New energy control parameter adaptive identification method based on double-layer particle swarm optimization

Abstract

The invention provides a new energy control parameter adaptive identification method based on double-layer particle swarm optimization, and belongs to the technical field of power system simulation analysis. The typical control strategies of the heterogeneous new energy unit are integrated, and a strategy database is constructed and verified; acquiring test data for processing and feature extraction to obtain high and low pass threshold values, a current initial state and test feature data; and constructing a fitness function based on the strategy library, screening an optimal strategy combination from the strategy library by using a discrete particle swarm algorithm in a global optimization layer, and continuously optimizing a parameter set of a selected strategy in combination with a momentum factor and a learning rate in a local optimization layer. According to the method, the characteristic value of the actual unit test data is extracted as input of the double-layer particle swarm algorithm, the optimal strategy-parameter pair is judged and output through total error index weighting, the accuracy of the strategy-parameter pair is verified, and the efficiency and precision of heterogeneous new energy equipment modeling are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to a new energy control parameter adaptive identification method based on double-layer particle swarm optimization, belonging to the technical field of power system simulation analysis. BACKGROUND

[0002] With the rapid growth of installed capacity of wind power, photovoltaic and other new energy, the penetration rate of new energy equipment in the power system continues to rise. Its large-scale access to the grid makes the accurate identification of control strategies and parameters a key to ensuring the stable operation of the system. The importance of new energy simulation modeling for power system operation mode analysis is also increasingly prominent.

[0003] In the process of building a structured model of new energy, establishing a standardized simulation model of new energy can provide a convenient and efficient verification method and simulation analysis tool for the analysis of grid-connected characteristics of new energy, verification and optimization of control strategies, and also provide theoretical and technical support for large-scale wind power grid planning, operation control, fault analysis, etc. The structured modeling of new energy covers the construction of standardized technical processes for new energy unit modeling, research on unit key control parameter identification algorithms, and testing and verification of new energy unit models.

[0004] However, the current related work faces many challenges. Existing parameter identification methods mostly focus on the optimization of parameters of a single device type, and improve the convergence efficiency by improving intelligent algorithms. For example, the Chinese patent application with publication number CN117335486A discloses a photovoltaic inverter parameter identification method and system based on a chaotic particle swarm algorithm. It constructs a photovoltaic inverter double-loop control model, uses a chaotic disturbance and fitness variance determination mechanism to optimize parameter search, and significantly improves the identification accuracy in the photovoltaic scenario. However, the model architecture of this patent is fixed to the control strategy of a specific device (such as a photovoltaic inverter), and cannot be compatible with the strategy library of diversified new energy devices such as wind turbines. Moreover, the optimization process only uses a single particle swarm framework to handle mixed optimization problems, making it difficult to balance global exploration and local development. In addition, its verification mechanism relies on static calculation of current error, lacks multi-dimensional closed-loop verification based on dynamic response characteristics, and results in insufficient generalization of the model in actual grid fault ride-through and other transient scenarios.

[0005] In summary, there is an urgent need for a new energy control parameter identification method that supports multi-strategy compatibility, hierarchical collaborative optimization and dynamic feature verification, to break through key technical bottlenecks such as poor adaptability of heterogeneous devices, low efficiency of strategy-parameter coupling optimization, and disconnection between model and actual working conditions, and to provide theoretical support and engineering tools for stable control of high-proportion new energy power grids. SUMMARY

[0006] To solve the problems existing in the prior art, the present application proposes a new energy control parameter adaptive identification method based on double-layer particle swarm optimization.

[0007] The technical scheme of the present application is as follows: In one aspect, the present application provides a new energy control parameter adaptive identification method based on double-layer particle swarm optimization, which comprises the following steps: Typical control strategies of four types of heterogeneous new energy units, i.e., wind power, photovoltaic, energy storage and SVG, are integrated to construct a strategy database containing mathematical models of voltage-current response characteristics in the form of piecewise functions, value ranges and initial parameter values of associated parameters of each control strategy; Actual unit test data are acquired, and feature extraction is performed on the test data to obtain test feature data; A double-layer particle swarm optimization framework containing a global optimization layer and a local optimization layer is constructed based on the strategy database, and a hierarchical fitness function is set; The test feature data are input into the double-layer particle swarm optimization framework, and an optimal strategy-parameter pair is output, wherein the global optimization layer adopts a discrete particle swarm algorithm, and an optimal strategy combination is selected by taking a strategy error function as a fitness function; the local optimization layer adopts a continuous particle swarm algorithm, and associated parameters of the optimal strategy combination are optimized by taking a parameter error function as a fitness function.

[0008] Preferably, the strategy database contains a strategy sub-database of SVG, which includes SVG reactive power control strategies, specifically including voltage-controlled current with superimposed initial reactive current component, specified reactive current control, specified reactive power control, SVG current remaining unchanged, SVG reactive current generating a specified value change on the basis of before the fault, and voltage-controlled current without superimposed initial reactive current component.

[0009] Preferably, the strategy database contains a strategy sub-database for wind power and photovoltaic, which includes wind-solar reactive power control strategies and wind-solar active power control strategies, wherein the wind-solar reactive power control strategies include specified reactive current control and specified reactive power control; the wind-solar active power control strategies include specified active power control, specified active current control, pre-fault active current control and low-voltage limit active current control.

[0010] Preferably, the strategy database contains a strategy sub-database of energy storage, which includes energy storage reactive power control strategies and energy storage active power control strategies in charging and discharging modes, wherein the energy storage reactive power control strategies include specified reactive current control and specified reactive power control; the energy storage active power control strategies in charging and discharging modes include specified active power control, specified active current control, pre-fault active current control and low-voltage limit active current control.

[0011] Preferably, the method further comprises the following steps: After the construction of the strategy database, the accuracy of the strategy database is verified through the simulation platform to ensure that the dynamic response characteristic curves corresponding to the voltage-current response characteristic mathematical model in the simulation data and the strategy database are completely matched.

[0012] Preferably, the method further comprises: In the feature extraction of the actual unit test data, the step voltage curve is drawn synchronously, and when the current mutation is detected, the voltage critical value of the step voltage curve is taken as the high and low threshold value, and the piecewise function interval boundary of the voltage-current response characteristic mathematical model in the strategy database is defined through the high and low threshold value.

[0013] Preferably, the method further comprises: In the feature extraction of the test data, the fault ride-through test data under different initial reactive values in the test data is used to analyze whether the reactive current changes of different initial reactive values during the fault are consistent, and the current superposition mode is determined according to the correlation, specifically: The consistency of the change trend and amplitude of the reactive current with time under different initial reactive values is determined, and the correlation coefficient between the changes of the reactive current under different initial reactive values is calculated; When the correlation coefficient of the reactive current changes under different initial reactive values during the fault is greater than a preset correlation coefficient threshold, it is determined that the incremental mathematical model is used; When the correlation coefficient of the reactive current changes under different initial reactive values during the fault is less than or equal to the preset correlation coefficient threshold, it is determined that the absolute value mathematical model is used; The current superposition mode is used to control the optimal strategy combination selection process of the global optimization layer, and only the mathematical model of the corresponding type in the strategy database is activated.

[0014] Preferably, the feature extraction of the test data uses the fault partition method, which is divided into a low voltage ride-through zone, a steady state zone and a high voltage ride-through zone, the active current effective value, the reactive current effective value and the voltage effective value in each partition are extracted, and the extracted values are taken as test feature data.

[0015] Preferably, the method further comprises constructing the value range and initial parameter value of each control strategy associated parameter into an associated parameter set .

[0016] Preferably, the particle update of the discrete particle swarm algorithm in the iteration process is expressed in the formula as: ; In the formula, represents the global speed at the moment; represents the global speed at the moment; represents the global speed at the moment; represents the global speed at the moment; Inertial weights; and For learning factors; and In order to be in Random numbers within; This represents the optimal position in the particle's history. The globally optimal position; This represents the particle's current position. During particle update, the Discrete Particle Swarm Optimization (DPSO) algorithm evaluates different policy combinations in the policy database using a policy error function. This policy error function measures the quality of the current policy combination, and the optimal policy combination is obtained based on this function, expressed by the following formula: ; In the formula, The optimal strategy combination; The initial sample size for evaluating the effectiveness of the strategy; For the first The predicted current value corresponding to each sample; For the first The effective current value corresponding to each sample; Indicated in the policy database Find the strategy that minimizes the policy error function among all strategy combinations. ; For strategy combination The corresponding strategy error function.

[0017] Preferably, the optimization process of the continuous particle swarm optimization algorithm is as follows: The local optimization layer corrects particle velocities in real time based on parameter error feedback, expressed by the following formula: ; In the formula, for Local velocity at a given moment; for Local velocity at a given moment; The learning rate; Momentum factor; Associating parameters for the optimal strategy combination The corresponding parameter error function; The optimal strategy combination is associated with parameters; The parameter error is expressed by the formula: ; In the formula, To comprehensively evaluate the number of data samples; for The effective value of the current at any given time; For the voltage effective value at the moment; The selected optimal strategy combination associated parameter is optimized in combination with the parameter error, and an optimal strategy combination associated optimal parameter is obtained, which is expressed by a formula as follows: ; In the formula, is the optimal strategy combination associated optimal parameter; The unit control model is represented, and the optimal strategy combination , the optimal strategy combination associated parameter and the external input at the moment, the predicted current value of the unit at the moment is calculated; The associated parameter in the associated parameter set is searched to minimize the parameter error function value.

[0018] Preferably, the optimal strategy-parameter pair is output, specifically: In the double-layer particle swarm optimization framework, the global optimization layer performs a preset number of cycles, and the parameter optimization cycle of the local optimization layer is performed after the strategy optimization cycle of the global optimization layer. Through the double-layer collaborative optimization cycle, the total error index of each strategy-parameter pair is calculated, which is expressed by a formula as follows: ; In the formula, is the total error index; is the optimal strategy combination corresponding strategy error function; is the optimal strategy combination associated optimal parameter corresponding parameter error function; When the total error index is less than a preset error threshold, it is considered that the optimization is completed, and the current strategy-parameter pair is output as the optimal strategy-parameter pair, otherwise the optimization is re-performed.

[0019] Preferably, the method further comprises constructing a simulation model based on the optimal strategy-parameter pair, performing feature extraction on simulation data generated by the simulation model to obtain simulation feature data, and performing error checking on the test feature data and the simulation feature data. The error checking adopts mean square error MSE, mean absolute error MAE or relative error.

[0020] Preferably, the method further comprises visualizing and displaying the error checking result.

[0021] In still another aspect, the present application also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the new energy control parameter adaptive identification method based on double-layer particle swarm optimization as described in the present application when executing the program.

[0022] In still another aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, wherein the program is executable on a processor to implement the new energy control parameter adaptive identification method based on double-layer particle swarm optimization as described in the present application.

[0023] The present application has the following beneficial effects: 1. The present application is a new energy control parameter adaptive identification method based on double-layer particle swarm optimization, which integrates multiple manufacturer control strategies to construct a strategy library containing a reactive power-active power coupling model, defines the dynamic range of each strategy parameter, and realizes layered collaboration of strategy selection and parameter optimization by combining a double-layer particle swarm algorithm, wherein the global optimization layer adopts a discrete particle swarm algorithm to quickly select an adaptive control strategy (such as a reactive power control combined with a low-voltage current limiting), and the local optimization layer dynamically corrects the parameter search direction through a momentum factor and a learning rate, thereby solving the local optimal problem caused by the strong coupling of strategy and parameter in single optimization, compatible with the differentiated mathematical models of different manufacturers' strategies, significantly improving the global adaptation capability of new energy equipment under complex working conditions, and supporting the construction of a unified optimization platform for heterogeneous equipment. 2. The present application is a new energy control parameter adaptive identification method based on double-layer particle swarm optimization, which extracts dynamic response characteristics from measured data to construct a multi-dimensional feature vector, uses it as an optimization target to drive the parameter identification process, and designs a total error index for iterative optimization and threshold determination, further generates a simulation model based on the optimal strategy-parameter pair, verifies the dynamic error through feature comparison, and forms a "feature extraction-optimization-verification" closed loop. The present application avoids the risk of disconnection between the model and the actual working condition in traditional open-loop identification, while supporting dynamic expansion of the strategy library and parameter set, ensuring the long-term adaptability of the algorithm to new equipment and complex power grid environment. 3. The present application is a new energy control parameter adaptive identification method based on double-layer particle swarm optimization, which proposes an automatic identification of mathematical model type (incremental vs. absolute value) based on test data, analyzes the correlation of reactive current changes during faults under different reactive power initial values to determine the superposition mode, and dynamically activates the corresponding type of model in the strategy database accordingly, thereby solving the key problem of model type uncertainty in practical application, significantly improving the automation, accuracy and robustness of identification.

[0024] 4. The application is a new energy control parameter adaptive identification method based on double-layer particle swarm optimization, which extracts the active current effective value, reactive current effective value and voltage effective value of each zone as features by using fault partition method (low-pass zone, steady-state zone, high-pass zone), focuses on the core information reflecting the dynamic response of the system, and more effectively represents the control characteristics; 5. The application is a new energy control parameter adaptive identification method based on double-layer particle swarm optimization, which draws a stepped voltage curve and determines the voltage threshold as a high-low pass threshold at the current mutation, which is used to define the segment interval boundary of the strategy model, and improves the adaptive ability of the method. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 The method flowchart of the application; Figures 2-9 is a simulation wind turbine fault period response characteristic curve diagram under different control strategies of the embodiment of the application, wherein, Figure 2 is a simulation wind turbine fault period response characteristic curve diagram under strategy 1, Figure 3 is a simulation wind turbine fault period response characteristic curve diagram under strategy 2, Figure 4 is a simulation wind turbine fault period response characteristic curve diagram under strategy 3, Figure 5 is a simulation wind turbine fault period response characteristic curve diagram under strategy 4, Figure 6 is a simulation wind turbine fault period response characteristic curve diagram under strategy 5, Figure 7 is a simulation wind turbine fault period response characteristic curve diagram under strategy 6, Figure 8 is a simulation wind turbine fault period response characteristic curve diagram under strategy 7, Figure 9 is a simulation wind turbine fault period response characteristic curve diagram under strategy 8; Figures 10-11 is a judgment of high-low pass threshold in the embodiment of the application, wherein Figure 10 is a low-pass threshold judgment result diagram, Figure 11 is a high-pass threshold judgment result diagram; Figure 12 is a judgment diagram of whether to superimpose the initial reactive current in the embodiment of the application; Figure 13 is a double-layer particle swarm optimization framework flowchart of the embodiment of the application; Figure 14 is an error checking result diagram of test feature data and simulation feature data corresponding to different control strategies under different working conditions of the embodiment of the application, wherein, Figure 14 (a) is a small working condition reactive control error checking result diagram, Figure 14 (b) is a large working condition reactive control error checking result diagram, Figure 14 (c) is a small working condition active control error checking result diagram, Figure 14(d) is a large working condition active control error check result graph. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work under the premise that the prior art is not changed belong to the scope of protection of the present application.

[0027] It should be understood that the step numbers used herein are only for the convenience of description, and are not limited to the execution sequence of the steps.

[0028] It should be understood that the terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application and the appended claims, unless otherwise clearly indicated by the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0029] The terms "comprise" and "include" indicate the presence of described features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0030] The term "and / or" means any combination of one or more of the associated listed terms and all possible combinations thereof, and includes these combinations.

[0031] Embodiment 1 Referring to Figure 1 The present embodiment provides a new energy control parameter adaptive identification method based on double-layer particle swarm optimization, which comprises: S1, comprehensively collect controller related information of different types of heterogeneous new energy units such as wind power, photovoltaic, energy storage, SVG, etc. The controller related information covers typical control strategy documents, control parameter manuals and actual operation measured data provided by various equipment manufacturers under different working conditions. Different types of heterogeneous new energy units have their own unique control strategies due to differences in energy characteristics, working principles and application scenarios. Taking wind power as an example, the control strategy information of various types of wind turbine generators in wind farms under normal power generation, wind speed mutation, power grid fault and other typical working conditions is collected. Taking photovoltaic as an example, the control strategy related information of photovoltaic inverters in photovoltaic power stations under different light intensities, temperature changes, day and night alternation and other working conditions is obtained. Taking energy storage as an example, the controller information of energy storage systems under various working conditions such as charging, discharging, energy regulation and participation in power grid frequency modulation is collected. The control strategy of the energy storage system needs to consider battery life, charging and discharging efficiency and power grid demand and other factors. Taking SVG as an example, the control strategy information of SVG under different application scenarios such as improving power factor, stabilizing voltage and suppressing harmonics is obtained to meet the requirements of power grid for dynamic compensation of reactive power.

[0032] Based on the collected controller related information of the above heterogeneous new energy units, a comprehensive strategy database is established. The database will contain voltage-current response characteristic mathematical models of various typical control strategies for different types of units, such as common voltage control, current control and low / high penetration logic, etc. These mathematical models accurately describe the electrical response characteristics of the equipment under each control strategy in the form of formulas.

[0033] Further, in the embodiment, the strategy database includes a strategy sub-library of SVG, a strategy sub-library for wind power and photovoltaic, and a strategy sub-library of energy storage, wherein: The policy sub-library of the SVG includes SVG reactive power control policies, specifically including voltage-controlled current with superimposed initial reactive current component, specified reactive current control, specified reactive power control, SVG current remains unchanged, SVG reactive current produces a specified value change based on the value before the fault, and voltage-controlled current without superimposed initial reactive current component, wherein the SVG reactive current produces a specified value change based on the value of the SVG (static var generator) reactive current before the system fault, and a pre-set, explicit value change is generated based on the value, the SVG outputs a certain size of reactive current in the normal operation state of the power system, and this current value is the "pre-fault basis". In power system analysis, the operating state of the system before and after the fault will change significantly, and the influence of the fault on the SVG reactive current output and the subsequent control strategy can be more clearly measured by taking the pre-fault state as a reference. For example, before the fault occurs, the SVG outputs a reactive current of 50 A, which is the starting point for subsequent changes. The specified value is a fixed value set in advance by the relevant control policy or the operator according to the specific power system demand, operation target, etc. The specified value can be an increase in a certain value or a decrease in a certain value. It should be particularly noted that the SVG, as a reactive power compensation device, only involves reactive current and power regulation, and does not include active control functions.

[0034] The policy sub-library for wind power and photovoltaic power includes wind and light reactive power control policies and wind and light active power control policies, wherein the wind and light reactive power control policies include specified reactive current control and specified reactive power control; the wind and light active power control policies include specified active power control, specified active current control, pre-fault active current control, and low-voltage limit active current control.

[0035] The policy database contains a strategy sub-library of energy storage, which includes energy storage reactive power control policies and energy storage active power control policies in charging and discharging modes, wherein the energy storage reactive power control policies include specified reactive current control and specified reactive power control; the energy storage active power control policies in charging and discharging modes include specified active power control, specified active current control, pre-fault active current control, and low-voltage limit active current control.

[0036] In order to better understand the present embodiment, the policy sub-library for wind power and photovoltaic power will be described. Each policy can be expressed in the form of a formula through a corresponding voltage-current response characteristic mathematical model, which is in the form of a piecewise function, specifically: The specified reactive power policy is expressed in a formula as: ; In the formula, for specifying the reactive power; for the reactive power proportionality coefficient; for the initial reactive power; for the reactive power setpoint; The specified reactive current strategy is expressed in formula as: ; In the formula, for the specified reactive current; for the voltage proportionality coefficient; for the voltage setpoint; for the effective value of the voltage at the moment; for the initial reactive current; for the reactive current setpoint; The specified active power strategy is expressed in formula as: ; In the formula, for the specified active power; for the active power proportionality coefficient; for the initial active power; for the active power setpoint; The specified active current strategy is expressed in formula as: ; In the formula, for the specified active current; for the active current proportionality coefficient; for the initial active current; for the active current setpoint; Under the rule of the pre-crossing current value, the specified active current is equal to the initial active current, so the pre-fault active current control is expressed in formula as: ; The low-voltage limit active current strategy is expressed in formula as: ; In the formula, for the low-voltage limit value corresponding to the maximum allowed active current increment, used to limit the specified active current in the voltage range; for the high-voltage threshold voltage; for the low-voltage threshold voltage; for the maximum active current; In the control process of new energy equipment (such as wind turbine generator), active and reactive power control are not independent of each other, but there are various constraints, such as active power limit, reactive power limit, total current limit, active current limit and reactive current limit. For example, the total current capacity of the equipment is limited, when the reactive current increases, the active current needs to be reduced accordingly to ensure that the total current does not exceed the limit; at the same time, the active control will also be affected by the reactive control. This means that in actual operation, active control strategy or reactive control strategy cannot be simply considered alone, but the mutual relationship between them needs to be considered comprehensively.

[0037] In order to make the equipment run safely and efficiently under various operating conditions, it is necessary to combine the reactive control strategy and the active control strategy. Different combinations can adapt to different grid conditions and equipment states. For example, in the case of low grid voltage, it may be necessary to use a specified reactive current strategy to provide sufficient reactive support, while combining a low-voltage limited active current strategy to limit active output to ensure stable operation of the equipment; while in the case of normal grid voltage and maximum active output, a combination of specified active power strategy and appropriate reactive control strategy can be used.

[0038] Therefore, in the present embodiment, the reactive control strategy and the active control strategy are combined into multiple strategies, for example, 8 combinations can be formed by 2 reactive strategies and 4 active strategies in the present embodiment, and the above combinations can establish a strategy database , which is expressed by the formula as follows: ; In the formula, is the strategy combination, and in the present embodiment ; Preferably, in order to more accurately describe and execute these strategies, the strategy database also includes an associated parameter set for each strategy setting a value range. Through the setting of the associated parameter set, the strategy can be flexibly adjusted according to the actual running situation, and it is ensured that the new energy equipment can run stably and efficiently under different operating conditions. The associated parameter set is constructed according to the corresponding formula of the voltage-current response characteristic mathematical model of each strategy .

[0039] Taking the specified active current control strategy as an example, the formula is as follows: ; The mathematical form can be simplified to a linear form , wherein corresponds to , which has a clear physical meaning (reflecting the adjustment intensity of voltage change on active current), and the constant term then integrates the initial current correction term and the active current reference value. In the actual parameter identification process, The slope of the response curve can be directly identified, and a value range of [0.5, 1.5] pu can be set to match the device's dynamic response capability. However, All three parameters are included in the constant term in the simplified model. This leads to a redundancy problem in parameter degrees of freedom—that is, different combinations of parameters may produce the same result. To address this issue, this embodiment establishes constraints based on historical device operating data. It is limited to the average active current of the cycle preceding the fault. Constrained within 90%-110% of the rated current, while setting... The rate of change does not exceed 0.2 pu per second. This processing method effectively reduces the degree of freedom in parameter identification while preserving the physical meaning of the parameters.

[0040] To verify the effectiveness and adaptability of the aforementioned strategy library in actual wind turbine failure scenarios, this embodiment uses a simulation platform to verify the accuracy of the strategy database. Based on the eight combinations of strategy databases constructed above, wind turbine failure scenarios are simulated in the simulation environment, yielding the following results: Figures 2-9 The simulated wind turbine fault response characteristic curve shown corresponds to two reactive power control strategies and four active power control strategy combinations under eight different strategies. This curve visually demonstrates the control effect of different strategy combinations during wind turbine faults. Figure 2 Strategy 1, which combines specified reactive power control with specified active power control. Figure 3 Strategy 2, which combines specified reactive power control with specified active current control. Figure 4 Strategy 3, which adds active current control before crossing to the specified reactive power control, Figure 5 Strategy 4, which combines reactive power control with low-voltage-limited active current control, Figure 6 Strategy 5, which combines specified reactive current control with specified active current control. Figure 7 Strategy 6, which combines specified reactive current control with specified active current control. Figure 8 Strategy 7: To specify reactive current control plus active current control before crossing. Figure 9 To specify strategy 8, which combines reactive current control with low-voltage limit active current control, ensure that the dynamic response characteristic curves corresponding to the voltage-current response characteristic mathematical model in the strategy database are completely matched between the simulation data and the data.

[0041] S2, such as Figure 13As shown, a two-layer particle swarm optimization framework, comprising a global optimization layer and a local optimization layer, is constructed based on a policy database, and a hierarchical fitness function is set. This framework utilizes a two-layer particle swarm algorithm to achieve adaptive policy selection and parameter identification. The specific execution process of the two-layer particle swarm algorithm is as follows: S21, Data Preprocessing Stage: The data in the strategy database is processed, including data cleaning (e.g., removing outliers and filling in missing values) and data standardization (e.g., unifying the data scale; different data in the strategy database may have different units and ranges of values. For example, voltage data may range from hundreds of volts to thousands of volts, while current data may range from a few amperes to tens of amperes. To prevent certain data from dominating the algorithm due to their large range, it is necessary to standardize such data, such as Z-score standardization). The initial number of particles and iterations are set for the two-layer particle swarm optimization (PSO) algorithm, and a penalty term is determined. The initial number of particles determines the number of samples searched in the search space, the number of iterations specifies the maximum number of search steps for the algorithm, and the penalty term is set based on various constraints in new energy equipment control (such as active power limits, reactive power limits, total current limits, etc.) to ensure that the two-layer PSO algorithm does not violate these constraints during the search process. S22, Optimization Phase: After completing the above data preprocessing, based on the pre-designed error evaluation function, collaborative optimization is performed between the global optimization layer and the local optimization layer, with the global optimization layer serving as the upper layer and the local optimization layer as the lower layer. S221. The global optimization layer uses the Discrete Particle Swarm Optimization (PSO) algorithm to select the optimal policy combination from the policy database. This layer uses a strategy with decreasing inertial weights to search the feasible region of the parameters. During the iterative process of the PSO algorithm, its core particle update formula is used to guide the particles to find a better solution in the search space. The particle update of the global optimization layer is expressed by the formula: ; In the formula, express Global velocity at any given moment; express Global velocity at any given moment; Inertial weights; and This is the learning factor, which is usually set to a fixed value; and In order to be in Random numbers within; This represents the optimal position in the particle's history. The globally optimal position; This represents the particle's current position. In this process, the Discrete Particle Swarm Optimization (DPSO) algorithm uses the policy error function as the fitness function to evaluate different policy combinations in the policy database. The policy error function measures the quality of the current policy combination, and the optimal policy combination is obtained based on the policy error function, expressed by the formula: ; In the formula, The optimal strategy combination; The initial sample size for evaluating the effectiveness of the strategy; For the first The predicted current value corresponding to each sample; For the first The effective current value corresponding to each sample; Indicated in the policy database The goal is to find the strategy that minimizes the strategy error function among all strategy combinations, which is the strategy combination for each particle. According to strategy combination Corresponding policy error function ,Right now The fitness value is calculated; a smaller fitness value indicates a smaller error and better performance for the strategy combination. In practice, this needs to be determined based on the specific strategy combination. The wind power generation system was simulated to obtain the predicted current value. and the effective value of the current Compare the results and calculate the sum of squares of the errors.

[0042] Although the policy error function can initially assess the merits of policy combinations, iterative searches are required to find the true optimal solution due to factors such as the size of the policy database and initial information, ultimately determining the optimal combination of reactive and active power control policies. The global optimization layer is the key step in the entire optimization process; it filters possible optimal policy combinations from the large search space of the policy database, providing a foundation for subsequent local dynamic adjustments.

[0043] S222. The local optimization layer uses a continuous particle swarm optimization algorithm to continuously optimize the parameter set associated with the optimal strategy combination. This layer corrects the particle velocity in real time based on parameter error feedback, expressed by the following formula: ; In the formula, for Local velocity at a given moment; for Local velocity at a given moment; The learning rate; Momentum factor; Associating parameters for the optimal strategy combination The corresponding parameter error function; The optimal strategy combination is associated with parameters; The local optimization layer optimizes the association parameters of the optimal strategy combination using a parameter error function as the fitness function. The parameter error function measures the difference between the actual operating effect and the target state under the optimal strategy combination association parameters, and is expressed by the formula: ; In the formula, In order to comprehensively evaluate the number of data samples, in this embodiment, The number of samples collected at different time points; for The effective value of the current at any given time; By incorporating the parameter error function, improved PSO optimization is performed on the association parameters of the selected optimal strategy combination. This continuous optimization yields the optimal association parameters for the optimal strategy combination, expressed as a formula: ; In the formula, Associating optimal parameters with the optimal strategy combination; This represents the wind turbine control model, based on the optimal strategy combination. Optimal strategy combination associated parameters and external input at time The predicted current value of the wind turbine at that moment is calculated. The local optimization layer focuses on fine-tuning the associated parameters of the optimal strategy combination selected by the global optimization layer. Based on real-time parameter error feedback, it adaptively adjusts the particle velocity, thereby optimizing the associated parameters. Through continuous iterative optimization, it achieves accurate identification of the optimal associated parameters, enabling the control strategy to better adapt to the actual situation and reach the optimal strategy-parameter pair.

[0044] S3. Obtain actual unit test data, extract features from the actual unit test data to obtain test feature data, and input the test feature data into a two-layer particle swarm optimization framework to obtain the optimal policy-parameter pair. Specifically: S31. In this embodiment, the actual unit is a wind turbine. Test data of the wind turbine is obtained through semi-physical testing or on-site testing. In semi-physical testing, part of the system uses actual physical equipment, while the other part is simulated by computer simulation models. For example, when testing a wind turbine, an actual generator and controller can be used, while the power grid part uses a simulation model to simulate different fault conditions. The operating data of the unit under different fault ride-through conditions obtained in this way is the semi-physical test data. On-site testing is to conduct fault ride-through testing on the unit at the actual power production site.

[0045] The actual unit test data is expressed by a formula as follows: In the formula, is the actual unit test data, i.e., the wind turbine test data in the embodiment; is the active current effective value at the moment; is the reactive current effective value at the moment.

[0046] The actual unit test data is subjected to feature extraction, and redundant information that has no direct influence on analysis of the unit fault ride-through performance is removed, and only key data that can best reflect the unit fault ride-through characteristics are retained. Specifically, in the embodiment, the fault partition method is adopted to divide the actual unit test data into a low-voltage ride-through zone, a steady-state zone and a high-voltage ride-through zone, the active current effective value, the reactive current effective value and the voltage effective value in each zone are extracted, and the extracted values are taken as the test feature data, i.e., test feature data S32, the test feature data is input into an algorithm, under the collaborative optimization framework of the global optimization layer and the local optimization layer, the upper layer is subjected to a preset number of cycles, in the embodiment, the preset number is 6, and in each upper layer cycle, the strategy combination is adjusted or the search direction is changed to expand the search space and find a better strategy combination.

[0047] Preferably, each upper layer cycle is also subjected to a lower layer cycle to optimize the strategy combination associated parameters.

[0048] Through the continuous upper and lower layer collaborative optimization cycles, the total error index of each strategy-parameter pair is calculated, and the total error index is expressed by a formula as follows: In the formula, is the total error index; is the optimal strategy combination corresponding to the strategy error function; is the optimal strategy combination associated optimal parameter corresponding to the parameter error function; Preferably, in order to keep the order of magnitude consistent, the embodiment also provides another formula for calculating the total error index as follows: In the formula, and are weight coefficients of the total error index; ​​​​​​​When the total error index is less than the preset error threshold, it is considered that the optimization is completed, and the current strategy-parameter pair is output as the optimal strategy-parameter pair, otherwise, re-optimization is performed. For example, in the embodiment, the preset error threshold is 2%, and the optimization is completed when the total error index is less than 2%, and the optimal strategy-parameter pair is obtained.

[0049] S33, preferably, the embodiment further includes synchronously drawing a stepped voltage curve when feature extraction is performed on the actual unit test data, and when a current mutation is detected, as shown in Figures 10-11 , the voltage threshold of the stepped voltage curve is taken as a high threshold and a low threshold, Figure 10 the low threshold is judged as a low threshold, Figure 11 the high threshold is judged as a high threshold, and the high and low threshold values are used to define the interval boundaries of the piecewise function of the voltage-current response characteristic mathematical model in the strategy database.

[0050] S34, the embodiment further includes, when feature extraction is performed on the test data, through the fault ride-through test data under different initial reactive power values in the test data (as shown in Figure 12 , first, analyze whether the reactive current changes of different initial reactive power values during the fault are consistent, that is, by comparing the change trend and amplitude of the reactive current with time under different initial reactive power values, it is judged whether the changes are consistent; If it is difficult to accurately determine by intuitive comparison, further correlation analysis is used to accurately determine the current superposition mode, the correlation coefficient between the reactive current changes under different initial reactive power values is calculated, and the correlation coefficient is determined according to the size: When the correlation coefficient of the reactive current changes under different initial reactive power values during the fault is greater than a preset correlation coefficient threshold, it indicates that the consistency of the reactive current changes is high, and it is determined as an incremental mathematical model; When the correlation coefficient of the reactive current changes under different initial reactive power values during the fault is less than or equal to the preset correlation coefficient threshold, it indicates that the consistency of the reactive current changes is low, and it is determined as an absolute value mathematical model; The current superposition mode is used to control the optimal strategy combination selection process of the global optimization layer, and only the mathematical model of the corresponding type in the strategy database is activated.

[0051] S4, in order to verify the effectiveness and accuracy of the method of the embodiment, a simulation model is constructed by using the optimal strategy-parameter pair obtained by step S3, and simulation data generated by the simulation model is subjected to feature extraction to obtain simulation feature data .

[0052] ​Error checking is performed on the test characteristic data and the simulation characteristic data, and the error checking adopts mean square error (MSE), mean absolute error (MAE) or relative error. In this embodiment, the relative error is adopted for error checking, error checking results are obtained, and the error checking results are visually displayed, including drawing line graphs, column graphs and other graphs, so as to intuitively display the comparison and error distribution of the test characteristic data and the simulation characteristic data. In this embodiment, as shown in FIG. 22, the actual data is tested in two working conditions of large and small. The small working condition refers to that the initial active power is 0.2Pn, and the large working condition refers to that the initial active power is 0.9Pn. Here, Pn is the rated power. Figure 14 Figure 14 (a) and Figure 14 (c) are a group, which are respectively small working condition reactive power control identification verification and active power control identification verification, Figure 14 (b) and Figure 14 (d) are a group, which are respectively large working condition reactive power control identification verification and active power control identification verification. By comparing the differences between the test data and the simulation data, the simulation characteristic data is visually displayed, the point error of the simulation characteristic data tracking the test characteristic data is within 0.02, which proves the effectiveness of the method in this embodiment and verifies the accuracy of the simulation model.

[0053] It is worth noting that the above control strategy identification method and steps are universal. The SVG simulation modeling only needs to refer to the above steps to identify the reactive power control strategy and parameters; the energy storage simulation modeling needs to consider the active and reactive power control strategies in the charging and discharging modes respectively. The mathematical model expressions of the strategies in different modes are consistent with the control strategies of wind power and photovoltaic power, which does not affect the identification steps and methods. Therefore, the parameter identification process of the SVG and the energy storage is not repeated.

[0054] Embodiment 2 The embodiment provides an electronic device, including a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the new energy control parameter adaptive identification method based on double-layer particle swarm optimization according to any embodiment of the present application when executing the program.

[0055] Embodiment 3 The embodiment provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the new energy control parameter adaptive identification method based on double-layer particle swarm optimization according to any embodiment of the present application.

[0056] It is worth noting that the electronic device and the computer readable storage medium of the present application are based on the same inventive concept as the method of embodiment 1 of the present application, and will not be repeated here.

[0057] ​In the embodiments of the present application, “at least one” means one or more, and “multiple” means two or more. “And / or” describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B can represent the cases of A alone, A and B together, and B alone. Wherein A and B can be singular or plural. The character “ / ” generally represents an “or” relationship between the front and rear associated objects. “At least one of the following” and the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, and c can be single or multiple.

[0058] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be realized in electronic hardware, computer software, and a combination of electronic hardware and computer software. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0059] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0060] In several embodiments provided by the present application, any function realized in the form of a software function unit and sold or used as an independent product can be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory; hereinafter referred to as: ROM), a random access memory (Random Access Memory; hereinafter referred to as: RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0061] The above only describes the embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation based on the content of the specification and drawings of the present application, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An adaptive identification method for new energy control parameters based on two-layer particle swarm optimization, characterized in that, The method includes: By integrating the typical control strategies of four types of heterogeneous new energy units, namely wind power, photovoltaic, energy storage and SVG, a strategy database is constructed that includes a mathematical model of voltage-current response characteristics with multiple different typical control strategies, the value range of parameters associated with each control strategy and the initial parameter values. The mathematical model of voltage-current response characteristics is in the form of a piecewise function. Obtain actual unit test data, extract features from the test data, and obtain test feature data; A two-layer particle swarm optimization framework, comprising a global optimization layer and a local optimization layer, is constructed based on a policy database, and a hierarchical fitness function is set. The test feature data is input into a two-layer particle swarm optimization framework, which outputs the optimal policy-parameter pair. The global optimization layer uses a discrete particle swarm algorithm, which selects the optimal policy combination using the policy error function as the fitness function. The local optimization layer uses a continuous particle swarm algorithm, which optimizes the associated parameters of the optimal policy combination using the parameter error function as the fitness function.

2. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, The strategy database contains a strategy sub-library of SVG, which includes SVG reactive power control strategies, specifically including voltage-controlled current with superimposed initial reactive current component, specified reactive current control, specified reactive power control, SVG current remaining unchanged, SVG reactive current changing to a specified value based on the pre-fault condition, and voltage-controlled current without superimposed initial reactive current component.

3. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, The strategy database includes strategy sub-libraries for wind power and photovoltaics, which include wind and solar reactive power control strategies and wind and solar active power control strategies. The wind and solar reactive power control strategies include specified reactive current control and specified reactive power control; the wind and solar active power control strategies include specified active power control, specified active current control, active current control based on pre-fault conditions, and low-voltage limit active current control.

4. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, The strategy database includes a strategy sub-library for energy storage, which includes energy storage reactive power control strategies and energy storage active power control strategies under charging and discharging modes. The energy storage reactive power control strategies include specified reactive current control and specified reactive power control. The energy storage active power control strategies under charging and discharging modes include specified active power control, specified active current control, active current control based on pre-fault conditions, and low-voltage limit active current control.

5. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, The method further includes: After constructing the strategy database, the accuracy of the strategy database is verified through a simulation platform to ensure that the simulation data and the dynamic response characteristic curves corresponding to the voltage-current response characteristic mathematical model in the strategy database are completely matched.

6. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, The method further includes: When extracting features from actual unit test data, a stepped voltage curve is plotted simultaneously. When a sudden change in current is detected, the voltage critical value of the stepped voltage curve is used as the high and low breakdown threshold. The high and low breakdown threshold is used to define the boundary of the piecewise function interval of the mathematical model of voltage-current response characteristics in the strategy database.

7. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 6, characterized in that, The method further includes: When extracting features from the test data, the fault ride-through test data under different initial reactive power values ​​are analyzed to determine whether the reactive current changes during the fault are consistent, and the current superposition mode is determined based on the correlation. Specifically: By comparing the trend and magnitude of reactive current changes over time with different initial reactive values, we can determine whether the changes are consistent and calculate the correlation coefficient between reactive current changes under different initial reactive values. When the correlation coefficient of reactive current changes with different initial reactive values ​​during the fault period is greater than the preset correlation coefficient threshold, it is determined to be an incremental mathematical model. When the correlation coefficient of reactive current change with different initial reactive values ​​during the fault period is less than or equal to the preset correlation coefficient threshold, it is determined to be an absolute value mathematical model. The current superposition mode is used to control the optimal strategy combination selection process of the global optimization layer, and only activates the corresponding type of mathematical model in the strategy database.

8. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, The feature extraction of the test data adopts the fault partitioning method, which divides the test data into low voltage ride-through zone, steady state zone and high voltage ride-through zone. The effective values ​​of active current, reactive current and voltage are extracted in each zone and the extracted values ​​are used as test feature data.

9. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, The method further includes constructing an association parameter set by combining the value ranges and initial parameter values ​​of the associated parameters of each control strategy. .

10. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, The particle update in the iterative process of the discrete particle swarm optimization algorithm is expressed by the following formula: ； In the formula, express Global velocity at any given moment; express Global velocity at any given moment; Inertial weight; and For learning factors; and In order to be in Random numbers within; This represents the optimal position in the particle's history. The globally optimal position; This represents the particle's current position. During particle update, the Discrete Particle Swarm Optimization (DPSO) algorithm evaluates different policy combinations in the policy database using a policy error function. This policy error function measures the quality of the current policy combination, and the optimal policy combination is obtained based on this function, expressed by the following formula: ； In the formula, The optimal strategy combination; The initial sample size for evaluating the effectiveness of the strategy; For the first The predicted current value corresponding to each sample; For the first The effective current value corresponding to each sample; Indicated in the policy database Find the strategy that minimizes the policy error function among all strategy combinations. ; For strategy combination The corresponding strategy error function.

11. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, The optimization process of the continuous particle swarm optimization algorithm is as follows: The local optimization layer corrects particle velocities in real time based on parameter error feedback, expressed by the following formula: ； In the formula, for Local velocity at a given moment; for Local velocity at a given moment; The learning rate; Momentum factor; Associating parameters for the optimal strategy combination The corresponding parameter error function; The optimal strategy combination is associated with parameters; The parameter error is expressed by the formula: ； In the formula, To comprehensively evaluate the number of data samples; for The effective value of the current at any given time; for The effective value of the voltage at any given time; By optimizing the correlation parameters of the selected optimal strategy combination based on the parameter error, the optimal correlation parameters of the optimal strategy combination are obtained, which can be expressed by the formula: ； In the formula, Associating optimal parameters with the optimal strategy combination; This represents the unit control model, based on the optimal strategy combination. Optimal strategy combination associated parameters and external input at time Calculate the unit The predicted current value at that moment; Indicates in the associated parameter set Find the correlation parameter that minimizes the parameter error function value. .

12. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, Output the optimal policy-parameter pair, specifically: In the two-layer particle swarm optimization framework, the global optimization layer performs a preset number of iterations, and after the policy optimization iteration of the global optimization layer, the parameter optimization iteration of the local optimization layer is performed. Through the two-layer collaborative optimization iteration, the total error index of each policy-parameter pair is calculated, expressed by the formula: ； In the formula, This is the total error index; For the optimal strategy combination The corresponding policy error function; Associating optimal parameters with the optimal strategy combination The corresponding parameter error function; When the total error index is less than the preset error threshold, the optimization is considered complete, and the current policy-parameter pair is output as the optimal policy-parameter pair; otherwise, the optimization is restarted.

13. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, The method further includes constructing a simulation model based on the optimal strategy-parameter pair, extracting features from the simulation data generated by the simulation model to obtain simulation feature data, and performing error verification on the test feature data and simulation feature data. The error verification adopts mean square error (MSE), mean absolute error (MAE), or relative error.

14. The adaptive identification method for new energy control parameters based on two-layer particle swarm optimization according to claim 1, characterized in that, The method also includes visualizing the error verification results.

15. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the adaptive identification method for new energy control parameters based on two-layer particle swarm optimization as described in any one of claims 1 to 14.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the adaptive identification method for new energy control parameters based on two-layer particle swarm optimization as described in any one of claims 1 to 14.

Images