Dynamic voltage regulation method of pole-mounted circuit breaker in new energy grid connection

Abstract

The invention discloses a dynamic voltage regulation method of a pole-mounted circuit breaker in new energy grid connection, and relates to the technical field of power equipment control, and the method comprises the steps: obtaining new energy grid connection voltage monitoring data and pole-mounted circuit breaker state data, carrying out the voltage abnormality detection, and obtaining an abnormality coefficient; and judging whether the abnormal coefficient exceeds a preset threshold, if so, activating a circuit breaker control decision model, inputting the abnormal coefficient and circuit breaker state data, and outputting a control strategy. And adjusting the on-off state of the pole-mounted circuit breaker according to the control strategy, and dynamically adjusting the voltage of the power grid. The technical problem that the voltage fluctuation caused by new energy grid connection is difficult to deal with due to the fact that the power grid voltage cannot be dynamically adjusted in real time in the prior art is solved, and the voltage fluctuation possibly occurring in the new energy grid connection process is effectively dealt with by monitoring and dynamically adjusting the control strategy of the pole-mounted circuit breaker in real time. Therefore, the stability of the power grid voltage is ensured.

Description

Technical Field

[0001] The present application relates to the field of power equipment control technology, and in particular to a dynamic voltage regulation method for a pole-mounted circuit breaker in the connection to a new energy grid. Background Art

[0002] With the large-scale access of new energy sources such as wind and solar energy, voltage fluctuations often occur in the grid during the grid connection process. Especially when the output of new energy sources fluctuates greatly, the voltage stability of the grid is seriously affected. Traditional voltage regulation methods usually rely on large substations or static voltage regulation equipment, which cannot achieve real-time dynamic regulation of grid voltage, especially in the environment of new energy grid connection, it is difficult to effectively deal with voltage fluctuations. This technology that lacks real-time regulation capabilities cannot guarantee the stable operation of the grid, and may even cause equipment damage and system failures. Therefore, how to improve voltage stability and cope with the challenges brought by the grid connection of new energy sources by real-time dynamic regulation of grid voltage, especially by using equipment such as pole-mounted circuit breakers, has become a technical problem that needs to be solved in the current power system.

[0003] At present, relevant technologies have the technical problem of being unable to dynamically adjust the grid voltage in real time, which makes it difficult to cope with voltage fluctuations caused by the connection of new energy to the grid. Summary of the invention

[0004] The present application solves the technical problem that the prior art cannot dynamically adjust the grid voltage in real time, making it difficult to cope with voltage fluctuations caused by the connection of new energy to the grid, by providing a dynamic voltage regulation method for pole-mounted circuit breakers in the connection of new energy to the grid.

[0005] The present application provides a dynamic voltage regulation method for a pole-mounted circuit breaker in a renewable energy grid connection, including:

[0006] Obtaining new energy grid-connected voltage monitoring data and circuit breaker status data of a pole-mounted circuit breaker; performing anomaly detection according to the new energy grid-connected voltage monitoring data to obtain a grid-connected voltage anomaly coefficient; judging whether the grid-connected voltage anomaly coefficient is greater than or equal to a grid-connected voltage anomaly threshold; if the grid-connected voltage anomaly coefficient is greater than or equal to the grid-connected voltage anomaly threshold, activating a circuit breaker control decision model; inputting the grid-connected voltage anomaly coefficient and the circuit breaker status data into the circuit breaker control decision model, and outputting a circuit breaker control strategy; and controlling the pole-mounted circuit breaker based on the circuit breaker control strategy.

[0007] The dynamic voltage regulation method of the pole-mounted circuit breaker in the new energy grid connection proposed in this application first obtains the new energy grid connection voltage monitoring data and the pole-mounted circuit breaker status data, performs voltage anomaly detection and obtains the abnormality coefficient. It is judged whether the abnormality coefficient exceeds the preset threshold. If it exceeds, the circuit breaker control decision model is activated, the abnormality coefficient and the circuit breaker status data are input, and the control strategy is output. According to the control strategy, the switching state of the pole-mounted circuit breaker is adjusted to dynamically adjust the grid voltage, achieving the technical effect of effectively responding to the voltage fluctuations that may occur during the new energy grid connection process by real-time monitoring and dynamic adjustment of the control strategy of the pole-mounted circuit breaker, thereby ensuring the stability of the grid voltage. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0009] Figure 1 A schematic flow chart of a dynamic voltage regulation method for a pole-mounted circuit breaker in a new energy grid connection provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of a circuit breaker update control flow of a dynamic voltage regulation method for a pole-mounted circuit breaker in a new energy grid-connected system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0012] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0013] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0014] The embodiment of the present application provides a dynamic voltage regulation method of a pole-mounted circuit breaker in a new energy grid connection, such as Figure 1 As shown, the method includes:

[0015] Step S100, obtain the voltage monitoring data of the new energy grid connection and the circuit breaker status data of the pole-mounted circuit breaker. Specifically, build a data acquisition network, install high-precision voltage sensors with wide range, high resolution and fast response characteristics at the new energy grid connection access points and key nodes of the power grid to accurately measure voltage signals of different amplitudes and frequencies, such as sensors with a measurement range of hundreds of volts to tens of kilovolts, a resolution of millivolts, and a response time of milliseconds; equip the pole-mounted circuit breaker with an intelligent monitoring module connected to the contacts, operating mechanism, energy storage device, etc., to obtain data such as switch position, number of actions, operating mechanism travel speed and energy storage status, and use optical fiber or high-speed wireless communication technology to transmit the collected data to the data processing center. Set the data collection frequency and synchronize it. The voltage monitoring data of new energy grid connection is collected 100 times per second to capture amplitude fluctuations, phase changes and harmonic components, etc., because the grid voltage changes rapidly and the power generation of new energy fluctuates greatly. The status data of the pole-mounted circuit breaker is collected every 10 seconds because the change is relatively slow but the accuracy and timeliness of the action are important. It includes information such as switch position and number of actions. With the help of GPS or high-precision clock synchronization equipment, a unified time base is provided for the collection terminal to facilitate subsequent correlation analysis. Perform data quality verification and preprocessing. The voltage monitoring data is first checked for integrity. When missing, it is supplemented by linear interpolation or weighted average interpolation of adjacent data, and then compared with the standard voltage source or historical normal data to verify accuracy. If the deviation is too large, check the sensor fault or interference signal. The status data of the pole-mounted circuit breaker verifies the logic. For example, the switch position can only be closed or open, and the number of actions should increase reasonably. After the verification is completed, low-pass filtering is used to remove high-frequency noise and high-pass filtering is used to remove DC components. Preprocessing, such as preprocessing, lays the foundation for abnormal detection and analysis.

[0016] Step S200, perform anomaly detection according to the new energy grid-connected voltage monitoring data to obtain the grid-connected voltage anomaly coefficient. Specifically, the data is cleaned and standardized to check the missing values, abnormal values ​​and erroneous data points in the new energy grid-connected voltage monitoring data. Missing values ​​can be filled by calculating reasonable interpolation values ​​based on the voltage values ​​at adjacent moments through linear interpolation of the previous and subsequent data, or replaced by the average value of historical data using the mean filling method; abnormal values ​​are identified based on the threshold range of ±10% of the rated voltage, and the reasons are further analyzed if they exceed this range. The erroneous data points are directly deleted, and the actual voltage value is divided by the rated voltage value after cleaning to convert it into a relative voltage value between 0 and 1 to unify the dimension scale. Feature extraction and construction are performed to extract statistical features such as voltage mean, variance, maximum value, peak-to-peak value, etc. from the processed monitoring data. The mean reflects the average level, the variance reflects the degree of discreteness, and a sudden increase in variance means that the voltage fluctuation is unstable. Spectral features can also be extracted. The amplitude distribution of different frequency components of the voltage signal is obtained by fast Fourier transform, and whether the harmonic components of a specific frequency increase abnormally is analyzed. The combined features construct a feature vector as the input of the anomaly detection model. To implement the training and application of the anomaly detection model, machine learning methods such as support vector machines, neural networks or isolation forest algorithms can be used. Taking neural networks as an example, a multi-layer perceptron structure is constructed. The number of nodes in the input layer is the same as the number of features, a hidden layer is set in the middle, and a single node in the output layer outputs the grid-connected voltage anomaly coefficient. The feature vectors of historical monitoring data are divided into training sets and test sets. The neural network is trained with the training set and the weight threshold is adjusted to enable it to master the normal voltage feature pattern. After training, the feature vectors of real-time monitoring data are input. The network judges and outputs the anomaly coefficient based on the learned pattern. A coefficient of 0 indicates that it conforms to the normal mode, 0.5 indicates that there is a certain anomaly, and a coefficient greater than 1 may be a more serious anomaly that requires further processing.

[0017] In a possible implementation, anomaly detection is performed according to the new energy grid-connected voltage monitoring data to obtain the grid-connected voltage anomaly coefficient, and step S200 further includes step S210, data cleaning is performed according to the new energy grid-connected voltage monitoring data to obtain grid-connected voltage monitoring standard data. Specifically, data cleaning processing is performed on the new energy grid-connected voltage monitoring data. Check whether there are missing values ​​in the data. If there are, a variety of strategies can be used to process them. For example, for a small number of scattered missing values, linear interpolation can be used to construct a linear relationship based on the adjacent data points before and after the missing values ​​to estimate the missing values. Assuming that the voltage data at a certain moment is missing, and the voltage value at the previous moment is 220V, the voltage value at the next moment is 222V, and the time interval is the same, then the voltage value at the missing moment can be estimated to be 221V. For the case of a large number of missing data, a filling method based on a statistical model is used, such as using the mean and standard deviation of the historical voltage data of the monitoring point to construct a normal distribution model, and then randomly generating values ​​that conform to the distribution according to the model to fill the missing data. At the same time, in order to identify outliers in the data, a reasonable outlier judgment threshold should be set by analyzing the distribution range and statistical characteristics of historical data. For example, if the historical voltage data is mostly concentrated between 210V and 230V, and the standard deviation is 5V, then data exceeding 230V+3*5V or below 210V-3*5V can be regarded as outliers. For outliers, further investigation of their causes may be due to sensor failure, instantaneous electromagnetic interference and other factors. After processing missing values ​​and outliers, the data is standardized and all data are transformed according to unified rules. For example, the voltage data is normalized so that the data is mapped to the 0-1 interval or the -1-1 interval, thereby obtaining the grid-connected voltage monitoring standard data.

[0018] Step S220, draw a grid-connected voltage monitoring curve according to the grid-connected voltage monitoring standard data. Specifically, the grid-connected voltage monitoring curve is drawn with time as the horizontal axis and the voltage value in the obtained grid-connected voltage monitoring standard data as the vertical axis. In the drawing process, it is necessary to ensure that the scale division of the time axis is reasonable and can clearly reflect the voltage change trend over time. For example, if the data acquisition frequency is once per second, the time axis can be marked with scales in seconds as the basic unit, and large time interval marks can be appropriately set as needed, such as every 10 seconds, every 1 minute, etc., so as to observe the voltage change trend over a long period of time. For the voltage value axis, the scale is divided according to the range and accuracy requirements of the data to ensure that the voltage fluctuation can be accurately displayed. For example, if the voltage value is mostly between 200V and 250V, the scale range of the voltage axis can be set to 190V to 260V, and the scale interval is 1V or 2V, so that the small fluctuations of the voltage can be clearly seen. By drawing the grid-connected voltage monitoring curve, the dynamic change process of the grid-connected voltage of new energy can be intuitively presented, providing a visual basis for subsequent abnormal detection.

[0019] Step S230, perform anomaly detection according to the grid-connected voltage monitoring curve and generate the grid-connected voltage anomaly coefficient. Specifically, perform feature extraction on the grid-connected voltage monitoring curve, and obtain the slope change rate by calculating the slope difference between adjacent data points. If large positive and negative values ​​frequently appear in a certain interval, the voltage change acceleration is large and may be abnormal. At the same time, the curve curvature feature is extracted based on a specific mathematical formula (such as the second-order derivative method). A large curvature change means that the voltage suddenly changes near this point. It is also necessary to count the number of data points of the curve in different voltage intervals (such as the normal interval of ±5% of the rated voltage, the mild abnormal interval of ±5% to ±10%, and the severe abnormal interval exceeding ±10%). Then, an anomaly detection model is constructed based on the extracted features. The multilayer perceptron in the neural network can be used. The number of nodes in the input layer corresponds to the number of features such as the slope change rate, curvature, and the number of data points in different voltage intervals, and the hidden layer is set to several layers according to the actual situation. For example, the two hidden layers have 2n and n nodes respectively. The single node in the output layer is used to output the grid-connected voltage anomaly coefficient. The historical curve data is divided into training sets and test sets to train the model. The weight threshold is adjusted using the back propagation algorithm according to the difference between the output anomaly coefficient and the actual known anomaly situation until the model has an accuracy rate of more than 90% on the test set. The real-time curve data is input into the trained model, and the grid-connected voltage anomaly coefficient with a value range of 0 to 1 is output after calculation and analysis. 0 means completely normal, the coefficient increases as the anomaly increases, 0-0.2 is normal fluctuation, 0.2-0.5 has mild anomalies, and 0.5-1 has more serious anomalies. Based on this coefficient, it can be determined whether to activate the circuit breaker control decision model to ensure the safe and stable operation of the new energy grid-connected system.

[0020] In a possible implementation, data cleaning is performed according to the new energy grid-connected voltage monitoring data to obtain grid-connected voltage monitoring standard data, and step S210 further includes step S211, obtaining first grid-connected voltage monitoring characteristic data according to the new energy grid-connected voltage monitoring data. Specifically, the first grid-connected voltage monitoring characteristic data is obtained from the new energy grid-connected voltage monitoring data. The purpose of extracting characteristic data is to mine key information in the data for subsequent more in-depth analysis and processing. For example, statistical features such as the mean, variance, maximum value, minimum value, and voltage change rate within a specific time period of voltage data can be extracted as the first grid-connected voltage monitoring characteristic data. The mean can reflect the average level of voltage, the variance reflects the degree of discreteness of voltage data, the maximum and minimum values ​​can help determine the fluctuation range of voltage, and the voltage change rate can indicate the dynamic change trend of voltage. Through comprehensive consideration of the characteristics, the basic characteristics and change laws of the new energy grid-connected voltage can be preliminarily understood.

[0021] Step S212, decentralized processing is performed on the first grid-connected voltage monitoring characteristic data to obtain the second grid-connected voltage monitoring characteristic data. Specifically, the first grid-connected voltage monitoring characteristic data obtained is decentralized, so as to obtain the second grid-connected voltage monitoring characteristic data. The purpose of decentralized processing is to eliminate the influence of the mean in the data, so that the data can be more focused on the relative changes and characteristic structures of the data during the processing. The specific operation is to subtract the mean of the feature from each eigenvalue in the first grid-connected voltage monitoring characteristic data. For example, for the feature of the voltage mean, if its original mean is 220V, then during the decentralized processing, each data point related to the voltage mean is subtracted by 220V. After such processing, the center of the data is translated to the origin, and subsequent operations such as covariance matrix calculation can more accurately reflect the intrinsic correlation and change characteristics of the data, and avoid interference of the mean with the analysis results.

[0022] Step S213, according to the second grid-connected voltage monitoring characteristic data, obtain the first grid-connected voltage monitoring characteristic covariance matrix. Specifically, based on the decentralized second grid-connected voltage monitoring characteristic data, the first grid-connected voltage monitoring characteristic covariance matrix is ​​calculated. The covariance matrix can measure the linear correlation between different features. For multiple features (such as the mean, variance, maximum value, etc. mentioned above), each element in the covariance matrix represents the covariance between the corresponding two features. For example, the i-th row and j-th column element in the covariance matrix represents the covariance between the i-th feature and the j-th feature. By calculating the covariance matrix, the relationship between different voltage monitoring features can be obtained, such as whether there is a certain correlation between the voltage mean and the voltage change rate, whether it is positively correlated or negatively correlated, etc. Correlation analysis helps to discover the potential laws and characteristic patterns hidden in the data, and provides an important basis for further data processing and anomaly detection.

[0023] Step S214, according to the first grid-connected voltage monitoring characteristic covariance matrix, obtain the first grid-connected voltage monitoring eigenvalue and the first grid-connected voltage monitoring eigenvector. Specifically, according to the calculated first grid-connected voltage monitoring characteristic covariance matrix, solve the first grid-connected voltage monitoring eigenvalue and the first grid-connected voltage monitoring eigenvector. Eigenvalues ​​and eigenvectors are of great significance in data processing. The eigenvalue reflects the variance of the data in the characteristic direction represented by the corresponding eigenvector, that is, the degree of discreteness of the data in this direction. The eigenvector determines the main direction of change of the data. For example, the eigenvector corresponding to a larger eigenvalue indicates that the data has a larger variation range in this direction, and the main eigenvectors constitute the main feature space of the data. By solving the eigenvalues ​​and eigenvectors, the data can be reduced in dimension or the main components of the data can be extracted, thereby simplifying the data structure, highlighting the key information of the data, and facilitating subsequent analysis and processing.

[0024] Step S215, according to the first grid-connected voltage monitoring characteristic value and the first grid-connected voltage monitoring characteristic vector, the grid-connected voltage monitoring standard data is obtained. Specifically, according to the first grid-connected voltage monitoring characteristic value and the first grid-connected voltage monitoring characteristic vector, the grid-connected voltage monitoring standard data is obtained. The original data can be transformed using the eigenvalues ​​and eigenvectors, for example, by using the principal component analysis (PCA) method to project the original data into a new space composed of the main eigenvectors, and obtain the data representation in the new space, and the data is the grid-connected voltage monitoring standard data. On the basis of retaining the key information of the original data, the standard data has better structure and stability, and can be more effectively used in subsequent anomaly detection, model training and other operations, thereby improving the accuracy and reliability of the entire new energy grid-connected voltage monitoring and analysis system.

[0025] In a possible implementation, anomaly detection is performed according to the grid-connected voltage monitoring curve to generate the grid-connected voltage anomaly coefficient, and step S230 further includes step S231, loading the grid-connected voltage anomaly detection record set. Specifically, the loading operation of the grid-connected voltage anomaly detection record set is performed. The record set is accumulated through long-term monitoring and analysis of the grid-connected voltage of new energy sources, and contains a large amount of historical voltage data and corresponding anomaly annotation information. For example, each piece of data in the record set may include a sequence of continuous voltage monitoring values ​​within a certain time period, and a mark of whether a voltage anomaly occurs within the time period (such as normal marked as 0, abnormal marked as 1). The data covers the grid-connected voltage conditions of new energy sources under various working conditions and environmental conditions, is rich in information and representative, and provides a solid data foundation for the subsequent training of neural networks.

[0026] Step S232, data is divided according to the grid-connected voltage anomaly detection record set to obtain a voltage anomaly detection training set and a voltage anomaly detection verification set. Specifically, data division processing is performed according to the loaded grid-connected voltage anomaly detection record set, so as to obtain a voltage anomaly detection training set and a voltage anomaly detection verification set. In the division process, a random division method is adopted, but it is necessary to ensure that the divided training set and verification set can reasonably reflect the overall characteristics and distribution of the data. For example, the record set can be divided into a training set and a verification set in a ratio of 80:20, that is, 80% of the data is used as a training set for neural network learning and parameter adjustment, and 20% of the data is used as a verification set for evaluating the performance and generalization ability of the model during the training process. When dividing, it is necessary to ensure that the ratio of abnormal data to normal data in the training set and the verification set is roughly the same, so as to avoid deviations in model training due to uneven data distribution. For example, if the proportion of abnormal data in the entire record set is 10%, then the proportion of abnormal data in the training set should also be as close to 10% as possible, and the same is true in the verification set.

[0027] Step S233, according to the voltage anomaly detection training set and the voltage anomaly detection verification set, the neural network is trained and verified to generate a grid-connected voltage anomaly detection network. Specifically, according to the voltage anomaly detection training set and the voltage anomaly detection verification set obtained by division, the neural network is trained and verified to generate a grid-connected voltage anomaly detection network. During the training process, the voltage data in the training set is input into the input layer of the neural network, and the neural network performs forward propagation calculation according to its internal structure and algorithm to obtain a prediction result (i.e., whether there is a voltage anomaly prediction), and the prediction result is compared with the real label (known abnormal labeling information) in the training set to calculate the value of the loss function. Based on the value of the loss function, the back propagation algorithm is used to adjust the parameters such as the weight and bias of the neural network to gradually reduce the difference between the prediction result and the real label. Repeatedly perform multiple times until the preset training stop condition is reached, such as the number of training times reaches the set maximum value, or the value of the loss function has converged to a smaller range. During the training process, the validation set is also used regularly to verify the trained model, and the performance indicators such as the accuracy, recall rate, and F1 value of the model on the validation set are calculated. If it is found that the performance of the model on the validation set begins to decline, it means that the model may be overfitting. At this time, some measures can be taken, such as adjusting the structure of the neural network (reducing the number of hidden layer nodes, increasing regularization terms, etc.), adjusting training parameters (such as reducing the learning rate), etc. to prevent overfitting and ensure that the final generated grid-connected voltage anomaly detection network has good generalization ability and accuracy.

[0028] Step S234, input the grid-connected voltage monitoring curve into the grid-connected voltage anomaly detection network to obtain the grid-connected voltage anomaly coefficient. Specifically, after completing the training and verification of the neural network and generating the grid-connected voltage anomaly detection network, the real-time grid-connected voltage monitoring curve is input into the network to obtain the grid-connected voltage anomaly coefficient. The specific operation is to process and organize the data points in the grid-connected voltage monitoring curve according to the requirements of the neural network input layer, for example, input the voltage data sequence within a certain time window as an input sample into the network. The network analyzes and judges the input voltage monitoring curve data according to the characteristic patterns and rules it has learned, and finally outputs a grid-connected voltage anomaly coefficient. The size of the grid-connected voltage anomaly coefficient reflects the degree of deviation of the voltage situation represented by the current input grid-connected voltage monitoring curve from the normal voltage mode. The larger the coefficient, the greater the possibility of voltage anomaly and the farther it deviates from the normal mode. For example, if the coefficient is 0, it means that the network judges that the voltage data is completely in line with the normal mode; if the coefficient is 0.5, it means that there is a certain degree of abnormality; when the coefficient is greater than 1, it may indicate that a more serious voltage abnormality has occurred, and further measures need to be taken to deal with it, such as activating the circuit breaker control decision model, etc., to ensure the safe and stable operation of the new energy grid-connected system.

[0029] Step S300, determine whether the grid voltage anomaly coefficient is greater than or equal to the grid voltage anomaly threshold. Specifically, the setting of the grid voltage anomaly threshold is based on many factors, and needs to be based on the normal voltage fluctuation range determined by the relevant standards and specifications for grid operation, and consider the rated working voltage range and tolerance of various types of equipment in the new energy grid-connected system. For example, precision electronic equipment can only withstand ±5% fluctuations in the rated voltage, and large power transformers generally do not exceed ±10% fluctuations in the rated voltage. Combined with a large amount of actual operation data and experience in the past, analyze the boundary values ​​of voltage abnormal fluctuations under different working conditions that do not cause serious effects and the corresponding values ​​that cause fault damage. After in-depth research through statistical analysis, determine the appropriate threshold, which can ensure the safe and stable operation of the system and avoid frequent triggering of unnecessary control operations due to conservative thresholds. After obtaining the grid-connected voltage anomaly coefficient, it is accurately compared with the set threshold value. This is the key node of the control decision. If the coefficient is less than the threshold, the new energy grid-connected voltage will fluctuate slightly but remain within the normal range. The system can maintain the current operating state and continue to monitor the voltage to detect abnormal trends; if the coefficient is greater than or equal to the threshold, the voltage exceeds the normal safety range, which may affect the stability of the power grid, the safe operation of equipment and the quality of power. At this time, a series of control measures need to be started immediately, such as activating the circuit breaker control decision model to adjust the state of the pole-mounted circuit breaker, quickly and effectively respond to voltage anomalies, prevent problems from worsening, and ensure the reliable operation of the new energy grid-connected system.

[0030] Step S400, if the grid voltage anomaly coefficient is greater than or equal to the grid voltage anomaly threshold, activate the circuit breaker control decision model. Specifically, when the grid voltage anomaly coefficient is greater than or equal to the grid voltage anomaly threshold, the new energy grid voltage falls into a dangerous or unstable state, posing a serious threat to the safe operation of the power system. At this time, the special monitoring and control unit automatically triggers the instruction to activate the circuit breaker control decision model. The unit continuously monitors and compares the grid voltage anomaly coefficient. Once the conditions are met, it immediately transmits an activation signal to the computing device or system module storing the circuit breaker control decision model through a wired communication network (such as industrial Ethernet) or a wireless communication method (such as a wireless network in a specific frequency band) to start the model, prepare to analyze and decide the current voltage anomaly situation, and take effective control measures in time to deal with potential risks; after the circuit breaker control decision model receives the activation signal, it first Carry out its own initialization operations, including loading predefined model parameters, configuring operating environment variables, initializing internal calculation logic and data structure, etc. At the same time, receive and process data, obtain the grid-connected voltage anomaly coefficient and the circuit breaker status data of the pole-mounted circuit breaker from the data storage system or directly from the data acquisition module. The data is the key basis for the model to make accurate decisions. The former reflects the degree and characteristics of voltage anomalies, and the latter covers the opening and closing status of the circuit breaker, the number of actions, the last action time and the operating status of internal key components. The model will convert the data format, clean (remove noise or erroneous data) and standardize the data, and convert the data into the expected numerical range and distribution form, so as to ensure data quality and availability, and lay a solid foundation for the subsequent output of circuit breaker control strategies.

[0031] In one possible implementation, Figure 2 As shown, if the grid voltage anomaly coefficient is greater than or equal to the grid voltage anomaly threshold, the circuit breaker control decision model is activated, and step S400 further includes step S410, if the grid voltage anomaly coefficient is less than the grid voltage anomaly threshold, a grid voltage continuous monitoring instruction is generated. Specifically, when it is determined that the grid voltage anomaly coefficient is less than the grid voltage anomaly threshold, the current new energy grid voltage fluctuates but is still within an acceptable normal range. The system will automatically generate a grid voltage continuous monitoring instruction. The instruction is issued by the core control unit of the monitoring system, with the aim of maintaining close attention to the grid voltage so as to promptly detect possible abnormal change trends. The instruction contains information such as the monitoring time interval, the accuracy requirements of data acquisition, and the data transmission path to ensure that subsequent monitoring work can be carried out in an orderly and efficient manner.

[0032] Step S420, based on the grid voltage continuous monitoring instruction, the grid voltage update monitoring data and the circuit breaker update status data are obtained. Specifically, based on the generated grid voltage continuous monitoring instruction, the system starts to obtain the grid voltage update monitoring data and the circuit breaker update status data. For the grid voltage update monitoring data, the data acquisition device accurately measures the grid voltage of the new energy within the specified time interval according to the requirements in the instruction. For example, if the instruction requires data to be collected every 5 minutes, the voltage sensor will collect the voltage value at the corresponding time node and transmit the data to the data processing center through a high-speed data transmission line (such as an optical fiber communication network). At the same time, the circuit breaker update status data is obtained from the intelligent monitoring module of the column circuit breaker, including the current opening and closing state of the circuit breaker (whether it is in a closed conduction state or an open isolation state), the number of actions since the last monitoring, the specific time of the most recent action, and the operating status information of the internal key components (such as contacts, operating mechanisms, etc.) (such as the degree of wear of the contacts, the energy storage level of the operating mechanism, etc.). The acquisition of data provides a comprehensive and real-time basis for subsequent abnormal detection and control strategy formulation.

[0033] Step S430, perform anomaly detection based on the grid-connected voltage update monitoring data to obtain the grid-connected voltage abnormal update coefficient. Specifically, perform multi-dimensional feature extraction on the grid-connected voltage update monitoring data, and calculate its statistical features such as mean, variance, maximum, minimum and median, where the mean reflects the average voltage level during the period, the variance reflects the discreteness of the voltage value, the maximum and minimum values ​​determine the fluctuation range, and the median assists in judging the symmetry of the data distribution. For example, when the mean is 225V and the variance is 10, the voltage fluctuates slightly around 225V; at the same time, analyze the voltage change rate between adjacent data points, that is, the slope change, and observe the voltage change trend and rate. If the slope is more positive and larger in a certain period, the voltage rises faster; spectrum analysis is also required to determine whether there are specific frequency harmonic components, and exceeding the normal range will become an important consideration for abnormality. Based on the extracted features, anomaly detection is performed to obtain the grid-connected voltage anomaly update coefficient. First, the feature data is input into a pre-trained anomaly detection model such as a neural network model. The model outputs a numerical value representing the degree of anomaly as a coefficient based on the difference between normal and abnormal data patterns. 0 is completely normal, and the closer to 1, the higher the anomaly. Second, based on the set rules, judgments are made, such as the maximum voltage exceeding the rated voltage by 110%, the variance exceeding the preset threshold, or the detection of a specific high-content harmful harmonic component. According to the severity and quantity of the anomaly, the coefficient is calculated through comprehensive evaluation methods such as weighted summation. If the maximum voltage exceeds the standard and there are harmful harmonics, the two are weighted during the calculation to show their greater potential harm to the operation of the power grid, thereby obtaining an update coefficient that can accurately reflect the current abnormal condition of the grid-connected voltage, laying the foundation for subsequent control decisions.

[0034] Step S440, based on the grid voltage anomaly update coefficient and the circuit breaker update status data, according to the circuit breaker control decision model, output the circuit breaker update control strategy. Specifically, based on the calculated grid voltage anomaly update coefficient and the acquired circuit breaker update status data, output the circuit breaker update control strategy according to the circuit breaker control decision model. The circuit breaker control decision model is an intelligent decision-making system built on a large amount of historical data, power system operation principles and expert experience. The grid voltage anomaly update coefficient and circuit breaker update status data are used as inputs, and through the internal complex calculation and reasoning process, the impact of voltage anomalies on the power grid system, the current operating status of the circuit breaker, and the possible consequences of different control operations and other factors are analyzed to output a suitable circuit breaker update control strategy. For example, if the grid-connected voltage anomaly update coefficient shows that the voltage has a slight upward trend but is still within an acceptable range, and the circuit breaker is in a closed state and operates stably, the model may output a strategy to continue to maintain the current circuit breaker state and continue monitoring; if the voltage anomaly update coefficient indicates that the voltage has fluctuated significantly and the circuit breaker is close to its upper limit of the number of operations, the model may output a strategy to adjust the circuit breaker protection parameters (such as action threshold, delay time, etc.) to adapt to the voltage changes and ensure the safe and reliable operation of the circuit breaker.

[0035] Step S450, update control of the pole-mounted circuit breaker based on the circuit breaker update control strategy. Specifically, update control of the pole-mounted circuit breaker is performed based on the generated circuit breaker update control strategy. The control instruction is transmitted to the operating mechanism of the pole-mounted circuit breaker through a communication link (such as a wireless remote control signal or a wired control network), and the operating mechanism performs corresponding actions according to the instruction, such as adjusting the opening and closing state of the contact, modifying the protection parameter setting, etc., thereby realizing precise control of the pole-mounted circuit breaker and ensuring the stable operation of the new energy grid-connected system.

[0036] In a possible implementation, based on the grid voltage abnormality update coefficient and the circuit breaker update state data, according to the circuit breaker control decision model, the circuit breaker update control strategy is output, and step S440 further includes step S441, judging whether the grid voltage abnormality update coefficient is greater than or equal to the grid voltage abnormality threshold. Specifically, the calculated grid voltage abnormality update coefficient is compared with the preset grid voltage abnormality threshold. The threshold is a key indicator determined by analyzing the stability of power grid operation, the safety tolerance range of equipment, and a large amount of actual operation data in the past. For example, if the voltage fluctuation range of most equipment in the power grid that can operate normally is between ±8% relative to the rated voltage, and considering a certain safety margin, the abnormal threshold is set to the coefficient value corresponding to the voltage deviation of 10% from the rated value. In the comparison process, it is necessary to ensure the matching of data types and calculation accuracy to obtain accurate comparison results. If the grid voltage abnormality update coefficient is less than the threshold, it means that although the current voltage has some fluctuations, it is still in a relatively safe range. The system can continue to maintain the normal monitoring process and will not start special control measures for the time being.

[0037] Step S442, if the grid voltage anomaly update coefficient is greater than or equal to the grid voltage anomaly threshold, activate the circuit breaker control decision model. Specifically, if the grid voltage anomaly update coefficient is greater than or equal to the grid voltage anomaly threshold, it indicates that the voltage anomaly has reached a level that requires intervention control, and the circuit breaker control decision model will be activated at this time. The activation signal is sent by the control core of the monitoring system and transmitted to the computing device or module storing the circuit breaker control decision model through a reliable communication link (such as high-speed Ethernet or a dedicated control bus). During the activation process, a series of preparations will be performed on the operating environment where the model is located, including checking whether the software dependencies required by the model are complete and whether the hardware resources are sufficient (such as CPU, memory, etc.), to ensure that the model can be started smoothly and run efficiently.

[0038] Step S443, input the grid voltage abnormality update coefficient and the circuit breaker update state data into the circuit breaker control decision model to obtain the circuit breaker update control strategy. Specifically, when the circuit breaker control decision model is activated, the grid voltage abnormality update coefficient and the circuit breaker update state data are input into it. The model first parses and preprocesses the input data to make it meet the requirements of the internal algorithm. Based on its built-in intelligent algorithm and the decision logic obtained by training a large amount of historical data, the severity of the voltage abnormality (reflected by the abnormal update coefficient) and the current actual state of the circuit breaker (such as the opening and closing state, the number of actions, the wear of internal components, etc.) are analyzed. For example, if the voltage abnormality is high and the circuit breaker is in a long-term closed state and the number of actions is small, the model will tend to generate a control strategy for disconnecting the circuit breaker to isolate the abnormal voltage source; if the voltage abnormality is relatively light and the circuit breaker has frequent actions recently, the model will consider adjusting the protection parameters of the circuit breaker (such as delay time, action sensitivity, etc.) to adapt to the voltage change, while continuing to monitor the voltage situation. Through such a complex calculation and reasoning process, we can eventually obtain the most appropriate circuit breaker update control strategy for the current situation, providing accurate and effective operational guidance to ensure the safe and stable operation of the power grid.

[0039] In a possible implementation, if the grid voltage anomaly coefficient is greater than or equal to the grid voltage anomaly threshold, the circuit breaker control decision model is activated, and step S400 further includes step S460, if the grid voltage anomaly coefficient is greater than or equal to the grid voltage anomaly threshold, the grid voltage anomaly early warning device is activated. Specifically, when it is determined that the grid voltage anomaly coefficient is greater than or equal to the grid voltage anomaly threshold, it indicates that the current new energy grid voltage condition has exceeded the normal allowable range, and there is a risk of threatening the safe and stable operation of the power grid. The monitoring and control unit in the system will automatically trigger the instruction to activate the grid voltage anomaly early warning device. The instruction is generated based on a preset logical judgment condition. Once the condition is met, an activation signal is sent to the grid voltage anomaly early warning device through an internal communication bus or a dedicated signal line. The transmission of the activation signal must be fast, accurate and stable to ensure that the early warning device can respond in time and enter a working state.

[0040] Step S470, input the grid-connected voltage abnormality coefficient into the grid-connected voltage abnormality early warning device to obtain a grid-connected voltage abnormality early warning signal. Specifically, after receiving the activation signal, the grid-connected voltage abnormality early warning device receives and processes the input grid-connected voltage abnormality coefficient. The correspondence between different abnormality coefficient ranges and early warning signal levels is pre-set inside the early warning device. For example, when the abnormality coefficient is in the interval from the threshold to a certain intermediate value, it may correspond to a mild early warning signal, indicating that the voltage has a certain degree of abnormality, but the risk is relatively controllable; when the abnormality coefficient exceeds the intermediate value, it corresponds to a severe early warning signal, reflecting that the voltage abnormality is more serious and may cause greater damage to the power grid equipment. The device generates a corresponding grid-connected voltage abnormality early warning signal based on the specific abnormality coefficient received and the above-mentioned correspondence. The early warning signal can be in many forms, such as sound and light alarm signals (sounds and flashing lights of specific frequencies are emitted in the monitoring center), digital signals (transmitted to the terminal equipment of relevant operation and maintenance personnel through the network, displaying specific abnormal coefficients and early warning level information) or control signals (triggering other auxiliary equipment, such as starting the backup power supply or adjusting the reactive power compensation device, etc.), so that the operation and maintenance personnel or the automatic control system can detect the voltage abnormality in time and take corresponding countermeasures, such as further checking the power grid equipment, adjusting the power generation capacity or performing emergency power outage operations, etc., to ensure the safe operation of the new energy grid-connected system.

[0041] In a possible implementation, if the grid voltage anomaly coefficient is greater than or equal to the grid voltage anomaly threshold, the grid voltage anomaly warning device is activated, and step S460 further includes step S461, wherein the grid voltage anomaly warning device includes a grid voltage anomaly graded warning table, and the grid voltage anomaly graded warning table includes multiple grid voltage anomaly predetermined intervals and multiple grid voltage anomaly graded warning signals, and the multiple grid voltage anomaly predetermined intervals have a one-to-one correspondence with the multiple grid voltage anomaly graded warning signals. Specifically, the construction of the grid voltage anomaly graded warning table is derived from the in-depth analysis of the grid voltage anomaly of new energy and the statistical summary of a large amount of historical data. First, by exploring many past voltage anomaly events, combined with the grid operation theory and the tolerance characteristics of related equipment, a series of representative grid voltage anomaly predetermined intervals are determined, and the division fully considers the effect of the voltage anomaly degree on various levels of the grid, such as a smaller deviation interval corresponding to a situation where the power quality is slightly affected but the equipment is not in immediate danger, and a larger deviation interval is associated with serious conditions such as equipment damage, grid instability, and even large-scale power outages. For each predetermined interval, according to the severity of the consequences caused by it, carefully plan the matching grid-connected voltage abnormality graded warning signal, from slight prompt signal to strong emergency alarm signal to form a complete system, so as to accurately convey the dangerous level of voltage abnormality to the operation and maintenance personnel or the automatic control system, which is conducive to taking appropriate response measures. When the grid-connected voltage abnormality warning device receives the input abnormal coefficient, it immediately starts the warning signal generation process, compares the abnormal coefficient with the predetermined interval in the warning table one by one, and uses the efficient search and matching mechanism to quickly lock the specific interval, and then quickly extracts and generates the corresponding graded warning signal according to the preset corresponding relationship. For example, if the abnormal coefficient is in the medium abnormal degree interval, the device will generate a medium-intensity warning signal, such as the monitoring center sends a specific frequency tone alarm, the monitoring screen displays the abnormal information and recommends preliminary processing measures in eye-catching colors, and sends the information to the operation and maintenance personnel's mobile terminal through the communication network to ensure that the operation and maintenance personnel know the abnormal details in time and respond quickly, such as sending people to the site to check the equipment, adjust the grid parameters or start the emergency plan, so as to minimize the adverse effects of voltage abnormality on the new energy grid-connected system and protect the safe and stable operation of the power grid.

[0042] Step S500, input the grid voltage anomaly coefficient and the circuit breaker status data into the circuit breaker control decision model, and output the circuit breaker control strategy. Specifically, the grid voltage anomaly coefficient and the circuit breaker status data are input into the circuit breaker control decision model. Before input, it is necessary to ensure that the data format and type meet the model requirements, and complete data cleaning, standardization and other pre-processing work, such as converting the grid voltage anomaly coefficient in percentage form into the normalized value required by the model. The circuit breaker status data covers multi-dimensional information such as the current opening and closing state represented in binary, the number of actions, the last action time accurate to seconds or milliseconds, and the health status of internal key components monitored by sensors and converted to 0-1 values ​​to represent the health degree, and are input in order according to the model structure. After receiving the data, the circuit breaker control decision model launches a complex internal analysis and decision-making process. It calculates based on a large amount of historical data, the physical laws of power system operation and preset algorithm rules, and judges the degree of abnormality based on the grid-connected voltage abnormality coefficient. When the abnormality coefficient is small and close to the normal range boundary, the number of circuit breaker operations and health status are focused on. If the number of operations is small and the health status is not good, even if the voltage is slightly abnormal, it may tend to maintain the current state and increase the voltage monitoring frequency to observe changes; when the abnormality coefficient is large, the decision is made based on the circuit breaker opening and closing state. If the circuit breaker is closed, it will calculate whether disconnecting the circuit breaker will cause local power outages, cause impacts on parallel equipment and other chain reactions based on the type and severity of the voltage abnormality. If disconnection is the safest and most effective measure, the control strategy for disconnecting the circuit breaker is output. If there are better solutions such as adjusting the reactive power compensation device, adjusting the power factor setting value of related equipment, or switching the backup power supply line, the corresponding control strategy for performing other specific operations is output, so as to achieve precise control and protection of the new energy grid-connected system.

[0043] Step S600, control the pole-mounted circuit breaker based on the circuit breaker control strategy. Specifically, when the circuit breaker control decision model outputs the circuit breaker control strategy, the system generates corresponding control instructions based on the strategy. If the strategy is to disconnect the circuit breaker, the instruction clearly requires the pole-mounted circuit breaker operating mechanism to perform the disconnection action; if it is to maintain the current state, the instruction tells the monitoring system to continuously monitor the current state of the circuit breaker without operating it temporarily; if it is to perform other specific operations, such as adjusting the power factor setting value of the equipment or switching the backup power supply line, the control instruction will cover the relevant equipment operation parameters and step information in detail. After the instruction is generated, it is transmitted to the pole-mounted circuit breaker control terminal via a reliable communication link. This communication link can be a wired form using a dedicated control cable to ensure signal transmission stability and anti-interference, or it can be a wireless form based on a specific frequency band industrial wireless network to have flexibility and convenience, and the instruction will be encrypted and verified during transmission to prevent tampering or erroneous transmission, ensuring that it is accurately delivered to the control terminal. After receiving the command, the control terminal of the pole-mounted circuit breaker analyzes and verifies it. If the verification is passed, it drives the actuator to act according to the command. For example, when the circuit breaker is disconnected, the actuator uses electromagnetic force or mechanical force to separate the contacts and cut off the circuit to protect the new energy grid-connected system. When the circuit breaker is in action, the internal sensor monitors the contact position, action speed, operating mechanism pressure and other parameters in real time and feeds them back to the control terminal. The control terminal then transmits this information back to the monitoring system via the communication link, which is convenient for the operation and maintenance personnel to understand the execution status and confirm whether it is successfully acted according to the strategy. If the circuit breaker refuses to operate (unable to open or close normally due to mechanical failure, etc.) or the action timeout (exceeds the preset normal action time) during the execution, the control terminal immediately sends an alarm message to the monitoring system and takes corresponding emergency measures, such as executing the command again, starting the backup operating mechanism or issuing an emergency power outage signal, etc., to ensure the safe operation of the new energy grid-connected system and provide a basis for the operation and maintenance personnel to troubleshoot and repair faults.

[0044] The embodiment of the present application adopts the method of obtaining the voltage monitoring data of the new energy grid connection and the status data of the pole-mounted circuit breaker to detect the voltage anomaly and obtain the abnormal coefficient. It is judged whether the abnormal coefficient exceeds the preset threshold value. If it exceeds, the circuit breaker control decision model is activated, the abnormal coefficient and the circuit breaker status data are input, and the control strategy is output. According to the control strategy, the switching state of the pole-mounted circuit breaker is adjusted, and the grid voltage is dynamically adjusted, so as to achieve the technical effect of effectively coping with the voltage fluctuations that may occur in the process of new energy grid connection through real-time monitoring and dynamic adjustment of the control strategy of the pole-mounted circuit breaker, thereby ensuring the stability of the grid voltage.

[0045] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A dynamic voltage regulation method for a pole-mounted circuit breaker in a renewable energy grid connection, characterized in that: The method comprises: Obtaining new energy grid-connected voltage monitoring data and circuit breaker status data of pole-mounted circuit breakers; Performing anomaly detection based on the new energy grid-connected voltage monitoring data to obtain a grid-connected voltage anomaly coefficient; Determining whether the grid-connected voltage abnormality coefficient is greater than or equal to the grid-connected voltage abnormality threshold; If the grid voltage abnormality coefficient is greater than or equal to the grid voltage abnormality threshold, activating the circuit breaker control decision model; Inputting the grid voltage abnormality coefficient and the circuit breaker status data into the circuit breaker control decision model, and outputting the circuit breaker control strategy; The pole mounted circuit breaker is controlled based on the circuit breaker control strategy.

2. The method according to claim 1, characterized in that Anomaly detection is performed according to the new energy grid-connected voltage monitoring data to obtain a grid-connected voltage anomaly coefficient, including: Perform data cleaning according to the new energy grid-connected voltage monitoring data to obtain grid-connected voltage monitoring standard data; According to the grid-connected voltage monitoring standard data, a grid-connected voltage monitoring curve is drawn; Anomaly detection is performed according to the grid-connected voltage monitoring curve to generate the grid-connected voltage anomaly coefficient.

3. The method according to claim 2, characterized in that Data cleaning is performed according to the new energy grid-connected voltage monitoring data to obtain grid-connected voltage monitoring standard data, including: According to the new energy grid-connected voltage monitoring data, obtaining first grid-connected voltage monitoring characteristic data; Decentralizing the first grid-connected voltage monitoring characteristic data to obtain second grid-connected voltage monitoring characteristic data; Obtaining a first grid-connected voltage monitoring characteristic covariance matrix according to the second grid-connected voltage monitoring characteristic data; Obtaining a first grid-connected voltage monitoring eigenvalue and a first grid-connected voltage monitoring eigenvector according to the first grid-connected voltage monitoring characteristic covariance matrix; The grid-connected voltage monitoring standard data is obtained according to the first grid-connected voltage monitoring characteristic value and the first grid-connected voltage monitoring characteristic vector.

4. The method according to claim 2, characterized in that Performing abnormality detection according to the grid-connected voltage monitoring curve to generate the grid-connected voltage abnormality coefficient includes: Load the grid-connected voltage anomaly detection record set; Data is divided according to the grid-connected voltage anomaly detection record set to obtain a voltage anomaly detection training set and a voltage anomaly detection verification set; Training and verifying a neural network according to the voltage anomaly detection training set and the voltage anomaly detection verification set to generate a grid-connected voltage anomaly detection network; The grid-connected voltage monitoring curve is input into the grid-connected voltage anomaly detection network to obtain the grid-connected voltage anomaly coefficient.

5. The method according to claim 1, characterized in that Determining whether the grid-connected voltage abnormality coefficient is greater than or equal to the grid-connected voltage abnormality threshold comprises: If the grid voltage abnormality coefficient is less than the grid voltage abnormality threshold, generating a grid voltage continuous monitoring instruction; Based on the grid voltage continuous monitoring instruction, obtaining grid voltage update monitoring data and circuit breaker update status data; Perform anomaly detection based on the grid-connected voltage update monitoring data to obtain a grid-connected voltage anomaly update coefficient; Based on the grid voltage abnormality update coefficient and the circuit breaker update state data, and according to the circuit breaker control decision model, output a circuit breaker update control strategy; The pole mounted circuit breaker is updated and controlled based on the circuit breaker update control strategy.

6. The method according to claim 5, characterized in that Based on the grid voltage abnormality update coefficient and the circuit breaker update state data, and according to the circuit breaker control decision model, a circuit breaker update control strategy is output, including: Determining whether the grid-connected voltage abnormality update coefficient is greater than or equal to the grid-connected voltage abnormality threshold; If the grid voltage abnormality update coefficient is greater than or equal to the grid voltage abnormality threshold, activating the circuit breaker control decision model; The grid-connected voltage abnormality update coefficient and the circuit breaker update state data are input into the circuit breaker control decision model to obtain the circuit breaker update control strategy.

7. The method according to claim 1, characterized in that If the grid-connected voltage abnormality coefficient is greater than or equal to the grid-connected voltage abnormality threshold, activating the grid-connected voltage abnormality early warning device; The grid-connected voltage abnormality coefficient is input into the grid-connected voltage abnormality early warning device to obtain a grid-connected voltage abnormality early warning signal.

8. The method according to claim 7, characterized in that The grid-connected voltage abnormality warning device includes a grid-connected voltage abnormality graded warning table, which includes multiple grid-connected voltage abnormality predetermined intervals and multiple grid-connected voltage abnormality graded warning signals, and the multiple grid-connected voltage abnormality predetermined intervals and the multiple grid-connected voltage abnormality graded warning signals have a one-to-one correspondence.

Images