Stability control method and device for electric energy quality control system

Abstract

The invention discloses a stability control method and device for an electric energy quality control system. The method is characterized by comprising the following steps: extracting characteristic parameters of acquired three-phase data of a power grid, and determining system state characteristic data; performing system compensation parameter estimation on the power quality compensation system according to the system state characteristic data and the power grid three-phase data, and determining system compensation parameter estimation data; determining an optimal control parameter according to the system state characteristic data and the system compensation parameter estimation data; performing system control prediction on the power quality compensation system according to the system compensation parameter estimation data, and determining a real-time control quantity of the power quality compensation system; performing control operation on the electric energy quality compensation system according to the real-time control quantity, and determining a control operation result; and optimizing the optimal control parameter based on the control operation result to obtain a target control parameter, and determining a target compensation current instruction according to the target control parameter. Efficient control is achieved, and economical efficiency, energy efficiency and reliability are met.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a stability control method and device for a power quality management system. Background Art

[0002] With the continuous development of social economy and power electronic devices, more and more non-resistive loads have appeared in the distribution network, which has brought great challenges to the safe and reliable operation of the power system and the power quality provided by the power grid. Therefore, reactive power compensation has become increasingly important in the power system. At the same time, in order to better solve the power quality problems of the power system such as low power factor, large harmonics, and large negative sequence components, a power quality compensation system must be adopted to effectively manage the power quality problems of the traction power supply network. The static var generator (SVG) is a reactive compensation device with strong dynamic compensation performance. The current output on the AC side can quickly track the command current; the fixed capacitor (FC) belongs to a passive filter, which can effectively suppress the integer harmonics in the system and compensate for the fundamental reactive power. The use of FC and SVG for joint compensation can reduce the SVG capacity and improve the system economy. However, when the two are used in combination, the control of both parties will conflict, resulting in instability of the shampoo cream, and the control methods of both need to be optimized. Summary of the invention

[0003] The present invention provides a stability control method and device for a power quality management system to solve the technical problem of system instability caused by joint compensation of a static VAR generator and a fixed capacitor.

[0004] According to one aspect of the present invention, there is provided a stability control method for a power quality management system, comprising:

[0005] Collecting three-phase data of the power grid of the power quality compensation system; extracting characteristic parameters based on the three-phase data of the power grid to determine the system state characteristic data; wherein the three-phase data of the power grid includes instantaneous three-phase voltage and instantaneous three-phase current,

[0006] Estimating system compensation parameters of the power quality compensation system according to the system state characteristic data and the three-phase data of the power grid, and determining system compensation parameter estimation data;

[0007] Determining the optimal control parameters of the power quality compensation system according to the system state characteristic data and the system compensation parameter estimation data;

[0008] Performing system control prediction on the power quality compensation system according to the system compensation parameter estimation data to determine the real-time control amount of the power quality compensation system;

[0009] Performing a control operation on the power quality compensation system according to the real-time control amount, and determining a control operation result;

[0010] The optimal control parameter is optimized based on the control operation result to obtain a target control parameter, and a target compensation current instruction is determined according to the target control parameter.

[0011] In an embodiment of the present invention, the optimizing the optimal control parameter based on the control operation result to obtain a target control parameter, and determining a target compensation current instruction according to the target control parameter includes:

[0012] Calculating a comprehensive performance index of the power quality compensation system according to the system state characteristic data and the control operation result, and determining system performance evaluation data corresponding to the power quality compensation system;

[0013] Constructing a performance prediction model based on the system performance evaluation data to obtain a performance prediction function;

[0014] The optimal control parameters are optimized by applying a performance prediction function through a Bayesian optimization algorithm to obtain target control parameters, and a target compensation current instruction is determined according to the target control parameters.

[0015] In an embodiment of the present invention, the optimal control parameter is optimized by applying a performance prediction function through a Bayesian optimization algorithm to obtain a target control parameter, and a target compensation current instruction is determined according to the target control parameter, including:

[0016] Defining upper and lower bounds of the control parameter search space, setting a reasonable variation range for each parameter in the control parameter search space, and normalizing each parameter to obtain a standard control parameter search space;

[0017] constructing a performance data set according to the standard control parameter search space and the performance prediction function;

[0018] Initializing a preset first proxy model according to the performance data set to obtain a second proxy model;

[0019] The target parameter point is determined by searching for the maximum value in the standard control parameter search space through a preset expected improvement function;

[0020] Performing performance prediction on the target parameter point according to the performance prediction function, determining target performance data, updating the target performance data to the performance data set, and determining an updated performance data set;

[0021] Optimizing and updating the second proxy model according to the updated performance data set to determine a target proxy model;

[0022] In a case where the target proxy model meets a preset convergence condition, the target control parameter is obtained according to the performance data set, and the target compensation current instruction is determined according to the target control parameter.

[0023] In the embodiment of the present invention, the collecting of three-phase data of the power grid of the power quality compensation system; extracting characteristic parameters according to the three-phase data of the power grid to determine the system state characteristic data includes:

[0024] Collecting three-phase data of the power grid of the power quality compensation system to obtain original adopted data;

[0025] Performing wavelet threshold denoising processing on the original adopted data to obtain three-phase data of the power grid;

[0026] Converting the three-phase data of the power grid into a two-phase orthogonal coordinate system to obtain converted three-phase data;

[0027] Performing parameter estimation on the converted three-phase data to obtain a signal parameter estimation result;

[0028] Constructing an analytical expression of the signal according to the signal parameter estimation result to obtain an analytical expression of the signal;

[0029] Perform calculations based on the signal analytical expression to determine system power data;

[0030] Performing time-frequency analysis on the system power data to obtain power fluctuation characteristic data, extracting key characteristic parameters from the power fluctuation characteristic data to obtain system state characteristic data.

[0031] In an embodiment of the present invention, estimating the system compensation parameters of the power quality compensation system according to the system state characteristic data and the three-phase data of the power grid to determine the system compensation parameter estimation data includes:

[0032] Based on the system state characteristic data, a nonlinear state space model of the power quality compensation system is constructed to obtain a system dynamic equation;

[0033] By using the unscented Kalman filter algorithm, state estimation and parameter identification are performed according to the system dynamic equation and the real-time measurement data of the power quality compensation system to obtain the estimated value of the reactive generator parameter;

[0034] Estimation is performed based on the converted three-phase data by using an adaptive forgetting factor and the least square method to determine an estimated value of a fixed capacitor parameter;

[0035] The system compensation parameter estimation data is determined according to the reactive generator parameter estimation value and the fixed capacitor parameter estimation value.

[0036] In an embodiment of the present invention, determining the optimal control parameters of the power quality compensation system according to the system state characteristic data and the system compensation parameter estimation data includes:

[0037] Constructing a multi-objective optimization function and a first constraint condition using system state characteristic data and system parameter estimation data;

[0038] Solving the multi-objective optimization function and the constraint conditions by a multi-objective differential evolution algorithm to determine the non-dominated solution;

[0039] A fuzzy decision method is applied to the non-dominated solution set to select the best compensation strategy and obtain the optimal control parameters.

[0040] In an embodiment of the present invention, the method of performing system control prediction on the power quality compensation system according to the system compensation parameter estimation data to determine the real-time control amount of the power quality compensation system includes:

[0041] Constructing a discrete time prediction model based on the system parameter estimation data and determining a system state prediction equation;

[0042] According to the system state prediction equation, a rolling horizon optimization problem is constructed to obtain a target optimization function and a second constraint condition;

[0043] Solving the objective optimization function and the second constraint condition by a sequential quadratic programming algorithm to determine an optimal control sequence;

[0044] Feedforward control and feedback correction are performed on the optimal control sequence to determine the real-time control amount.

[0045] According to another aspect of the present invention, there is provided a stability control device for a power quality management system, comprising:

[0046] The system data acquisition module is used to collect the three-phase data of the power grid of the power quality compensation system; extract characteristic parameters based on the three-phase data of the power grid to determine the system state characteristic data; wherein the three-phase data of the power grid includes instantaneous three-phase voltage and instantaneous three-phase current,

[0047] A system parameter estimation module, used to estimate the system compensation parameters of the power quality compensation system according to the system state characteristic data and the three-phase data of the power grid, and determine the system compensation parameter estimation data;

[0048] An optimal operating parameter calculation module, used to determine the optimal control parameters of the power quality compensation system according to the system state characteristic data and the system compensation parameter estimation data;

[0049] A system control calculation module, used to perform system control prediction on the power quality compensation system according to the system compensation parameter estimation data, and determine the real-time control amount of the power quality compensation system;

[0050] A system control module, used to perform a control operation on the power quality compensation system according to the real-time control quantity and determine a control operation result;

[0051] The compensation current calculation module is used to optimize the optimal control parameter based on the control operation result to obtain a target control parameter, and determine a target compensation current instruction according to the target control parameter.

[0052] In an embodiment of the present invention, the compensation current calculation module includes:

[0053] A system performance evaluation unit, configured to calculate a comprehensive performance index of the power quality compensation system according to the system state characteristic data and the control operation result, and determine system performance evaluation data corresponding to the power quality compensation system;

[0054] A performance prediction function building unit, used to build a performance prediction model according to the system performance evaluation data to obtain a performance prediction function;

[0055] The instruction calculation unit is used to optimize the optimal control parameters by applying the performance prediction function through the Bayesian optimization algorithm to obtain the target control parameters, and determine the target compensation current instruction according to the target control parameters.

[0056] In an embodiment of the present invention, the instruction calculation unit includes:

[0057] A parameter calculation subunit is used to define the upper and lower bounds of the control parameter search space, set a reasonable variation range of each parameter in the control parameter search space, and perform normalization processing on each parameter to obtain a standard control parameter search space;

[0058] A data set calculation subunit, used for constructing a performance data set according to the standard control parameter search space and the performance prediction function;

[0059] An agent model updating subunit, configured to initialize a preset first agent model according to the performance data set to obtain a second agent model;

[0060] A function calculation subunit, used to search for a maximum value in the standard control parameter search space through a preset expected improvement function, and determine a target parameter point;

[0061] A performance prediction subunit, configured to perform performance prediction on the target parameter point according to the performance prediction function, determine target performance data, update the target performance data to the performance data set, and determine an updated performance data set;

[0062] A proxy model optimization subunit, configured to optimize and update the second proxy model according to the updated performance data set, and determine a target proxy model;

[0063] The compensation current instruction calculation subunit is used to obtain the target control parameter according to the performance data set when the target proxy model meets the preset convergence condition, and determine the target compensation current instruction according to the target control parameter.

[0064] In the embodiment of the present invention, the system data acquisition module includes:

[0065] A collection unit, used for collecting three-phase data of the power grid of the power quality compensation system to obtain original adopted data;

[0066] A denoising unit, used for performing wavelet threshold denoising processing on the original adopted data to obtain three-phase data of the power grid;

[0067] A power grid three-phase calculation unit, used for converting the power grid three-phase data into a two-phase orthogonal coordinate system to obtain converted three-phase data;

[0068] A signal parameter estimation unit, used for performing parameter estimation on the converted three-phase data to obtain a signal parameter estimation result;

[0069] A signal analysis unit, used for constructing an analytical expression of the signal according to the signal parameter estimation result to obtain a signal analytical expression;

[0070] A system power calculation unit, used to perform calculations according to the signal analytical expression to determine system power data;

[0071] The characteristic data extraction unit is used to perform time-frequency analysis on the system power data to obtain power fluctuation characteristic data, extract key characteristic parameters from the power fluctuation characteristic data, and obtain system state characteristic data.

[0072] In an embodiment of the present invention, the system parameter estimation module includes:

[0073] A system equation building unit, used to build a nonlinear state space model of the power quality compensation system based on system state characteristic data to obtain a system dynamic equation;

[0074] An unscented Kalman filter calculation unit, used to perform state estimation and parameter identification according to the system dynamic equation and the real-time measurement data of the power quality compensation system through the unscented Kalman filter algorithm to obtain the estimated value of the reactive generator parameter;

[0075] A least squares method recursive unit, used to estimate according to the converted three-phase data by using an adaptive forgetting factor and the least squares method to determine an estimated value of a fixed capacitor parameter;

[0076] A data calculation unit is used to determine the system compensation parameter estimation data according to the reactive generator parameter estimation value and the fixed capacitor parameter estimation value.

[0077] In an embodiment of the present invention, the optimal working parameter calculation module includes:

[0078] An optimization function construction unit, used to construct a multi-objective optimization function and a first constraint condition from system state characteristic data and system parameter estimation data;

[0079] A solving unit, used for solving the multi-objective optimization function and the constraint conditions by using a multi-objective differential evolution algorithm to determine the non-dominated solution;

[0080] The control parameter calculation unit is used to apply a fuzzy decision method to the non-dominated solution set to select the best compensation strategy to obtain the optimal control parameters.

[0081] In an embodiment of the present invention, the system control module includes:

[0082] A system state prediction unit, used to construct a discrete time prediction model according to the system parameter estimation data and determine a system state prediction equation;

[0083] A system optimization unit, used for constructing a rolling horizon optimization problem according to the system state prediction equation to obtain a target optimization function and a second constraint condition;

[0084] An optimal control sequence solving unit, used for solving the objective optimization function and the second constraint condition by a sequential quadratic programming algorithm to determine an optimal control sequence;

[0085] A real-time control unit is used to perform feedforward control and feedback correction on the optimal control sequence to determine the real-time control amount.

[0086] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0087] at least one processor; and

[0088] a memory communicatively connected to the at least one processor; wherein,

[0089] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the stability control method for the power quality management system described in any embodiment of the present invention.

[0090] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the stability control method for a power quality management system described in any embodiment of the present invention when executed.

[0091] The technical solution of the embodiment of the present invention collects the three-phase data of the power grid of the power quality compensation system; extracts characteristic parameters based on the three-phase data of the power grid to determine the system state characteristic data, which can be used as the basis for optimizing the dispatch of the power system and improve the economy of the power system; estimates the system compensation parameters of the power quality compensation system based on the system state characteristic data and the three-phase data of the power grid to determine the system compensation parameter estimation data, and based on the system compensation parameter estimation data, the reactive power of the power system can be effectively controlled to improve the stability of the power system; determines the optimal control parameters of the power quality compensation system based on the system state characteristic data and the system compensation parameter estimation data, and the stability and operation efficiency of the power system can be improved through the optimal control parameters. rate, and can effectively control the cost of the power system and improve economic efficiency; perform system control prediction on the power quality compensation system according to the system compensation parameter estimation data, determine the real-time control quantity of the power quality compensation system, perform control operations on the power quality compensation system according to the real-time control quantity, determine the control operation results, perform control operations based on the real-time control quantity, thereby achieving rapid control response of the power system and improving power quality; optimize the optimal control parameters based on the control operation results to obtain target control parameters, determine the target compensation current instructions according to the target control parameters, and through the precise control of the target compensation current, effectively improve the response efficiency of the power system, improve the quality of electric energy, and enhance stability and economic benefits. The technical problem of system instability caused by the joint compensation of static VAR generators and fixed capacitors is solved, and efficient control is achieved, meeting the requirements of economy, energy efficiency and reliability.

[0092] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0094] Figure 1 A flow chart of a stability control method for a power quality management system is provided for an embodiment of the present invention;

[0095] Figure 2 A flowchart of another stability control method for a power quality management system provided by an embodiment of the present invention;

[0096] Figure 3 A schematic diagram of a process control system for power quality management provided by an embodiment of the present invention;

[0097] Figure 4 A schematic diagram of the structure of a stability control device for a power quality management system provided by an embodiment of the present invention;

[0098] Figure 5 A schematic structural diagram of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0099] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 without creative work should fall within the scope of protection of the present invention.

[0100] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0101] Figure 1A flow chart of a stability control method for a power quality management system is provided for an embodiment of the present invention. This embodiment is applicable to the situation where precise control is performed on the joint compensation of a static VAR generator and a fixed capacitor in a power quality compensation system. The method can be executed by a stability control device for a power quality management system. The stability control device for a power quality management system can be implemented in the form of hardware and / or software. The stability control device for a power quality management system can be configured in an electronic device. Figure 1 As shown, the method includes:

[0102] S110, collecting three-phase data of the power grid of the power quality compensation system; extracting characteristic parameters according to the three-phase data of the power grid, and determining system state characteristic data.

[0103] Among them, the power quality compensation system is a compensation system composed of a static VAR generator and a fixed capacitor. The power quality compensation system can effectively control the power quality of the traction power supply network.

[0104] The three-phase data of the power grid may be the instantaneous three-phase voltage and instantaneous three-phase current of the power grid corresponding to the power quality compensation system.

[0105] The system state characteristic data may be key characteristic parameters of the power quality compensation system, and may include active power, reactive power, total harmonic distortion rate, and power fluctuation index.

[0106] Optionally, when collecting the three-phase data of the power grid of the power quality compensation system, the three-phase data of the power grid is obtained by using a high-speed synchronous sampling technology. The high-speed synchronous sampling technology can significantly improve the collection accuracy.

[0107] Specifically, for the power quality compensation system, the three-phase data of the power grid of the power quality compensation system is collected, and characteristic parameters of the three-phase data of the power grid are extracted to determine the system state characteristic data of the power quality compensation system.

[0108] Optionally, in another optional embodiment of the present invention, the collecting three-phase data of the power grid of the power quality compensation system; extracting characteristic parameters according to the three-phase data of the power grid to determine the system state characteristic data includes:

[0109] Collecting three-phase data of the power grid of the power quality compensation system to obtain original adopted data;

[0110] Performing wavelet threshold denoising processing on the original adopted data to obtain three-phase data of the power grid;

[0111] Converting the three-phase data of the power grid into a two-phase orthogonal coordinate system to obtain converted three-phase data;

[0112] Performing parameter estimation on the converted three-phase data to obtain a signal parameter estimation result;

[0113] Constructing an analytical expression of the signal according to the signal parameter estimation result to obtain an analytical expression of the signal;

[0114] Perform calculations based on the signal analytical expression to determine system power data;

[0115] Performing time-frequency analysis on the system power data to obtain power fluctuation characteristic data, extracting key characteristic parameters from the power fluctuation characteristic data to obtain system state characteristic data.

[0116] Among them, the original sampling data can be the instantaneous three-phase voltage and instantaneous three-phase current of the power grid directly collected using high-speed synchronous sampling technology; optionally, the instantaneous three-phase voltage data and current data of the power grid of the power quality compensation system are obtained by high-speed synchronous sampling technology at a sampling frequency of 20kHz to obtain the original sampling data.

[0117] Optionally, after obtaining the original sampled data, the original sampled data is subjected to wavelet decomposition by a wavelet function to obtain wavelet coefficients, the noise standard deviation estimate of each layer of wavelet coefficients is calculated to obtain noise standard deviation data, the adaptive threshold of each layer is calculated according to the noise standard deviation data and the signal length to obtain threshold data, the wavelet coefficients are subjected to soft threshold processing by using the threshold data to obtain denoised wavelet coefficients; the denoised wavelet coefficients are subjected to wavelet reconstruction to obtain three-phase data of the power grid. Exemplarily, the wavelet function may select the 4th order Daubechies wavelet.

[0118] Among them, converting three-phase data can be converting three-phase data; the signal parameter estimation result can be result data obtained by estimating the frequency, amplitude and phase of the signal based on the three-phase data of the power grid. Optionally, the instantaneous three-phase current of the three-phase data of the power grid is substituted into the Clarke transformation matrix, the three-phase data of the power grid is matrix-transformed, and the instantaneous three-phase current data of the two-phase stationary coordinate system (α-β coordinate system) is obtained, that is, the three-phase data is converted, and the Prony algorithm is applied to the converted three-phase data, respectively, by initializing the order of the Prony method; according to the initialized order, the signal model matrix is ​​constructed to obtain the model coefficient; the residual variance is calculated based on the model coefficient to obtain the residual data; the Akaike information criterion value is calculated using the residual data and the number of data points to obtain the information criterion value data; the order of the Prony method is adjusted, and the above process is repeated until the order that minimizes the information criterion value is found to obtain the optimal order; the Prony method is reapplied using the optimal order to estimate the frequency, amplitude and phase of the instantaneous three-phase current data to obtain the signal parameter estimation result.

[0119] Optionally, an embodiment of the present invention may also construct an improved Clarke transformation matrix, perform matrix transformation on the three-phase data of the power grid based on the improved Clarke transformation matrix, obtain conversion voltage data and conversion current data of a two-phase stationary coordinate system (α-β coordinate system), construct Hankel matrices for the conversion voltage data and the conversion current data respectively, perform singular value decomposition on each Hankel matrix to obtain a left singular matrix, a singular value matrix and a right singular matrix, determine the dimension of the signal subspace based on the singular value matrix using the minimum description length (MDL) criterion, and obtain signal subspace dimension data; based on the signal subspace dimension, construct a signal subspace matrix based on the left singular matrix, calculate the pseudo-inverse matrix of the signal subspace matrix, construct a shift invariant subspace, i.e., a first shift invariant subspace and a second shift invariant subspace, wherein the first shift invariant subspace is the signal subspace matrix with the last row removed, and the second shift invariant subspace is the signal subspace matrix with the first row removed, calculate the generalized eigenvalues ​​of the first shift invariant subspace and the second shift invariant subspace, and obtain a frequency estimate of the complex exponential signal; according to the complex exponential signal The frequency estimation value constructs a Vandermonde matrix, and the least squares method is used to solve the Vandermonde matrix to obtain a complex amplitude vector. The amplitude and phase are extracted from the complex amplitude vector, and the frequency, amplitude, and phase are combined to obtain signal parameter data of each signal component. The signal parameter data is sorted, and the frequency is arranged from low to high. The energy contribution of each signal component is calculated to obtain energy contribution data. Based on the energy contribution data, the first L components with the largest energy contribution are selected, where L is determined by the cumulative energy contribution reaching 99% of the total energy. The frequency, amplitude, and phase data of the selected L components are combined to obtain the final signal parameter estimation result.

[0120] Among them, the signal analytical expression can be an analytical expression of instantaneous three-phase current and instantaneous three-phase voltage in a two-phase stationary coordinate system. Optionally, in a two-phase stationary coordinate system, a signal analytical expression of instantaneous three-phase voltage and instantaneous three-phase current is constructed based on the signal parameter estimation result. Optionally, the signal analytical expression includes a first voltage expression, a second voltage expression, a first current expression and a second current expression. Exemplarily, the two-phase stationary coordinate system is expressed as: (α-β coordinate system), wherein the first voltage expression is expressed as u_α(t), the second voltage expression is expressed as u_β(t), the first current expression is expressed as i_α(t), and the second current expression is expressed as i_β(t).

[0121] Among them, the system power data can be the instantaneous reactive power and instantaneous active power of the power quality compensation system. Optionally, after obtaining the signal analysis expression, the first intermediate result is obtained by calculation based on the first voltage expression and the first current expression in the signal analysis expression, the second intermediate result is obtained by calculation based on the second voltage expression and the second current expression in the signal analysis expression, the first intermediate result and the second intermediate result are added to obtain the instantaneous active power, the third intermediate result is obtained by calculation based on the second voltage expression and the first current expression, the fourth intermediate result is obtained by calculation based on the first voltage expression and the second current expression, the third intermediate result is subtracted from the fourth intermediate result to obtain the instantaneous reactive power, and the system power data is determined based on the instantaneous reactive power and the instantaneous active power.

[0122] The power fluctuation characteristic data may be the power fluctuation of the power quality compensation system. Optionally, the system power data is subjected to empirical mode decomposition to obtain a series of intrinsic mode functions, and Hilbert transform is applied to each intrinsic mode function to calculate the instantaneous frequency and amplitude to obtain Hilbert spectrum data; based on the Hilbert spectrum data, the power fluctuation characteristics are analyzed to obtain the power fluctuation characteristic data.

[0123] Optionally, in the above embodiment, the system power data is subjected to empirical mode decomposition as follows: identify all local extreme value points; generate an upper envelope and a lower envelope using a cubic spline interpolation method; calculate the mean of the upper and lower envelopes to obtain a mean curve, subtract the mean curve from the original signal to obtain a candidate intrinsic mode function; repeat the decomposition process and select the candidate intrinsic mode function that satisfies the conditions that the number of extreme value points is equal to the number of zero-crossing points or the difference does not exceed 1 and the mean of the upper and lower envelopes is close to zero at any point as the first intrinsic mode function; repeat the above process to obtain all intrinsic mode functions and residual signals, obtain a complete decomposition result of the signal, apply Hilbert transform to each intrinsic mode function, calculate the instantaneous frequency and amplitude, and obtain Hilbert spectrum data; based on the Hilbert spectrum data, analyze the power fluctuation characteristics to obtain power fluctuation characteristic data.

[0124] Optionally, data extraction is performed based on the power fluctuation characteristic data to extract the fundamental active power, reactive power and total harmonic distortion rate to obtain power quality characteristic data, calculate the power fluctuation index to obtain system dynamic characteristic data, and combine the power quality characteristic data and the system dynamic characteristic data to obtain the final system state characteristic data.

[0125] S120. Estimating system compensation parameters of the power quality compensation system according to the system state characteristic data and the three-phase data of the power grid, and determining system compensation parameter estimation data.

[0126] The system compensation parameter estimation data may be an estimated value of a system compensation parameter of a power quality compensation system, and the system compensation parameter is composed of an estimated value of a reactive generator parameter and an estimated value of a fixed capacitor parameter.

[0127] Specifically, system compensation parameter estimation is performed on the power quality compensation system based on the system state characteristic data and the three-phase data of the power grid to determine system compensation parameter estimation data.

[0128] Optionally, in another optional embodiment of the present invention, estimating the system compensation parameters of the power quality compensation system according to the system state characteristic data and the three-phase data of the power grid to determine the system compensation parameter estimation data includes:

[0129] A nonlinear state space model of the power quality compensation system is constructed based on system state characteristic data to obtain a system dynamic equation; state estimation and parameter identification are performed according to the system dynamic equation and real-time measurement data of the power quality compensation system through the unscented Kalman filter algorithm to obtain a reactive generator parameter estimation value; an estimation is performed according to the converted three-phase data through an adaptive forgetting factor and the least squares method to determine a fixed capacitor parameter estimation value; and the system compensation parameter estimation data is determined according to the reactive generator parameter estimation value and the fixed capacitor parameter estimation value.

[0130] The system dynamic equation may be an equation corresponding to a nonlinear state space model.

[0131] The first state vector, control input vector and system parameter vector are constructed according to the system state characteristic data, and the system dynamic equation is established based on the first state vector, control input vector and system parameter vector. The first state vector includes: the current and voltage in the synchronous rotating coordinate system, the DC side voltage of the reactive generator; the control input vector includes the modulation ratio of the reactive generator; the system parameter vector includes the system equivalent inductance, the system equivalent resistance, the DC side capacitance of the reactive generator, the inductance of the fixed capacitor and the capacitance of the fixed capacitor.

[0132] Among them, the reactive transmitter parameter estimation value can be an estimation value of the reactive transmitter for system compensation of the power quality compensation system. Optionally, a measurement equation is established based on the first state vector and the control input vector, and the measurement equation and the system dynamic equation are combined to obtain a nonlinear state space model; the first state vector and the system parameter vector are merged to construct an extended state vector, and a Sigma point set is generated based on the extended state vector X and the system dynamic equation to obtain a priori state estimation, and the measurement equation and the priori state estimation are used to calculate the predicted measurement value to obtain measurement prediction data; the measurement error is obtained based on the actual measurement value and the measurement prediction data, and the measurement error covariance matrix and the state-measurement cross covariance matrix are calculated; the Kalman gain is calculated according to the measurement error covariance matrix and the state-measurement cross covariance matrix; the state estimation value is updated according to the Kalman gain, the measurement error and the priori state estimation to obtain the a posteriori state estimation; the reactive transmitter parameter estimation value is extracted from the a posteriori state estimation to obtain the updated reactive transmitter parameter estimation value.

[0133] Among them, the fixed capacitor parameter estimation value can be the estimation value of the fixed capacitor for system compensation of the power quality compensation system. Optionally, the input-output relationship of the reactive transmitter is constructed according to the voltage and current data in the two-phase stationary coordinate system to obtain a regression vector; the parameter estimation value and covariance matrix of the reactive transmitter are initialized, and the predicted output is calculated according to the parameter estimation value and the regression vector to obtain output prediction data; the prediction error is calculated according to the actual output and the output prediction data to obtain error data; the adaptive adjustment forgetting factor is adjusted based on the error data and the state of the reactive transmitter, and the gain matrix is ​​calculated according to the adaptive adjustment forgetting factor, the regression vector and the covariance matrix; the parameter estimation value and the covariance matrix are updated according to the gain matrix and the prediction error to obtain the updated parameter estimation value and the covariance matrix, and the step of executing the updated parameter estimation value and the covariance matrix is ​​returned, and the updating process of the parameter estimation value is repeated until the parameter estimation value converges to obtain the final fixed capacitor parameter estimation value.

[0134] Optionally, complete system compensation parameter estimation data is obtained by combining the reactive generator parameter estimation values ​​and the fixed capacitor parameter estimation values.

[0135] S130. Determine optimal control parameters of the power quality compensation system according to the system state characteristic data and the system compensation parameter estimation data.

[0136] Among them, the optimal control parameter of the power quality compensation system may be the optimal control variable for realizing the control of the power quality compensation system.

[0137] Specifically, the power quality compensation system is optimized by multi-objectives through system state characteristic data and system compensation parameter estimation data to obtain the optimal control parameters of the power quality compensation system.

[0138] Optionally, in another optional embodiment of the present invention, determining the optimal control parameters of the power quality compensation system based on the system state characteristic data and the system compensation parameter estimation data includes: constructing a multi-objective optimization function and a first constraint condition using the system state characteristic data and the system parameter estimation data; solving the multi-objective optimization function and the constraint condition by a multi-objective differential evolution algorithm to determine a non-dominated solution set; and applying a fuzzy decision-making method to the non-dominated solution set to select the optimal compensation strategy to obtain optimal control parameters.

[0139] Among them, the multi-objective optimization function can be a function of optimizing various objectives of the electric energy system compensation system; the first constraint condition can be used to make the multi-objective optimization function more suitable for the electric energy system compensation system.

[0140] Optionally, a system stability index function is constructed based on the system state characteristic data, a compensation efficiency index function is constructed based on the total harmonic distortion rate of the system state characteristic data, the static VAR generator capacity data of the electric energy system compensation system is obtained to construct an economic index function, the system stability index function, the compensation efficiency index function and the economic index function are combined to obtain a multi-objective optimization function, and the first constraint condition is constructed for the multi-objective optimization function based on the system parameter estimation data.

[0141] Optionally, the process of solving the multi-objective optimization function and the constraints by a multi-objective differential evolution algorithm is as follows: initialize the population as the initial population, randomly generate multiple individuals in the decision variable space, i.e., decision variable vectors, evaluate the multi-objective optimization function for each individual, and obtain the objective function value of the initial population; for each individual in the population, randomly select three different individuals in the initial population, generate mutation vectors based on the scaling factor, determine whether the mutation vectors satisfy the boundary constraints, and if the mutation vectors do not satisfy the boundary constraints, perform boundary processing, cross-operate the mutation vectors of the individuals and obtain experimental vectors, evaluate the function value of the experimental vector in the multi-objective optimization function, and obtain the function evaluation result; based on the function evaluation result, use the Pareto dominance relationship to evaluate the individuals and the experimental vectors. Perform dominance judgment, determine the updated initial population and external archive, perform fast non-dominated sorting on the individuals in the updated initial population and external archive, obtain at least one non-dominated frontier, sort the individuals in each non-dominated frontier according to the function evaluation result, obtain the non-dominated sorting result, set the crowding degree of the boundary solution to infinity, and for other solutions, calculate the crowding index to obtain the crowding degree of the individual, select the next generation of individuals according to the non-dominated sorting result and the crowding degree of the individual, obtain a new population, add the non-dominated solutions of the new population to the external archive, perform non-dominated sorting on the solutions in the external archive, and only retain the solutions of the first non-dominated frontier. If the size of the external archive exceeds the preset maximum capacity, delete the redundant solutions based on the crowding degree of the individual until the size of the external archive equals the preset maximum capacity. Check the preset termination condition. If the preset termination condition is not met, return to the operation of performing mutation operation to updating the external archive until the termination condition is met, and use the solution set of the external archive as the final non-dominated solution set. Among them, the way to select the next generation of individuals according to the non-dominated sorting results and the crowding degree of the individuals is to give priority to individuals with higher non-dominated sorting results. If the non-dominated sorting results are the same, individuals with higher crowding degrees are given priority. The termination condition can be that the preset maximum number of iterations is reached.

[0142] Optionally, in an embodiment of the present invention, for each solution in the non-dominated solution set, a normalized value on each function of the multi-objective optimization function is calculated, the maximum and minimum values ​​of each function of the multi-objective optimization function in the non-dominated solution set are determined, the fuzzy membership function of each objective function is defined, the membership value of each solution in each function of the multi-objective optimization function is calculated, and a membership matrix is ​​obtained. The hierarchical analysis method is used to determine the function weights of each function of the multi-objective optimization function, a judgment matrix is ​​constructed to represent the importance of each objective, the eigenvector corresponding to the maximum eigenvalue of the judgment matrix is ​​calculated, the eigenvector is normalized, and the weight vector of each function of the multi-objective optimization function is obtained. The comprehensive membership of each solution is calculated using the membership matrix and the weight vector to obtain comprehensive membership data, and the solution with the largest comprehensive membership is selected as the optimal compensation strategy based on the comprehensive membership data to obtain the optimal control parameters.

[0143] S140: Perform system control prediction on the power quality compensation system according to the system compensation parameter estimation data to determine the real-time control amount of the power quality compensation system.

[0144] The real-time control quantity may be a parameter for real-time control of the power quality compensation system; the real-time control quantity enables the power quality compensation system to respond quickly to instantaneous changes in the power grid.

[0145] Specifically, the system control prediction of the power quality compensation system is performed through the system compensation parameter estimation data to determine the real-time control quantity of the power quality compensation system.

[0146] S150. Perform control operations on the power quality compensation system according to the real-time control quantity, and determine control operation results.

[0147] The control operation result may be a result after the power quality compensation system performs the control operation.

[0148] Specifically, in the power quality compensation system, the actual compensation operation is performed on the drive circuit through the real-time control quantity to obtain the control operation result.

[0149] S160. Optimize the optimal control parameter based on the control operation result to obtain a target control parameter, and determine a target compensation current instruction according to the target control parameter.

[0150] Among them, the target control parameter can be a control parameter with the best performance in the power quality compensation system. The target control parameters include the optimal modulation ratio of the static VAR generator, the optimal compensation capacity of the fixed capacitor, the optimal coordinated control coefficient of the static VAR generator and the fixed capacitor, the optimal cutoff frequency of the bandpass filter, the optimal cutoff frequency of the low-pass filter and the optimal compensation current instruction. The target compensation current instruction can be the instruction information for controlling the power quality compensation system.

[0151] Specifically, after obtaining the control operation result corresponding to the power quality compensation system based on the real-time control quantity, the optimal control parameter is optimized based on the control operation result to obtain the target control parameter, and the target compensation current instruction is determined according to the target control parameter.

[0152] The technical solution of the embodiment of the present invention collects the three-phase data of the power grid of the power quality compensation system; extracts characteristic parameters based on the three-phase data of the power grid to determine the system state characteristic data, which can be used as the basis for optimizing the dispatch of the power system and improve the economy of the power system; estimates the system compensation parameters of the power quality compensation system based on the system state characteristic data and the three-phase data of the power grid to determine the system compensation parameter estimation data, and based on the system compensation parameter estimation data, the reactive power of the power system can be effectively controlled to improve the stability of the power system; determines the optimal control parameters of the power quality compensation system based on the system state characteristic data and the system compensation parameter estimation data, and the stability and operation efficiency of the power system can be improved through the optimal control parameters. rate, and can effectively control the cost of the power system and improve economic efficiency; perform system control prediction on the power quality compensation system according to the system compensation parameter estimation data, determine the real-time control quantity of the power quality compensation system, perform control operations on the power quality compensation system according to the real-time control quantity, determine the control operation results, perform control operations based on the real-time control quantity, thereby achieving rapid control response of the power system and improving power quality; optimize the optimal control parameters based on the control operation results to obtain target control parameters, determine the target compensation current instructions according to the target control parameters, and through the precise control of the target compensation current, effectively improve the response efficiency of the power system, improve the quality of electric energy, and enhance stability and economic benefits. The technical problem of system instability caused by the joint compensation of static VAR generators and fixed capacitors is solved, and efficient control is achieved, meeting the requirements of economy, energy efficiency and reliability.

[0153] Figure 2 This is a flowchart of another stability control method for a power quality management system provided by an embodiment of the present invention. The relationship between this embodiment and the above embodiment is a specific method for optimizing the optimal control parameters. Figure 2 As shown, the method includes:

[0154] S210, collecting three-phase data of the power grid of the power quality compensation system; extracting characteristic parameters according to the three-phase data of the power grid, and determining system state characteristic data.

[0155] S220. Estimating system compensation parameters of the power quality compensation system according to the system state characteristic data and the three-phase data of the power grid, and determining system compensation parameter estimation data.

[0156] S230. Determine optimal control parameters of the power quality compensation system according to the system state characteristic data and the system compensation parameter estimation data.

[0157] S240: Perform system control prediction on the power quality compensation system according to the system compensation parameter estimation data to determine the real-time control amount of the power quality compensation system.

[0158] S250: Perform control operations on the power quality compensation system according to the real-time control quantity, and determine control operation results.

[0159] Optionally, in another optional embodiment of the present invention, performing system control prediction on the power quality compensation system according to the system compensation parameter estimation data to determine the real-time control amount of the power quality compensation system includes:

[0160] A discrete-time prediction model is constructed based on the system parameter estimation data to determine the system state prediction equation; a rolling time domain optimization problem is constructed based on the system state prediction equation to obtain a rolling time domain optimization function and a second constraint condition; the rolling time domain optimization function and the second constraint condition are solved by a sequential quadratic programming algorithm to determine an optimal control sequence; feedforward control and feedback correction are performed on the optimal control sequence to determine the real-time control quantity.

[0161] Among them, the system state prediction equation can be a prediction equation corresponding to a discrete time prediction model. Optionally, a system state matrix, an input matrix, an output matrix and a direct transfer matrix are constructed based on system parameter estimation data, an interference matrix is ​​estimated based on historical data of the power quality compensation system, a discrete time state prediction equation of a discrete time prediction model is constructed based on the system state matrix, the input matrix, the output matrix, the direct transfer matrix and the interference matrix, an output prediction equation is constructed based on the output matrix and the direct transfer matrix, and a system state prediction equation is determined based on the discrete time state prediction equation and the output prediction equation.

[0162] Among them, the rolling time domain optimization function can be an optimization function applied to the rolling time domain optimization problem; the second constraint condition can be a control target pre-set based on the physical constraints of the power quality compensation system; the second constraint condition includes: upper and lower limits of the control quantity, upper and lower limits of the control increment, and upper and lower limits of the state variable; the second constraint condition can make the multi-rolling time domain optimization function more in line with the constraints of the rolling time domain optimization problem. Optionally, based on the discrete time prediction model corresponding to the system state prediction equation, define the prediction time domain, and construct a reference trajectory of the prediction time domain, define the state deviation weight matrix and the control increment weight matrix to construct the rolling time domain optimization function, based on the physical constraints of the power quality compensation system, set the upper and lower limits of the control quantity, the upper and lower limits of the control increment, and the upper and lower limits of the state variable, combine the rolling time domain optimization function and the second constraint condition, and obtain a complete rolling time domain optimization problem.

[0163] Optionally, the process of solving the target optimization function and the second constraint condition by the sequential quadratic programming algorithm is as follows: based on the rolling time domain optimization function and the second constraint condition corresponding to the rolling time domain optimization problem, construct a Lagrangian function, calculate the gradient and Hessian matrix of the Lagrangian function, obtain the gradient vector and Hessian matrix data, construct and solve the quadratic programming subproblem based on the gradient vector and Hessian matrix data, obtain the search direction, perform a one-dimensional search based on the search direction, determine the optimal step size, obtain a new iteration point based on the optimal step size, and obtain the optimal control sequence when the convergence condition is met; if the convergence condition is not met, return to the step of constructing and solving the quadratic programming subproblem. The convergence condition can be a preset maximum number of iterations.

[0164] Optionally, the process of performing feedforward control and feedback correction on the optimal control sequence is as follows: extracting the control quantity of the power quality compensation system at the current moment in the optimal control sequence as the feedforward control quantity, decomposing the feedforward control quantity into a modulation ratio component of the static VAR generator and a compensation capacity component of the fixed capacitor, obtaining the current system state of the power quality compensation system, calculating the state deviation, and then designing a state feedback controller; decomposing the state feedback controller into a modulation ratio correction quantity of the static VAR generator and a compensation capacity correction quantity of the fixed capacitor, adding the modulation ratio component and the modulation ratio correction quantity of the static VAR generator, adding the compensation capacity component of the fixed capacitor and the compensation capacity correction quantity of the fixed capacitor, synthesizing a composite control quantity, generating a PWM pulse sequence of the static VAR generator and a switch control signal of the fixed capacitor based on the composite control quantity, combining the PWM pulse sequence and the switch control signal to form a complete real-time control quantity.

[0165] S260. Calculate a comprehensive performance index of the power quality compensation system according to the system state characteristic data and the control operation result, and determine system performance evaluation data corresponding to the power quality compensation system.

[0166] The system performance evaluation data may be a comprehensive performance index corresponding to the control operation result of the power quality compensation system.

[0167] Specifically, after the power quality compensation system executes the real-time control quantity, the control operation result of the power quality compensation system is obtained. In the control operation result of the power quality compensation system, the system state characteristic data is used to calculate the stability index. Based on the total harmonic distortion rate data, the degree of reduction of the harmonic distortion rate is calculated. Based on the static VAR generator capacity data, the economic index is calculated. According to the stability index, the degree of reduction of the harmonic distortion rate and the calculated economic index, the function weights of each function of the multi-objective optimization function are calculated to determine the system performance evaluation data.

[0168] S270: construct a performance prediction model according to the system performance evaluation data to obtain a performance prediction function.

[0169] The performance prediction function may be a function for predicting the performance corresponding to the control parameters of the power quality compensation system.

[0170] Optionally, construct an input feature vector and an output vector according to the system performance evaluation data, randomly initialize the input weight matrix and the bias vector, calculate the hidden layer output according to the input feature vector, the input weight matrix and the bias vector, obtain the hidden layer output, solve the output weight vector using the least square method according to the hidden layer output and the output vector; obtain the performance prediction function according to the input feature vector, the input weight matrix, the bias vector and the weight vector. Among them, the input feature vector includes the control parameters and system state characteristic data of the power quality compensation system; the output vector corresponds to the system performance index of the power quality compensation system.

[0171] S280, optimizing the optimal control parameters by applying a performance prediction function through a Bayesian optimization algorithm to obtain target control parameters, and determining a target compensation current instruction according to the target control parameters.

[0172] Specifically, the optimal control parameters are optimized by applying the performance prediction function through the Bayesian optimization algorithm to obtain the target control parameters, and the target compensation current command is determined according to the target control parameters.

[0173] Optionally, in another optional embodiment of the present invention, the optimal control parameter is optimized by applying a performance prediction function through a Bayesian optimization algorithm to obtain a target control parameter, and a target compensation current instruction is determined according to the target control parameter, including:

[0174] The upper and lower bounds of the control parameter search space are defined, a reasonable variation range of each parameter in the control parameter search space is set, and each parameter is normalized to obtain a standard control parameter search space; a performance data set is constructed according to the standard control parameter search space and the performance prediction function; a preset first proxy model is initialized according to the performance data set to obtain a second proxy model; a maximum value is searched in the standard control parameter search space by a preset expected improvement function to determine a target parameter point; performance prediction is performed on the target parameter point according to the performance prediction function to determine target performance data, and the target performance data is updated to the performance data set; the second proxy model is optimized and updated according to the performance data set to determine a target proxy model; when the target proxy model meets a preset convergence condition, the target control parameter is obtained according to the performance data set, and a target compensation current instruction is determined according to the target control parameter.

[0175] The control parameter search space may be a set of possible control parameter value ranges defined by the Bayesian optimization algorithm. Optionally, based on the physical constraints and prior knowledge corresponding to the control parameters of the power quality compensation system, a reasonable range of variation for each control parameter is set, and each control parameter is normalized to obtain a standard control parameter search space. The standard control parameter search space is the control parameter search space after the control parameters are normalized.

[0176] The performance data set may be the performance corresponding to the initial point in the standard control parameter search space. Optionally, multiple initial points are uniformly sampled in the standard control parameter search space, the performance of each initial point is evaluated using the performance prediction function, and the performance data set is constructed based on the initial point and the performance of the initial point.

[0177] The first proxy model may be a pre-set Gaussian process. It should be noted that the Gaussian process is used as the first proxy model, the kernel function of the first proxy model is defined, the hyperparameters are set, and the hyperparameters of the Gaussian process are optimized using the maximum likelihood estimation or cross-validation method to obtain the first proxy model.

[0178] The second proxy model may be a model obtained by training the first proxy model with the performance data set. Optionally, the second proxy model may be obtained by training the first proxy model with the performance data set.

[0179] The preset expected improvement function may be a preset acquisition function. Optionally, the preset expected improvement function is used to find the maximum value in the standard control parameter search space to determine the target parameter point, which may be the point where the preset expected improvement function has the maximum value in the standard control parameter search space.

[0180] Optionally, the performance of the target parameter point is predicted according to the performance prediction function to determine the target performance data, the target performance data is updated to the performance data set, and the updated performance data set is determined; the second proxy model is optimized and updated according to the updated performance data set to determine the target proxy model; when the target proxy model meets the preset convergence condition, the target control parameter is obtained according to the performance data set, and the target compensation current instruction is determined according to the target control parameter. The target proxy model can be a model obtained by training the second proxy model with the updated performance data set; the preset convergence condition can be reaching the maximum number of iterations.

[0181] The embodiments of the present invention greatly improve the dynamic response capability and control accuracy of the system through the application of predictive control and composite control strategies. Through the combination of forward-looking control and real-time feedback, the power quality compensation system can respond to power grid changes in advance and accurately compensate for various power quality problems; the system can still maintain efficient and stable operation when facing complex and changeable power grid conditions; comprehensive performance evaluation and adaptive optimization provide the power quality compensation system with the ability of continuous improvement. Through real-time performance evaluation and prediction, combined with intelligent parameter optimization, the power quality compensation system can continuously learn and adapt to the new power grid environment to achieve long-term performance improvement.

[0182] Figure 3 A schematic diagram of a process control system for power quality management provided by an embodiment of the present invention; Figure 3 As shown: In the power quality management system, the instantaneous three-phase current and instantaneous three-phase voltage of the power quality compensation system are detected and collected, the instantaneous reactive power is calculated based on the instantaneous three-phase current and instantaneous three-phase voltage, the corresponding reactive compensation strategy is calculated based on the instantaneous reactive power, and whether the protection triggering condition is triggered is determined based on the reactive compensation strategy. If the protection triggering condition is triggered, the fault information is recorded and the machine is shut down immediately. If the protection triggering condition is not triggered, the control model is sent to switch the capacitor, and dynamic reactive compensation is performed through the static reactive generator, and the reactive compensation strategy is optimized by human-computer interactive control state. Among them, the instantaneous reactive power can be calculated by the instantaneous reactive theoretical algorithm, the reactive compensation strategy can be to increase or decrease the reactive power, and the protection triggering condition can be a condition pre-set by the power quality management system, such as abnormal voltage or abnormal current.

[0183] Optionally, the reactive power compensation strategy is used to adjust the input or removal of capacitor groups to achieve dynamic reactive power compensation. The power quality management system provides a human-computer interaction interface, and the operating personnel monitor the operating status of the power quality management system. The reactive power compensation strategy is manually adjusted or automatically optimized to adapt to grid changes, ensure the stability and efficiency of the power system, and reduce energy loss and improve power quality.

[0184] Figure 4 The present invention provides a schematic diagram of a stability control device for a power quality control system according to an embodiment of the present invention. Figure 4 As shown, the device includes: a system data acquisition module 410, a system parameter estimation module 420, an optimal working parameter calculation module 430, a system control calculation module 440, a system control module 450 and a compensation current calculation module 460, wherein:

[0185] The system data acquisition module 410 is used to collect the three-phase data of the power grid of the power quality compensation system; extract characteristic parameters according to the three-phase data of the power grid to determine the system state characteristic data; wherein the three-phase data of the power grid includes instantaneous three-phase voltage and instantaneous three-phase current,

[0186] A system parameter estimation module 420, configured to estimate system compensation parameters of the power quality compensation system according to the system state characteristic data and the three-phase data of the power grid, and determine system compensation parameter estimation data;

[0187] An optimal operating parameter calculation module 430, configured to determine the optimal control parameters of the power quality compensation system according to the system state characteristic data and the system compensation parameter estimation data;

[0188] A system control calculation module 440, configured to perform system control prediction on the power quality compensation system according to the system compensation parameter estimation data, and determine a real-time control amount of the power quality compensation system;

[0189] A system control module 450, configured to perform a control operation on the power quality compensation system according to the real-time control amount and determine a control operation result;

[0190] The compensation current calculation module 460 is used to optimize the optimal control parameter based on the control operation result to obtain a target control parameter, and determine a target compensation current instruction according to the target control parameter.

[0191] The technical solution of the embodiment of the present invention collects the three-phase data of the power grid of the power quality compensation system; extracts characteristic parameters based on the three-phase data of the power grid to determine the system state characteristic data, which can be used as the basis for optimizing the dispatch of the power system and improve the economy of the power system; estimates the system compensation parameters of the power quality compensation system based on the system state characteristic data and the three-phase data of the power grid to determine the system compensation parameter estimation data, and based on the system compensation parameter estimation data, the reactive power of the power system can be effectively controlled to improve the stability of the power system; determines the optimal control parameters of the power quality compensation system based on the system state characteristic data and the system compensation parameter estimation data, and the stability and operation efficiency of the power system can be improved through the optimal control parameters. rate, and can effectively control the cost of the power system and improve economic efficiency; perform system control prediction on the power quality compensation system according to the system compensation parameter estimation data, determine the real-time control quantity of the power quality compensation system, perform control operations on the power quality compensation system according to the real-time control quantity, determine the control operation results, perform control operations based on the real-time control quantity, thereby achieving rapid control response of the power system and improving power quality; optimize the optimal control parameters based on the control operation results to obtain target control parameters, determine the target compensation current instructions according to the target control parameters, and through the precise control of the target compensation current, effectively improve the response efficiency of the power system, improve the quality of electric energy, and enhance stability and economic benefits. The technical problem of system instability caused by the joint compensation of static VAR generators and fixed capacitors is solved, and efficient control is achieved, meeting the requirements of economy, energy efficiency and reliability.

[0192] Optionally, the compensation current calculation module is specifically used for:

[0193] A system performance evaluation unit, configured to calculate a comprehensive performance index of the power quality compensation system according to the system state characteristic data and the control operation result, and determine system performance evaluation data corresponding to the power quality compensation system;

[0194] A performance prediction function building unit, used to build a performance prediction model according to the system performance evaluation data to obtain a performance prediction function;

[0195] The instruction calculation unit is used to optimize the optimal control parameters by applying the performance prediction function through the Bayesian optimization algorithm to obtain the target control parameters, and determine the target compensation current instruction according to the target control parameters.

[0196] Optionally, the instruction calculation unit is used to:

[0197] A parameter calculation subunit is used to define the upper and lower bounds of the control parameter search space, set a reasonable variation range of each parameter in the control parameter search space, and perform normalization processing on each parameter to obtain a standard control parameter search space;

[0198] A data set calculation subunit, used for constructing a performance data set according to the standard control parameter search space and the performance prediction function;

[0199] An agent model updating subunit, configured to initialize a preset first agent model according to the performance data set to obtain a second agent model;

[0200] A function calculation subunit, used to search for a maximum value in the standard control parameter search space through a preset expected improvement function, and determine a target parameter point;

[0201] A performance prediction subunit, configured to perform performance prediction on the target parameter point according to the performance prediction function, determine target performance data, update the target performance data to the performance data set, and determine an updated performance data set;

[0202] A proxy model optimization subunit, configured to optimize and update the second proxy model according to the updated performance data set, and determine a target proxy model;

[0203] The compensation current instruction calculation subunit is used to obtain the target control parameter according to the performance data set when the target proxy model meets the preset convergence condition, and determine the target compensation current instruction according to the target control parameter.

[0204] Optionally, the system data acquisition module is used to:

[0205] A collection unit, used for collecting three-phase data of the power grid of the power quality compensation system to obtain original adopted data;

[0206] A denoising unit, used for performing wavelet threshold denoising processing on the original adopted data to obtain three-phase data of the power grid;

[0207] A power grid three-phase calculation unit, used for converting the power grid three-phase data into a two-phase orthogonal coordinate system to obtain converted three-phase data;

[0208] A signal parameter estimation unit, used for performing parameter estimation on the converted three-phase data to obtain a signal parameter estimation result;

[0209] A signal analysis unit, used for constructing an analytical expression of the signal according to the signal parameter estimation result to obtain a signal analytical expression;

[0210] A system power calculation unit, used to perform calculations according to the signal analytical expression to determine system power data;

[0211] The characteristic data extraction unit is used to perform time-frequency analysis on the system power data to obtain power fluctuation characteristic data, extract key characteristic parameters from the power fluctuation characteristic data, and obtain system state characteristic data.

[0212] Optionally, the system parameter estimation module is used to:

[0213] A system equation building unit, used to build a nonlinear state space model of the power quality compensation system based on system state characteristic data to obtain a system dynamic equation;

[0214] An unscented Kalman filter calculation unit, used to perform state estimation and parameter identification according to the system dynamic equation and the real-time measurement data of the power quality compensation system through the unscented Kalman filter algorithm to obtain the estimated value of the reactive generator parameter;

[0215] A least squares method recursive unit, used to estimate according to the converted three-phase data by using an adaptive forgetting factor and the least squares method to determine an estimated value of a fixed capacitor parameter;

[0216] A data calculation unit is used to determine the system compensation parameter estimation data according to the reactive generator parameter estimation value and the fixed capacitor parameter estimation value.

[0217] Optionally, the optimal operating parameter calculation module is used to:

[0218] An optimization function construction unit, used to construct a multi-objective optimization function and a first constraint condition from system state characteristic data and system parameter estimation data;

[0219] A solution unit, used for solving the multi-objective optimization function and the constraint conditions by using a multi-objective differential evolution algorithm to determine a non-dominated solution set;

[0220] The control parameter calculation unit is used to apply a fuzzy decision method to the non-dominated solution set to select the best compensation strategy to obtain the optimal control parameters.

[0221] Optionally, the system control module is used to:

[0222] A system state prediction unit, used to construct a discrete time prediction model according to the system parameter estimation data and determine a system state prediction equation;

[0223] A system optimization unit, used for constructing a rolling horizon optimization problem according to the system state prediction equation to obtain a target optimization function and a second constraint condition;

[0224] An optimal control sequence solving unit, used for solving the objective optimization function and the second constraint condition by a sequential quadratic programming algorithm to determine an optimal control sequence;

[0225] A real-time control unit is used to perform feedforward control and feedback correction on the optimal control sequence to determine the real-time control amount.

[0226] The stability control device for a power quality management system provided in an embodiment of the present invention can execute the stability control method for a power quality management system provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0227] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their modes are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0228] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0229] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer grid such as the Internet and / or various telecommunication grids.

[0230] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a stability control method for a power quality management system.

[0231] In some embodiments, the stability control method for the power quality management system may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the stability control method for the power quality management system described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the stability control method for the power quality management system in any other appropriate manner (e.g., by means of firmware).

[0232] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0233] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the modes / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0234] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0235] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0236] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a grid browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication grid). Examples of communication grids include: a local area network (LAN), a wide area network (WAN), a blockchain grid, and the Internet.

[0237] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication grid. The client and server relationship is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0238] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0239] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the stability control method steps for a power quality management system provided by any embodiment of the present invention are implemented. The method includes:

[0240] Collecting three-phase data of the power grid of the power quality compensation system; extracting characteristic parameters based on the three-phase data of the power grid to determine the system state characteristic data; wherein the three-phase data of the power grid includes instantaneous three-phase voltage and instantaneous three-phase current,

[0241] Estimating system compensation parameters of the power quality compensation system according to the system state characteristic data and the three-phase data of the power grid, and determining system compensation parameter estimation data;

[0242] Determining the optimal control parameters of the power quality compensation system according to the system state characteristic data and the system compensation parameter estimation data;

[0243] Performing system control prediction on the power quality compensation system according to the system compensation parameter estimation data to determine the real-time control amount of the power quality compensation system;

[0244] Performing a control operation on the power quality compensation system according to the real-time control amount, and determining a control operation result;

[0245] The optimal control parameter is optimized based on the control operation result to obtain a target control parameter, and a target compensation current instruction is determined according to the target control parameter.

[0246] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0247] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0248] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0249] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of grid, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0250] It should be understood by those skilled in the art that the above modules or steps of the present invention can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a grid composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0251] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0252] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A stability control method for a power quality management system, characterized in that: include: Collecting three-phase data of the power grid of the power quality compensation system; extracting characteristic parameters based on the three-phase data of the power grid to determine the system state characteristic data; wherein the three-phase data of the power grid includes instantaneous three-phase voltage and instantaneous three-phase current, Estimating system compensation parameters of the power quality compensation system according to the system state characteristic data and the three-phase data of the power grid, and determining system compensation parameter estimation data; Determining the optimal control parameters of the power quality compensation system according to the system state characteristic data and the system compensation parameter estimation data; Performing system control prediction on the power quality compensation system according to the system compensation parameter estimation data to determine the real-time control amount of the power quality compensation system; Performing a control operation on the power quality compensation system according to the real-time control amount, and determining a control operation result; The optimal control parameter is optimized based on the control operation result to obtain a target control parameter, and a target compensation current instruction is determined according to the target control parameter.

2. The method according to claim 1, characterized in that The optimizing the optimal control parameter based on the control operation result to obtain a target control parameter, and determining a target compensation current instruction according to the target control parameter, comprises: Calculating a comprehensive performance index of the power quality compensation system according to the system state characteristic data and the control operation result, and determining system performance evaluation data corresponding to the power quality compensation system; Constructing a performance prediction model based on the system performance evaluation data to obtain a performance prediction function; The optimal control parameters are optimized by applying a performance prediction function through a Bayesian optimization algorithm to obtain target control parameters, and a target compensation current instruction is determined according to the target control parameters.

3. The method according to claim 2, characterized in that The method of optimizing the optimal control parameters by applying the performance prediction function through the Bayesian optimization algorithm to obtain target control parameters, and determining the target compensation current instruction according to the target control parameters, includes: Defining upper and lower bounds of the control parameter search space, setting a reasonable variation range for each parameter in the control parameter search space, and normalizing each parameter to obtain a standard control parameter search space; constructing a performance data set according to the standard control parameter search space and the performance prediction function; Initializing a preset first proxy model according to the performance data set to obtain a second proxy model; The target parameter point is determined by searching for the maximum value in the standard control parameter search space through a preset expected improvement function; Performing performance prediction on the target parameter point according to the performance prediction function, determining target performance data, updating the target performance data to the performance data set, and determining an updated performance data set; Optimizing and updating the second proxy model according to the updated performance data set to determine a target proxy model; In a case where the target proxy model meets a preset convergence condition, the target control parameter is obtained according to the performance data set, and the target compensation current instruction is determined according to the target control parameter.

4. The method according to claim 1, characterized in that: The collecting of three-phase data of the power grid of the power quality compensation system; extracting characteristic parameters according to the three-phase data of the power grid to determine the system state characteristic data includes: Collecting three-phase data of the power grid of the power quality compensation system to obtain original adopted data; Performing wavelet threshold denoising processing on the original adopted data to obtain three-phase data of the power grid; Converting the three-phase data of the power grid into a two-phase orthogonal coordinate system to obtain converted three-phase data; Performing parameter estimation on the converted three-phase data to obtain a signal parameter estimation result; Constructing an analytical expression of the signal according to the signal parameter estimation result to obtain an analytical expression of the signal; Perform calculations based on the signal analytical expression to determine system power data; Performing time-frequency analysis on the system power data to obtain power fluctuation characteristic data, extracting key characteristic parameters from the power fluctuation characteristic data to obtain system state characteristic data.

5. The method according to claim 4, characterized in that The estimating the system compensation parameters of the power quality compensation system according to the system state characteristic data and the three-phase data of the power grid to determine the system compensation parameter estimation data includes: Based on the system state characteristic data, a nonlinear state space model of the power quality compensation system is constructed to obtain a system dynamic equation; By using an unscented Kalman filter algorithm, state estimation and parameter identification are performed according to the system dynamic equation and the real-time measurement data of the power quality compensation system to obtain the estimated value of the reactive generator parameter; Estimation is performed based on the converted three-phase data by using an adaptive forgetting factor and a least square method to determine an estimated value of a fixed capacitor parameter; The system compensation parameter estimation data is determined according to the reactive generator parameter estimation value and the fixed capacitor parameter estimation value.

6. The method according to claim 5, characterized in that The determining the optimal control parameters of the power quality compensation system according to the system state characteristic data and the system compensation parameter estimation data comprises: Constructing a multi-objective optimization function and a first constraint condition using system state characteristic data and system parameter estimation data; Solving the multi-objective optimization function and the constraint conditions by a multi-objective differential evolution algorithm to determine a non-dominated solution set; A fuzzy decision method is applied to the non-dominated solution set to select the best compensation strategy and obtain the optimal control parameters.

7. The method according to claim 6, characterized in that The performing system control prediction on the power quality compensation system according to the system compensation parameter estimation data to determine the real-time control amount of the power quality compensation system includes: Constructing a discrete time prediction model based on the system parameter estimation data and determining a system state prediction equation; According to the system state prediction equation, a rolling horizon optimization problem is constructed to obtain a target optimization function and a second constraint condition; Solving the objective optimization function and the second constraint condition by a sequential quadratic programming algorithm to determine an optimal control sequence; Feedforward control and feedback correction are performed on the optimal control sequence to determine the real-time control amount.

8. A stability control device for a power quality management system, characterized in that: include: The system data acquisition module is used to collect the three-phase data of the power grid of the power quality compensation system; extract characteristic parameters according to the three-phase data of the power grid to determine the system state characteristic data; wherein the three-phase data of the power grid includes instantaneous three-phase voltage and instantaneous three-phase current, A system parameter estimation module, used to estimate the system compensation parameters of the power quality compensation system according to the system state characteristic data and the three-phase data of the power grid, and determine the system compensation parameter estimation data; An optimal operating parameter calculation module, used to determine the optimal control parameters of the power quality compensation system according to the system state characteristic data and the system compensation parameter estimation data; A system control calculation module, used to perform system control prediction on the power quality compensation system according to the system compensation parameter estimation data, and determine the real-time control amount of the power quality compensation system; A system control module, used to perform a control operation on the power quality compensation system according to the real-time control quantity and determine a control operation result; The compensation current calculation module is used to optimize the optimal control parameter based on the control operation result to obtain a target control parameter, and determine a target compensation current instruction according to the target control parameter.

9. The device according to claim 8, characterized in that The compensation current calculation module comprises: A system performance evaluation unit, configured to calculate a comprehensive performance index of the power quality compensation system according to the system state characteristic data and the control operation result, and determine system performance evaluation data corresponding to the power quality compensation system; A performance prediction function building unit, used to build a performance prediction model according to the system performance evaluation data to obtain a performance prediction function; The instruction calculation unit is used to optimize the optimal control parameters by applying the performance prediction function through the Bayesian optimization algorithm to obtain the target control parameters, and determine the target compensation current instruction according to the target control parameters.

10. The device according to claim 9, characterized in that The instruction calculation unit comprises: A parameter calculation subunit is used to define the upper and lower bounds of the control parameter search space, set a reasonable variation range of each parameter in the control parameter search space, and perform normalization processing on each parameter to obtain a standard control parameter search space; A data set calculation subunit, used for constructing a performance data set according to the standard control parameter search space and the performance prediction function; An agent model updating subunit, configured to initialize a preset first agent model according to the performance data set to obtain a second agent model; A function calculation subunit, used to search for a maximum value in the standard control parameter search space through a preset expected improvement function, and determine a target parameter point; A performance prediction subunit, configured to perform performance prediction on the target parameter point according to the performance prediction function, determine target performance data, update the target performance data to the performance data set, and determine an updated performance data set; A proxy model optimization subunit, configured to optimize and update the second proxy model according to the updated performance data set, and determine a target proxy model; The compensation current instruction calculation subunit is used to obtain the target control parameter according to the performance data set when the target proxy model meets the preset convergence condition, and determine the target compensation current instruction according to the target control parameter.

11. The device according to claim 8, characterized in that The system data acquisition module comprises: A collection unit, used for collecting three-phase data of the power grid of the power quality compensation system to obtain original adopted data; A denoising unit, used for performing wavelet threshold denoising processing on the original adopted data to obtain three-phase data of the power grid; A power grid three-phase calculation unit, used for converting the power grid three-phase data into a two-phase orthogonal coordinate system to obtain converted three-phase data; A signal parameter estimation unit, used for performing parameter estimation on the converted three-phase data to obtain a signal parameter estimation result; A signal analysis unit, used for constructing an analytical expression of the signal according to the signal parameter estimation result to obtain a signal analytical expression; A system power calculation unit, used to perform calculations according to the signal analytical expression to determine system power data; The characteristic data extraction unit is used to perform time-frequency analysis on the system power data to obtain power fluctuation characteristic data, extract key characteristic parameters from the power fluctuation characteristic data, and obtain system state characteristic data.

12. The device according to claim 11, characterized in that The system parameter estimation module comprises: A system equation building unit, used to build a nonlinear state space model of the power quality compensation system based on system state characteristic data to obtain a system dynamic equation; An unscented Kalman filter calculation unit, used to perform state estimation and parameter identification according to the system dynamic equation and the real-time measurement data of the power quality compensation system through an unscented Kalman filter algorithm to obtain a reactive generator parameter estimation value; A least squares method recursive unit, used to estimate according to the converted three-phase data by using an adaptive forgetting factor and a least squares method to determine an estimated value of a fixed capacitor parameter; A data calculation unit is used to determine the system compensation parameter estimation data according to the reactive generator parameter estimation value and the fixed capacitor parameter estimation value.

13. The device according to claim 12, characterized in that The optimal working parameter calculation module includes: An optimization function construction unit, used to construct a multi-objective optimization function and a first constraint condition from system state characteristic data and system parameter estimation data; A solution unit, used for solving the multi-objective optimization function and the constraint conditions by a multi-objective differential evolution algorithm to determine a non-dominated solution set; The control parameter calculation unit is used to apply a fuzzy decision method to the non-dominated solution set to select the best compensation strategy to obtain the optimal control parameters.

14. The device according to claim 13, characterized in that The system control module comprises: A system state prediction unit, used to construct a discrete time prediction model according to the system parameter estimation data and determine a system state prediction equation; A system optimization unit, used for constructing a rolling horizon optimization problem according to the system state prediction equation to obtain a target optimization function and a second constraint condition; An optimal control sequence solving unit, used for solving the objective optimization function and the second constraint condition by a sequential quadratic programming algorithm to determine an optimal control sequence; A real-time control unit is used to perform feedforward control and feedback correction on the optimal control sequence to determine the real-time control amount.

15. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the stability control method for a power quality management system as described in any one of claims 1-7.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the stability control method for a power quality management system as described in any one of claims 1-7 when executed.

Images