Control strategy method of substation static var generator and related equipment

Abstract

The invention discloses a control strategy method for a static var generator of a transformer substation and related equipment. The method comprises the following steps: firstly, preprocessing real-time data acquired by a transformer substation to obtain to-be-analyzed data; performing feature extraction on the to-be-analyzed data to obtain a voltage feature value; classifying the voltage characteristic values to obtain voltage fluctuation types; performing reactive power optimization adjustment solution according to the voltage characteristic value and the voltage fluctuation type to obtain a predicted reactive power adjustment amount; and finally, adjusting the reactive current output of the static var generator according to the predicted reactive adjustment amount and an equation in a static var generator control strategy so as to realize real-time optimized operation of the static var generator. In the process, the predicted reactive adjustment amount is obtained through the reactive optimization adjustment model, so that the reactive current output of the static var generator can be adjusted in combination with the static var generator control strategy, the voltage fluctuation of the transformer substation is effectively inhibited, and the stability of the voltage of the power grid is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of controlling a static VAR generator, and in particular to a control strategy method and related equipment for a static VAR generator in a substation. Background Art

[0002] In industrial enterprises, strong voltage fluctuations generated by the power supply system can cause oscillations in the synchronous motors within the enterprise, affecting product quality. In addition, voltage fluctuations can also cause inaccurate data from electronic equipment and testing instruments, making it impossible for electronic computers and precision instruments to work properly. Therefore, controlling and suppressing voltage fluctuations is crucial to improving the stability and power supply quality of the power system. Since the Static Var Generator (SVG) can effectively suppress voltage fluctuations and prevent voltage flicker and short-term voltage changes from affecting equipment by quickly responding to system voltage changes, SVG is usually installed in substations to effectively regulate voltage and provide reactive power compensation, especially to improve the stability and power supply quality of the power system when there are large load changes.

[0003] The existing SVG technology is to stabilize the voltage by real-time monitoring of grid voltage changes and dynamically adjusting reactive power output. One of the methods is a hybrid control method of constant voltage control and constant reactive current control, but due to the complexity of the control algorithm, it is difficult to implement, and when the voltage and reactive power requirements conflict, it is difficult to quickly find the best balance point, resulting in unsatisfactory regulation effect. Summary of the invention

[0004] The present application provides a control strategy method and related equipment for a static VAR generator in a substation. By establishing an optimization model and comprehensively considering voltage stability and reactive power balance, dual optimization regulation of voltage and reactive power is achieved. The results of the optimization model are combined with a constant voltage control strategy to enable the static VAR generator to respond quickly and improve the overall performance of the power system.

[0005] In a first aspect, the present application provides a control strategy method for a static VAR generator in a substation, the method comprising:

[0006] Pre-process the real-time data collected by the substation to obtain the data to be analyzed;

[0007] Extract features of the data to be analyzed and obtain voltage characteristic values;

[0008] Classify the voltage characteristic values ​​to obtain the voltage fluctuation type;

[0009] According to the voltage characteristic value and voltage fluctuation type, the reactive power optimization regulation is solved to obtain the predicted reactive power adjustment amount;

[0010] According to the predicted reactive adjustment amount and the equation in the static VAR generator control strategy, the reactive current output of the static VAR generator is adjusted to achieve real-time optimized operation of the static VAR generator.

[0011] Optionally, the real-time data collected by the substation is preprocessed to obtain data to be analyzed, including:

[0012] Use low-pass filtering method and high-pass filtering method to filter the real-time data;

[0013] The wavelet transform method is used to denoise the filtered data to obtain the data to be analyzed.

[0014] Optionally, the voltage characteristic value includes the voltage effective value, the instantaneous value of the voltage signal, the voltage frequency component and the time-frequency characteristics of the voltage fluctuation. The characteristic extraction is performed on the data to be analyzed to obtain the voltage characteristic value, including:

[0015] Calculate the root mean square value of the voltage signal in the data to be analyzed to obtain the effective value of the voltage;

[0016] Extracting the instantaneous value of the voltage signal from the voltage signal in the data to be analyzed;

[0017] Fast Fourier transform is used to perform spectrum analysis on the voltage signal in the data to be analyzed and extract the voltage frequency component;

[0018] Short-time Fourier transform is used to perform time-frequency analysis on the voltage signal in the data to be analyzed to obtain the time-frequency characteristics of voltage fluctuation.

[0019] Optionally, the voltage characteristic values ​​are classified to obtain voltage fluctuation types, including:

[0020] The voltage characteristic value is input into the classification model to obtain the voltage fluctuation type. The classification model is a trained random forest algorithm model, and the training samples of the classification model are historical voltage characteristic values ​​and corresponding historical voltage fluctuation types.

[0021] Optionally, reactive power optimization regulation is solved according to voltage characteristic values ​​and voltage fluctuation types to obtain predicted reactive power adjustment, including:

[0022] The voltage characteristic value and the voltage fluctuation type are combined with the static VAR generator parameters to perform reactive optimization regulation, and a reactive optimization regulation model is established, which specifically includes the following formula:

[0023]

[0024] Where J represents the voltage control deviation, x(k+i|k) represents the voltage characteristic value at the future i moments predicted based on the voltage characteristic at the k moment, x0(k+i|k) represents the known voltage characteristic value at the i moments based on the k moment, and N represents the total number of moments;

[0025] The above formula represents that the voltage control deviation is minimum, wherein the constraint conditions of the reactive power optimization regulation model include the following formula:

[0026] xmin≤x≤xmax

[0027]

[0028] Where x represents the voltage magnitude vector, x max and x min Respectively represent the upper and lower limit vectors of the voltage amplitude, Q 1max and Q 1min They represent the upper and lower limits of the reactive power output of the static VAR generator, respectively; Q1(k|k) represents the predicted value of reactive power at time k; ΔQ1(k+i|k) represents the reactive adjustment amount of the static VAR generator at the i-th moment in the future based on time k; N represents the total number of moments;

[0029] The reactive power optimization regulation model is solved to obtain the predicted reactive power adjustment amount.

[0030] Optionally, adjusting the reactive current output of the static VAR generator according to the predicted reactive adjustment amount and an equation in the static VAR generator control strategy includes:

[0031] The voltage fluctuation is controlled within a set range through the voltage equation of the static VAR generator, so as to realize that the static VAR generator is in a constant voltage mode;

[0032] Substituting the predicted reactive power adjustment amount into the control equation of the constant voltage mode in the static VAR generator control strategy to obtain the output current of the static VAR generator after setting;

[0033] According to the output current of the static VAR generator after setting, the reactive current output of the static VAR generator is adjusted in real time.

[0034] Optionally, before preprocessing the real-time data collected by the substation, the following steps are also included:

[0035] The data collection equipment in the substation is calibrated according to the standard signal, and the data of the collection equipment is time synchronized and calibrated.

[0036] In a second aspect, the present application provides a control strategy device for a static VAR generator in a substation, the device comprising:

[0037] A processing unit, used to pre-process the real-time data collected by the substation to obtain data to be analyzed;

[0038] An extraction unit, used for extracting features from the data to be analyzed and obtaining voltage feature values;

[0039] A classification unit, used for classifying voltage characteristic values ​​to obtain voltage fluctuation types;

[0040] An obtaining unit, used for performing reactive power optimization adjustment and solving according to the voltage characteristic value and the voltage fluctuation type, and obtaining a predicted reactive power adjustment amount;

[0041] The adjustment unit is used to adjust the reactive current output of the static VAR generator according to the predicted reactive adjustment amount and the equation in the static VAR generator control strategy to achieve real-time optimized operation of the static VAR generator.

[0042] Optionally, the processing unit is specifically configured to:

[0043] Use low-pass filtering method and high-pass filtering method to filter the real-time data;

[0044] The wavelet transform method is used to denoise the filtered data to obtain the data to be analyzed.

[0045] Optionally, the voltage characteristic value includes a voltage effective value, a voltage signal instantaneous value, a voltage frequency component, and a time-frequency characteristic of a voltage fluctuation, and the extraction unit is specifically used for:

[0046] Calculate the root mean square value of the voltage signal in the data to be analyzed to obtain the effective value of the voltage;

[0047] Extracting the instantaneous value of the voltage signal from the voltage signal in the data to be analyzed;

[0048] Fast Fourier transform is used to perform spectrum analysis on the voltage signal in the data to be analyzed and extract the voltage frequency component;

[0049] Short-time Fourier transform is used to perform time-frequency analysis on the voltage signal in the data to be analyzed to obtain the time-frequency characteristics of voltage fluctuation.

[0050] Optionally, the taxonomic unit is specifically used for:

[0051] The voltage characteristic value is input into the classification model to obtain the voltage fluctuation type. The classification model is a trained random forest algorithm model, and the training samples of the classification model are historical voltage characteristic values ​​and corresponding historical voltage fluctuation types.

[0052] Optionally, the obtaining unit is specifically used for:

[0053] The voltage characteristic value and voltage fluctuation type are combined with the static VAR generator parameters to perform reactive optimization regulation and establish a reactive optimization regulation model, which specifically includes the following formulas:

[0054]

[0055] Where J represents the voltage control deviation, x(k+i|k) represents the voltage characteristic value at the future i moments predicted based on the voltage characteristic at the k moment, x0(k+i|k) represents the known voltage characteristic value at the i moments based on the k moment, and N represents the total number of moments;

[0056] The above formula represents that the voltage control deviation is minimum, wherein the constraint conditions of the reactive power optimization regulation model include the following formula:

[0057] xmin≤x≤xmax

[0058]

[0059] Where x represents the voltage magnitude vector, x max and x min Respectively represent the upper and lower limit vectors of the voltage amplitude, Q 1max and Q 1min They represent the upper and lower limits of the reactive power output of the static VAR generator, respectively; Q1(k|k) represents the predicted value of reactive power at time k; ΔQ1(k+i|k) represents the reactive adjustment amount of the static VAR generator at the i-th moment in the future based on time k; N represents the total number of moments;

[0060] The reactive power optimization regulation model is solved to obtain the predicted reactive power adjustment amount.

[0061] Optionally, the adjustment unit is specifically used for:

[0062] The voltage fluctuation is controlled within a set range through the voltage equation of the static VAR generator, so as to realize that the static VAR generator is in a constant voltage mode;

[0063] Substitute the predicted reactive power adjustment into the control equation of the constant voltage mode in the static VAR generator control strategy to obtain the output current of the static VAR generator after setting;

[0064] According to the output current of the static VAR generator after setting, the reactive current output of the static VAR generator is adjusted in real time.

[0065] Optionally, the device further comprises:

[0066] The calibration unit is used to calibrate the data of the acquisition equipment in the substation according to the standard signal, and to perform time synchronization calibration on the data of the acquisition equipment.

[0067] In a third aspect, the present application provides an electronic device, the electronic device comprising a memory and a processor:

[0068] The memory is used to store computer programs;

[0069] The processor is used to execute the method provided by the first aspect according to the computer program.

[0070] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program for executing the method provided in the first aspect.

[0071] It can be seen that this application has the following beneficial effects:

[0072] The present application provides a control strategy method for a static VAR generator in a substation. First, the real-time data collected by the substation is preprocessed to obtain data to be analyzed; feature extraction is performed on the data to be analyzed to obtain voltage characteristic values; the voltage characteristic values ​​are classified to obtain voltage fluctuation types; reactive power optimization adjustment is solved according to the voltage characteristic values ​​and the voltage fluctuation types to obtain predicted reactive power adjustment amounts; finally, according to the predicted reactive power adjustment amounts and the equations in the static VAR generator control strategy, the reactive current output of the static VAR generator is adjusted to achieve real-time optimized operation of the static VAR generator. In this process, the predicted reactive power adjustment amount is obtained through the reactive power optimization adjustment model, so that the reactive current output of the static VAR generator can be adjusted in combination with the static VAR generator control strategy, effectively suppressing the voltage fluctuation of the substation, improving the power supply quality of the power grid, and ensuring the stability of the power grid voltage. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0074] Figure 1 A flow chart of an embodiment of a control strategy method for a static VAR generator in a substation according to an embodiment of the present application;

[0075] Figure 2 A schematic diagram of the architecture of a random forest algorithm in an embodiment of the present application;

[0076] Figure 3 A flow chart of another embodiment of a control strategy method for a static VAR generator in a substation according to an embodiment of the present application;

[0077] Figure 4This is a structural schematic diagram of a control strategy device for a static VAR generator in a substation according to an embodiment of the present application;

[0078] Figure 5 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0079] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0080] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0081] First, the technical terms involved in the embodiments of the present application are explained:

[0082] (1) Voltage fluctuation: a series of changes or continuous changes in the effective value (root mean square value) of the grid voltage. The voltage fluctuation value is expressed as a percentage of the difference between the adjacent maximum and minimum root mean square values ​​of the voltage to the rated voltage of the grid. The frequency of voltage fluctuation refers to the number of voltage fluctuations per unit time. Voltage fluctuation is one of the important indicators for measuring the quality of electricity use. In industrial enterprises, strong voltage fluctuations generated by the power supply system can cause oscillations in the synchronous motors within the enterprise, affecting product quality. In addition, voltage fluctuations can also cause inaccurate data from electronic equipment and testing instruments, making it impossible for electronic computers and precision instruments to work properly. Therefore, controlling and suppressing voltage fluctuations is crucial to improving the stability of the power system and the quality of power supply.

[0083] (2) Static Var Generator (SVG): It is a device that adjusts reactive power by quickly responding to system voltage changes and can effectively suppress voltage fluctuations. SVG dynamically adjusts reactive power to prevent voltage flicker and short-term voltage changes from affecting equipment. Installing SVG in a substation can provide reactive power compensation, especially when the load changes greatly, significantly improving the stability and power supply quality of the power system.

[0084] At present, there are three control strategies for static VAR generators: (1) constant voltage control mode, SVG maintains grid voltage stability by adjusting reactive power according to the set target voltage value. This control strategy is suitable for scenarios with large voltage fluctuations; (2) constant reactive current control mode, SVG maintains grid reactive power balance by adjusting reactive power according to the set reactive power value. This control strategy is suitable for scenarios with relatively stable reactive power demand; (3) hybrid control mode, which combines the advantages of constant voltage and constant reactive power control, and can provide stable voltage regulation effect under the dual conditions of voltage fluctuations and changes in reactive power demand.

[0085] Although the above methods are relatively mature, they also have disadvantages: (1) The constant voltage control mode mainly focuses on the stability of voltage and responds slowly to changes in reactive power. Therefore, when the reactive power demand changes drastically, it may not be able to adjust in time, resulting in an imbalance in the reactive power of the system. Therefore, it is necessary to continuously adjust the reactive power to maintain voltage stability, which may lead to high consumption of SVG equipment resources and reduced efficiency; (2) The constant reactive power control mode mainly focuses on the balance of reactive power and has weak regulation capabilities for voltage fluctuations. When the voltage fluctuates greatly, the voltage cannot be effectively stabilized. Therefore, only the regulation of reactive power is focused on, and the lack of comprehensive regulation capabilities for voltage changes may lead to insufficient overall system stability. (3) The hybrid control mode needs to handle the regulation of voltage and reactive power at the same time. The control algorithm is complex and difficult to implement. In addition, when the voltage and reactive power demand conflict, it is difficult to quickly find the optimal balance point, which may lead to unsatisfactory regulation effects. It can be seen that the response speed and regulation accuracy of the above technologies still have room for improvement when facing complex and changeable grid conditions.

[0086] In the embodiment of the present application, by establishing an optimization model, voltage stability and reactive power balance are comprehensively considered to achieve dual optimization regulation of voltage and reactive power, and the results of the optimization model are combined with a constant voltage control strategy to improve the overall performance of the power system.

[0087] In specific implementation, the method may include, for example: preprocessing the real-time data collected by the substation to obtain data to be analyzed; extracting features from the data to be analyzed to obtain voltage characteristic values; classifying the voltage characteristic values ​​to obtain voltage fluctuation types; performing reactive optimization adjustment and solving according to the voltage characteristic values ​​and the voltage fluctuation types to obtain predicted reactive adjustment amounts; adjusting the reactive current output of the static VAR generator according to the predicted reactive adjustment amount and the equations in the static VAR generator control strategy to achieve real-time optimized operation of the static VAR generator.

[0088] It can be seen that the method provided by the implementation of the present application obtains the predicted reactive adjustment amount through the reactive optimization regulation model, so that the reactive current output of the static VAR generator can be adjusted in combination with the static VAR generator control strategy, thereby realizing the intelligent and automatic control of SVG, reducing human intervention, improving the response speed and control accuracy of the power grid system, effectively suppressing the voltage fluctuation of the substation, improving the power supply quality of the power grid, and ensuring the stability of the power grid voltage.

[0089] To facilitate understanding of the specific implementation of the control strategy method for the substation static VAR generator provided in the embodiment of the present application, it will be described below with reference to the accompanying drawings.

[0090] It should be noted that the subject of the control strategy method for the substation static VAR generator can be the control strategy device for the substation static VAR generator provided in the embodiment of the present application, and the control strategy device for the substation static VAR generator can be carried in an electronic device or a functional module of an electronic device. The electronic device in the embodiment of the present application can be any device that can implement the control strategy method for the substation static VAR generator in the embodiment of the present application, for example, it can be an Internet of Things (IoT) device.

[0091] Figure 1 The present invention provides a flow chart of a control strategy method for a substation static VAR generator. The method can also be applied to a control strategy device for a substation static VAR generator, which can be, for example, Figure 4 The control strategy device 400 of the static VAR generator of the substation is shown. Alternatively, the control strategy device of the static VAR generator of the substation can also be integrated in Figure 5 Functional modules in the electronic device 500 are shown.

[0092] like Figure 1 As shown, the method includes the following S101 to S105:

[0093] S101: Preprocess the real-time data collected by the substation to obtain data to be analyzed.

[0094] In order to realize the real-time optimization operation of the static VAR generator, the real-time data collected by the substation is first preprocessed to obtain the data to be analyzed; the data to be analyzed is feature extracted to obtain the voltage characteristic value; the voltage characteristic value is classified to obtain the voltage fluctuation type; the reactive optimization adjustment is solved according to the voltage characteristic value and the voltage fluctuation type to obtain the predicted reactive adjustment amount; finally, according to the predicted reactive adjustment amount and the equation in the static VAR generator control strategy, the reactive current output of the static VAR generator is adjusted to realize the real-time optimization operation of the static VAR generator. Therefore, the embodiment of the present application obtains the data to be analyzed through S101 to make a pre-preparation for the subsequent acquisition of the voltage characteristic value.

[0095] As an example, S101 may include: S1011, using low-pass filtering method and high-pass filtering method to filter real-time data, where the real-time data includes parameters such as voltage, current, reactive power, active power, frequency, harmonics, etc.; S1012, using wavelet transform method to denoise the filtered data to obtain data to be analyzed.

[0096] In the above S1011, low-pass filtering and high-pass filtering are used. Low-pass filtering is used to remove high-frequency noise and retain the main components of the voltage signal; high-pass filtering is used to remove low-frequency interference and highlight the characteristics of voltage fluctuations.

[0097] In the embodiment of the present application, a Butterworth low-pass filter and a Butterworth high-pass filter may be used. The following formula (1) is the transfer function of the Butterworth low-pass filter; formula (2) is the transfer function of the Butterworth high-pass filter:

[0098]

[0099]

[0100] Wherein, H(s) represents the transfer function; s represents the complex frequency domain variable; ω0 represents the cutoff frequency; and n represents the order of the filter.

[0101] In the above S1012, the noise is removed by wavelet transform, which can effectively remove the noise in the voltage signal while retaining the main features of the signal, thereby achieving high-quality voltage fluctuation analysis.

[0102] The process of wavelet transform is wavelet decomposition to decompose the voltage signal into wavelet coefficients of different scales. Although the voltage is a continuous value, the voltage acquisition is a discrete value, so discrete wavelet transform is used to decompose the voltage signal x(t) into wavelet coefficients of multiple scales. Assuming that the original voltage signal is x(t), the wavelet function is The scaling function is φ(t), and the function of the original voltage signal is as shown in the following formula (3):

[0103]

[0104] Where x(t) represents the original voltage signal; represents the wavelet function; φ(t) represents the scaling function; Cj0,k represents the scaling coefficient; d j,k represents the detail coefficient; j0 represents an arbitrary starting scale.

[0105] After that, the wavelet coefficients are soft-thresholded to remove noise, and the processed detail coefficients can be obtained. The processed detail coefficient is shown in the following formula (4):

[0106]

[0107] in, Represents the detail coefficient after processing; d j,k represents the detail coefficient; λ represents the threshold selected according to the voltage level.

[0108] Finally, wavelet reconstruction is performed, and the processed wavelet coefficients are reconstructed back to the time domain signal through inverse wavelet transform. The time domain signal is shown in the following formula (5):

[0109]

[0110] in, represents the time domain signal after wavelet transform processing; represents the wavelet function; φ(t) represents the scaling function; represents the scale coefficient after threshold processing; represents the detail coefficient after threshold processing; j0 represents an arbitrary starting scale.

[0111] It should be noted that before preprocessing the real-time data collected by the substation, that is, before formally collecting the data, the embodiment of the present application needs to calibrate the collection equipment of the substation, specifically including: calibrating the data of the collection equipment in the substation according to the standard signal to ensure the accuracy of the data, and performing time synchronization calibration on the data of the collection equipment to ensure that the data is analyzed under the same time reference.

[0112] In this process, the accuracy of the data can be improved by filtering and denoising the real-time data collected by the substation, so as to improve the accuracy of the subsequent prediction of reactive power adjustment.

[0113] S102: Extract features from the data to be analyzed to obtain voltage feature values.

[0114] As an example, S102 may include: S1021, calculating the root mean square value of the voltage signal in the data to be analyzed to obtain the effective value of the voltage; S1022, extracting the instantaneous value of the voltage signal from the voltage signal in the data to be analyzed; S1023, using fast Fourier transform to perform spectrum analysis on the voltage signal in the data to be analyzed to extract the voltage frequency component; S1024, using short-time Fourier transform to perform time-frequency analysis on the voltage signal in the data to be analyzed to obtain the time-frequency characteristics of the voltage fluctuation.

[0115] The root mean square value (RMS) of the voltage signal calculated in S1021 can be used to evaluate the magnitude and change of the voltage. The specific method for calculating the root mean square value is shown in the following formula (6):

[0116]

[0117] Wherein, RMS represents the root mean square value (effective value); N represents the number of samples of the discrete voltage signal; Represents the time domain signal after wavelet transform processing.

[0118] The above S1022 can extract the instantaneous value of the voltage signal from the voltage signal in the data to be analyzed, which is used to analyze the instantaneous value of the voltage signal and detect rapid voltage changes, wherein the instantaneous value of the voltage signal includes a maximum value, a minimum value, etc.

[0119] The above S1023 performs spectrum analysis through fast Fourier transform (FFT) to extract voltage frequency components for analyzing the spectrum characteristics of the voltage signal and identifying voltage flicker and harmonic components. The specific process of extracting voltage frequency components is shown in the following formula (7):

[0120]

[0121] Where X(f) represents the amplitude and phase information of each frequency component f; N represents the total number of sampling points of the signal, that is, N points are sampled in one cycle; Represents the sampling value of a discrete-time signal, usually the sampling value of the original signal in the time domain; n represents the index of the discrete sampling point in time, from 0 to N-1; f represents the discrete value of frequency; j represents any scale.

[0122] The above S1024 combines the time domain and frequency domain information and uses short-time Fourier transform (STFT) to obtain the time-frequency characteristics of voltage fluctuations. The specific process is shown in the following formula (8):

[0123]

[0124] Among them, STFT represents the time domain signal The short-time Fourier transform result is a joint representation of time and frequency, which analyzes the time-frequency characteristics of the signal; represents the sampled value of the discrete-time signal, which is consistent with the first formula The same; ω (nm) represents the time window function, which is used to intercept a short period of time of the signal; m represents the center point of the window function, which is used to control the local range of the signal in time; ω represents the angular frequency of the frequency component; j represents an arbitrary scale.

[0125] In this process, the features of the data to be analyzed are extracted in different ways to obtain voltage characteristic values, so that the predicted reactive power adjustment amount can be obtained later based on the voltage characteristic values.

[0126] S103: Classify the voltage characteristic values ​​to obtain the voltage fluctuation type.

[0127] As an example, S103 may include: inputting the voltage characteristic value into a classification model to obtain the voltage fluctuation type, wherein the classification model is a trained random forest algorithm model, and the training samples of the classification model are historical voltage characteristic values ​​and corresponding historical voltage fluctuation types.

[0128] The random forest algorithm of the machine learning algorithm is used to classify the extracted voltage characteristic values ​​and identify the voltage fluctuation type. The random forest algorithm is used for classification. The random forest is an ensemble learning method composed of multiple decision trees. It can effectively handle multi-class classification problems. The training set is used for model training, and the test set is predicted. Then, the classification accuracy, precision, recall rate and other evaluation indicators are calculated to evaluate the model performance. Finally, the random forest parameters that meet the requirements are used to make random forest decisions on the extracted voltage characteristic values ​​again. Figure 2 As shown, a classification model of the random forest algorithm is constructed based on the training set, where the combiner selects the majority of classification results as the final result in the classification problem, and takes the average of multiple regression results as the final result in the regression problem.

[0129] Among them, the types of voltage fluctuations include: (1) Voltage sag refers to the voltage amplitude dropping to between 90% and 10% of the rated value in a short period of time, and the duration ranges from a few milliseconds to a few seconds. It is often caused by short circuit faults, large equipment startup or high load changes in the power system. (2) Voltage swell refers to the voltage amplitude rising to between 110% and 180% of the rated value in a short period of time, and the duration is usually short. This fluctuation is usually caused by the sudden removal of certain loads or failure of voltage regulation equipment. (3) Voltage interruption refers to the voltage amplitude dropping to near zero or completely interrupted, and the duration ranges from a few milliseconds to a few minutes. Interruptions are usually caused by short circuits, equipment failures or human operations. (4) Voltage flicker refers to the frequent changes in voltage fluctuations, causing fluctuations in the brightness of the light source. Flicker is usually caused by rapid changes in loads (such as arc furnaces or welding equipment), which can affect visual comfort and normal operation of equipment. (5) Voltage Harmonics: Due to the influence of nonlinear loads (such as power electronic equipment), higher harmonic components other than the fundamental frequency are superimposed on the voltage waveform. Harmonic distortion can cause equipment heating, increased losses, and reduced grid efficiency. (6) Voltage Fluctuation: refers to continuous, periodic, small fluctuations in voltage around the rated value. Voltage fluctuations are usually caused by periodic changes in loads. Lighter fluctuations will not cause equipment damage, but may cause flicker problems.

[0130] In this process, identifying the type of voltage fluctuation can help the subsequent regulation strategy, that is, different optimization schemes can be adopted and the optimization parameters can be adjusted according to the different types of voltage fluctuations. For example, for voltage fluctuations with higher frequencies, a faster reactive power response may be required, while slower fluctuations can be adjusted more gently. In this way, the identification of voltage fluctuation types can not only be used as input for the reactive power optimization regulation model in the future, but also improve the pertinence and response speed of the regulation scheme.

[0131] S104: Perform reactive power optimization adjustment and solution according to voltage characteristic values ​​and voltage fluctuation types to obtain predicted reactive power adjustment amount.

[0132] As an example, S104 may include: S1041, combining voltage characteristic values ​​and voltage fluctuation types with static VAR generator parameters to perform reactive optimization regulation and establish a reactive optimization regulation model; S1042, solving the reactive optimization regulation model to obtain a predicted reactive adjustment amount.

[0133] The reactive power optimization regulation model in the above S1041 is combined with the SVG auxiliary discrete capacitor / reactor group to perform reactive power optimization regulation, with voltage characteristic value and voltage fluctuation type as parameters, minimum voltage control deviation as the objective function, and upper and lower limits of node voltage amplitude and SVG adjustment range as constraints.

[0134] Among them, the objective function of the reactive power optimization regulation model is the following formula (9):

[0135]

[0136] Where J represents the voltage control deviation, x(k+i|k) represents the voltage characteristic value at the future i moments predicted based on the voltage characteristic at the k moment, x0(k+i|k) represents the known voltage characteristic value at the i moments based on the k moment, and N represents the total number of moments;

[0137] Among them, the constraints of the reactive power optimization regulation model include the following formula (10) and formula (11):

[0138] x min ≤x≤x max Formula (10)

[0139]

[0140] Where x represents the voltage magnitude vector, x max and x min Respectively represent the upper and lower limit vectors of the voltage amplitude, Q 1max and Q 1min They represent the upper and lower limits of the reactive output of the static VAR generator respectively, Q1(k|k) represents the predicted value of the reactive power at time k, ΔQ1(k+i|k) represents the reactive adjustment amount of the static VAR generator at the i-th moment in the future based on time k; N represents the total number of moments.

[0141] The upper and lower limit constraints in the constraint conditions indicate that within the reactive power adjustment range, the voltage stability requirement of the power grid is met while the output capacity of the SVG is not exceeded.

[0142] In this process, according to the reactive power optimization regulation model, the reactive power adjustment amount of the optimized SVG at the i-th moment in the future can be obtained according to the voltage characteristic values ​​at the i-th moment in the future, that is, the predicted reactive power adjustment amount.

[0143] S105: According to the predicted reactive adjustment amount and the equation in the static VAR generator control strategy, the reactive current output of the static VAR generator is adjusted to achieve real-time optimized operation of the static VAR generator.

[0144] As an example, S105 may include: S1051, controlling the voltage fluctuation within a set range through the voltage equation of the static VAR generator to achieve the static VAR generator in a constant voltage mode; S1052, substituting the predicted reactive adjustment amount into the control equation of the constant voltage mode in the static VAR generator control strategy to obtain the output current of the static VAR generator after adjustment; S1053, adjusting the reactive current output of the static VAR generator in real time according to the output current of the static VAR generator after adjustment.

[0145] In the above S1051, a mathematical model of SVG is constructed, and a voltage equation of SVG is obtained according to physical parameters. Furthermore, a variable equation in a simplified dq coordinate system (transformation from rectangular coordinate system to polar coordinate system) is obtained by Parker transformation, as shown in the following formula (12):

[0146]

[0147] Among them, L g Represents the equivalent inductance of SVG; R g is the equivalent resistance of SVG; ω represents the grid angular frequency; i g Indicates SVG output current; u g Indicates SVG output voltage; u c is the grid-side voltage, and the subscripts d and q represent the d-axis and q-axis components after Park transformation, respectively.

[0148] The parameters in the above formula (12) are parameters obtained using a voltage transformer or a current transformer.

[0149] That is, the voltage fluctuation is controlled within a set range through the voltage equation of the static VAR generator, so that the static VAR generator is in a constant voltage mode, so as to subsequently utilize the control equation of the constant voltage mode in the static VAR generator control strategy.

[0150] The control equations of the constant voltage mode in the static VAR generator control strategy in S1052 above can be shown as the following formulas (13) and (14):

[0151]

[0152]

[0153] Among them, i' d and i' q Indicates the output current of SVG after setting; k p1 and k i1represents the proportional and integral gain of the d-axis current PI regulator; kp3 and ki3 represent the proportional and integral gain of the q-axis current PI regulator; kp2 and ki2 represent the proportional and integral gain of the SVG reactive power PI regulator; Vdcref and Vref are the DC voltage reference value and grid-connected point voltage reference value of SVG respectively; kp4 and ki4 are the proportional and integral gain of the SVG voltage PI regulator respectively; Vdc and V are the DC voltage and grid-connected point voltage of SVG respectively.

[0154] Therefore, the reactive current output of the static VAR generator is adjusted in real time according to the output current of the static VAR generator after setting. In this process, the reactive current output of the static VAR generator is adjusted according to the predicted reactive adjustment amount and the equation in the static VAR generator control strategy. Based on the predicted reactive adjustment amount and the direct current control method with real-time response, the constant voltage control of SVG is realized, thereby realizing intelligent and automatic control, reducing manual intervention, and improving the response speed and control accuracy of the power grid voltage system.

[0155] It can be seen that the embodiment of the present application can obtain the predicted reactive adjustment amount of SVG according to the voltage characteristic value by establishing a reactive optimization and regulation model, that is, the reactive compensation strategy is dynamically adjusted by using an advanced optimization algorithm, and after the SVG is set to a constant voltage control mode, the predicted reactive adjustment amount can be combined with the equation under the constant voltage control mode in the static VAR generator control strategy, and the reactive current output of the static VAR generator can be adjusted, that is, the SVG can automatically perform reactive compensation adjustment to ensure the intelligent control technology of stable grid voltage.

[0156] In order to make the method provided in the embodiment of the present application clearer and easier to understand, Figure 3 A specific example of this method is described.

[0157] like Figure 3 As shown, the implementation may include:

[0158] S301: Performing data calibration on data collection equipment in the substation according to standard signals, and performing time synchronization calibration on the data of the data collection equipment.

[0159] After the data is transmitted to the server through the acquisition device, the data acquisition device in the substation is calibrated according to the known standard signal to ensure the accuracy of the real-time data collected. Since there are multiple acquisition devices in the substation, the data of multiple acquisition devices need to be time-synchronized and calibrated to ensure that the data is subsequently analyzed under the same time reference, making the subsequent voltage fluctuation control more accurate.

[0160] S302: Preprocess the real-time data collected by the substation to obtain data to be analyzed.

[0161] The preprocessing process in the embodiment of the present application includes filtering and denoising, wherein filtering adopts two methods, low-pass filtering and high-pass filtering, which can not only remove high-frequency noise with the help of low-pass filtering, retain the main components of the voltage signal, but also remove low-frequency interference with high-pass filtering, highlighting the characteristics of voltage fluctuations. Denoising is to remove noise through wavelet transform, which can effectively remove noise in the voltage signal while retaining the main characteristics of the signal, thereby achieving high-quality voltage fluctuation analysis.

[0162] It should be noted that the filtering process method and the denoising process method in the embodiments of the present application are as shown in the above embodiments and will not be repeated here.

[0163] S303: Calculate the root mean square value of the voltage signal in the data to be analyzed to obtain the effective value of the voltage.

[0164] In order to evaluate the magnitude and change of the voltage, the embodiment of the present application needs to calculate the root mean square value of the voltage signal in the data to be analyzed to obtain the effective value of the voltage. The specific calculation method is shown in the above embodiment and will not be repeated here.

[0165] S304: extracting the instantaneous value of the voltage signal from the voltage signal in the data to be analyzed.

[0166] In order to detect rapid voltage changes, the instantaneous value of the voltage signal needs to be analyzed. Therefore, the embodiment of the present application needs to extract the instantaneous value of the voltage signal from the voltage signal in the data to be analyzed, where the instantaneous value of the voltage signal includes a maximum value, a minimum value, etc.

[0167] S305: Perform spectrum analysis on the voltage signal in the data to be analyzed by using fast Fourier transform to extract the voltage frequency component.

[0168] In order to analyze the spectral characteristics of the voltage signal and identify voltage flicker and harmonic components, the embodiment of the present application uses fast Fourier transform to perform spectral analysis on the voltage signal in the data to be analyzed and extract the voltage frequency component. The specific extraction formula is shown in the above embodiment and will not be repeated here.

[0169] S306: Perform time-frequency analysis on the voltage signal in the data to be analyzed by using short-time Fourier transform to obtain time-frequency characteristics of voltage fluctuation.

[0170] In order to obtain the time-frequency characteristics of voltage fluctuations, the embodiment of the present application uses short-time Fourier transform to perform time-frequency analysis on the voltage signal in the data to be analyzed to obtain the time-frequency characteristics of voltage fluctuations. The specific analysis formula is shown in the above embodiment and will not be repeated here.

[0171] S307: Input the voltage characteristic value into a classification model to obtain a voltage fluctuation type, wherein the classification model is a trained random forest algorithm model, and the training samples of the classification model are historical voltage characteristic values ​​and corresponding historical voltage fluctuation types.

[0172] Based on the various eigenvalues ​​obtained above, the embodiment of the present application adopts a random forest algorithm model for classification, and uses random forest parameters that meet the requirements to perform random forest decisions on each eigenvalue, so as to obtain the voltage fluctuation type that helps the regulation strategy.

[0173] It should be noted that not only the random forest algorithm model can be used for classification, but also other types of classification models can be used.

[0174] S308: Combining the voltage characteristic value and the voltage fluctuation type with the static VAR generator parameters to perform reactive power optimization regulation and establish a reactive power optimization regulation model.

[0175] After the voltage characteristic value and the voltage fluctuation type are obtained, the voltage characteristic value is used as a parameter, and the voltage fluctuation type and the auxiliary discrete capacitor / reactor group in the static VAR generator are combined to perform reactive optimization regulation, wherein the voltage control deviation is minimized as the objective function, and the node voltage amplitude upper and lower limits and the adjustment range of SVG are used as constraints to establish a reactive optimization regulation model. The specific objective function and constraints are shown in the above embodiment and are not described in detail here.

[0176] S309: Solve the reactive power optimization regulation model to obtain the predicted reactive power adjustment amount.

[0177] In the embodiment of the present application, after solving the reactive power optimization regulation model, the optimization result obtained is the reactive power adjustment amount of the SVG at the i-th moment in the future, that is, the predicted reactive power adjustment amount.

[0178] S310: Controlling voltage fluctuation within a set range through a voltage equation of the static VAR generator, so as to achieve a constant voltage mode of the static VAR generator.

[0179] In the embodiment of the present application, the constant voltage mode in the static VAR generator control strategy is adopted for control. Therefore, it is necessary to control the voltage fluctuation within a set range through the voltage equation of the static VAR generator to achieve the static VAR generator in the constant voltage mode. The specific voltage equation of the static VAR generator is shown in the above embodiment and will not be repeated here.

[0180] S311: Substitute the predicted reactive power adjustment amount into the control equation of the constant voltage mode in the static VAR generator control strategy to obtain the output current of the static VAR generator after adjustment.

[0181] When the STATCOM is in constant voltage mode, the predicted reactive adjustment amount can be substituted into the control equation of the constant voltage mode in the STATCOM control strategy to obtain the output current of the STATCOM after setting. The specific control equation of the constant voltage mode is shown in the above embodiment and will not be described in detail here.

[0182] S312: According to the output current of the static VAR generator after setting, the reactive current output of the static VAR generator is adjusted in real time.

[0183] Finally, according to the output current of the static VAR generator after setting, the reactive current output of the static VAR generator can be adjusted in real time, and reactive compensation adjustment can be automatically performed to ensure the stability of the grid voltage and the power supply quality.

[0184] This embodiment provides a control strategy method for a static VAR generator in a substation, including: (1) data preprocessing and real-time processing to ensure data quality and response speed. Data preprocessing such as filtering, denoising and calibration can effectively improve data accuracy, making voltage fluctuation control more accurate. (2) The reactive power optimization regulation model is combined with the reactive power compensation strategy, which is scientific and effective. By comprehensively considering the optimization model of voltage control deviation, node voltage amplitude upper and lower limits and SVG adjustment range, and using advanced optimization algorithms to dynamically adjust the reactive power compensation strategy, the scientificity and effectiveness of the optimization results are ensured, and a scientific and effective reactive power compensation solution is provided, which can smooth voltage fluctuations and improve grid stability and power supply quality. (3) Intelligent and automated control reduces the complexity of operation and maintenance. Based on the output results of the optimization model, combined with the direct current control method of real-time response, the intelligent and automated control of SVG is realized. This reduces manual intervention, improves the system response speed and control accuracy, reduces the complexity of operation and maintenance, improves the intelligence level of the system, and ensures the stability and reliability of the grid voltage.

[0185] See also Figure 4 The present application embodiment provides a control strategy device 400 for a static VAR generator in a substation, the device comprising:

[0186] The processing unit 401 is used to pre-process the real-time data collected by the substation to obtain data to be analyzed;

[0187] An extraction unit 402 is used to extract features from the data to be analyzed and obtain voltage feature values;

[0188] A classification unit 403 is used to classify the voltage characteristic value to obtain the voltage fluctuation type;

[0189] An obtaining unit 404 is used to perform reactive power optimization adjustment and solution according to the voltage characteristic value and the voltage fluctuation type to obtain a predicted reactive power adjustment amount;

[0190] The adjustment unit 405 is used to adjust the reactive current output of the static VAR generator according to the predicted reactive adjustment amount and the equation in the static VAR generator control strategy to achieve real-time optimized operation of the static VAR generator.

[0191] Optionally, the processing unit 401 is specifically configured to:

[0192] Use low-pass filtering method and high-pass filtering method to filter the real-time data;

[0193] The wavelet transform method is used to denoise the filtered data to obtain the data to be analyzed.

[0194] Optionally, the voltage characteristic value includes a voltage effective value, a voltage signal instantaneous value, a voltage frequency component, and a time-frequency characteristic of a voltage fluctuation, and the extraction unit 402 is specifically used for:

[0195] Calculate the root mean square value of the voltage signal in the data to be analyzed to obtain the effective value of the voltage;

[0196] Extracting the instantaneous value of the voltage signal from the voltage signal in the data to be analyzed;

[0197] Fast Fourier transform is used to perform spectrum analysis on the voltage signal in the data to be analyzed and extract the voltage frequency component;

[0198] Short-time Fourier transform is used to perform time-frequency analysis on the voltage signal in the data to be analyzed to obtain the time-frequency characteristics of voltage fluctuation.

[0199] Optionally, the classification unit 403 is specifically used for:

[0200] The voltage characteristic value is input into the classification model to obtain the voltage fluctuation type. The classification model is a trained random forest algorithm model, and the training samples of the classification model are historical voltage characteristic values ​​and corresponding historical voltage fluctuation types.

[0201] Optionally, the obtaining unit 404 is specifically configured to:

[0202] The voltage characteristic value and voltage fluctuation type are combined with the static VAR generator parameters to perform reactive optimization regulation and establish a reactive optimization regulation model, which specifically includes the following formulas:

[0203]

[0204] Where J represents the voltage control deviation, x(k+i|k) represents the voltage characteristic value at the future i moments predicted based on the voltage characteristic at the k moment, x0(k+i|k) represents the known voltage characteristic value at the i moments based on the k moment, and N represents the total number of moments;

[0205] The above formula represents that the voltage control deviation is minimum, wherein the constraint conditions of the reactive power optimization regulation model include the following formula:

[0206] xmin≤x≤xmax

[0207]

[0208] Where x represents the voltage magnitude vector, x max and x min Respectively represent the upper and lower limit vectors of the voltage amplitude, Q 1max and Q 1min They represent the upper and lower limits of the reactive power output of the static VAR generator, respectively; Q1(k|k) represents the predicted value of reactive power at time k; ΔQ1(k+i|k) represents the reactive adjustment amount of the static VAR generator at the i-th moment in the future based on time k; N represents the total number of moments;

[0209] The reactive power optimization regulation model is solved to obtain the predicted reactive power adjustment amount.

[0210] Optionally, the adjusting unit 405 is specifically configured to:

[0211] The voltage fluctuation is controlled within a set range through the voltage equation of the static VAR generator, so as to realize that the static VAR generator is in a constant voltage mode;

[0212] Substitute the predicted reactive power adjustment into the control equation of the constant voltage mode in the static VAR generator control strategy to obtain the output current of the static VAR generator after setting;

[0213] According to the output current of the static VAR generator after setting, the reactive current output of the static VAR generator is adjusted in real time.

[0214] Optionally, the device 400 further includes:

[0215] The calibration unit is used to calibrate the data of the acquisition equipment in the substation according to the standard signal, and to perform time synchronization calibration on the data of the acquisition equipment.

[0216] It should be noted that the specific implementation method and effect of the control strategy device 400 of the substation static VAR generator can be referred to the above Figure 1 or Figure 3 The relevant descriptions in the provided methods will not be repeated here.

[0217] The present application embodiment also provides an electronic device 500, such as Figure 5 As shown, the device 500 includes a memory 501 and a processor 502:

[0218] The memory 501 is used to store computer programs;

[0219] The processor 502 is used to execute the above Figure 1 or Figure 3 The method provided.

[0220] In addition, the present application also provides a computer-readable storage medium, the computer-readable storage medium is used to store a computer program, and the computer program is used to execute Figure 1 or Figure 3 The method provided.

[0221] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0222] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is only schematic, in which the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the goals of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0223] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A control strategy method for a static VAR generator in a substation, characterized in that: The method comprises: Pre-process the real-time data collected by the substation to obtain the data to be analyzed; Extracting features from the data to be analyzed to obtain voltage feature values; Classifying the voltage characteristic values ​​to obtain voltage fluctuation types; Perform reactive power optimization adjustment and solution according to the voltage characteristic value and the voltage fluctuation type to obtain a predicted reactive power adjustment amount; According to the predicted reactive adjustment amount and the equation in the static VAR generator control strategy, the reactive current output of the static VAR generator is adjusted to achieve real-time optimized operation of the static VAR generator.

2. The method according to claim 1, characterized in that The real-time data collected from the substation is preprocessed to obtain data to be analyzed, including: Using a low-pass filtering method and a high-pass filtering method to filter the real-time data; The wavelet transform method is used to perform denoising on the filtered data to obtain the data to be analyzed.

3. The method according to claim 1, characterized in that The voltage characteristic value includes the voltage effective value, the instantaneous value of the voltage signal, the voltage frequency component and the time-frequency characteristics of the voltage fluctuation. The feature extraction of the data to be analyzed to obtain the voltage characteristic value includes: Calculating the root mean square value of the voltage signal in the data to be analyzed to obtain the voltage effective value; Extracting the instantaneous value of the voltage signal from the voltage signal in the data to be analyzed; Performing spectrum analysis on the voltage signal in the data to be analyzed by using fast Fourier transform to extract the voltage frequency component; Short-time Fourier transform is used to perform time-frequency analysis on the voltage signal in the data to be analyzed to obtain the time-frequency characteristics of the voltage fluctuation.

4. The method according to claim 1, characterized in that: The classifying the voltage characteristic values ​​to obtain the voltage fluctuation type includes: The voltage characteristic value is input into a classification model to obtain the voltage fluctuation type. The classification model is a trained random forest algorithm model, and the training samples of the classification model are historical voltage characteristic values ​​and corresponding historical voltage fluctuation types.

5. The method according to claim 1, characterized in that The performing reactive power optimization regulation and solving according to the voltage characteristic value and the voltage fluctuation type to obtain the predicted reactive power adjustment amount includes: The voltage characteristic value and the voltage fluctuation type are combined with the static VAR generator parameters to perform reactive optimization regulation, and a reactive optimization regulation model is established, which specifically includes the following formula: Where J represents the voltage control deviation, x(k+i|k) represents the voltage characteristic value at the future i moments predicted based on the voltage characteristic at the k moment, x0(k+i|k) represents the known voltage characteristic value at the i moments based on the k moment, and N represents the total number of moments; The above formula represents that the voltage control deviation is minimum, wherein the constraint conditions of the reactive power optimization regulation model include the following formula: xmin≤x≤xmax Where x represents the voltage magnitude vector, x max and x min Respectively represent the upper and lower limit vectors of the voltage amplitude, Q 1max and Q 1min They represent the upper and lower limits of the reactive power output of the static VAR generator, respectively; Q1(k|k) represents the predicted value of reactive power at time k; ΔQ1(k+i|k) represents the reactive adjustment amount of the static VAR generator at the i-th moment in the future based on time k; N represents the total number of moments; The reactive power optimization regulation model is solved to obtain the predicted reactive power adjustment amount.

6. The method according to claim 1, characterized in that The step of adjusting the reactive current output of the static VAR generator according to the predicted reactive adjustment amount and an equation in the static VAR generator control strategy comprises: Controlling voltage fluctuation within a set range through a voltage equation of the static VAR generator, so as to achieve a constant voltage mode of the static VAR generator; Substituting the predicted reactive power adjustment amount into the control equation of the constant voltage mode in the static VAR generator control strategy to obtain the output current of the static VAR generator after setting; According to the output current of the static VAR generator after setting, the reactive current output of the static VAR generator is adjusted in real time.

7. The method according to claim 1, characterized in that Before the real-time data collected from the substation is preprocessed, the method further includes: The data collection equipment in the substation is calibrated according to the standard signal, and the data of the collection equipment is calibrated for time synchronization.

8. A control strategy device for a static VAR generator in a substation, characterized in that: The device comprises: A processing unit, used to pre-process the real-time data collected by the substation to obtain data to be analyzed; An extraction unit, used for performing feature extraction on the data to be analyzed to obtain voltage feature values; A classification unit, used for classifying the voltage characteristic value to obtain a voltage fluctuation type; An obtaining unit, configured to perform reactive power optimization adjustment and solution according to the voltage characteristic value and the voltage fluctuation type, and obtain a predicted reactive power adjustment amount; The adjustment unit is used to adjust the reactive current output of the static VAR generator according to the predicted reactive adjustment amount and the equation in the static VAR generator control strategy to achieve real-time optimized operation of the static VAR generator.

9. An electronic device, characterized in that: The device includes a memory and a processor, and the processor is used to execute a program stored in the memory to run the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method according to any one of claims 1 to 7.

Images