A Power System Inertia Regulation Method and System Based on Grid Information

Abstract

The present invention discloses a power system inertia regulation method based on grid information, which relates to the field of power system automation. The method includes constructing a regional inertia parameter identification model, inputting the preprocessed data into the regional inertia parameter identification model to perform the first regional inertia identification on the power system; fusing the preprocessed data and inputting it into the regional inertia parameter identification model to perform the second regional inertia identification on the power system; dynamically adjusting the inertia of each region according to the differences between the inertias of each region identified in the two identifications, and optimizing the inertia distribution in real time through closed-loop control. Through a series of steps such as data acquisition and preprocessing, intelligent zoning and adaptive inertia distribution, inertia identification technology of multi-source data fusion, dynamic adjustment and closed-loop control, the precise management and dynamic regulation of the inertia of the power system are realized. The present invention improves the operation stability of the power system and the ability to adapt to complex working conditions, thereby enhancing the reliability and economy of the entire power system.

Description

Technical Field

[0001] The present invention relates to the field of power system automation, and particularly to a power system inertia regulation method and system based on grid information. Background Art

[0002] With the rapid development of power systems, especially the large-scale integration of renewable energy sources such as wind energy and solar energy, the inertia characteristics of power systems have changed significantly. Traditionally, the inertia of power systems is mainly provided by synchronous generators, while new energy generation equipment usually does not have sufficient inertia to maintain the stable operation of the system due to its inherent characteristics. Therefore, how to effectively manage and regulate the inertia of power systems has become an important research topic. In recent years, the application of wide-area measurement systems has made it possible to dynamically monitor power systems. Synchronous phasor measurement units can collect the operation data of power systems in real time, including key indicators such as node frequency, generator status, and active power, providing an important basis for the state estimation and control of power systems. However, due to the high complexity and uncertainty of power systems themselves, how to extract useful information from massive data to achieve accurate system state estimation and control remains an urgent problem to be solved.

[0003] First, in the data processing link, due to the existence of various types of noise interference in power systems, such as impulse noise and Gaussian noise, traditional data preprocessing methods are difficult to effectively remove these noises, resulting in inaccurate subsequent data analysis results. Second, in the process of identifying inertia parameters, traditional identification methods often rely on a single data source and lack comprehensive consideration of multi-source heterogeneous data, limiting the accuracy and reliability of the identification results. The above problems limit the application effect of existing technologies in complex power systems. The present invention aims to improve the accuracy and robustness of inertia parameter identification by introducing advanced data preprocessing technologies and multi-source data fusion methods, and then achieve effective management and dynamic regulation of the inertia of power systems. Summary of the Invention

[0004] In order to solve the problem of insufficient accuracy in identifying inertia parameters in traditional methods, the present invention provides the following technical solutions:

[0005] In a first aspect, the present invention provides a power system inertia regulation method based on grid information, which includes: collecting power data in real time and preprocessing the power data; partitioning node frequencies through multiple clustering analyses; constructing a regional inertia parameter identification model, inputting the preprocessed data into the regional inertia parameter identification model to perform the first regional inertia identification on the power system; fusing the preprocessed data and inputting it into the regional inertia parameter identification model to perform the second regional inertia identification on the power system; dynamically adjusting the inertia of each region according to the differences between the inertias of each region identified twice, and optimizing the inertia distribution in real time through closed-loop control.

[0006] As a preferred embodiment of the power system inertia regulation method based on grid information according to the present invention, wherein: the steps of collecting power data in real time and preprocessing the collected data are as follows:

[0007] Collect node frequencies, synchronous generator states, and active power of new energy power stations in real time through wide-area measurement, synchronous phasor measurement units, and smart meters;

[0008] Use median filtering and mean filtering to remove impulse noise and Gaussian noise.

[0009] As a preferred embodiment of the power system inertia regulation method based on grid information according to the present invention, wherein: the steps of partitioning node frequencies through multiple clustering analyses are as follows:

[0010] Perform standardization processing on the collected node frequencies, and perform multiple clustering analyses on the standardized node frequency sequences through the k-shape algorithm;

[0011] Randomly select multiple shapes as initial centroids, assign each data point to the cluster represented by the most similar centroid, recalculate the centroid of each cluster until the centroid no longer changes significantly or reaches the maximum number of iterations, record the results of each clustering, including the members and centroids of each cluster, and use evaluation metrics to measure the clustering quality under different numbers of clusters;

[0012] Gradually increase the number of clusters , record the results and evaluation metrics of each clustering, and determine the optimal number of clusters by combining the elbow method and the Silhouette method ;

[0013] The optimal number of clusters refers to the optimal number of node frequency partitions.

[0014] As a preferred solution of the power system inertia regulation method based on grid information according to the present invention, wherein: the regional inertia parameter identification model is constructed, and the preprocessed data is input into the regional inertia parameter identification model for the first regional inertia identification of the power system. The specific steps are as follows:

[0015] Based on the rotor swing equation, a regional inertia parameter identification model is constructed, and the expression is:

[0016] ;

[0017] Wherein, is the equivalent inertia of region , is the active power change of region , is the rated frequency, is the frequency deviation of region ;

[0018] The adaptive cubature Kalman filter algorithm is used for parameter identification. By establishing a state space model and initializing the state, the state estimation and covariance matrix are continuously adjusted using the prediction and update steps, the global equivalent inertia is gradually refined, and the inertia of each region is generated .

[0019] As a preferred solution of the power system inertia regulation method based on grid information according to the present invention, wherein: the preprocessed data is fused and input into the regional inertia parameter identification model for the second regional inertia identification of the power system. The specific steps are as follows:

[0020] The node frequency, synchronous generator state, and new energy power station active power after preprocessing are respectively standardized, and a convolutional neural network is used for training. The expression is:

[0021] ;

[0022] Wherein, is the standardized node frequency, is the active power of the standardized synchronous generator, is the active power of the standardized new energy power station, is the convolutional neural network parameter of the th data source;

[0023] The federated learning technology is used for joint training. The expression is:

[0024] ;

[0025] Wherein, is the parameter after joint training, is the total amount of data of all data sources, is the convolutional neural network parameter of the th data source, is the amount of data of the th data source, is the number of data sources;

[0026] Data fusion is performed using a federated learning model, and the expression is:

[0027] ;

[0028] Among them, is the fused data, is the normalized node frequency, is the normalized active power of the synchronous generator, is the normalized active power of the new energy power station;

[0029] The active power change and frequency deviation are calculated using the fused data, and the fused regional inertia is calculated through the rotor swing equation. The expression is:

[0030] ;

[0031] Among them, is the fused regional inertia, is the rated frequency.

[0032] As a preferred solution of the power system inertia regulation method based on grid information described in the present invention, wherein: according to the difference between the regional inertias identified twice, the regional inertias are dynamically adjusted. The specific steps are as follows:

[0033] Based on an adaptive PID controller for dynamic adjustment strategy;

[0034] Based on the deviation between the desired frequency and the actual frequency, an error signal is defined to measure the deviation between the current state and the target state. The expression is:

[0035] ;

[0036] Among them, is the error signal, is the desired frequency, is the actual frequency;

[0037] Initialize the PID parameters through each regional inertia and calculate the control output using the initialized PID parameters. The expression is:

[0038] ;

[0039] Among them, is for controlling the output, is the proportional coefficient, is the integral coefficient, is the differential coefficient;

[0040] Adjust the PID controller parameters through the fused inertia and calculate the adjusted control output using the adjusted PID parameters .

[0041] The real-time optimization of inertia distribution through closed-loop control is as follows:

[0042] Apply the control outputs and obtained from the two calculations to the power system respectively, adjust the active power output of the power system, and recalculate the node frequency data and error signal through the adjusted active power;

[0043] Continuously adjust the PID parameters and inertia through closed-loop control, set the error signal threshold, stop adjusting when the error signal reaches this threshold, set the maximum number of iterations, and stop adjusting if the error signal has not reached the threshold and the number of iterations is reached;

[0044] Define the control gain based on the proportional relationship between the error signal and the inertia change amount, which is used to quantify the influence degree of the control output on the behavior. The expression is:

[0045] ;

[0046] Among them, is the control gain, is the change amount of the inertia identified by the two regional inertia identifications;

[0047] Calculate the adjusted regional inertia. The expression is:

[0048] ;

[0049] Among them, is the adjusted regional inertia, is the adjustment factor.

[0050] In a second aspect, the present invention provides a power system inertia regulation system based on grid information, including a data acquisition module that collects power data in real time and preprocesses the power data; a frequency zoning module that zones the node frequencies through multiple clustering analyses; an inertia parameter identification module that constructs a regional inertia parameter identification model, inputs the preprocessed data into the regional inertia parameter identification model, and performs the first regional inertia identification on the power system; an inertia adjustment module that fuses the preprocessed data and inputs it into the regional inertia parameter identification model to perform the second regional inertia identification on the power system; and a closed-loop control module that dynamically adjusts the inertia of each region according to the differences between the inertias of each region identified twice, and optimizes the inertia distribution in real time through closed-loop control.

[0051] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the power system inertia regulation method based on grid information as described in the first aspect of the present invention is implemented.

[0052] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the power system inertia regulation method based on grid information as described in the first aspect of the present invention is implemented.

[0053] The beneficial effects of the present invention are as follows: Through a series of steps such as data acquisition and preprocessing, intelligent zoning and adaptive inertia distribution, inertia identification technology for multi-source data fusion, dynamic adjustment and closed-loop control, precise management and dynamic regulation of the inertia of the power system are realized. Especially in the data preprocessing stage, median filtering and mean filtering are used to remove impulse noise and Gaussian noise, further improving the data quality, providing a solid foundation for subsequent intelligent zoning and adaptive inertia distribution. Finally, the present invention improves the operation stability of the power system and the ability to adapt to complex working conditions, thereby enhancing the reliability and economy of the entire power system. Description of the Drawings

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0055] Figure 1 It is a flowchart of the power system inertia regulation method for grid information in Embodiment 1.

[0056] Figure 2 It is a flowchart of the power system inertia regulation system for grid information in Embodiment 1. Detailed implementation manners

[0057] To make the above objects, features and advantages of the present invention more obvious and understandable, the following detailed description of the specific implementation manners of the present invention will be given in conjunction with the accompanying drawings of the specification.

[0058] Embodiment 1

[0059] Referring to Figure 1 and Figure 2 , this is the first embodiment of the present invention. This embodiment provides a power system inertia regulation method based on grid information, including the following steps:

[0060] S1: Real-time collect power data and preprocess the power data;

[0061] Furthermore, the node frequency, synchronous generator status, and active power of new energy power stations are real-time collected through wide-area measurement, synchronized phasor measurement units, and smart meters; wide-area measurement usually consists of multiple synchronized phasor measurement units, which can provide synchronized and high-precision phasor measurement. The PMU device is installed at key nodes of the network to collect instantaneous values of voltage and current, and then uses the time stamp of global positioning to synchronize these measurement values;

[0062] Median filtering and mean filtering are used to remove impulse noise and Gaussian noise;

[0063] It should be noted that median filtering slides a selected-size window in the data stream, sorts the data within the window, and takes the median value to replace the original data value at the center position of the window. This method can effectively remove impulse noise. Even if there are extreme values within the window, the median can resist the influence of such outliers, thereby retaining the basic characteristics of the signal without being disturbed;

[0064] Mean filtering replaces the original data value at the center position of the window by taking the average value of the data points within the window. This method is suitable for smoothing the signal and removing Gaussian-distributed random noise because the average value can reduce the influence of extreme values of individual data points on the overall signal, thereby making the signal smoother and retaining the basic trend and pattern of the signal.

[0065] S2: Partition the node frequency through multiple clustering analyses;

[0066] Furthermore, the collected node frequency is standardized, and multiple clustering analyses are performed on the standardized node frequency sequence through the k-shape algorithm; calculate the average value and standard deviation of each frequency time series, and use standardization to transform the data. The expression is:

[0067] ;

[0068] Among them, is the frequency-time series data, is the average value, is the standard deviation;

[0069] Randomly select shapes as the initial centroids multiple times. Assign each data point to the cluster represented by the most similar centroid, and recalculate the centroid of each cluster until the centroid no longer changes significantly or reaches the maximum number of iterations. Record the results of each clustering, including the members and centroids of each cluster. Use evaluation metrics to measure the clustering quality under different numbers of clusters. According to the historical data experience, randomly select k time series as the initial centroids;

[0070] Gradually increase the number of clusters , record the results and evaluation metrics of each clustering, and combine the elbow method and the Silhouette method to determine the optimal number of clusters ;

[0071] It should be noted that the Silhouette method measures the closeness of a sample to its belonging cluster and the separation from other clusters, and the elbow method observes the change of the clustering cost function corresponding to different k values;

[0072] The optimal number of clusters refers to the optimal node frequency partition number.

[0073] S3: Construct a regional inertia parameter identification model, input the preprocessed data into the regional inertia parameter identification model, and perform the first regional inertia identification on the power system;

[0074] Furthermore, based on the rotor swing equation, construct a regional inertia parameter identification model, and the expression is:

[0075] ;

[0076] Among them, is the equivalent inertia of region , is the active power change of region , is the rated frequency, is the frequency deviation of region In the power system, the rotor swing equation describes the relationship between the change of the synchronous generator rotor angular velocity and the active power imbalance in the power system, and the expression is:

[0077] ;

[0078] Among them, is the region The angular velocity change of the internal generator;

[0079] Use the adaptive cubature Kalman filter algorithm for parameter identification. By establishing a state space model and initializing the state, continuously adjust the state estimate and covariance matrix using the prediction and update steps, gradually refine the global equivalent inertia, and generate the inertia of each region. 。

[0080] It should be noted that define the state equation and observation equation, select reasonable initial state and covariance matrix, continuously adjust the state estimate and covariance matrix using the Kalman filter algorithm, and adjust the process noise and observation noise of the state to improve the robustness and accuracy of the filter.

[0081] S4: Fuse the preprocessed data and input it into the regional inertia parameter identification model to perform the second regional inertia identification of the power system;

[0082] Furthermore, standardize the preprocessed node frequency, synchronous generator status, and active power of new energy power stations respectively, and use a convolutional neural network for training. The expression is:

[0083] ;

[0084] Among them, is the standardized node frequency, is the active power of the standardized synchronous generator, is the active power of the standardized new energy power station, is the convolutional neural network parameter of the th data source. Build a CNN architecture for the convolutional neural network to process time series data. Extract local features through the convolutional layer, reduce the feature dimension through the pooling layer, and perform classification through the fully connected layer. Input the standardized data into the CNN for training, and use the backpropagation algorithm to optimize the network parameters

[0085] so that the network can learn the internal patterns and correlations in the data. The CNN can automatically learn the local features and long-range dependencies in the data, which is very suitable for processing time series data. Through training, the CNN can capture the important patterns in the frequency and power changes, providing a basis for subsequent fusion and analysis;

[0086] ;

[0087] Among them, is the parameter after joint training, is the total amount of data of all data sources, is the The convolutional neural network parameters of a data source, is the data volume of the th data source. The number of data sources is. Federated learning allows for joint training using data from different data sources while protecting privacy. This enables the common optimization of models through parameter updates without sharing actual data;

[0088] Use the federated learning model for data fusion. The expression is:

[0089] ;

[0090] Among them, is the fused data, is the normalized node frequency, is the normalized active power of the synchronous generator, is the normalized active power of the new energy power station. By fusing multi-source data through the jointly trained model, a comprehensive and more representative feature representation can be obtained, which is helpful for subsequent analysis and decision-making, especially in cases where multiple factors need to be considered comprehensively;

[0091] Calculate the active power change and frequency deviation using the fused data, and calculate the fused regional inertia through the rotor swing equation. The expression is:

[0092] ;

[0093] Among them, is the fused regional inertia, is the rated frequency. By calculating the active power change and frequency deviation using the fused data and combining with the rotor swing equation, a more accurate and comprehensive inertia can be obtained, which is helpful for dynamically adjusting the inertia of each region and optimizing the operation of the power system.

[0094] S5: According to the differences between the identified regional inertias in two times, dynamically adjust the regional inertias and optimize the inertia distribution in real time through closed-loop control;

[0095] Based on an adaptive PID controller for dynamic adjustment strategy, the adaptive PID controller can automatically adjust the controller parameters according to the real-time state of the power system and external disturbances, thereby improving the stability and response speed of the control system;

[0096] Define the error signal based on the deviation between the desired frequency and the actual frequency to measure the deviation between the current state and the target state. The expression is:

[0097] ;

[0098] Among them, is the error signal, is the desired frequency, is the actual frequency;

[0099] The error signal calculates the difference between the actual frequency and the desired frequency, intuitively understanding the deviation between the current state and the target state of the power system. The error signal can be used as the input of the controller to adjust the control output, so that the power system can reach the desired frequency state as soon as possible. In the dynamic adjustment strategy, the error signal provides real-time feedback to help the controller dynamically adjust the control parameters according to the current deviation to achieve better control performance;

[0100] Initialize the PID parameters through the inertia of each region and calculate the control output using the initialized PID parameters. The expression is:

[0101] ;

[0102] Among them, is the control output, is the proportional coefficient, is the integral coefficient, is the differential coefficient;

[0103] Use the adaptive algorithm to adjust the PID control parameters , , , and the expression is:

[0104] ;

[0105] ;

[0106] ;

[0107] Among them, is the learning rate of the proportional coefficient, is the learning rate of the integral coefficient, is the learning rate of the differential coefficient;

[0108] Adjust the PID controller parameters through the fused regional inertia and calculate the adjusted control output using the adjusted PID parameters , and the expression is:

[0109] ;

[0110] Among them, is the adjusted control output;

[0111] Combine the control outputs obtained from the two calculations and , which are respectively applied to the power system to adjust the active power output of the power system. Through the adjusted active power, the node frequency data and error signal are calculated again to adjust the active power of the generator. The expression is:

[0112] ;

[0113] Among them, is the active power output in the ground state, is the adjusted active power;

[0114] The PID parameters and inertia are continuously adjusted through closed-loop control, and the error signal threshold is set. When the error signal reaches this threshold, the adjustment stops. The maximum number of iterations is set. If the error signal has not reached the threshold and reaches the number of iterations, the adjustment stops. Through the set error signal threshold , check whether the error signal is less than or equal to the set error signal threshold;

[0115] When ≤ , stop the adjustment, indicating that it is close enough to the desired frequency;

[0116] When > , continue the adjustment;

[0117] Define the control gain based on the proportional relationship between the error signal and the change in inertia, which is used to quantify the influence degree of the control output on the behavior. The expression is:

[0118] ;

[0119] Among them, is the control gain, is the change in inertia between two regional inertia identifications;

[0120] Calculate the change in regional inertia using the fused regional inertia and the initially identified regional inertia. The expression is:

[0121] ;

[0122] The control gain provides a measure to quantify the influence degree of the control output on the behavior. Through this gain, the influence of the control output on the frequency change can be better understood;

[0123] Calculate the adjusted regional inertia. The expression is:

[0124] ;

[0125] Among them, is the adjusted regional inertia, is an adjustment factor, which is used to control the amplitude of adjustment. A smaller value means a milder adjustment, while a larger value means a greater adjustment. Selecting an appropriate value can balance the adjustment speed and stability;

[0126] It should be noted that the object of adjustment is the inertia of each region, and the difference in the inertia of each region after two identifications is calculated.

[0127] This embodiment also provides a power system inertia regulation system based on grid information, including: a data acquisition module, which collects power data in real time and preprocesses the power data;

[0128] a frequency zoning module, which zones the node frequencies through multiple clustering analyses;

[0129] an inertia parameter identification module, which constructs a regional inertia parameter identification model, inputs the preprocessed data into the regional inertia parameter identification model, and conducts the first regional inertia identification of the power system;

[0130] an inertia adjustment module, which fuses the preprocessed data and inputs it into the regional inertia parameter identification model to conduct the second regional inertia identification of the power system;

[0131] a closed-loop control module, which dynamically adjusts the inertia of each region according to the difference between the inertias of each region identified twice, and optimizes the inertia distribution in real time through closed-loop control.

[0132] This embodiment also provides a computer device, which is applicable to the situation of the power system inertia regulation method based on grid information, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the power system inertia regulation method based on grid information proposed in the above embodiment.

[0133] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad provided on the housing of the computer device. It can also be an external keyboard, touchpad, or mouse, etc.

[0134] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for regulating the inertia of a power system based on grid information as proposed in the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM for short), Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read-Only Memory (EPROM for short), Programmable Read-Only Memory (PROM for short), Read-Only Memory (ROM for short), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0135] In summary, through a series of steps such as data acquisition and preprocessing, intelligent partitioning and adaptive inertia allocation, inertia identification technology based on multi-source data fusion, dynamic adjustment and closed-loop control, the present invention realizes the precise management and dynamic regulation of the inertia of the power system. Especially in the data preprocessing stage, median filtering and mean filtering are used to remove impulse noise and Gaussian noise, further improving the data quality and providing a solid foundation for subsequent intelligent partitioning and adaptive inertia allocation. Finally, the present invention improves the operation stability of the power system and the ability to adapt to complex working conditions, thereby enhancing the reliability and economy of the entire power system.

[0136] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments.

Claims

1. A method for adjusting inertia of a power system based on power grid information, characterized in that: include, Collect power data in real time and pre-process the power data; Node frequencies were partitioned through multiple cluster analyses; Construct a regional inertia parameter identification model, input the preprocessed data into the regional inertia parameter identification model, perform the first regional inertia identification on the power system to obtain the inertia of each region ; The pre-processed data is integrated and input into the regional inertia parameter identification model to perform the second regional inertia identification of the power system; According to the difference between the inertia of each area identified twice, the inertia of each area is dynamically adjusted, and the inertia distribution is optimized in real time through closed-loop control; The fusion pre-processed data is input into the regional inertia parameter identification model to perform a second regional inertia identification on the power system. The specific steps are as follows: The preprocessed node frequency, synchronous generator state and active power of the new energy station are standardized respectively, and the convolutional neural network is used for training. The expression is: ； in, is the normalized node frequency, is the normalized active power of the synchronous generator, Standardized active power of new energy stations, It is Convolutional neural network parameters for each data source; Use federated learning technology for joint training, the expression is: ； in, are the parameters after joint training, is the total amount of data from all data sources, It is The convolutional neural network parameters of the data source, It is The amount of data from each data source, is the number of data sources; Using the federated learning model for data fusion, the expression is: ； in, is the fused data, is the normalized node frequency, is the normalized active power of the synchronous generator, Standardized active power of new energy stations; The fused data is used to calculate the active power change and frequency deviation, and the fused regional inertia is calculated through the rotor swing equation. The expression is: ； in, is the regional inertia after fusion, is the rated frequency; The inertia of each region is dynamically adjusted according to the difference between the inertia of each region identified twice. The specific steps are as follows: Dynamic adjustment strategy based on adaptive PID controller; The error signal is defined based on the deviation between the expected frequency and the actual frequency to measure the deviation between the current state and the target state. The expression is: ； in, is the error signal, is the expected frequency, is the actual frequency; Inertia of each area Initialize the PID parameters and use the initialized PID parameters to calculate the control output. The expression is: ； in, To control the output, is the proportionality coefficient, is the integration coefficient, is the differential coefficient; By the fused regional inertia Adjust the PID controller parameters and use the adjusted PID parameters to calculate the adjusted control output .

2. The method for adjusting the inertia of a power system based on power grid information according to claim 1, characterized in that: The real-time collection of power data and preprocessing of the collected data are carried out in the following specific steps: Real-time acquisition of node frequency, synchronous generator status and active power of new energy stations through wide-area measurement, synchronous phasor measurement units and smart meters; Median filtering and mean filtering are used to remove impulse noise and Gaussian noise.

3. The method for adjusting the inertia of a power system based on power grid information according to claim 2, characterized in that: The node frequencies are partitioned by multiple clustering analyses. The specific steps are as follows: The collected node frequencies are standardized, and the standardized node frequency sequences are clustered multiple times using the k-shape algorithm; Multiple random selections The shapes are used as the initial centroids, and each data point is assigned to the cluster represented by the most similar centroid. The centroid of each cluster is recalculated until the centroid no longer changes significantly or the maximum number of iterations is reached. The results of each clustering are recorded, including the members and centroids of each cluster. Evaluation indicators are used to measure the clustering quality under different cluster numbers. Gradually increase the number of clusters , record the results and evaluation indicators of each clustering, and combine the elbow method and Silhouette method to determine the optimal number of clusters ; The optimal number of clusters Refers to the optimal number of node frequency partitions.

4. The method for adjusting the inertia of a power system based on power grid information according to claim 3, characterized in that: The regional inertia parameter identification model is constructed, the pre-processed data is input into the regional inertia parameter identification model, and the first regional inertia identification of the power system is performed. The specific steps are as follows: Based on the rotor swing equation, the regional inertia parameter identification model is constructed, and the expression is: ； in, It is a region The equivalent inertia of It is a region The active power change, is the rated frequency, It is a region Frequency deviation; The adaptive volumetric Kalman filter algorithm is used for parameter identification. By establishing a state space model and initializing the state, the state estimation and covariance matrix are continuously adjusted using the prediction and update steps, the global equivalent inertia is gradually refined, and the inertia of each region is generated. .

5. The method for adjusting the inertia of a power system based on power grid information according to claim 4, characterized in that: The specific steps of optimizing inertia distribution in real time through closed-loop control are as follows: The control output is obtained by calculating twice and , respectively applied to the power system to adjust the active power output of the power system, and the node frequency data and error signal are calculated again through the adjusted active power; Continuously adjust PID parameters and inertia through closed-loop control, set the error signal threshold, stop adjustment when the error signal reaches this threshold, set the maximum number of iterations, if the error signal has not reached the threshold, reach the number of iterations, stop adjustment; The control gain is defined based on the proportional relationship between the error signal and the inertia change, which is used to quantify the influence of the control output on the behavior. The expression is: ； in, To control the gain, is the change in inertia of two regional inertia identifications; Calculate the adjusted area inertia, the expression is: ； in, Area inertia, is the adjustment factor.

6. A power system inertia adjustment system based on power grid information, based on the power system inertia adjustment method based on power grid information according to any one of claims 1 to 5, characterized in that: It includes data acquisition module, frequency partition module, inertia parameter identification module, inertia adjustment module and closed-loop control module. Data acquisition module, which collects power data in real time and pre-processes the power data; Frequency partitioning module, which partitions node frequencies through multiple clustering analyses; Inertia parameter identification module, builds a regional inertia parameter identification model, inputs the preprocessed data into the regional inertia parameter identification model, and performs the first regional inertia identification of the power system; The inertia adjustment module integrates the pre-processed data and inputs it into the regional inertia parameter identification model to perform the second regional inertia identification of the power system; The closed-loop control module dynamically adjusts the inertia of each area according to the difference between the inertia of each area identified twice, and optimizes the inertia distribution in real time through closed-loop control.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the power system inertia adjustment method based on power grid information described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power system inertia adjustment method based on power grid information described in any one of claims 1 to 5 are implemented.

Images