Micro-grid dynamic model simplification method

Abstract

The invention discloses a micro-grid dynamic model simplification method, which belongs to the technical field of data processing and computer application, and comprises the following steps: obtaining a real-time operation data set of a micro-grid, and obtaining a dynamic feature vector through dynamic feature hierarchical extraction; performing structure-parameter joint order reduction processing on the dynamic feature vector to generate an order reduction parameter set; executing a multi-objective optimization decision based on the reduced-order parameter set, and generating an optimization decision parameter; generating a simplified dynamic model according to the optimization decision parameters; wherein the dynamic feature hierarchical extraction adopts a preset frequency band division rule, and the structure-parameter joint order reduction processing comprises screening by using a preset sensitivity threshold. According to the method, the dynamic feature hierarchical extraction and structure-parameter combined order reduction technology is adopted, and the multi-target game optimization and error adaptive compensation mechanism is combined, so that the calculation efficiency can be remarkably improved while the dynamic simulation precision is ensured, and the requirements of different micro-grid operation conditions are met.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and computer applications, and particularly to a method for simplifying a microgrid dynamic model. Background Art

[0002] Microgrid dynamic modeling is one of the core technologies for power system analysis and control, which reflects the real-time dynamic characteristics of the microgrid through mathematical simulation. In the prior art, the dynamic model usually needs to run in the full-order mode to ensure accuracy, but the high-dimensional characteristics of the full-order model will lead to excessive consumption of computing resources and it is difficult to meet the requirements of real-time decision-making.

[0003] Currently, traditional reduction methods mainly adopt balanced truncation method or modal analysis method to achieve dimension reduction by removing high-frequency dynamic modes or low-sensitivity parameters. There are also methods that extract features through a fixed time window and combine empirical thresholds to screen key variables. In addition, the prior art obtains a set of reduced-order parameters through single-objective optimization, such as only pursuing the minimum voltage error, without considering the comprehensive balance of computing efficiency and system dynamic response ability.

[0004] However, the traditional feature extraction has a fixed time window length and cannot adapt to the changes in dynamic characteristics of different frequency bands, resulting in the misremoval of high-frequency key modes; the static sensitivity threshold is difficult to adapt to multi-condition scenarios, and the generalization ability of the set of reduced-order parameters is insufficient; the single-objective optimization process ignores key constraints such as topological response time, resulting in frequent decision failures of the model under complex conditions and relying on the full-order model to be reconstructed repeatedly. Summary of the Invention

[0005] To solve the above problems, the present invention provides a method for simplifying a microgrid dynamic model, which adopts dynamic feature hierarchical extraction and structure-parameter joint reduction technology, combines multi-objective game optimization and error adaptive compensation mechanism, and can significantly improve the computing efficiency while ensuring the accuracy of dynamic simulation and meet the requirements of different microgrid operating conditions.

[0006] The above object can be achieved by the following solutions: A method for simplifying a microgrid dynamic model, including obtaining a real-time operation data set of the microgrid, and obtaining a dynamic feature vector through dynamic feature hierarchical extraction; performing structure-parameter joint reduction processing on the dynamic feature vector to generate a set of reduced-order parameters; performing multi-objective optimization decision-making based on the set of reduced-order parameters to generate optimized decision-making parameters; generating a simplified dynamic model according to the optimized decision-making parameters; wherein, the dynamic feature hierarchical extraction adopts a preset frequency band division rule, and the structure-parameter joint reduction processing includes screening using a preset sensitivity threshold.

[0007] Optionally, the obtaining of the real-time operation data set of the microgrid and the extraction of the dynamic feature vectors through hierarchical extraction of dynamic features include: collecting the voltage volatility and power change rate of the microgrid nodes to form an original feature matrix; intercepting the original feature matrix according to a preset sliding time window to generate a windowed feature matrix, where the length of the sliding time window is adjusted according to a preset window adjustment coefficient; performing spectral feature extraction and non-steady state detection on the windowed feature matrix according to a preset frequency band division rule, and outputting dynamic feature vectors.

[0008] Optionally, the performing of the structure-parameter joint order reduction processing on the dynamic feature vectors to generate a set of reduced-order parameters includes: decomposing the dynamic feature vectors into a fast-changing feature subset and a slow-changing feature subset; calculating the sensitivity of the variables in the fast-changing feature subset, and removing the variables in the fast-changing feature subset whose sensitivity is lower than a preset sensitivity threshold to generate a fast-changing reduced-order subset; adjusting the variables in the fast-changing reduced-order subset by using a preset dynamic compensation factor, and combining with the slow-changing feature subset to obtain a set of reduced-order parameters.

[0009] Optionally, the sensitivity threshold includes: extracting the spectral feature parameters of the dynamic feature vectors; calculating the contribution degree index of the variables according to the spectral feature parameters and a preset frequency band weight coefficient; generating the sensitivity threshold according to the contribution degree index; where the update period of the sensitivity threshold is synchronized with the adjustment period of the sliding time window.

[0010] Optionally, the method further includes: extracting the comparison data of the state variables of the reduced-order model and the full-order model from a preset historical operation log to construct a historical reduced-order error data set; performing cross-correlation on the historical reduced-order error data set and the spectral feature parameters to calculate a gain coefficient; and correcting the dynamic compensation factor by using the gain coefficient.

[0011] Optionally, the performing of the multi-objective optimization decision based on the set of reduced-order parameters to generate optimization decision parameters includes: constructing an accuracy-efficiency game model, where the accuracy-efficiency game model uses the set of reduced-order parameters as input variables; the accuracy-efficiency game model performing a multi-stage Pareto optimization process and performing feature matching with a preset typical working condition scenario library to generate preliminary decision parameters; and performing a three-level fault tolerance correction on the preliminary decision parameters to output optimization decision parameters.

[0012] Optionally, the performing of the multi-stage Pareto optimization process includes: constructing a first objective pair of voltage error rate and calculation time consumption in the first stage; superimposing the topology change response time in the second stage to form a three-objective optimization space; applying a preset algorithm to obtain an iterative solution set in the three-objective optimization space; and performing feature matching on the iterative solution set with a preset typical working condition scenario library to generate preliminary decision parameters.

[0013] Optionally, a three - level fault - tolerance correction is performed on the preliminary decision parameters, and the output optimized decision parameters include: performing a critical constraint verification on the preliminary decision parameters to generate a verification result, where the critical constraint verification includes an impedance matching test and a power conservation test; triggering residual compensation according to the verification result and performing the critical constraint verification again to generate a compensation result; generating a full - order model reconstruction instruction according to the compensation result.

[0014] Optionally, the construction of the typical operating condition scenario library includes: collecting benchmark model parameters under multiple operating modes to form an original scenario set; extracting feature fingerprints from the original scenario set to generate fingerprint coding vectors; binding the fingerprint coding vectors with the hash values of the blockchain storage module; performing pre - loading matching according to the similarity between the dynamic feature vectors and the fingerprint coding vectors during the real - time operation process.

[0015] Optionally, the method further includes: collecting the voltage volatility and power change rate output by the simplified dynamic model to obtain a predicted operation data set; using the predicted operation data set and the real - time operation data set to calculate an error index; updating the frequency band division rule and the frequency band weight coefficient according to the magnitude of the error index.

[0016] Compared with the prior art, the present invention has the following advantages: 1. Through dynamic feature hierarchical extraction and structure - parameter joint order reduction processing, the present invention significantly reduces the complexity of the model; while ensuring the simulation accuracy, it effectively reduces the calculation time consumption, and solves the problem of low calculation efficiency of the traditional full - order model in high - dynamic change scenarios. 2. The present invention introduces a multi - objective optimization decision - making mechanism to optimize the game balance between accuracy and efficiency; through the matching of the Pareto optimization process and the typical operating condition scenario library, it can automatically generate highly adaptable optimal decision parameters under complex operating conditions, avoiding the loss of key dynamic characteristics caused by single - objective optimization. 3. Based on the dynamic compensation factor correction technology of historical error data, the present invention enhances the robustness of the model; through the error feedback mechanism across time scales, it can correct the order - reduction parameter deviation in real time, improving the adaptability of the simplified model to the non - steady - state conditions of the micro - grid, and solving the problem of long - term cumulative errors caused by static compensation in traditional methods.

[0017] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures pointed out in the specification, claims, and drawings. Brief Description of the Drawings

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a schematic flowchart of a method for simplifying the dynamic model of a microgrid according to an embodiment of the present invention.

[0020] Figure 2 It is a schematic diagram of the three - band sensitivity distribution according to an embodiment of the present invention.

[0021] Figure 3 It is a schematic diagram of the Pareto optimization space according to an embodiment of the present invention.

[0022] Figure 4 It is a schematic diagram of the three - level fault - tolerant correction effect according to an embodiment of the present invention. Specific embodiments

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0024] Refer to Figure 1 , an embodiment of the present invention proposes a method for simplifying the dynamic model of a microgrid. By using the technology of dynamic feature hierarchical extraction and structure - parameter joint order reduction, combined with multi - objective game optimization and error adaptive compensation mechanism, it can significantly improve the calculation efficiency while ensuring the dynamic simulation accuracy, and meet the requirements of different microgrid operating conditions.

[0025] The specific steps of the method in this embodiment are as follows: Obtain the real - time operation data set of the microgrid, and obtain the dynamic feature vector through dynamic feature hierarchical extraction; Perform structure - parameter joint order reduction processing on the dynamic feature vector to generate a set of reduced - order parameters; Execute multi - objective optimization decision - making based on the set of reduced - order parameters to generate optimized decision - making parameters; Generate a simplified dynamic model according to the optimized decision - making parameters; Among them, the dynamic feature hierarchical extraction adopts a preset frequency band division rule, and the structure - parameter joint order reduction processing includes screening using a preset sensitivity threshold.

[0026] Specifically, the frequency-domain decomposition is performed on the real-time operation data according to the preset frequency band division rule, and the dynamic response characteristics of the microgrid are distinguished into high-frequency transient components (such as the inverter switching frequency band) and low-frequency steady-state components (such as the slow dynamics of power regulation). An adjustable sliding time window is used to adaptively adjust the sampling period. A short window is used in the high-frequency band to improve the time resolution, and a long window is used in the low-frequency band to enhance the feature stability. A dynamic generation model of the parameter sensitivity threshold is established, and the contribution index of each parameter is calculated based on the frequency band weight coefficient and historical error data. For high-frequency fast-changing parameters, the key disturbance sources are retained by screening through the sensitivity threshold; for low-frequency slow-changing parameters, lossless retention is performed, and at the same time, a dynamic compensation factor is introduced to eliminate the energy loss caused by order reduction. A Pareto optimization space is constructed based on the accuracy-efficiency game model, and feature matching is performed in combination with the typical working condition scenario library. Through a three-level fault-tolerant verification system, the convergence reliability of the model simplification process is ensured, and a positive feedback loop of parameter screening and decision optimization is realized. Through the fusion of data-driven and physical models, the technical framework limitation of the single-objective optimization of accuracy and efficiency in traditional order reduction methods is broken through, and the collaborative optimization of feature extraction, parameter order reduction, and decision optimization is realized.

[0027] Optionally, the obtaining of the real-time operation data set of the microgrid and the dynamic feature vector obtained by dynamic feature hierarchical extraction include: Collect the voltage volatility and power change rate of the microgrid nodes to form an original feature matrix; Intercept the original feature matrix according to the preset sliding time window to generate a windowed feature matrix, wherein the length of the sliding time window is adjusted according to the preset window adjustment coefficient; Perform spectral feature extraction and non-steady state detection on the windowed feature matrix according to the preset frequency band division rule, and output a dynamic feature vector.

[0028] Specifically, first deploy voltage sensors and power monitoring devices to collect the real-time voltage volatility and power change rate of each node of the microgrid. Assume that the microgrid contains n nodes. The real-time voltage volatility and power change rate collected at each sampling time point t form an n×2-dimensional vector, and the data of T consecutive sampling time points are stacked in chronological order to form an n×2×T-dimensional original feature matrix . Subsequently, a sliding time window is used to segment and intercept the original feature matrix. The initial time window length is , and the window length is dynamically adjusted according to the window adjustment coefficient. When high-frequency fluctuations are detected, the time window is narrowed to improve the time resolution, and in the low-frequency band, the time window is widened to enhance the feature stability, and finally a windowed feature matrix is obtained . Then, for Perform multi-band spectrum sensing, extract the mean square deviation of the amplitude of the feature matrix in the preset frequency band as the spectrum parameter through discrete Fourier transform. The preset frequency band is determined by the preset frequency band division rule, for example, low frequency < 1 Hz, medium frequency is 1 - 10 Hz, high frequency > 10 Hz. At the same time, perform non-steady state detection on the data within the window, identify the non-steady state mutation moment by calculating the peak value of the second derivative of the signal, and finally combine the spectrum parameter and the non-steady state identification value into a dynamic feature vector 。

[0029] Exemplarily, for a microgrid system including 5 photovoltaic nodes and 3 energy storage nodes, collect the real-time voltage volatility and power change rate of each node at a sampling frequency of 1 kHz. The original feature matrix forms a 5×2×10000 matrix within 10 seconds. The initial time window L is set to 50 sampling points (0.05 seconds). When the sliding variance of the power change rate exceeds the threshold, the window adjustment coefficient is 0.5 to shorten the window to 25 sampling points; when the fluctuation is gentle, the window adjustment coefficient is adjusted to 1.2 to expand to 60 sampling points. In spectrum sensing, the window data is divided into three frequency bands: low frequency 0 - 0.5 Hz, medium frequency 0.5 - 5 Hz, and high frequency 5 - 50 Hz, and the energy ratio of the voltage volatility within each frequency band is calculated. In non-steady state detection, by calculating the second derivative of the power change rate within the window, the threshold is set to 3 times the standard deviation of the historical steady state data. When the second derivative of 3 consecutive sampling points exceeds the set threshold, it is marked as a non-steady state event. Finally, a 28-dimensional dynamic feature vector composed of 5 nodes × 3 frequency band energy coefficients + non-steady state flag bits is generated

[0030] Optionally, perform structure-parameter joint order reduction processing on the dynamic feature vector, and the generated order reduction parameter set includes: Decompose the dynamic feature vector into a fast-changing feature subset and a slow-changing feature subset; Calculate the sensitivity of the variables in the fast-changing feature subset, remove the variables in the fast-changing feature subset whose sensitivity is lower than the preset sensitivity threshold, and generate a fast-changing order reduction subset; Adjust the variables in the fast-changing order reduction subset using a preset dynamic compensation factor, and combine with the slow-changing feature subset to obtain the order reduction parameter set

[0031] Specifically, as Figure 2 shown, first, based on the spectrum decomposition characteristics of the dynamic feature vector, divide the vector into a fast-changing feature subset and a slow-changing feature subset. Specifically, through a preset frequency band division threshold , for example , classify the feature entries corresponding to the high-frequency components greater than or equal to in the spectrum feature parameters into the fast-changing feature subset , and classify the entries corresponding to the low-frequency components into the slow-changing feature subset . Subsequently, a sensitivity value evaluation method is adopted to evaluate each variable in the fast-changing feature subset to calculate its sensitivity to the system dynamic response : , where is the maximum deviation of the node voltage. Set the sensitivity threshold . When , determine that the variable is a minor disturbance source and eliminate it to form a fast-changing reduced-order subset . For the fast-changing reduced-order subset , introduce a dynamic compensation factor : , where is the fluctuation variance of the eliminated variable, is the total fluctuation variance. Based on the dynamic compensation factor, increase the weight of adjacent frequency (1Hz) components in the fast-changing reduced-order subset . Finally, merge the slow-changing feature subset with the compensated fast-changing reduced-order subset to generate a reduced-order parameter set .

[0032] Exemplarily, the dynamic characteristic vectors of a microgrid containing 2 wind turbines and 4 energy storage units include 8 groups of frequency band energy coefficients. Set , where 4 characteristic items corresponding to the high-frequency components (5Hz, 7Hz) of the wind turbine nodes are classified into the fast-changing feature subset , and the low-frequency components (0.2Hz, 1Hz) of the energy storage units form the slow-changing feature subset . By calculating the sensitivity , it is found that the sensitivity of the 0.2Hz component of the energy storage unit is 0.05, which is lower than the preset sensitivity threshold of 0.1. Eliminate this characteristic item. The of the eliminated feature is 0.003, and the total variance is 0.012. The dynamic compensation factor . Increase the weight of adjacent frequency (1Hz) components in the fast-changing reduced-order subset according to the dynamic compensation factor. Finally, the reduced-order parameter set contains 6 core characteristic items. Through modal separation, the coupling effect between the fast dynamics caused by the pitch regulation of the wind turbine and the slow fluctuation characteristics of the grid frequency is accurately distinguished. The dynamic adjustment of the sensitivity threshold avoids the interference of high-frequency noise modes on the model accuracy, and the compensation factor effectively makes up for the energy loss caused by feature screening. The collaborative reduced-order processing of fast and slow-changing features significantly improves the adaptability of the model to the fault ride-through scenario of doubly-fed wind turbines.

[0033] Optionally, the sensitivity threshold includes: Extract the spectral feature parameters of the dynamic feature vector; Calculate the contribution index of the variable according to the spectral feature parameters and the preset frequency band weight coefficients; Generate a sensitivity threshold according to the contribution index; Wherein, the update period of the sensitivity threshold is synchronized with the adjustment period of the sliding time window.

[0034] Specifically, first extract the energy ratio parameters of each frequency band from the dynamic feature vector , where k represents the frequency band index. Define the contribution index of a single variable as : , where is the preset frequency band weight coefficient, represents the energy ratio of the variable in the k frequency band, is the total energy. For the sensitivity threshold , there is: , where is the basic threshold coefficient, is the shape adjustment factor. When the variable contribution index increases, the sensitivity threshold exponentially decays. The above parameters , are all positively correlated with the current sliding time window length L and the window adjustment coefficient. When the time window is shortened, for the updated basic threshold coefficient , there is: , where, is the original basic threshold coefficient, so as to ensure that the sensitivity threshold update period is completely synchronized with the time window adjustment.

[0035] Exemplarily, the dynamic feature vector of a three-phase inverter grid-connected node contains 3 frequency bands (0.5 - 2 Hz), (2 - 10 Hz), (10 - 50 Hz) energy ratios. Let the weight , calculate the contribution index to be 0.425. At this time, the basic threshold , the current time window length is adjusted to , then the updated basic threshold of g , take the shape adjustment factor to get At this time, if the sensitivity of a certain parameter is 0.16, which is less than the sensitivity threshold of 0.175, then this parameter will be eliminated. The contribution degree calculation based on the frequency band energy ratio can accurately reflect the dynamic influence differences of different variables in the key frequency bands. Through the anti-correlation dynamic threshold function, low-threshold protection of high-contribution degree parameters is achieved, effectively avoiding the mis-elimination of important dynamic modes. The threshold parameter is updated in real time with the window adjustment to ensure that the sensitivity criterion always matches the time resolution of the current analysis period. This adaptive mechanism in the microgrid containing multiple power sources of wind, light, and energy storage can not only quickly reduce the slow dynamic redundant parameters of the energy storage system but also completely retain the fast fluctuation characteristics of the photovoltaic output, ensuring the simulation accuracy of the dynamic model under variable time scales.

[0036] Optionally, the method further includes: Extracting the comparison data of the state variables of the reduced-order model and the full-order model from the preset historical operation log to construct a historical reduced-order error data set; Cross-correlating the historical reduced-order error data set with the spectral feature parameters to calculate the gain coefficient; Using the gain coefficient to correct the dynamic compensation factor.

[0037] Specifically, to construct the historical reduced-order error data set, the comparison data of the state variables of the reduced-order model and the full-order model needs to be extracted from the system historical operation log. Define the error term as the absolute percentage deviation of the voltage amplitude of the reduced-order model from the value of the full-order model on the same time section, and construct the error set according to the time stamp sequence . Construct an error feedback link. By correlating and learning the error data set with the spectral feature parameters of the dynamic feature vector, cross-time-scale feature matching is achieved. Specifically, extract the k main frequency band energy weight coefficients in the dynamic feature vector at the current moment to form a frequency band weight vector ; perform weighted moving average processing on the historical reduced-order error data set to generate a time-varying error memory sequence : , where is the forgetting factor, with a range of 0.9 - 0.99, is the length of the time window. Establish the correlation matrix between the frequency band weight vector and the error memory sequence , where ⊗ represents the Kronecker product, and output a k×m-dimensional correlation tensor. Perform a bilinear pooling operation on the correlation tensor R to calculate the gain coefficient : , where U and V are trainable parameter matrices for the bilinear pooling operation, is the Sigmoid function, which is used to compress the gain coefficient into the interval (0, 1), and ⊙ represents the element-wise product. The gain coefficient is applied to the original dynamic compensation factor to obtain the corrected dynamic compensation factor : , where is the current dynamic compensation factor, is the learning rate parameter, and its value ranges from 0.01 to 0.1. During this process, the cross-correlation between the spectral feature parameters and the historical error can identify the model mismatch law in a specific frequency band. For example, when the error in the high-frequency band accumulates continuously, the activation value of the corresponding channel in the correlation matrix increases, and the intensity of the dynamic compensation factor in this frequency band is increased through the gain coefficient to achieve adaptive error suppression

[0038] Exemplarily, taking a microgrid with 3 sets of energy storage converters as an example, the main frequency bands k = 3 (0.5 - 2 Hz, 2 - 5 Hz, 5 - 10 Hz) are set. When the average error in the 5 - 10 Hz frequency band in 10 consecutive window periods, that is, the time-varying error memory sequence reaches 1.2%, the weight of this frequency band . After calculation by the correlation matrix, the corresponding channel is activated to generate the gain coefficient . Assuming the original compensation factor , the learning rate , then the corrected compensation factor . By strengthening the high-frequency band compensation, the reduced-order model can still keep the simulation error of the bus voltage below 0.5% when the photovoltaic output fluctuates rapidly. The dynamic association between error memory and spectral features can adaptively locate the frequency-domain root cause of model mismatch. The bilinear pooling mechanism can decouple the coupling effects of errors in different frequency bands, and the non-linear mapping of the gain coefficient avoids over-amplifying noise in single-frequency band compensation, ensuring that the correction process of the compensation factor has frequency-domain selectivity and time-domain smoothness, and effectively improving the model accuracy margin in the scenario of drastic changes in wind and light output

[0039] Optionally, performing multi-objective optimization decision-making based on the set of reduced-order parameters, and the generated optimization decision parameters include: Constructing an accuracy-efficiency game model, and the accuracy-efficiency game model uses the set of reduced-order parameters as input variables; The accuracy-efficiency game model performs a multi-stage Pareto optimization process and matches features with a preset typical working condition scenario library to generate preliminary decision parameters; Performing three-level fault tolerance correction on the preliminary decision parameters and outputting optimization decision parameters

[0040] Specifically, as Figure 3As shown in the figure, first, a precision-efficiency game model is constructed. The key parameters in the reduced-order parameter set are mapped to the optimization input variables, and the model voltage error rate index is defined. And the calculation time-consuming index . Secondly, multi-stage Pareto optimization is performed. In the first stage, minimizing and is taken as the optimization direction to generate the initial Pareto solution set; in the second stage, the topological change response time index is superimposed to form a three-dimensional objective space, and the dominance level of the solution set is adjusted through adaptive weights. Finally, a three-level fault tolerance correction is performed on the Pareto front solution: in the first step, it is checked whether the voltage error rate exceeds the preset residual threshold; if it exceeds, the steady-state residual compensation module is activated to inject correction current into the key nodes; if it still does not meet the requirements after compensation, the full-order model reconstruction is triggered, and the reference model parameters are quickly matched through the typical operating condition scheme library. Among them, the matching logic of the typical operating condition scheme library is to calculate the cosine similarity of the feature fingerprints between the reduced-order parameter set and the schemes in the library, and select the scheme with the highest similarity and the lowest historical error as the reference benchmark to generate the preliminary decision parameters. The three-level fault tolerance correction is implemented on the preliminary decision parameters, and the optimized decision parameters are output.

[0041] Exemplarily, for a microgrid containing a wind-solar-storage hybrid system, the reduced-order parameter set contains 8 key variables. First, it is input into the precision-efficiency game model, and the target weights [0.6, 0.3, 0.1] are set according to the operation data of the recent 24 hours. In the first stage of optimization, 15 groups of Pareto solutions are generated, and the optimal solution is at the balance point of an error rate of 2.1% and a time consumption of 0.8 seconds; in the second stage, after superimposing the topological change response time constraint seconds, the optimization space shrinks to 5 groups of solutions. The scheme matching engine detects that the similarity between the current dynamic feature vector and the fingerprint code of the typhoon Tian Gao high-fluctuation working condition reaches 0.82, and calls the reference parameters of this working condition for cross-verification. In the three-level fault tolerance correction, it is detected that the voltage error rate of a certain energy storage node reaches 3.5%, and an injection compensation current of 0.3 is triggered, and the error rate drops to 1.2% after correction. At this time, the model successfully passes the impedance matching test, and a decision set containing 6 optimized parameters is output. The phased optimization process effectively balances multiple conflicting objectives, the typical working condition matching mechanism quickly locks the optimal decision area, and the three-level fault tolerance system classifies and processes model deviations of different severities, ensuring the robustness of the decision parameters under complex working conditions. By introducing the topological response time constraint, the sacrifice of the system's dynamic regulation ability due to simply pursuing precision is avoided, and the progressive processing of residual compensation and full-order reconstruction ensures the recoverability of the model under fault conditions.

[0042] Optionally, the process of performing multi-stage Pareto optimization includes: Constructing the first objective pair of voltage error rate and calculation time-consuming in the first stage; Superimposing the topological change response time to form a three-objective optimization space in the second stage; Use a preset algorithm to obtain an iterative solution set in the three-objective optimization space; Match the features of the iterative solution set with a preset typical operating condition scenario library to generate preliminary decision parameters.

[0043] Specifically, in the construction stage of the first-stage objective, define the voltage error rate and the computing time consumption as the optimization objectives. The calculation formula for the voltage error rate is: , where is the simulated voltage value of the kth node, is the measured voltage value of the kth node, m is the number of key nodes, is the reference voltage. The computing time consumption objective is defined as: , In the formula, is the single-iteration computing time. When initializing the population, n parameters in the reduced-order parameter set are used as chromosome coding, each parameter corresponds to a gene position, and the value range of the parameters is dynamically constrained by the historical data of the typical operating condition scenario library.

[0044] In the second-stage three-objective expansion stage, introduce the topological change response time index : , is the current stabilization time after the topological change of the ith branch. At this time, the objective space expands from two-dimensional to three-dimensional, and a three-objective optimization space is constructed to simultaneously optimize the voltage error rate, computing time consumption, and topological change response time. The preset algorithm can be a non-dominated sorting algorithm, such as an improved non-dominated sorting genetic algorithm, to obtain an iterative solution set in the three-objective optimization space. By introducing an adaptive weight factor, dynamically adjust the priorities of each objective to ensure finding the Pareto optimal solution in a complex multi-objective environment. The iterative solution set contains multiple equilibrium solutions, achieving different trade-offs between the voltage error rate, computing time consumption, and topological change response time. Input the iterative solution set into a preset scenario matching engine, and perform feature matching in combination with the typical operating condition scenario library to generate preliminary decision parameters. The scenario matching engine calculates the similarity between the iterative solution and the historical typical operating condition scenarios, screens out the optimal parameter combination, and outputs the preliminary decision parameters.

[0045] Exemplarily, consider a microgrid system with 10 nodes, 2 photovoltaic power generation units, and 1 energy storage system. In the first stage, the voltage error rate and the calculation time are defined as the optimization objectives. Through 50 iterations of the improved non-dominated sorting algorithm, 20 balanced solutions are obtained. These solutions achieve a balance between the voltage error rate of 0.5% to 1% and the calculation time of 0.1 to 0.5 seconds. In the second stage, the topology change response time is superimposed as the third objective to form a three-objective optimization space. The algorithm is further iterated 30 times to obtain 15 Pareto optimal solutions. Among them, the optimal solution has a voltage error rate of 0.8%, a calculation time of 0.25 seconds, and a topology change response time of 0.15 seconds. Finally, through the scheme matching engine, the parameter combination with the lowest voltage error rate and reasonable calculation time and topology response time is screened out and output as the preliminary decision-making parameters. Through phased optimization, it is possible to take into account the model accuracy, calculation efficiency, and system dynamic response ability at the same time, and avoid the performance imbalance caused by a single optimization objective. The improved non-dominated sorting algorithm shows high efficiency and robustness in multi-objective optimization, ensuring the diversity and high quality of Pareto optimal solutions. At the same time, the scheme matching engine combines historical operating condition data to effectively improve the applicability and adaptability of the parameter combination. The finally output preliminary decision-making parameters significantly improve the simulation accuracy and calculation efficiency of the microgrid dynamic model in a complex and changing environment.

[0046] Optionally, the three-level fault tolerance correction of the preliminary decision-making parameters and the output of the optimized decision-making parameters include: Performing critical constraint verification on the preliminary decision-making parameters to generate a verification result. The critical constraint verification includes impedance matching inspection and power conservation inspection; Triggering residual compensation according to the verification result and performing the critical constraint verification again to generate a compensation result; Generating a full-order model reconstruction instruction according to the compensation result.

[0047] Specifically, such as Figure 4As shown, the operation of implementing three-level fault-tolerant correction for the preliminary decision parameters is first performed on the preliminary decision parameters. The critical constraint verification includes dual standards of impedance matching test and power conservation test. For the impedance matching test, the deviation rate between the theoretical value of the equivalent impedance of each connection node and the value calculated by the reduced-order model is calculated. When the deviation rate of any node exceeds the threshold, it is determined to be a test failure. The power conservation test verifies the residual of the total input power of the system and the sum of the load power and the loss power. If the absolute value of the residual exceeds the set threshold, the failure mark is triggered. The setting of the residual threshold adopts a sliding window statistical method, extracts the standard deviation of the residual historical data with a window period of T, and takes 3 times the standard deviation of the residual historical data as the trigger threshold. When the critical constraint verification result triggers the residual threshold, the steady-state residual compensation module is loaded. Its logic is to inject a correction current vector into the impedance mismatch node according to the current node list that failed the verification, and adjust the virtual energy storage compensation power of the power residual node. The power compensation amount is generated by multiplying the residual by the compensation coefficient, and the compensation coefficient is dynamically adjusted with the node type. If the power residual still exceeds the threshold after three consecutive compensations or the single compensation amount exceeds the equipment safety limit, the compensation result is a failure. If the compensation fails, the full-order model reconstruction instruction is activated, the benchmark model parameters closest to the characteristic fingerprint in the typical working condition solution library are called, the reduced-order parameter calculation is re-executed, and the decision parameters are updated. During the reconstruction process, the authenticity of the solution library parameters is verified through the hash chain to ensure that they have not been tampered with.

[0048] For example, after the initial decision parameters were applied, a microgrid detected that the impedance deviation rate of node 5 continued to exceed 2%, and the total power residual reached 5%. The system started the steady-state residual compensation module, injected a compensation current with a correction current of 0.3 into node 5, and added 2kW virtual compensation power at the bus. Monitoring found that the impedance deviation remained at 1.5% after two compensations, triggering the reconstruction of the full-order model. After fingerprint matching, the typhoon condition benchmark parameters were selected to reconstruct the reduced-order model, and finally the impedance deviation rate of node 5 was reduced to 0.3%, and the power residual was less than 0.5%. The beneficial effect of this verification example is reflected in the hierarchical processing of different levels of model mismatch, the use of progressive fault-tolerant strategies, and the reliability of the model under the premise of minimizing the cost of system reconstruction. Impedance matching test effectively intercepts the equivalent model deviation caused by equipment parameter aging, dynamic residual compensation avoids the computational burden caused by frequent reconstruction, and blockchain verification ensures the legitimacy of the reconstruction parameters. A multi-level parameter verification and compensation mechanism is established, the root cause of model mismatch is accurately identified through critical constraint verification, the instantaneous parameter deviation is processed by steady-state residual compensation, and the full-order reconstruction is used to deal with systemic model failure. The technical effect is reflected in significantly improving the dynamic adaptability of the model, reducing the risk of false operation, and ensuring the simulation reliability under extreme working conditions.

[0049] Optionally, the construction of the typical operating condition solution library includes: Collect the benchmark model parameters under multiple operating modes in the typical operating condition scenario library to form an original scenario set; Extract the feature fingerprints from the original scenario set to generate fingerprint coding vectors; Bind the fingerprint coding vectors to the hash values of the preset blockchain storage module; Perform preloading matching according to the similarity between the dynamic feature vectors and the fingerprint coding vectors during the real-time operation process.

[0050] Specifically, first, collect the benchmark model parameters under multiple operating modes to form an original scenario set. The benchmark model parameters refer to the key parameters that can accurately describe the dynamic characteristics of the microgrid under different operating conditions. These parameters usually include information such as node voltage, power flow, and frequency response. The collection process can be achieved by deploying a sensor system and data acquisition devices to ensure sufficient data samples are obtained under different operating modes (such as full-load operation, partial-load operation, fault conditions, etc.). Secondly, extract the feature fingerprints from the original scenario set to generate fingerprint coding vectors. Feature fingerprint extraction means processing the benchmark model parameters through algorithms to extract the unique identifier that can represent this operating mode. The fingerprint coding vectors can be encoded using methods such as support vector machines (SVM) and deep learning to ensure that each feature fingerprint can accurately reflect a specific operating mode. For example, parameters such as voltage volatility, power change rate, and frequency response of each operating mode can be combined into a high-dimensional vector, and a fingerprint coding vector can be generated through a dimensionality reduction algorithm (such as principal component analysis PCA). Next, bind the fingerprint coding vectors to the hash values of the blockchain storage module. Blockchain technology provides an immutable data storage and management system. Each fingerprint coding vector is assigned a unique hash value, which is embedded in the blockchain to ensure the security and integrity of the data. Specifically, the data of the fingerprint coding vectors can be encrypted and stored in the blocks of the blockchain, and each block has a unique and sequentially related hash value to ensure that the data cannot be tampered with. Finally, during the real-time operation process, perform preloading matching according to the similarity between the dynamic feature vectors and the fingerprint coding vectors. Preloading matching means that during actual operation, the dynamic feature vectors collected in real time are used to calculate the similarity with the fingerprint coding vectors stored in the blockchain, so as to quickly match the closest operating condition mode. The similarity calculation can use methods such as cosine similarity and Euclidean distance. For example, when the cosine similarity between the dynamically collected feature vectors and the stored fingerprint coding vectors is close to 1, it means that the two have a high similarity, and the corresponding benchmark model parameters can be quickly preloaded.

[0051] Exemplarily, assume there is a microgrid system with multiple operating modes, including normal operation, sudden load increase, fault recovery, etc. First, collect parameters such as voltage, power, and frequency under each operating mode to form an original reference model parameter set. Then, perform feature extraction on these parameter sets to generate corresponding fingerprint coding vectors. For example, obtain the feature vectors of each operating condition through PCA dimensionality reduction. Next, store these fingerprint coding vectors in the blockchain, and each vector corresponds to a hash value. During real-time operation, collect the dynamic feature vectors of the current operating condition, calculate the similarity between them and the fingerprint coding vectors stored in the blockchain, and select the most similar operating mode for preloading and matching of parameters. Thus, the construction process of the typical operating condition solution library is completed. By combining the feature fingerprints with the blockchain, a secure and reliable typical operating condition solution library is constructed, which can quickly match and preload the optimal reference model parameters. This method not only improves the efficiency of model update but also ensures data security, avoiding model errors caused by data tampering or loss. At the same time, the immutability of the blockchain ensures the long-term validity of the operating modes, providing a solid foundation for the dynamic model optimization of the microgrid.

[0052] Optionally, the method further includes: Collect the voltage volatility and power change rate output by the simplified dynamic model to obtain a predicted operation data set; Calculate an error index using the predicted operation data set and the real-time operation data set; Update the frequency band division rule and the frequency band weight coefficient according to the magnitude of the error index.

[0053] Specifically, implementing the method includes the following steps: First, collect the voltage volatility and power change rate output by the simplified dynamic model to form a predicted operation data set. Synchronously obtain the actual operation data set of the microgrid, which includes the measured voltage volatility and power change rate. Align the predicted values and the actual values in time, calculate the voltage absolute error and power absolute error at each sampling point to obtain an error sequence. Define a sliding error statistical window with a window period of T, and calculate the window average error mean of the error sequence within the window period 、 and variance 、 . For the error index , there is: , where 、 are the voltage and power error weight coefficients, where and . According to the error index Compared with the preset error level standard, the trigger frequency band division rule is updated. The update logic of the frequency band division rule is as follows: When exceeds the threshold events occur and exceed 3 consecutive window periods, the original number of divided frequency bands is adjusted proportionally. Specifically, the original m frequency bands are expanded to m + 1 frequency bands, and the new frequency band boundary point is located at the center frequency of the original maximum error frequency band. The frequency band weight coefficient is updated according to the proportion of the error index in each frequency band. For the new frequency band weight coefficient , there is: , where is the old frequency band weight coefficient, is the average error increment of the k-th frequency band in the most recent window period, is the learning rate, and the value range is 0.1 - 0.3.

[0054] Exemplarily, a microgrid includes 6 photovoltaic nodes and 2 sets of energy storage systems. The preset initial frequency band division is three frequency bands: low frequency 0 - 2Hz, medium frequency 2 - 5Hz, and high frequency 5 - 10Hz. The predicted operation data after simplifying the acquisition model shows that the error index in the high frequency band continuously exceeds the threshold within 5 window periods, triggering the update of the frequency band division rule. The new splitting point 7.5Hz splits the high frequency band into 5 - 7.5Hz and 70% of the total error in the segment, so the weight coefficient of this sub - frequency band is adjusted from the initial 0.3 to 0.45. Verification shows that the updated frequency band division can more precisely track the 7.8Hz frequency oscillation caused by the pitch control of the fan, and improve the model voltage prediction accuracy by about 40% under this condition. By establishing a dynamic feedback mechanism between the error index and the frequency band parameters, the online identification of the frequency - domain characteristics of the model error is realized; multi - window error statistics avoid mis - adjustment triggered by single - time abnormal fluctuations; the adaptive update of the weight coefficient strengthens the feature extraction ability for high - error frequency bands while ensuring the complete retention of the steady - state characteristics of the low - frequency band; the new frequency band division effectively captures the narrow - band resonance phenomenon missed by the traditional wide - band coverage.

[0055] It should be noted that for the formulas mentioned above, through the principle of dimensional consistency and mathematical standardization means (such as normalization processing, dimensionless parameter conversion, or unit system unification), physical quantities with different attributes can be translated into dimensionless standard values or superimposable parameters of the same dimension, so as to eliminate the interference of different dimensions on the operation logic, and make the formulas have mathematical operation rationality and objective law adaptability while retaining the original data distribution characteristics. This is a conventional technical means and will not be elaborated here. The electrical connections between the above - mentioned various units do not necessarily mean direct connection of the lines. Indirect connection methods can be applied to the embodiments of the present invention as long as the purpose of the present invention is achieved. The above - mentioned are only exemplary embodiments of the present invention, and the scope of the present invention cannot be limited thereby.

[0056] That is, any equivalent changes and modifications made in accordance with the teachings of the present invention still fall within the scope covered by the present invention. After considering the specification and the disclosure of the practical truth, those skilled in the art will easily think of other embodiments of the present invention. This application aims to cover any variations, uses, or adaptive changes of the present invention, which follow the general principles of the present invention and include the common general knowledge or conventional technical means in the technical field not recorded in the present invention.

Claims

1. A method for simplifying the dynamic model of a microgrid, characterized in that, The method further includes: Obtaining a real-time operation data set of the microgrid, and obtaining a dynamic feature vector through hierarchical extraction of dynamic features; Performing joint structure-parameter order reduction processing on the dynamic feature vector to generate a set of reduced-order parameters; Performing multi-objective optimization decision-making based on the set of reduced-order parameters to generate optimized decision-making parameters; Generating a simplified dynamic model according to the optimized decision-making parameters; Wherein, the hierarchical extraction of dynamic features adopts a preset frequency band division rule, and the joint structure-parameter order reduction processing includes screening using a preset sensitivity threshold.

2. The method for simplifying the dynamic model of a microgrid according to claim 1, characterized in that, The obtaining a real-time operation data set of the microgrid and obtaining a dynamic feature vector through hierarchical extraction of dynamic features includes: Collecting the voltage volatility and power change rate of the microgrid nodes to form an original feature matrix; Intercepting the original feature matrix according to a preset sliding time window to generate a windowed feature matrix, wherein the length of the sliding time window is adjusted according to a preset window adjustment coefficient; Performing spectrum feature extraction and non-steady state detection on the windowed feature matrix according to a preset frequency band division rule, and outputting a dynamic feature vector.

3. The method for simplifying the dynamic model of a microgrid according to claim 2, characterized in that, The performing joint structure-parameter order reduction processing on the dynamic feature vector to generate a set of reduced-order parameters includes: Decomposing the dynamic feature vector into a fast-changing feature subset and a slow-changing feature subset; Calculating the sensitivity of the variables in the fast-changing feature subset, and removing the variables in the fast-changing feature subset whose sensitivity is lower than a preset sensitivity threshold to generate a fast-changing reduced-order subset; Adjusting the variables in the fast-changing reduced-order subset by using a preset dynamic compensation factor, and combining with the slow-changing feature subset to obtain a set of reduced-order parameters.

4. The method for simplifying the dynamic model of a microgrid according to claim 3, characterized in that, The sensitivity threshold includes: Extracting the spectrum feature parameters of the dynamic feature vector; Calculating the contribution degree index of the variable according to the spectrum feature parameters and a preset frequency band weight coefficient; Generating a sensitivity threshold according to the contribution degree index; Wherein, the update period of the sensitivity threshold is synchronized with the adjustment period of the sliding time window.

5. The method for simplifying the dynamic model of a microgrid according to claim 4, characterized in that, The method further includes: Extracting the comparison data of the state variables between the reduced-order model and the full-order model from a preset historical operation log to construct a historical reduced-order error data set; Performing cross-correlation on the historical reduced-order error data set and the spectrum feature parameters, and calculating to obtain a gain coefficient; Correcting the dynamic compensation factor by using the gain coefficient.

6. The method for simplifying the dynamic model of a microgrid according to claim 4, characterized in that, The performing multi-objective optimization decision-making based on the set of reduced-order parameters to generate optimized decision-making parameters includes: Constructing an accuracy-efficiency game model, and using the set of reduced-order parameters as an input variable for the accuracy-efficiency game model; The accuracy-efficiency game model performs a multi-stage Pareto optimization process and performs feature matching with a preset typical working condition scenario library to generate preliminary decision-making parameters; Performing three-level fault tolerance correction on the preliminary decision-making parameters, and outputting optimized decision-making parameters.

7. The method for simplifying the dynamic model of a microgrid according to claim 6, characterized in that, Performing the multi-stage Pareto optimization process includes: Constructing a first objective pair of voltage error rate and calculation time consumption in the first stage; Superimposing the topology change response time in the second stage to form a three-objective optimization space; Applying a preset algorithm to obtain an iterative solution set in the three-objective optimization space; Match the iterative solution set with a preset typical operating condition scenario library to generate preliminary decision parameters.

8. A method for simplifying a microgrid dynamic model according to claim 7, characterized in that, Performing three-level fault-tolerant correction on the preliminary decision parameters, the output optimization decision parameters include: Perform critical constraint verification on the preliminary decision parameters to generate a verification result, and the critical constraint verification includes impedance matching test and power conservation test; Trigger residual compensation according to the verification result and perform the critical constraint verification again to generate a compensation result; Generate a full-order model reconstruction instruction according to the compensation result.

9. A method for simplifying a microgrid dynamic model according to claim 6, characterized in that, The construction of the typical operating condition scenario library includes: Collect benchmark model parameters under multiple operating modes to form an original scenario set; Extract feature fingerprints from the original scenario set to generate fingerprint coding vectors; Bind the fingerprint coding vector to the hash value of the blockchain storage module; Perform preloading matching according to the similarity between the dynamic feature vector and the fingerprint coding vector during real-time operation.

10. A method for simplifying a microgrid dynamic model according to claim 9, characterized in that, The method further includes: Collect the voltage volatility and power change rate output by the simplified dynamic model to obtain a predicted operation data set; Calculate an error index by using the predicted operation data set and the real-time operation data set; Update the frequency band division rule and the frequency band weight coefficient according to the magnitude of the error index.

Images