Method for analyzing stability abnormity of virtual synchronous generator

Abstract

The invention relates to the technical field of power grid monitoring, and discloses a method for analyzing stability abnormity of a virtual synchronous generator, which comprises the following steps of: 1, acquiring operation data of the virtual synchronous generator and a power grid system at all time points in real time, and classifying to form a data set; 2, setting a monitoring period and a reference threshold value, and generating a corresponding abnormal data group; 3, establishing a time axis according to a monitoring period, inserting corresponding nodes in combination with an abnormal data group, analyzing change characteristics of all the nodes in a frequency domain and a time domain, generating corresponding fluctuation indexes and distribution frequencies, and flexibly adapting to load change and being high in stability; and 4, setting a fluctuation threshold value and a distribution threshold value, judging whether the virtual synchronous generator has an operation fault or not, generating a corresponding decision tree according to a monitoring period, diagnosing a fault reason in the operation process of the virtual synchronous generator in real time, and notifying maintenance and management personnel, so that the accuracy of diagnosing the fault reason in real time is high.

Description

Technical Field

[0001] The invention relates to the technical field of power grid monitoring, and in particular to a method for analyzing abnormal stability of a virtual synchronous generator. Background Art

[0002] Virtual synchronous generator is a technology that simulates the operating characteristics of traditional synchronous generators. It simulates the mechanical and electromagnetic characteristics of synchronous generators by controlling inverters to provide the inertia and damping required by the power grid. In large-scale renewable energy grid connection, virtual synchronous generators simulate the active frequency regulation and reactive voltage regulation functions of synchronous generators, participate in the regulation of grid frequency and voltage, and achieve load peak shaving and valley filling by absorbing excess renewable grid-connected energy in the grid, optimize the power consumption process, improve the stability and compatibility of the grid, and reduce the impact of fluctuations in renewable energy generation on the grid. When a power grid fails, the power angle instability problem is easily caused by improper system parameters or control strategies. Targeted formulation of transient control strategies for adaptive regulation can reduce active power imbalance and ensure the reliable operation of virtual synchronous generators in power systems. A deep understanding of the causes and solutions for VSG stability anomalies will help promote the development of power systems in a more efficient and stable direction.

[0003] At present, the traditional analysis method of virtual synchronous generator stability anomaly lacks flexibility and adaptability. Faced with complex load changes in the power grid system, the algorithm model is relatively simple and the data analysis capability is limited. It is impossible to detect whether the virtual synchronous generator has an operating failure in time, and the cause of the fault cannot be located accurately and reliably. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a method for analyzing the stability anomaly of a virtual synchronous generator, which has the advantages of flexible adaptation to load changes, strong stability, and high accuracy in real-time diagnosis of fault causes. It solves the problems that the traditional method for analyzing the stability anomaly of a virtual synchronous generator lacks flexibility and adaptability, and the positioning of the fault cause is not accurate and reliable enough.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for analyzing the stability anomaly of a virtual synchronous generator, comprising the following steps: Step 1: Acquire the operation data of the virtual synchronous generator and the power grid system at all time points in real time through the network connection sensor device, and classify the acquired data into a power data set and a load data set. The power data set includes the real-time speed, real-time current, real-time voltage and real-time frequency output by the virtual synchronous generator, and the load data set includes the real-time current, real-time voltage and real-time frequency required by the power grid system; Step 2: Set a fixed monitoring period , and then for the monitoring cycle Set the reference threshold for a fixed range , based on the power data set and the load data set, identify the monitoring period Abnormal operation data within, generate corresponding abnormal data group ; Step 3: According to the monitoring cycle Create a timeline , combined with the abnormal data set Insert the corresponding nodes, analyze the change characteristics of all nodes in the frequency domain and time domain, and generate the corresponding fluctuation index and distribution frequency ; Step 4: Set a fixed range of fluctuation thresholds and distribution threshold , and combined with the volatility index and distribution frequency , determine whether the virtual synchronous generator has an operating fault, according to the monitoring cycle Divide the training set and test set to generate the corresponding decision tree , diagnose the cause of the fault during the operation of the virtual synchronous generator in real time and notify the maintenance management personnel.

[0006] Preferably, in step 1, the expression of the power data set is , Indicates the real-time speed output by the virtual synchronous generator. Indicates the real-time current output by the virtual synchronous generator, Indicates the real-time voltage output by the virtual synchronous generator, Indicates the real-time frequency output by the virtual synchronous generator, Indicates the time point for obtaining the operating data of the virtual synchronous generator.

[0007] Preferably, in step 1, the expression of the load data set is , Indicates the real-time current required by the power grid system, Indicates the real-time voltage required by the power grid system. Indicates the real-time frequency required by the power grid system, Indicates the time point for obtaining the power grid system operation data.

[0008] Preferably, in step 2, the reference threshold Including speed threshold , Current threshold , voltage threshold and frequency threshold .

[0009] Preferably, in step 2, the abnormal data set The calculation process is as follows: Based on the power data set, extract the monitoring period Real-time speed output by the internal virtual synchronous generator , real-time current , real-time voltage and real-time frequency ; Extract monitoring cycles based on load data sets Real-time current required by the internal power grid system , real-time voltage and real-time frequency ; ; In the formula, represents an abnormal data set, Indicates the minimum speed threshold value, Indicates the maximum speed threshold value. If the monitoring cycle Real-time speed output by the internal virtual synchronous generator When the speed threshold is exceeded, it is marked as abnormal speed. Indicates the minimum current threshold value, Indicates the maximum current threshold value. If the monitoring cycle Real-time current output of the internal virtual synchronous generator When the current threshold is exceeded, it is marked as abnormal output current. Indicates the minimum voltage threshold, Indicates the maximum voltage threshold. If the monitoring cycle Real-time voltage output of the internal virtual synchronous generator When the voltage threshold is exceeded, it is marked as abnormal output voltage. Indicates the minimum frequency threshold value, Indicates the maximum value of the frequency threshold. If the monitoring period Real-time frequency output of the internal virtual synchronous generator When the frequency threshold is exceeded, it is marked as abnormal output frequency. Real-time current required by the internal power grid system When the current threshold is exceeded, it is marked as abnormal load current. Real-time voltage required by the internal power grid system When the voltage threshold is exceeded, it is marked as abnormal load voltage. Real-time frequency required by the internal power grid system When the frequency threshold is exceeded, it is marked as abnormal load frequency.

[0010] Preferably, in step 3, the volatility index The calculation process is as follows: The abnormal data group Insert the abnormal speed, abnormal output current, abnormal output voltage, abnormal output frequency, abnormal load current, abnormal load voltage or abnormal load frequency marked in the time axis , and generate one-to-one corresponding nodes; If the abnormal data set Marked in Abnormal output current, The expression of abnormal output current is , to In turn, each abnormal output current is shown on the time axis The corresponding node in ; ; In the formula, represents the volatility index, The sum of the abnormal output currents divided by the number of nodes gives the average value of the abnormal output currents. Representing the timeline Middle The abnormal output current corresponding to each node is: According to the variance formula, The difference between the abnormal output current and the average value is obtained, and the variance value obtained is the fluctuation index of the abnormal output current in the frequency domain.

[0011] Preferably, in step 3, the distribution frequency The calculation process is as follows: According to the timeline , count the time difference between every two adjacent abnormal output currents and mark them as , to Sequentially indicate The time difference between every two adjacent abnormal output currents in a node; ;. In the formula, represents the distribution frequency, express The sum of the group time differences, Indicates the frequency of occurrence of abnormal output current in the time domain, and also indicates The distribution probability of abnormal output current nodes in the time domain.

[0012] Preferably, in step 4, the volatility index Comparison Fluctuation Threshold , if a single monitoring cycle Internal volatility index Exceeding the volatility threshold , it indicates that there is an operating fault in the virtual synchronous generator.

[0013] Preferably, in step 4, the distribution frequency Comparison distribution threshold , if a single monitoring cycle Internal distribution frequency Distribution threshold exceeded , it indicates that there is an operating fault in the virtual synchronous generator.

[0014] Preferably, in step 4, the decision tree The training process is as follows: Divide by time from early to late Monitoring cycle The operation data of the virtual synchronous generator and the power grid system will be Monitoring cycle The running data is used as the training set. Monitoring cycle The running data is used as the test set, and the reference threshold , Fluctuation threshold and distribution threshold As a decision tree Hyperparameters of Build a decision tree using the training set The backbone of the system is then used to generate a one-to-one decision tree based on the data types in the power data set and the load data set. branches, and each branch corresponds to a set of abnormal data groups , Volatility Index , distribution frequency and operation fault judgment results; Evaluate the decision tree on the test set The accuracy of the generated operation fault judgment results is , indicating that training generates a decision tree With real-time diagnosis capability, if the accuracy rate is not reached , indicating that training generates a decision tree Insufficient real-time diagnostic capabilities, adding multiple monitoring cycles Running data and continue to update the decision tree , until the accuracy reaches .

[0015] Compared with the prior art, the present invention provides a method for analyzing the stability anomaly of a virtual synchronous generator, which has the following beneficial effects: 1. The present invention obtains the operation data of the virtual synchronous generator and the power grid system at all time points in real time through a network-connected sensor device, and classifies the acquired data into power data sets and load data sets, which is conducive to the subsequent rapid judgment of whether the supply and demand relationship between the virtual synchronous generator and the power grid system is balanced, and sets a fixed-time monitoring cycle , and then for the monitoring cycle Set the reference threshold for a fixed range , based on the power data set and the load data set, identify the monitoring period Abnormal operation data within, generate corresponding abnormal data group , according to the monitoring cycle Create a timeline , combined with the abnormal data set Insert the corresponding nodes, analyze the change characteristics of all nodes in the frequency domain and time domain, and calculate the fluctuation index in the frequency domain and time domain according to the type of abnormal values. and distribution frequency , flexible to adapt to load changes and strong stability.

[0016] 2. The present invention sets a fixed range of fluctuation thresholds and distribution threshold , volatility index Comparison Fluctuation Threshold , if a single monitoring cycle Internal volatility index Exceeding the volatility threshold When the virtual synchronous generator has an operating fault, the frequency distribution Comparison distribution threshold , if a single monitoring cycle Internal distribution frequency Distribution threshold exceeded When the virtual synchronous generator has an operating fault, according to the monitoring cycle Divide the training set and test set to generate the corresponding decision tree , the trained decision tree The judgment accuracy must reach , decision tree Each branch of corresponds to a set of abnormal data sets , Volatility Index , distribution frequency and operation fault judgment results, ensuring the decision tree The accuracy of each branch can diagnose the cause of the fault during the operation of the virtual synchronous generator in real time and notify the maintenance management personnel. The real-time diagnosis of the cause of the fault is highly accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a step diagram of the method of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The traditional analysis method of abnormal stability of virtual synchronous generator lacks flexibility and adaptability. In the face of complex load changes in the power grid system, the algorithm model is relatively simple and the data analysis ability is limited. It is not possible to timely detect whether there is an operating fault in the virtual synchronous generator, and the fault cause is not accurate and reliable enough. Therefore, a method for analyzing abnormal stability of virtual synchronous generator is provided. Please refer to Figure 1 , the method comprises the following steps: Step 1: Use the network to connect the sensor device to obtain the operating data of the virtual synchronous generator and the power grid system at all time points in real time, and classify the acquired data into power data sets and load data sets. The power data set includes the real-time speed, real-time current, real-time voltage and real-time frequency output by the virtual synchronous generator. The expression of the power data set is , Indicates the real-time speed output by the virtual synchronous generator. Indicates the real-time current output by the virtual synchronous generator, Indicates the real-time voltage output by the virtual synchronous generator, Indicates the real-time frequency output by the virtual synchronous generator, It indicates the time point for obtaining the operation data of the virtual synchronous generator. The load data set includes the real-time current, real-time voltage and real-time frequency required by the power grid system. The expression of the load data set is , Indicates the real-time current required by the power grid system, Indicates the real-time voltage required by the power grid system. Indicates the real-time frequency required by the power grid system, Indicates the time point for obtaining the operation data of the power grid system, comprehensively collects the real-time operation data of the virtual synchronous generator and the power grid system, which is conducive to the subsequent rapid judgment of whether the supply and demand relationship between the virtual synchronous generator and the power grid system is balanced; Step 2: Set a fixed monitoring period , and then for the monitoring cycle Set the reference threshold for a fixed range , the reference threshold includes the speed threshold , Current threshold , voltage threshold and frequency threshold , based on the power data set and the load data set, identify the monitoring period Abnormal operation data within, generate corresponding abnormal data group , the calculation process is as follows: Based on the power data set, extract the monitoring period Real-time speed output by the internal virtual synchronous generator , real-time current , real-time voltage and real-time frequency ; Extract monitoring cycles based on load data sets Real-time current required by the internal power grid system , real-time voltage and real-time frequency ; ; In the formula, represents an abnormal data set, Indicates the minimum speed threshold value, Indicates the maximum speed threshold value. If the monitoring cycle Real-time speed output by the internal virtual synchronous generator When the speed threshold is exceeded, it is marked as abnormal speed. Indicates the minimum current threshold value, Indicates the maximum current threshold value. If the monitoring cycle Real-time current output of the internal virtual synchronous generator When the current threshold is exceeded, it is marked as abnormal output current. Indicates the minimum voltage threshold, Indicates the maximum voltage threshold. If the monitoring cycle Real-time voltage output of the internal virtual synchronous generator When the voltage threshold is exceeded, it is marked as abnormal output voltage. Indicates the minimum frequency threshold value, Indicates the maximum value of the frequency threshold. If the monitoring period Real-time frequency output of the internal virtual synchronous generator When the frequency threshold is exceeded, it is marked as abnormal output frequency. Real-time current required by the internal power grid system When the current threshold is exceeded, it is marked as abnormal load current. Real-time voltage required by the internal power grid system When the voltage threshold is exceeded, it is marked as abnormal load voltage. Real-time frequency required by the internal power grid system When the frequency threshold is exceeded, it is marked as abnormal load frequency, and a preliminary analysis is performed on the real-time operation data to quickly identify abnormal data, which facilitates subsequent in-depth analysis of the abnormal characteristics of the data; Step 3: According to the monitoring cycle Create a timeline , combined with the abnormal data set Insert the corresponding nodes, analyze the change characteristics of all nodes in the frequency domain and time domain, and generate the corresponding fluctuation index and distribution frequency , the calculation process is as follows: The abnormal data group Insert the abnormal speed, abnormal output current, abnormal output voltage, abnormal output frequency, abnormal load current, abnormal load voltage or abnormal load frequency marked in the time axis , and generate one-to-one corresponding nodes. In actual use, each abnormal value corresponds to a node of a color, and subsequent in-depth analysis will be performed based on the node data of the same color; If the abnormal data set Marked in Abnormal output current, The expression of abnormal output current is , to In turn, each abnormal output current is shown on the time axis The corresponding node in ; In the formula, represents the volatility index, The sum of the abnormal output currents divided by the number of nodes gives the average value of the abnormal output currents. Representing the timeline Middle The abnormal output current corresponding to each node is: According to the variance formula, The difference between the abnormal output current and the average value is the variance value, which is the fluctuation index of the abnormal output current in the frequency domain. Similarly, the fluctuation index of each abnormal value in the frequency domain is calculated according to the above formula. ; According to the timeline , count the time difference between every two adjacent abnormal output currents and mark them as , to respectively represent the time difference between every two adjacent abnormal output currents in the nodes; ; In the formula, represents the distribution frequency, express The sum of the group time differences, Indicates the frequency of occurrence of abnormal output current in the time domain, and also indicates The distribution probability of an abnormal output current node in the time domain is calculated by analogy. The distribution frequency of each abnormal value in the time domain is calculated according to the above formula. , flexible to adapt to load changes and strong stability; Step 4: Set a fixed range of fluctuation thresholds and distribution threshold , the volatility index Comparison Fluctuation Threshold , if a single monitoring cycle Internal volatility index Exceeding the volatility threshold When the virtual synchronous generator has an operating fault, the frequency distribution Comparison distribution threshold , if a single monitoring cycle Internal distribution frequency Distribution threshold exceeded When , it indicates that there is an operating fault in the virtual synchronous generator; According to the monitoring cycle Divide the training set and test set to generate the corresponding decision tree , the training process is as follows: Divide by time from early to late Monitoring cycle The operation data of the virtual synchronous generator and the power grid system will be Monitoring cycle The running data is used as the training set. Monitoring cycle The running data is used as the test set, and the reference threshold , Fluctuation threshold and distribution threshold As a decision tree Hyperparameters of Build a decision tree using the training set The backbone of the system is then used to generate a one-to-one decision tree based on the data types in the power data set and the load data set. The real-time speed, real-time current, real-time voltage, real-time frequency output by the virtual synchronous generator and the real-time current, real-time voltage, and real-time frequency required by the power grid system correspond to six groups of branches, and each branch corresponds to a group of abnormal data , Volatility Index , distribution frequency and operation fault judgment results; Evaluate the decision tree on the test set The accuracy of the generated operation fault judgment results is , indicating that training generates a decision tree With real-time diagnosis capability, if the accuracy rate is not reached , indicating that training generates a decision tree Insufficient real-time diagnostic capabilities, adding multiple monitoring cycles Running data and continue to update the decision tree , until the accuracy reaches , ensuring that the decision tree The accuracy of each branch can diagnose the cause of the fault during the operation of the virtual synchronous generator in real time and notify the maintenance management personnel. The real-time diagnosis of the cause of the fault is highly accurate.

[0020] Example 1: In this experiment, 10 hours of operating data of a virtual synchronous generator and a power grid system are selected as experimental objects. According to statistics, the speed threshold in the reference threshold is 3000-4000RPM, the current threshold is 1500-2000A, the voltage threshold is 210-230V, and the frequency threshold is 50-60Hz. The 10 hours of operating data of the virtual synchronous generator are marked with 5 abnormal output current values ​​of 1200A, 1280A, 1440A, 1390A, and 1300A, and each abnormal output current value has a corresponding node in the time axis. The fluctuation index calculation formula corresponding to the abnormal output current value of the virtual synchronous generator within 10 hours is as follows: ; In the formula, represents the volatility index, Indicates the average value of abnormal output current, Indicates that according to the variance formula, the difference between the five abnormal output current values ​​and the average value is calculated at the same time, and the variance value is obtained It is the fluctuation index of the abnormal output current in the frequency domain.

[0021] Example 2: In this experiment, the operating data of the virtual synchronous generator and the power grid system for 6 hours are used as experimental objects. According to statistics, the 4 abnormal output current values ​​of 1800A, 2000A, 1500A and 1930A are marked in the 6-hour operating data of the virtual synchronous generator, and each abnormal output current value has a corresponding node in the time axis. The time difference between every two adjacent abnormal output currents is 37min, 66min and 10min. The distribution frequency corresponding to the abnormal output current value of the virtual synchronous generator within 6 hours is The calculation formula is as follows: ; In the formula, It represents the distribution frequency. 38min / time represents the frequency of occurrence of abnormal output current in the time domain. It also represents the distribution probability of these four abnormal output current nodes in the time domain.

[0022] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for analyzing abnormal stability of a virtual synchronous generator, characterized in that: The following steps are involved: Step 1: Acquire the operation data of the virtual synchronous generator and the power grid system at all time points in real time through the network connection sensor device, and classify the acquired data into a power data set and a load data set. The power data set includes the real-time speed, real-time current, real-time voltage and real-time frequency output by the virtual synchronous generator, and the load data set includes the real-time current, real-time voltage and real-time frequency required by the power grid system; Step 2: Set a fixed monitoring period , and then for the monitoring cycle Set the reference threshold for a fixed range , based on the power data set and the load data set, identify the monitoring period Abnormal operation data within, generate corresponding abnormal data group ; Step 3: According to the monitoring cycle Create a timeline , combined with the abnormal data set Insert the corresponding nodes, analyze the change characteristics of all nodes in the frequency domain and time domain, and generate the corresponding fluctuation index and distribution frequency ; Step 4: Set a fixed range of fluctuation thresholds and distribution threshold , and combined with the volatility index and distribution frequency , determine whether the virtual synchronous generator has an operating fault, according to the monitoring cycle Divide the training set and test set to generate the corresponding decision tree , diagnose the cause of the fault during the operation of the virtual synchronous generator in real time and notify the maintenance management personnel.

2. The method for analyzing the stability anomaly of a virtual synchronous generator according to claim 1, characterized in that: In step 1, the expression of the power data set is: , Indicates the real-time speed output by the virtual synchronous generator. Indicates the real-time current output by the virtual synchronous generator, Indicates the real-time voltage output by the virtual synchronous generator, Indicates the real-time frequency output by the virtual synchronous generator, Indicates the time point for obtaining the operating data of the virtual synchronous generator.

3. The method for analyzing the stability anomaly of a virtual synchronous generator according to claim 2, characterized in that: In step 1, the expression of the load data set is: , Indicates the real-time current required by the power grid system, Indicates the real-time voltage required by the power grid system. Indicates the real-time frequency required by the power grid system, Indicates the time point for obtaining the power grid system operation data.

4. The method for analyzing the stability anomaly of a virtual synchronous generator according to claim 3, characterized in that: In the step 2, the reference threshold Including speed threshold , Current threshold , voltage threshold and frequency threshold .

5. The method for analyzing the stability anomaly of a virtual synchronous generator according to claim 4, characterized in that: In step 2, the abnormal data group The calculation process is as follows: Based on the power data set, extract the monitoring period Real-time speed output by the internal virtual synchronous generator , real-time current , real-time voltage and real-time frequency ; Extract monitoring cycles based on load data sets Real-time current required by the internal power grid system , real-time voltage and real-time frequency ; ； In the formula, represents an abnormal data set, Indicates the minimum speed threshold value, Indicates the maximum speed threshold value. If the monitoring cycle Real-time speed output by the internal virtual synchronous generator When the speed threshold is exceeded, it is marked as abnormal speed. Indicates the minimum current threshold value, Indicates the maximum current threshold value. If the monitoring cycle Real-time current output of the internal virtual synchronous generator When the current threshold is exceeded, it is marked as abnormal output current. Indicates the minimum voltage threshold, Indicates the maximum voltage threshold. If the monitoring cycle Real-time voltage output of the virtual synchronous generator When the voltage threshold is exceeded, it is marked as abnormal output voltage. Indicates the minimum frequency threshold value, Indicates the maximum value of the frequency threshold. If the monitoring period Real-time frequency output of the internal virtual synchronous generator When the frequency threshold is exceeded, it is marked as abnormal output frequency. Real-time current required by the internal power grid system When the current threshold is exceeded, it is marked as abnormal load current. Real-time voltage required by the internal power grid system When the voltage threshold is exceeded, it is marked as abnormal load voltage. Real-time frequency required by the internal power grid system When the frequency threshold is exceeded, it is marked as abnormal load frequency.

6. The method for analyzing the stability anomaly of a virtual synchronous generator according to claim 5, characterized in that: In step 3, the volatility index The calculation process is as follows: The abnormal data group Insert the abnormal speed, abnormal output current, abnormal output voltage, abnormal output frequency, abnormal load current, abnormal load voltage or abnormal load frequency marked in the time axis , and generate one-to-one corresponding nodes; If the abnormal data set Marked in Abnormal output current, The expression of abnormal output current is , to In turn, each abnormal output current is shown on the time axis The corresponding node in ; ； In the formula, represents the volatility index, The sum of the abnormal output currents divided by the number of nodes gives the average value of the abnormal output currents. Representing the timeline Middle The abnormal output current corresponding to each node is: According to the variance formula, The difference between the abnormal output current and the average value is obtained, and the variance value obtained is the fluctuation index of the abnormal output current in the frequency domain.

7. The method for analyzing the stability anomaly of a virtual synchronous generator according to claim 6, characterized in that: In step 3, the distribution frequency The calculation process is as follows: According to the timeline , count the time difference between every two adjacent abnormal output currents and mark them as , to Sequentially indicate The time difference between every two adjacent abnormal output currents in a node; ； In the formula, represents the distribution frequency, express The sum of the group time differences, Indicates the frequency of occurrence of abnormal output current in the time domain, and also indicates The distribution probability of abnormal output current nodes in the time domain.

8. The method for analyzing the abnormal stability of a virtual synchronous generator according to claim 7, characterized in that: In step 4, the volatility index Comparison Fluctuation Threshold , if a single monitoring cycle Internal volatility index Exceeding the volatility threshold , it indicates that there is an operating fault in the virtual synchronous generator.

9. The method for analyzing the stability anomaly of a virtual synchronous generator according to claim 8, characterized in that: In the step 4, the distribution frequency Comparison distribution threshold , if a single monitoring cycle Internal distribution frequency Distribution threshold exceeded , it indicates that there is an operating fault in the virtual synchronous generator.

10. The method for analyzing the stability anomaly of a virtual synchronous generator according to claim 9, characterized in that: In step 4, the decision tree The training process is as follows: Divide by time from early to late Monitoring cycle The operation data of the virtual synchronous generator and the power grid system will be Monitoring cycle The running data is used as the training set. Monitoring cycle The running data is used as the test set, and the reference threshold , Fluctuation threshold and distribution threshold As a decision tree Hyperparameters of Build a decision tree using the training set The backbone of the system is then used to generate a one-to-one decision tree based on the data types in the power data set and the load data set. branches, and each branch corresponds to a set of abnormal data groups , Volatility Index , distribution frequency and operation fault judgment results; Evaluate the decision tree on the test set The accuracy of the generated operation fault judgment results is , indicating that training generates a decision tree With real-time diagnosis capability, if the accuracy rate is not reached , indicating that training generates a decision tree Insufficient real-time diagnostic capabilities, adding multiple monitoring cycles Running data and continue to update the decision tree , until the accuracy reaches .

Images