptability test classification can show obvious performance advantages when dealing with a large amount of grid data and complex grid models, which helps to improve the overall efficiency and real-time performance of grid tests, can complete classification more efficiently, and is conducive to promoting the intelligent and modern development of the grid. Description of the Drawings

[0016] Figure 1 It is a schematic flow chart of a method for testing the grid adaptability of a wind power storage power station provided by an embodiment of the present invention; Figure 2 It is a schematic structural diagram of a system for testing the grid adaptability of a wind power storage power station provided by an embodiment of the present invention; Figure 3 It is a schematic structural diagram of an electronic device disclosed by an embodiment of the present invention. Detailed implementation manners

[0017] This detailed implementation manner is only an explanation of the embodiments of the present invention, and it does not limit the embodiments of the present invention. Those skilled in the art can make modifications without creative contributions to this embodiment as needed after reading this specification, but as long as they are within the scope of the claims of the embodiments of the present invention, they are protected by the patent law.

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts fall within the scope of protection of the embodiments of the present invention.

[0019] The term "including" and any variation thereof in the specification and claims of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0020] In the embodiments of the present invention, words such as "exemplary" or "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner. Embodiment

[0021] Please refer to Figure 1 as shown, a method for testing the grid adaptability of a wind power storage power station, as Figure 1 shown, includes the following steps: Step S1: Establish an initial test model of the wind power storage power station, conduct grid adaptability testing on the initial test model, and obtain first model index data; the initial test model includes a wind power model, an energy storage model, and a power grid model; Specifically, the initial test model for establishing a wind power storage power station includes: Establish a wind power model according to the type of wind turbine; establish a energy storage model according to the energy storage device of the wind power storage power station; establish a power grid model according to the topological structure, line parameters, and transformer parameters of the power grid.

[0022] In this embodiment, existing technology models can be used to establish the wind power model, energy storage model, and power grid model. As a specific embodiment, it may include: a. In specific implementation, the wind turbine is a doubly-fed wind turbine, and the wind power model is established through the Simulink platform. The wind power model specifically includes: Wind speed model: Simulate the change of wind speed as the input of the wind turbine. Specifically, a random wind speed model is used to simulate the change of wind speed.

[0023] Wind turbine power model: Convert wind speed into mechanical power.

[0024] Electrical model: Build the electrical model of the doubly-fed induction generator (DFIG) in Simulink, including the voltage equations, flux linkage equations, and motion equations of the stator and rotor.

[0025] Mechanical drive model: Describe the energy transfer process from the wind turbine blades to the generator.

[0026] b. In specific implementation, simulation tools (such as MATLAB / Simulink, PSCAD, etc.) can be used to implement the construction and testing of the energy storage model. The establishment of the energy storage model is the basis for the design and optimization of the wind power storage power station. The energy storage model specifically includes: Battery model: Describe the electrical characteristics and dynamic behavior of the battery. Use the Thevenin equivalent circuit model.

[0027] Power conversion system (PCS) model: Includes a DC / AC converter and its control system. Build the DC / AC converter model in Simulink and use a PI controller to achieve current and power control.

[0028] Energy management system (EMS) model: Achieve charge and discharge control and energy management of the energy storage system, and achieve charge and discharge control based on the state of charge (SOC): Power grid interface model: Simulate the interaction between the energy storage system and the power grid. Use a three-phase voltage source to simulate the power grid and add a fault module.

[0029] By combining the battery model, PCS model, EMS model, and power grid interface model, the dynamic response of the energy storage system under different working conditions can be comprehensively simulated.

[0030] c. Power grid model: Simulate the voltage and frequency characteristics of the power grid, as well as fault conditions. Use a three-phase voltage source to simulate the power grid and add a short-circuit fault module to simulate power grid faults.

[0031] In this step, the first model index data includes: power-related index data, voltage-related index data, frequency-related index data, and power quality index data.

[0032] Among them, the power-related index data includes: Active power control accuracy: It refers to the deviation degree between the actual output active power of the wind power storage power station and the active power required by the power grid dispatching instruction. Reactive power regulation range: It measures the range between the maximum and minimum reactive powers that the wind power storage power station can output. Power change rate: It includes the active power change rate and the reactive power change rate, reflecting the change speed of the power output of the wind power storage power station.

[0033] Among them, the voltage-related index data includes: Voltage deviation: It refers to the difference between the actual voltage at the connection point of the wind power storage power station and the rated voltage. Generally, it is required that the voltage deviation is within the range of ±5% or ±10% of the rated voltage. Excessive voltage deviation may cause abnormal operation or damage to equipment.

[0034] Voltage fluctuation: It is reflected as the fluctuation amplitude of the voltage at the connection point within a certain period of time. Usually, it is expressed as the percentage of the voltage fluctuation value to the rated voltage. For example, the voltage fluctuation does not exceed ±2% to ensure the stability of the power grid voltage and avoid adverse effects on user equipment.

[0035] Voltage unbalance degree: It is used to measure the unbalance degree of the three-phase voltage. Generally, it is required that the voltage unbalance degree does not exceed 2% - 3%. Excessive unbalance degree will increase equipment losses and affect equipment life.

[0036] Among them, the frequency-related index data includes: Frequency deviation: It refers to the difference between the actual operating frequency of the power grid and the rated frequency (such as 50Hz). The wind power storage power station should be able to operate normally within a certain frequency deviation range, such as ±0.2Hz or ±0.5Hz. Exceeding this range may lead to a decrease in power grid stability or even system disconnection.

[0037] Frequency response ability: It reflects the ability of the wind power storage power station to quickly adjust the active power output to support the recovery of the power grid frequency when the power grid frequency changes. Usually, it is measured by indicators such as frequency response time and frequency response amplitude.

[0038] Among them, the power quality index data includes: Harmonic content: It includes the voltage harmonic distortion rate and current harmonic distortion rate of each harmonic. For example, the total voltage harmonic distortion rate generally should not exceed 5%, and the individual harmonic voltage content rate should not exceed 3% to prevent harmonics from interfering with grid equipment and communication systems.

[0039] Interharmonics and subsynchronous harmonics: Interharmonics and subsynchronous harmonics may cause problems such as motor vibration and misoperation of relay protection, and there are also corresponding limit requirements for their content. Generally, the amplitudes of interharmonics and subsynchronous harmonics within a specific frequency range are measured for evaluation.

[0040] Flicker: It is measured by the flicker value, which reflects the impact of voltage fluctuations on visual effects such as lamp flickering. For example, the long-term flicker value generally should not exceed 1.0 to ensure the power consumption experience of users.

[0041] Among them, the stability index data includes: Transient stability: It is evaluated through indicators such as power angle stability and voltage stability during and after a fault. For example, after a severe fault such as a three-phase short circuit occurs in the system, it is required that the wind power storage power station can maintain stable operation, the power angle swing does not exceed a certain range, and the voltage can recover to the allowable value within a specified time.

[0042] Dynamic stability: It mainly examines the dynamic response characteristics of the wind power storage power station after being subjected to small disturbances, such as the oscillation frequency and damping ratio of variables such as system frequency and voltage after the disturbance. It is required that the oscillation can decay rapidly and the system can return to a stable state.

[0043] Voltage stability: It evaluates the ability of the wind power storage power station to maintain the voltage stability at the connection point under various operating conditions, usually measured by indicators such as voltage stability margin. The voltage stability margin should be greater than a certain safety threshold to prevent unstable phenomena such as voltage collapse.

[0044] Among them: The main contents of the grid adaptability test include: Voltage fluctuation test: It evaluates the response of the system to grid voltage fluctuations.

[0045] Frequency change test: It evaluates the adjustment ability of the system to grid frequency changes.

[0046] Fault ride-through test: It evaluates the dynamic behavior of the system during grid faults (such as short circuits and voltage dips).

[0047] Power regulation test: It evaluates the adjustment ability of the system to changes in grid power demand.

[0048] Energy management test: It evaluates the smoothing effect of the energy storage system on wind power fluctuations.

[0049] (1) Voltage fluctuation test Test objective: To evaluate the dynamic response of the system during grid voltage fluctuations. Test steps: Set voltage fluctuations (such as a voltage change of ±10%) in the grid model.

[0050] Observe the dynamic response of the wind power system and the energy storage system, including power output, voltage, and current changes.

[0051] Analyze the voltage regulation ability and stability of the system.

[0052] (2) Frequency change test Test objective: To evaluate the regulation ability of the system during grid frequency changes. Test steps: Set frequency changes (such as a frequency fluctuation of ±0.5 Hz) in the grid model.

[0053] Observe the frequency response of the wind power system and the energy storage system, including power output and frequency regulation.

[0054] Analyze the frequency regulation ability and stability of the system.

[0055] (3) Fault ride-through test Test objective: To evaluate the dynamic behavior of the system during grid faults. Test steps: Set a short-circuit fault or voltage dip (such as a voltage dip to 50%) in the grid model.

[0056] Observe the fault ride-through ability of the wind power system and the energy storage system, including current, voltage, and power changes.

[0057] Analyze the low voltage ride-through (LVRT) or high voltage ride-through (HVRT) ability of the system.

[0058] (4) Power regulation test Test objective: To evaluate the regulation ability of the system during grid power demand changes.

[0059] Test steps: Set power demand changes (such as step changes or random fluctuations) in the grid model.

[0060] Observe the power regulation ability of the wind power system and the energy storage system, including power output and SOC changes. Analyze the power regulation speed and accuracy of the system.

[0061] (5) Energy management test Test objective: To evaluate the smoothing effect of the energy storage system during wind power fluctuations. Test steps: Set wind speed fluctuations (such as random wind speed or step wind speed) in the wind power model.

[0062] Observe the charge and discharge behavior of the energy storage system, including power output and SOC changes.

[0063] Analyze the effect of the energy storage system on suppressing the power fluctuation of wind power.

[0064] The data of the wind power model reflects the operating status and performance of the wind turbine generator set.

[0065] In a specific embodiment, the first model index data may specifically include: (1) Wind speed data: The change of wind speed over time (m / s). As the input of the wind turbine, it affects the mechanical power and the generated power.

[0066] (2) Wind turbine data Mechanical power: The mechanical power output by the wind turbine (W or kW). It reflects the efficiency of converting wind energy into mechanical energy.

[0067] Tip speed ratio (λ): The change of the tip speed ratio over time. It reflects the operating status of the wind turbine.

[0068] Pitch angle (β): The change of the pitch angle over time. It is used to adjust the wind energy utilization coefficient (3) Generator data Stator voltage and current: The three-phase stator voltage and current. It reflects the electrical output of the generator.

[0069] Rotor voltage and current: The three-phase rotor voltage and current. It reflects the control effect of the rotor side converter.

[0070] Active power (P) and reactive power (Q): The active and reactive power output by the generator. It reflects the power contribution of the generator to the power grid.

[0071] Rotational speed (ω_r): The rotational speed of the generator (rad / s or rpm). It reflects the operating status of the generator.

[0072] (4) Battery data Battery voltage: The terminal voltage of the battery (V). It reflects the electrical state of the battery.

[0073] Battery current: The charging and discharging current of the battery (A). It reflects the charging and discharging status of the battery.

[0074] State of charge (SOC): The percentage of the remaining capacity of the battery (%). It reflects the energy state of the battery.

[0075] Battery temperature: The temperature of the battery (°C). It reflects the thermal state of the battery.

[0076] (5) Power conversion system (PCS) data DC bus voltage (V_dc): The DC bus voltage (V). It reflects the DC side status of the PCS.

[0077] AC - side voltage and current: Three - phase AC voltage and current (V, A). Reflect the interaction between the PCS and the power grid.

[0078] Active power (P) and reactive power (Q): Active and reactive power output by the PCS. Reflect the power contribution of the PCS to the power grid.

[0079] (6) Energy Management System (EMS) data Charge - discharge power: Charge - discharge power of the energy storage system (W). Reflect the power regulation ability of the energy storage system.

[0080] Control signal: Control signal sent by the EMS (such as charge - discharge instructions). Reflect the control strategy of the EMS.

[0081] (7) Grid voltage and frequency Grid voltage: Three - phase grid voltage (V). Reflect the voltage stability of the power grid.

[0082] Grid frequency: Reflect the frequency stability of the power grid.

[0083] (8) Load data Load power (P_load, Q_load): Active and reactive power of the load (W, VAR). Reflect the power demand of the power grid.

[0084] (9) Fault data Fault type: Short - circuit fault, voltage dip, etc. Reflect the fault conditions of the power grid.

[0085] Voltage and current during fault: Voltage and current changes during the fault (V, A). Reflect the fault - ride - through ability of the system.

[0086] (10) Dynamic response data Voltage fluctuation response: Voltage and power changes during voltage fluctuations. Reflect the voltage regulation ability of the system.

[0087] Frequency fluctuation response: Frequency and power changes during frequency fluctuations. Reflect the frequency regulation ability of the system.

[0088] (11) Fault - ride - through data Low - voltage ride - through (LVRT) data: Voltage, current and power changes during voltage dips. Reflect the low - voltage ride - through ability of the system.

[0089] High - voltage ride - through (HVRT) data: Voltage, current and power changes during voltage rises. Reflect the high - voltage ride - through ability of the system.

[0090] (12) Power regulation data Power regulation speed: The time response of power regulation (s). It reflects the dynamic regulation capability of the system.

[0091] Power regulation accuracy: The error of power regulation (%). It reflects the control accuracy of the system.

[0092] (13) Energy management data SOC change: The change of SOC over time (%). It reflects the energy status of the energy storage system.

[0093] Power smoothing effect: Comparison of wind power fluctuation and energy storage power output. Reflects the effect of energy storage system on smoothing wind power fluctuation.

[0094] As an optional embodiment, the testing method of the present invention further includes: Step S11: establishing a disturbance equation, performing a grid adaptability test using the disturbance equation, and using the index data of the grid adaptability test using the disturbance equation as the first simulation index data.

[0095] The step S11 specifically includes: According to the situations that may occur in the actual operation of the power grid, select the appropriate disturbance type for testing. Common disturbance types include voltage disturbance (such as voltage drop, voltage surge), frequency disturbance (such as frequency increase, frequency decrease), short circuit fault (such as three-phase short circuit, single-phase ground short circuit), etc. For example, simulate a short circuit fault at a certain moment and add the boundary conditions of the fault point (such as zero voltage) to the equation group.

[0096] Determine disturbance parameters: Determine the specific parameters of each disturbance, such as the depth and duration of voltage drop, the amplitude and rate of frequency change, etc. These parameters should be reasonably set according to relevant standards and actual needs to simulate grid abnormalities of different severity.

[0097] Set up test conditions: Consider different operating conditions of the wind power storage station, such as different wind power outputs, charging and discharging states of the energy storage system, etc., and conduct disturbance tests under each condition to comprehensively evaluate the adaptability of the power station under various operating conditions.

[0098] Test: Arrange the test sequence reasonably, generally conduct a lighter disturbance test first, and then gradually increase the severity of the disturbance. At the same time, avoid continuous high-intensity disturbance tests to avoid damage to the equipment.

[0099] Step S2: adjusting the parameters of the initial test model according to the first simulation index data until the simulation index data obtained according to the current test model meets the preset conditions, and obtaining the final adjusted target test model; Specifically, adjusting the parameters of the initial test model according to the first simulation index data until the simulation index data obtained according to the current test model meets the preset conditions includes: Step S201: Obtain the actual index data of the on-site test of the wind power storage power station to be tested, extract the third set of eigenvalue of the first model index data and the second set of eigenvalue of the actual test index data respectively according to the preset algorithm, and compare the average difference between the third set of eigenvalue and the second set of eigenvalue; In this step, the actual index data of the on-site test of the wind power storage power station to be tested refers to the grid adaptability test in the wind power storage power station on-site in the same way as the initial test model. The actual index data also includes power-related index data, voltage-related index data, frequency-related index data, and power quality index data, which have been described in detail in the previous examples of this embodiment and will not be introduced too much here.

[0100] Among them, extracting the third set of eigenvalue of the first model index data and the second set of eigenvalue of the actual test index data respectively according to the preset algorithm, and comparing the average difference between the third set of eigenvalue and the second set of eigenvalue includes: Step S2011: Use the RBM algorithm to extract the third set of eigenvalue of the first model index data to obtain the first eigenvector , where , use the RBM algorithm to extract the second set of eigenvalue of the actual test index data to obtain the second eigenvector , where .

[0101] In this step, first preprocess the first model index data and the actual test index data, then construct an RBM model, and define the network structure, including the input layer and the hidden layer; Among them, the number of input layer nodes is equal to the feature dimension of the first model index data, and the activation function uses the Tanh function, which can better reflect the difference between the eigenvalue extracted from the first model index data and the eigenvalue extracted from the actual test index data.

[0102] Then, train the RBM model, train the RBM through the Contrastive Divergence algorithm, maximize the likelihood function of the data, and then input the preprocessed first model index data and the actual test index data into the RBM model respectively, and calculate the activation value of the hidden layer. These activation values are the extracted eigenvalue, and the extracted eigenvalue satisfies the following formula: ; Where represents the activation value of the j-th node in the hidden layer, reflecting the characteristic information of the first model index data or the actual test index data extracted; is the bias term of the j-th node in the hidden layer; represents the state value of the i-th node in the visible layer, used to receive the first model index data or the actual test index data; is the connection weight between the i-th node in the visible layer and the j-th node in the hidden layer.

[0103] It should be noted that the Restricted Boltzmann Machine (RBM) is an unsupervised learning neural network model, commonly used for feature extraction and dimensionality reduction.

[0104] Step S2012: Calculate the mean vectors of the two sets of feature vectors in each dimension and , and take the Euclidean distance between the mean vectors and as the average difference between the third set of eigenvalues and the second set of eigenvalues. The average difference D satisfies the following formula ; ; ; where is the mean of the first feature vector in the k-th dimension, is the mean of the second feature vector in the k-th dimension, and d, k, n, and m are all natural numbers.

[0105] In the above implementation process, the eigenvalues of the grid adaptability test data are extracted by RBM, so as to compare the eigenvalues extracted from the first model index data of the simulation model with the eigenvalues extracted from the actual test index data, and adjust the initial test model, which is beneficial to making the model index data of the simulation system for grid adaptability test better represent the actual test data of the wind power storage power station, and is beneficial to improving the accuracy of the grid adaptability test.

[0106] Step S202: If the average difference is greater than the difference threshold, perform multiple iterative processes on the parameters of the test model until the simulation index data obtained according to the current test model meets the preset conditions.

[0107] The preset condition is that the average difference between the first set of eigenvalues corresponding to the simulation index data and the second set of eigenvalues corresponding to the actual index data is less than or equal to the difference threshold; In this step, the iterative process refers to separately extracting the first set of eigenvalue of the simulation index data of the test model determined by the current parameters and the second set of eigenvalue of the actual index data according to a preset algorithm, calculating the average difference between the first set of eigenvalue and the second set of eigenvalue. If the average difference is greater than the difference threshold, the parameters of the current test model are adjusted until the average difference between the first set of eigenvalue and the second set of eigenvalue is greater than the difference threshold.

[0108] Among them, when performing multiple iterative processes on the parameters of the test model, adjustments can be made according to a unified learning rate until the average difference between the first set of eigenvalue corresponding to the simulation index data and the second set of eigenvalue corresponding to the actual index data is less than or equal to the difference threshold.

[0109] In specific implementation, if the requirement for the classification accuracy of the grid adaptability test of the wind power storage power station is high, the difference threshold can be set to be relatively small.

[0110] As an optional embodiment, the adjustment method may specifically include: Step S211: Adjust based on the initial parameters of the wind power storage power station; for example, adjust according to the design parameters, technical specifications of the wind turbine and the on-site actual operation data. The initial parameters such as the wind wheel diameter, rated power, generator efficiency and other parameters can usually be obtained from the equipment manual.

[0111] Step S212: Gradually optimize: Adopt the method of gradual fine-tuning, and adjust one or a few relevant parameters each time. Do not make large adjustments to multiple parameters at one time, and then calculate the average difference between the first set of eigenvalue corresponding to the simulation index data and the second set of eigenvalue corresponding to the actual index data, and evaluate the adjustment effect to ensure the stability and convergence of the model.

[0112] In specific implementation, first adjust one or several parameters of the wind power model, then adjust one or several parameters of the energy storage model, and finally adjust the parameters of the grid model.

[0113] The following takes the adjustment of the wind power model parameters as an example for specific description: (1) The wind speed model of the wind power model is: ; Among them, v is the wind speed; k is the shape parameter (usually about 2); λ is the scale parameter; During adjustment, adjust the shape parameter k and the scale parameter λ of the wind speed model.

[0114] (2) The fan power model of the wind power model is: ; Among them, is the cut-in wind speed; is the rated wind speed; is the cut-out wind speed, ρ is the air density; A is the swept area of the wind turbine blades; Cp(λ,β) is the power coefficient, related to the tip speed ratio λ and the pitch angle β; is the rated power.

[0115] During adjustment, adjust the cut-in wind speed of the wind turbine power model and the rated wind speed and the cut-out wind speed and the power coefficient parameter Cp(λ,β).

[0116] The mechanical drive model of the wind power model is: ; where J is the equivalent moment of inertia; is the angular velocity of the drive system; is the aerodynamic torque of the wind turbine; is the electromagnetic torque of the generator; B is the equivalent damping coefficient; During adjustment, adjust the moment of inertia J and the damping coefficient B of the mechanical drive model.

[0117] (4)The electrical model of the wind power model is: ; During adjustment, adjust the stator resistance of the electrical model and the inductance and and the permanent magnet flux linkage parameter .

[0118] During the above adjustment process, by adjusting the parameters until the average difference between the first set of eigenvalues corresponding to the simulated index data and the second set of eigenvalues corresponding to the actual index data is less than the difference threshold, at this time, the simulated index data obtained according to the test model meets the preset conditions, indicating that the model can accurately simulate the operating characteristics of the actual wind power system, and then obtain the finally adjusted target test model.

[0119] Step S3: Perform grid adaptability testing on the target test model to obtain second model index data; In this step, the method for obtaining the second model index data refers to the method for obtaining the first model index data. The second model index data also includes: power-related index data, voltage-related index data, frequency-related index data, and power quality index data, which will not be elaborated here.

[0120] Step S4: Map the second model index data, input the mapped data into the quantum support vector machine algorithm model, and obtain the classification result of the grid adaptability of the wind power storage power station. The classification result is one of excellent, good, qualified, and unqualified.

[0121] Specifically, step S4 includes: Step S41: Map the second model index data into a quantum state through quantum encoding, specifically including: In specific implementation, first, perform normalization processing on the second model index data so that ; where 1 < i < m, both i and m are natural numbers; Then, perform encoding using amplitude encoding, and realize the entanglement and interaction between qubits through multi-qubit gates to construct a quantum state. The quantum state where is the quantum state composed of qubits.

[0122] In this step, since the second model index data is continuous data, amplitude encoding is used for encoding, and the magnitude of the data is reflected by adjusting the amplitude of the quantum state.

[0123] Step S42: Use the actual test index data as training sample data, train the quantum support vector machine through the training sample data, construct a Lagrangian function, and determine the optimal separation hyperplane in the feature space; In specific implementation, the training sample data adopts the actual test index data on-site, which can improve the classification accuracy. Among them, the training sample data is encoded into a quantum state using the same encoding mapping method as the second model index data.

[0124] Specifically, determining the optimal separation hyperplane in the feature space by constructing an objective function includes: The constructed Lagrangian function satisfies: where is the normal vector of the hyperplane, b is the bias term, is the vector representation of the input sample data mapped to the feature space, is the sample data category label; Then, take the partial derivatives of and b and set them to 0 to obtain and , and substitute them into the Lagrangian function to obtain the dual problem; ; Finally, use the sequential minimal optimization algorithm SMO to solve the dual problem and solve the Lagrange multiplier under the constraint conditions Each time, two Lagrange multipliers are selected and are optimized. By continuously iterating and updating values until the convergence condition is met, the parameters and b of the hyperplane are obtained, and the optimal separating hyperplane is obtained.

[0125] During the training process, the parameters of the model are adjusted through an optimization algorithm, thereby realizing the classification task of the data.

[0126] Step S43: Calculate the kernel matrix between the second model index data and the sample data using the quantum kernel function. Each element in the kernel matrix represents the similarity of the corresponding data under the quantum kernel function; In specific implementation, the quantum kernel function ; where and are respectively the vector representations of the input second model index data and the sample data after being mapped to the feature space by the mapping function, is the bandwidth parameter, which determines the width of the kernel function, is the square of the Euclidean distance between two mapped vectors in the feature space.

[0127] In this step, the encoded quantum states constitute a high-dimensional quantum feature space. By utilizing the properties such as the superposition of quantum states, the power grid data that is linearly inseparable in the low-dimensional space becomes linearly separable in the quantum feature space.

[0128] Step S44: Input the kernel matrix between the second model index data and the sample data into the quantum support vector machine for classification to obtain the classification result of the grid adaptability of the wind power storage power station.

[0129] In this step, the kernel matrix between the second model index data and the sample data constitutes a vector with the same number as the training data. Input the kernel matrix data into the quantum support vector machine, and through the decision function, obtain the class label, that is, the classification result.

[0130] In this step, the classification result is based on the class labels calibrated for the training data. During the training process of the quantum support vector machine, the class labels are first calibrated for the training data.

[0131] Specifically, the class labels can be determined through single-index evaluation and then integrated-index evaluation. Specifically as follows: Single - index comparison: Compare the data of each index with relevant standards, specifications or design requirements. For example, for the active power control accuracy index, if the standard requires it to be controlled within ±2%, and the actual measured value exceeds this range, it indicates that this index does not meet the requirements, and there may be problems with the power station in terms of active power control, so the single - index score is relatively low.

[0132] Comprehensive index evaluation: Weight determination: Considering that different indexes have different degrees of influence on the adaptability of wind - power storage power stations, it is necessary to determine reasonable weights for each index. Methods such as the expert scoring method and the analytic hierarchy process can be used to determine the weights. For example, the active power control accuracy and voltage stability are crucial for the stable operation of the power grid, and relatively high weights can be assigned; while some secondary indexes are assigned lower weights.

[0133] Comprehensive score calculation: Calculate the comprehensive score of the wind - power storage power station according to the evaluation results of single - indexes and the corresponding weights. The commonly used calculation method is the weighted average method, that is, comprehensive score = ∑(single - index score × the weight of this index). Through the comprehensive score, the adaptability to the power grid can be classified into four levels: excellent, good, qualified and unqualified. The characterization meanings of each level are as follows: Excellent: All evaluation indexes are significantly better than the standard requirements, can operate stably and efficiently under various working conditions, have strong supporting and regulating capabilities for the power grid, hardly have an adverse impact on the power grid, and can enhance the stability and reliability of the power grid.

[0134] Good: Most indexes meet or are slightly better than the standard, can better adapt to the power grid operation requirements, operate stably under common working conditions, but may need further optimization in extreme situations or complex working conditions.

[0135] Qualified: All indexes basically meet the standard, but some indexes are in a critical state, may have small fluctuations in certain specific situations, but do not affect the overall safe operation of the power grid, and need to strengthen monitoring and maintenance.

[0136] Unqualified: There are multiple unqualified indexes, which have an obvious adverse impact on the power grid operation, may lead to problems such as the decline of power grid power quality and the reduction of stability, and need to be comprehensively rectified and optimized.

[0137] Embodiment 2 Please refer to Figure 2 As shown in Figure 2 , it includes: Initial model acquisition unit 210: Used to establish an initial test model of the wind - power storage power station, conduct grid adaptability tests on the initial test model, and obtain the first model index data; the initial test model includes a wind power model, an energy storage model and a power grid model; An adjustment unit 220, configured to adjust the parameters of the initial test model according to the first simulation index data until the simulation index data obtained according to the current test model meets the preset conditions, and obtain a target test model after final adjustment; A target data acquisition unit 230, configured to perform a power grid adaptability test on the target test model to obtain second model index data; A classification unit 240, configured to map the second model index data, input the mapped data into a quantum support vector machine algorithm model, and obtain a classification result of the wind power storage power station's power grid adaptability, where the classification result is one of excellent, good, qualified, and unqualified.

[0138] Embodiment III Please refer to Figure 3 , Figure 3 , which is a schematic structural diagram of an electronic device disclosed in an embodiment of the present invention. As Figure 3 shown, the electronic device may include: A memory 310 storing executable program code; A processor 320 coupled to the memory 310; Wherein, the processor 320 calls the executable program code stored in the memory 310 and executes some or all of the steps in an automatic adjustment method of an intelligent seat in Embodiment I.

[0139] An embodiment of the present invention discloses a computer-readable storage medium, which stores a computer program, wherein the computer program enables a computer to execute some or all of the steps in an automatic adjustment method of an intelligent seat in Embodiment I.

[0140] An embodiment of the present invention also discloses a computer program product, wherein when the computer program product runs on a computer, it enables the computer to execute some or all of the steps in a power grid adaptability test method of a wind power storage power station in Embodiment I.

[0141] An embodiment of the present invention also discloses an application publishing platform, wherein the application publishing platform is used to publish a computer program product, and when the computer program product runs on a computer, it enables the computer to execute some or all of the steps in a power grid adaptability test method of a wind power storage power station in Embodiment I.

[0142] In various embodiments of the present invention, it should be understood that the magnitude of the sequence numbers of the various processes does not necessarily mean the inevitable sequence of execution. The execution sequence of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0143] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] In addition, each functional unit in the embodiments of the present invention can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0145] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several requests for causing a computer device (which can be a personal computer, a server, or a network device, etc., specifically, the processor in the computer device) to execute some or all of the steps of the methods described in the various embodiments of the present invention.

[0146] In the embodiments provided by the present invention, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0147] Those of ordinary skill in the art can understand that some or all of the steps in the various methods of the embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disc memories, tape memories, or any other computer-readable medium capable of carrying or storing data.

[0148] The above has introduced in detail an automatic adjustment method, device, electronic device and storage medium of an intelligent seat disclosed in the embodiments of the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for testing the grid adaptability of a wind power storage station, characterized in that: It includes the following steps: Establishing an initial test model of a wind power and energy storage power station, and performing a grid adaptability test on the initial test model to obtain first model indicator data; the initial test model includes a wind power model, an energy storage model, and a grid model; Adjusting the parameters of the initial test model according to the first simulation index data until the simulation index data obtained according to the current test model meets the preset conditions, and obtaining the final adjusted target test model; Conducting a grid adaptability test on the target test model to obtain second model indicator data; The second model indicator data is mapped, and the mapped data is input into the quantum support vector machine algorithm model to obtain a classification result of the grid adaptability of the wind power storage station, and the classification result is one of excellent, good, qualified and unqualified.

2. The method for testing the grid adaptability of a wind power storage station according to claim 1, characterized in that: The step of adjusting the parameters of the initial test model according to the first simulation indicator data until the simulation indicator data obtained according to the current test model meets a preset condition includes: The preset condition is that the average difference between the first set of characteristic values ​​corresponding to the simulated indicator data and the second set of characteristic values ​​corresponding to the actual indicator data is less than or equal to the difference threshold; The actual index data of the on-site test of the wind power storage station to be tested is obtained, and the third group of characteristic values ​​of the first model index data and the second group of characteristic values ​​of the actual test index data are respectively extracted according to a preset algorithm, and the average difference between the third group of characteristic values ​​and the second group of characteristic values ​​is compared. If the average difference is greater than the difference threshold, the parameters of the test model are iterated for multiple times until the simulation index data obtained according to the current test model meets the preset conditions.

3. The method for testing the grid adaptability of a wind power storage station according to claim 2, characterized in that: The extracting a third set of eigenvalues ​​of the first model index data and a second set of eigenvalues ​​of the actual test index data according to a preset algorithm, and comparing the average difference between the third set of eigenvalues ​​and the second set of eigenvalues, comprises: The RBM algorithm is used to extract the third set of eigenvalues ​​of the first model indicator data to obtain the first eigenvector , , the RBM algorithm is used to extract the second set of eigenvalues ​​of the actual test index data to obtain the second eigenvector , , calculate the mean vector of the two sets of eigenvectors in each dimension and , the mean vector and The Euclidean distance is the average difference between the third set of eigenvalues ​​and the second set of eigenvalues. The average difference D satisfies the following formula ; ; ;in, is the mean of the first eigenvector in the kth dimension, is the mean of the second eigenvector in the kth dimension, and d, k, n and m are all natural numbers.

4. The method for testing the grid adaptability of a wind power storage station according to claim 1, characterized in that: The initial test model of establishing a wind power storage station includes: A wind power model is established according to the type of wind turbine; an energy storage model is established according to the energy storage device of the wind power storage station; and a power grid model is established according to the topological structure, line parameters, and transformer parameters of the power grid.

5. The method for testing the grid adaptability of a wind power storage station according to claim 1, characterized in that: The first model indicator data includes power-related indicator data, voltage-related indicator data, frequency-related indicator data, and power quality indicator data; the grid adaptability test includes voltage fluctuation test, frequency change test, fault ride-through test, power regulation test, and energy management test.

6. According to the wind power storage station grid adaptability test method, it is characterized in that: The second model indicator data is mapped, and the mapped data is input into the quantum support vector machine algorithm model to obtain the classification result of the grid adaptability of the wind power storage station, including: Mapping the second model indicator data into a quantum state through quantum coding; Using actual test index data as training sample data, training the quantum support vector machine through the training sample data, constructing a Lagrangian function, and determining the optimal separation hyperplane in the feature space; The quantum kernel function is used to calculate the kernel matrix between the second model indicator data and the sample data, and each element in the kernel matrix represents the similarity of the corresponding data under the quantum kernel function; The kernel matrix is ​​input into a quantum support vector machine for classification, and a classification result of the adaptability of the wind power storage station to the power grid is obtained.

7. The method for testing the grid adaptability of a wind power storage station according to claim 1, characterized in that: Mapping the second model metric data to a quantum state through quantum encoding includes: performing normalization processing on the second model metric data, encoding the normalized data using amplitude encoding, and constructing a quantum state, where the quantum state , where is a quantum state composed of qubits, , is the i-th data in the second model metric data, 1 < i < m, both i and m are natural numbers, and the quantum kernel function uses a Gaussian kernel function.

8. A wind power storage station grid adaptability test system, characterized in that: It includes: Initial model acquisition unit: used to establish an initial test model of the wind power storage power station, perform a grid adaptability test on the initial test model, and obtain first model indicator data; the initial test model includes a wind power model, an energy storage model and a grid model; An adjustment unit, configured to adjust the parameters of the initial test model according to the first simulation index data, until the simulation index data obtained according to the current test model meets the preset conditions, thereby obtaining a final adjusted target test model; A target data acquisition unit, used to perform a power grid adaptability test on the target test model to obtain second model indicator data; The classification unit is used to map the second model indicator data, input the mapped data into the quantum support vector machine algorithm model, and obtain a classification result of the grid adaptability of the wind power storage station, wherein the classification result is one of excellent, good, qualified and unqualified.

9. An electronic device, characterized in that: It includes: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the wind power storage station grid adaptability testing method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: It stores a computer program, wherein the computer program enables a computer to execute the wind power storage station grid adaptability testing method as described in any one of claims 1-7.

Images