Medium-voltage power distribution network transfer operation identification method, system and equipment

Abstract

The invention relates to the technical field of operation identification, in particular to a medium-voltage power distribution network transfer operation identification method, system and device. The method comprises the following steps: acquiring feeder line real-time data and transformer area real-time data; performing data preprocessing on the feeder line real-time data and the transformer area real-time data to generate a transformer area feeder line processing data set; acquiring a power grid historical data set; performing two-dimensional curve fitting analysis on the power grid historical data set and the area feeder line processing data set to generate area feeder line two-dimensional fitting data; carrying out abnormal and disharmony area judgment on the two-dimensional fitting data of the feeder line in the transformer area, and generating load fluctuation voltage abnormal data; therefore, through a data-driven multi-level analysis and judgment method, the problems of dependence on artificial experience, response lag and the like in the traditional power grid transfer operation are solved, and the intelligent level and decision accuracy of the medium-voltage power distribution network transfer operation are improved.

Description

Technical Field

[0001] The present invention relates to the field of operation identification technology, and in particular to a method, system and device for identifying power transfer operations in a medium-voltage distribution network. Background Art

[0002] In modern distribution network systems, the transfer operation of medium-voltage distribution networks is crucial to maintaining the stability of the power grid and the life of equipment. However, traditional transfer operation identification and execution technologies have many shortcomings when dealing with complex and changeable load fluctuations and voltage anomalies. Traditional methods usually rely on preset rules or fixed thresholds to determine whether a transfer operation is required. The limitation of this method is that they are difficult to dynamically adapt to the complexity and real-time nature of the actual operation of the power grid. In addition, traditional methods usually lack flexibility in processing load fluctuations and voltage anomaly data, and fail to make full use of real-time data for accurate judgment and operation. This leads to the inability of traditional technologies to quickly and accurately identify the optimal transfer operation strategy in the face of multi-level voltage fluctuations and complex load changes in the actual operation of the power grid, which easily leads to misjudgment or delays in the best operation time, thereby increasing the risk of equipment failure and power grid instability. At the same time, traditional technologies usually lack effective processing mechanisms when dealing with low-priority transfer demands, fail to fully optimize operation priorities, and fail to make adequate preparations for future voltage fluctuations. Therefore, the traditional medium-voltage distribution network transfer operation technology is difficult to meet the requirements of modern power grids for efficiency, stability and intelligence due to its shortcomings in dynamic response, equipment life management and multi-level decision-making processing. These shortcomings not only increase the risks and maintenance costs of power grid operation, but also limit the overall operation efficiency of the power grid and the optimization of equipment life. Summary of the invention

[0003] Based on this, it is necessary to provide a method, system and device for identifying power transfer operations in a medium-voltage distribution network to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above object, a method for identifying a medium voltage distribution network transfer operation is provided, the method comprising the following steps:

[0005] Step S1: acquiring feeder real-time data and substation real-time data; performing data preprocessing on the feeder real-time data and substation real-time data to generate a substation feeder processing data set;

[0006] Step S2: Acquire a historical data set of the power grid; perform a two-dimensional curve fitting analysis on the historical data set of the power grid and the processed data set of the feeder line in the substation area to generate two-dimensional fitting data of the feeder line in the substation area; perform abnormal and disharmonious area determination on the two-dimensional fitting data of the feeder line in the substation area to generate abnormal load fluctuation voltage data;

[0007] Step S3: obtaining a maximum switching frequency range of the switch device; constructing an empirical model for the power grid historical data set based on the maximum switching frequency range of the switch device, and generating a switching frequency-equipment life empirical model;

[0008] Step S4: Use the real-time feeder data and the real-time substation data as input into the switching times-equipment life empirical model to generate real-time medium-voltage switching-equipment life data; use the preset load voltage threshold to perform load voltage judgment on the real-time medium-voltage switching-equipment life data and load fluctuation voltage abnormality data to generate a transfer operation judgment result; perform a transfer operation based on the transfer operation judgment result, thereby completing the medium-voltage distribution network transfer operation.

[0009] The beneficial effect of the present invention is that by acquiring and preprocessing the real-time data of feeders and real-time data of substations, a high-quality substation feeder processing data set is generated to ensure the reliability of subsequent analysis. By performing a two-dimensional curve fitting analysis on the historical data of the power grid and the feeder data of the substation, the potential patterns and correlations in the data are extracted, and then the abnormal and disharmonious areas are effectively judged. The generated load fluctuation voltage abnormality data provides key basic information for the subsequent power supply transfer judgment. By obtaining the maximum switching frequency range of the switchgear and combining the historical data of the power grid, an empirical model of switching frequency-equipment life is constructed. The model can predict the consumption of equipment life in a complex power grid environment and provide a data-driven basis for real-time operation. The feeder data acquired in real time is combined with the empirical model to generate real-time medium voltage switching-equipment life data. The load voltage is judged on the data and the load fluctuation voltage abnormality data by a preset load voltage threshold, and finally an accurate power supply transfer operation judgment result is generated. This process realizes an intelligent response to voltage abnormalities and ensures the rationality and executability of the operation at the data level. Therefore, the present invention solves the problems of reliance on manual experience and delayed response in traditional power grid transfer operations through a data-driven multi-level analysis and judgment method, and improves the intelligence level and decision-making accuracy of medium-voltage distribution network transfer operations.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire real-time data of feeder lines and substations;

[0012] Step S12: Process missing values ​​on the feeder real-time data and the substation real-time data to generate feeder missing value processed data and substation missing value processed data; use Z-score to detect and remove outliers on the feeder missing value processed data and substation missing value processed data to generate feeder outlier processed data and substation outlier processed data;

[0013] Step S13: performing interpolation time alignment processing on the feeder abnormal value processing data and the substation abnormal value processing data to generate feeder time alignment data and substation time alignment data; performing data standardization processing on the feeder time alignment data and the substation time alignment data to generate feeder standardization data and substation standardization data;

[0014] Step S14: constructing a data set for the feeder standardization data and the substation area standardization data to generate a substation area feeder processing data set.

[0015] The present invention uses the obtained feeder real-time data and substation real-time data as the starting point of data processing to ensure the real-time and relevance of information. By processing missing values ​​for feeder and substation real-time data, statistical methods are used to identify and process missing information in the data, and feeder missing value processing data and substation missing value processing data are generated. This process significantly reduces the potential impact of data missing on the analysis results. Further, by applying Z-score to detect and eliminate outliers on the processed data, feeder outlier processing data and substation outlier processing data are generated. This link effectively eliminates extreme outliers in the data and ensures the authenticity and stability of the data. Interpolation time alignment processing is performed on the feeder outlier processing data and the substation outlier processing data, and feeder time alignment data and substation time alignment data are generated. This step ensures the consistency of different data sources in time and eliminates errors caused by differences in data acquisition time. Through data standardization processing, the feeder time alignment data and the substation time alignment data are converted into feeder standardized data and substation standardized data, ensuring the comparability and consistency of the data under the same dimension. Data standardization not only optimizes the distribution characteristics of data, but also improves the effect of model training and analysis. Finally, by constructing data sets for feeder standardized data and substation standardized data, a substation feeder processing data set was generated, providing a comprehensive, accurate and standardized data foundation for subsequent analysis and modeling.

[0016] Preferably, step S2 comprises the following steps:

[0017] Step S21: Acquire power grid historical data set;

[0018] Step S22: calibrate the time coordinate axis of the power grid historical data set to generate the power grid time correlation axis; use the power grid time correlation axis to perform two-dimensional curve fitting analysis on the substation feeder processing data set to generate substation feeder two-dimensional fitting data; perform local spatial smoothing detection processing on the substation feeder two-dimensional fitting data to generate substation feeder spatial smoothing detection data;

[0019] Step S23: determining the abnormal and disharmonious area of ​​the two-dimensional fitting data of the feeder in the substation area, and generating load fluctuation voltage abnormality data.

[0020] The present invention provides a comprehensive historical background for data processing through the acquired power grid historical data set, and these data provide rich background information for subsequent analysis, ensuring the reliability of the analysis results. By calibrating the time coordinate axis of the power grid historical data set, the power grid time correlation axis is generated. This step ensures the correlation and consistency between data at different time points by accurately calibrating the time coordinate. Further, the power grid time correlation axis is used to perform a two-dimensional curve fitting analysis on the substation feeder processing data set to generate the substation feeder two-dimensional fitting data. This process reveals the potential trends and relationships in the data through the fitting model, laying the foundation for subsequent anomaly detection. In the following processing process, the substation feeder two-dimensional fitting data is subjected to local spatial smoothing detection processing to generate the substation feeder spatial smoothing detection data. This step removes local noise and irregular fluctuations in the data through smoothing processing, making the data more coherent and uniform in space. This not only improves the smoothness of the data, but also enhances the grasp of the overall trend of the data, making the subsequent analysis more accurate and reliable. The two-dimensional fitting data of the substation feeder is subjected to abnormal and disharmonious area judgment to generate load fluctuation voltage abnormal data. This step extracts abnormal information of load fluctuation voltage by identifying and determining abnormal areas of the data, providing a key basis for further grid optimization and management.

[0021] Preferably, step S3 comprises the following steps:

[0022] Step S31: obtaining the maximum switching frequency range of the switch device;

[0023] Step S32: extracting the operating life and switching times of the power grid historical data set to generate operating life data and switching times data of the medium-voltage distribution network; performing linear analysis on the operating life data and switching times data of the medium-voltage distribution network to generate operating life-switching times data of the medium-voltage distribution network;

[0024] Step S33: constructing an empirical model for the medium voltage distribution network operation life-switching number data based on the maximum switching number range of the switch device, and generating a switching number-equipment life empirical model.

[0025] The present invention provides a key reference boundary for subsequent analysis by obtaining the maximum switching number range of the switch device, ensuring the rationality and reliability of the data used in building the model. Through this range, the operating limit of the equipment can be accurately defined, thereby providing a reliable basis for the practical application of the model. The operating life and switching number of the power grid historical data set are extracted to generate operating life data and switching number data of the medium-voltage distribution network. This process constructs a basic data set of equipment performance by screening key operating indicators from historical data. Linear analysis is performed on these data to generate operating life-switching number data of the medium-voltage distribution network. This step reveals the potential linear relationship between the switching number and the equipment life by using the linear analysis method, providing an important basis for the prediction of the service life of the equipment. The results of the linear analysis not only help identify the main factors affecting the equipment life, but also lay a data foundation for further model construction. By constructing an empirical model for the operating life-switching number data of the medium-voltage distribution network based on the maximum switching number range of the switch device, an empirical model of switching number-equipment life is generated. This model combines the actual operation data of the equipment with its maximum switching number range to establish an empirical model that can reflect the actual situation. The model not only provides a prediction tool for equipment life, but also helps evaluate the changing trend of equipment life under different switching times, thus providing a scientific basis for equipment maintenance and replacement strategies. Through the application of empirical models, the remaining life of equipment can be effectively predicted, equipment maintenance plans can be optimized, system interruptions caused by equipment failures can be reduced, and the operating reliability and efficiency of the distribution network can be improved.

[0026] Preferably, step S32 includes the following steps:

[0027] Step S321: extracting the operating life and switching times of the power grid historical data set to generate operating life data and switching times data of the medium voltage distribution network;

[0028] Step S322: performing operation frequency interval analysis on the operation life data and the switching times data of the medium voltage distribution network to generate operation frequency interval data of the medium voltage distribution network; performing equipment status operation degree analysis on the operation frequency interval data of the medium voltage distribution network to generate equipment health degree data of the medium voltage distribution network;

[0029] Step S323: Use the Pearson correlation coefficient to perform equipment times-life linear analysis on the medium-voltage distribution network equipment health data, operating life data and medium-voltage distribution network switching times data to generate medium-voltage distribution network operating life-switching times data.

[0030] The present invention generates basic operating life data and switching number data of medium-voltage distribution network by extracting operating life and switching number data from the historical data set of power grid. These data provide a basic description of the performance of the equipment in actual operation, laying a data foundation for subsequent analysis. The operating life data and the switching number data of the medium-voltage distribution network are analyzed by operation frequency interval, and the operating frequency interval data of the medium-voltage distribution network is generated. This analysis process helps to identify the characteristics of the equipment operation interval and provides key data for evaluating the usage mode and frequency of the equipment. Further, the equipment state operation degree analysis is performed on the operation frequency interval data to generate the health data of the medium-voltage distribution network equipment. This analysis reveals the health status of the equipment in actual operation, reflects the operating stability and health status of the equipment under different operating frequencies, thereby providing a practical basis for equipment maintenance and fault prediction. By using the Pearson correlation coefficient to perform linear analysis on the health data, operating life data and switching number data of the medium-voltage distribution network equipment, the operating life-switching number data of the medium-voltage distribution network is generated. The application of the Pearson correlation coefficient enables the linear relationship between these data to be quantified, thereby revealing the statistical correlation between the switching number and the equipment life. This analysis not only clarifies the relationship between the health status and life of the equipment, but also provides a scientific basis for predicting equipment life and optimizing switching strategies through linear analysis.

[0031] Preferably, step S33 includes the following steps:

[0032] Step S331: Acquire equipment operation frequency interval data; construct a life and switching frequency model based on the health data of medium voltage distribution network equipment to generate a preliminary life and switching frequency model;

[0033] Step S332: performing differential identification on the output data of the preliminary model of life and switching times to generate switching times differential data; performing critical value prediction on the switching times differential data to generate switching times critical value data;

[0034] Step S333: Based on the critical value data of the switching number, a nonlinear fitting analysis is performed on the equipment operation frequency interval data and the preliminary model of life and switching number to generate a multi-dimensional nonlinear fitting result; the preliminary model of life and switching number is tested and corrected using the multi-dimensional nonlinear fitting result to generate an empirical model of switching number-equipment life.

[0035] The present invention obtains the equipment operation frequency interval data and constructs a preliminary model of life and switching times based on the health data of medium-voltage distribution network equipment. This process provides a life prediction model for equipment under different operation frequencies, which can reflect the performance changes of the equipment under actual operating conditions and lay the foundation for subsequent model optimization. The output data of the preliminary model of life and switching times is differentiated and identified to generate switching times differentiation data. This analysis reveals the performance differences of the equipment under different switching times, and generates switching times critical value data by predicting the critical value of the switching times differentiation data. The data provides the key threshold of the equipment under different operating conditions, which helps to understand the performance changes of the equipment when it is close to the critical operating conditions, thereby providing a reference for further model optimization. By performing nonlinear fitting analysis on the equipment operation frequency interval data and the preliminary model of life and switching times based on the switching times critical value data, a multi-dimensional nonlinear fitting result is generated. Multi-dimensional nonlinear fitting can reveal a more complex relationship between equipment life and switching times, and takes into account the nonlinear response of the equipment under different operating conditions. These nonlinear fitting results are used to test and correct the preliminary model, thereby generating a more accurate and comprehensive switching times-equipment life empirical model. This process significantly improves the understanding of the complex relationship between equipment life and switching times through detailed differentiation identification, critical value prediction and nonlinear fitting analysis. This in-depth analysis not only improves the accuracy and reliability of the model, but also optimizes the equipment usage strategy and maintenance plan. Through precise model construction and correction, it can effectively predict the life of the equipment, reduce the failure rate, and improve the efficiency and economy of the equipment.

[0036] Preferably, step S4 comprises the following steps:

[0037] Step S41: using the real-time data of feeder lines and the real-time data of substations as inputs into the switching times-equipment life empirical model to generate real-time medium voltage switching-equipment life data;

[0038] Step S42: performing voltage fluctuation severity priority judgment on the load fluctuation voltage abnormality data, and generating power transfer operation priority data;

[0039] Step S43: Use the preset load voltage threshold to perform load voltage judgment on the real-time medium voltage switching-equipment life data and the transfer operation priority data to generate a transfer operation judgment result; perform a transfer operation based on the transfer operation judgment result, thereby completing the medium voltage distribution network transfer operation.

[0040] The present invention generates real-time medium voltage switching-equipment life data by inputting real-time feeder data and real-time substation data into the switching times-equipment life empirical model. This process can reflect the state of the equipment under the current operating conditions in real time, ensuring real-time monitoring of the equipment life and switching times. Through the input of real-time data, the model can dynamically update the operating state and life prediction of the equipment, thereby improving the sensitivity and reaction speed to changes in equipment performance. The load fluctuation voltage abnormality data is judged by the voltage fluctuation severity priority, and the transfer operation priority data is generated. This process determines the priority of different abnormal situations by analyzing the voltage fluctuation situation, thereby providing an important basis for the decision-making of the transfer operation. The generation of priority data enables those abnormal situations that have a greater impact on the stability of the power grid to be handled preferentially when facing multiple transfer operations, thereby optimizing the allocation of resources and the timeliness of response. Further, the preset load voltage threshold is used to judge the load voltage of the real-time medium voltage switching-equipment life data and the transfer operation priority data, and the transfer operation judgment result is generated. This step ensures the effective judgment of voltage abnormality by comparing the real-time data with the preset threshold, and formulates the transfer operation strategy in combination with the priority data. This judgment result not only provides a clear basis for specific power transfer operations, but also optimizes the timing and scope of power transfer operations, thereby reducing the risks and impacts of power grid failures.

[0041] Preferably, step S43 includes the following steps:

[0042] Step S431: cross-check the real-time medium voltage switching-equipment life data with the transfer operation priority data to generate a priority-life matching coefficient; perform fluctuation coupling analysis on the priority-life matching coefficient and the real-time medium voltage switching-equipment life data based on a preset load voltage threshold to generate voltage-matching coefficient data;

[0043] Step S432: using a multi-level decision-making technique to perform load voltage judgment on the voltage-matching coefficient data, and generating a power transfer operation judgment result, wherein the power transfer operation judgment result includes a high necessity for power transfer operation and a low necessity for power transfer result;

[0044] Step S433: when the power transfer operation judgment result is that the power transfer operation is highly necessary, the load fluctuation voltage abnormality data is forcibly transferred through a preset response time window using an automated execution algorithm, and equipment switch closing data is generated;

[0045] Step S434: When the result of the power transfer operation is that the power transfer result is of low necessity, the load fluctuation voltage abnormality data is marked as to be observed, and low power transfer marking data is generated; based on the low power transfer marking data, the power transfer operation priority data is increased in priority, and low power transfer processing marking data is generated, thereby completing the medium voltage distribution network power transfer identification and operation.

[0046] The present invention generates a priority-life matching coefficient by cross-comparing the correlation of real-time medium voltage switching-equipment life data with the priority data of the transfer operation. This process enables the correlation of various data to be accurately quantified in real-time monitoring, and the fluctuation coupling analysis is performed in combination with the load voltage threshold, thereby generating voltage-matching coefficient data. The voltage-matching coefficient data can reflect the relationship between the voltage abnormality and the matching degree of the equipment life, and provide a quantitative basis for subsequent decision-making. The voltage-matching coefficient data is subjected to load voltage judgment using multi-level decision-making technology, and the judgment result of the transfer operation is generated. This step uses advanced decision-making technology to conduct an in-depth analysis of the relationship between voltage and matching coefficient, and distinguishes between high necessity and low necessity of the transfer operation. The high necessity result indicates that the current load fluctuation poses a greater threat to the equipment life, and immediate measures need to be taken, while the low necessity result indicates that the problem is relatively minor and can be further observed and processed in the future. When the judgment result is that the transfer operation is of high necessity, the automatic execution algorithm is used to perform forced transfer within the preset response time window to generate equipment switch closing data. This process ensures a rapid response to emergency situations through automated means, reduces the delay of manual intervention, and ensures the stability of the power grid and the safety of equipment.

[0047] In this specification, a medium-voltage distribution network transfer operation identification system is provided, which is used to execute the above-mentioned medium-voltage distribution network transfer operation identification method, and the medium-voltage distribution network transfer operation identification system includes:

[0048] Data acquisition and preprocessing module: acquire feeder real-time data and substation real-time data; perform data preprocessing on feeder real-time data and substation real-time data to generate substation feeder processing data set;

[0049] Historical data fitting and anomaly detection module: obtain the historical data set of the power grid; perform two-dimensional curve fitting analysis on the historical data set of the power grid and the feeder processing data set of the substation area to generate the two-dimensional fitting data of the feeder area; determine the abnormal and disharmonious areas of the two-dimensional fitting data of the feeder area to generate load fluctuation voltage abnormality data;

[0050] Empirical model building module: obtain the maximum switching times range of the switchgear; construct an empirical model for the historical data set of the power grid based on the maximum switching times range of the switchgear, and generate an empirical model of switching times-equipment life;

[0051] Real-time data judgment and transfer operation module: The real-time data of the feeder and the real-time data of the substation are used as input into the switching times-equipment life empirical model to generate real-time medium-voltage switching-equipment life data; the preset load voltage threshold is used to judge the load voltage of the real-time medium-voltage switching-equipment life data and the load fluctuation voltage abnormality data to generate the transfer operation judgment result; the transfer operation is performed based on the transfer operation judgment result, thereby completing the medium-voltage distribution network transfer operation.

[0052] The beneficial effect of the present invention is that the data acquisition and preprocessing module collects the data of the feeder and the substation in real time, performs data preprocessing on the data, and generates the substation feeder processing data set. This process ensures the integrity and accuracy of the data through efficient data acquisition and processing, and provides a reliable basis for subsequent analysis. The optimization operations in the data preprocessing stage, such as missing value processing and outlier detection, provide a clean and consistent data source for the establishment of subsequent analysis models, and effectively reduce the interference of noise and errors. The historical data fitting and anomaly detection module uses two-dimensional curve fitting analysis to comprehensively analyze the power grid historical data set and the substation feeder processing data set to generate two-dimensional fitting data of the substation feeder. This step reveals the potential relationship between the data through fitting analysis, and determines the abnormal and disharmonious areas to generate load fluctuation voltage abnormal data. This process enables the identification of abnormal patterns and trends based on historical data, provides an effective prediction basis for real-time monitoring, and can warn potential voltage fluctuation problems in advance. The empirical model construction module constructs an empirical model for the power grid historical data set based on the maximum switching number range of the switchgear, and generates a switching number-equipment life empirical model. By modeling the relationship between the number of switching times and the life of the equipment, this module provides a quantitative reference standard for the evaluation and decision-making of real-time data. This empirical model not only reveals the relationship between the life of the equipment and the number of switching times, but also provides theoretical support for the subsequent real-time data judgment. The real-time data judgment and transfer operation module takes the real-time feeder data and the substation data as input, and uses the switching times-equipment life empirical model to generate real-time medium voltage switching-equipment life data. Through the preset load voltage threshold, the real-time data and the load fluctuation voltage abnormality data are comprehensively judged to generate the judgment result of the transfer operation. This module dynamically adjusts the power grid operation strategy according to the changes in real-time data through an intelligent decision support system, thereby realizing efficient transfer operation and ensuring the stability and reliability of power grid operation. The high-speed data acquisition module is responsible for obtaining sensor acquisition instructions and calling feeder and substation data for high-speed data sensors based on these instructions. The collected data is transmitted to the processing system through a high-speed flow network, realizing high-speed update and transmission of real-time data. The design of this module ensures the real-time and transmission efficiency of the data and provides timely data information support for the system. In summary, the system has significantly improved the intelligence level of the power grid system through efficient data collection, processing, analysis and decision-making modules. The accurate processing and dynamic adjustment capabilities at the data level have effectively improved the stability and response efficiency of power grid operation, solved the delay and inaccuracy problems in traditional power grid management methods, and provided advanced technical solutions for modern power grid management. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A schematic diagram of the steps of a method, system and device for identifying power transfer operations in a medium voltage distribution network;

[0054] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0055] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0056] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0057] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0059] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0060] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0061] To achieve this, please refer to Figures 1 to 4 , a method for identifying a medium voltage distribution network transfer operation, the method comprising the following steps:

[0062] Step S1: acquiring feeder real-time data and substation real-time data; performing data preprocessing on the feeder real-time data and substation real-time data to generate a substation feeder processing data set;

[0063] Step S2: Acquire a historical data set of the power grid; perform a two-dimensional curve fitting analysis on the historical data set of the power grid and the processed data set of the feeder line in the substation area to generate two-dimensional fitting data of the feeder line in the substation area; perform abnormal and disharmonious area determination on the two-dimensional fitting data of the feeder line in the substation area to generate abnormal load fluctuation voltage data;

[0064] Step S3: obtaining a maximum switching frequency range of the switch device; constructing an empirical model for the power grid historical data set based on the maximum switching frequency range of the switch device, and generating a switching frequency-equipment life empirical model;

[0065] Step S4: Use the real-time feeder data and the real-time substation data as input into the switching times-equipment life empirical model to generate real-time medium-voltage switching-equipment life data; use the preset load voltage threshold to perform load voltage judgment on the real-time medium-voltage switching-equipment life data and load fluctuation voltage abnormality data to generate a transfer operation judgment result; perform a transfer operation based on the transfer operation judgment result, thereby completing the medium-voltage distribution network transfer operation.

[0066] The beneficial effect of the present invention is that by acquiring and preprocessing the real-time data of feeders and real-time data of substations, a high-quality substation feeder processing data set is generated to ensure the reliability of subsequent analysis. By performing a two-dimensional curve fitting analysis on the historical data of the power grid and the feeder data of the substation, the potential patterns and correlations in the data are extracted, and then the abnormal and disharmonious areas are effectively judged. The generated load fluctuation voltage abnormality data provides key basic information for the subsequent power supply transfer judgment. By obtaining the maximum switching frequency range of the switchgear and combining the historical data of the power grid, an empirical model of switching frequency-equipment life is constructed. The model can predict the consumption of equipment life in a complex power grid environment and provide a data-driven basis for real-time operation. The feeder data acquired in real time is combined with the empirical model to generate real-time medium voltage switching-equipment life data. The load voltage is judged on the data and the load fluctuation voltage abnormality data by a preset load voltage threshold, and finally an accurate power supply transfer operation judgment result is generated. This process realizes an intelligent response to voltage abnormalities and ensures the rationality and executability of the operation at the data level. Therefore, the present invention solves the problems of reliance on manual experience and delayed response in traditional power grid transfer operations through a data-driven multi-level analysis and judgment method, and improves the intelligence level and decision-making accuracy of medium-voltage distribution network transfer operations.

[0067] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for identifying a medium-voltage distribution network transfer operation of the present invention. In this example, the method for identifying a medium-voltage distribution network transfer operation includes the following steps:

[0068] Step S1: acquiring feeder real-time data and substation real-time data; performing data preprocessing on the feeder real-time data and substation real-time data to generate a substation feeder processing data set;

[0069] In the embodiment of the present invention, obtaining real-time data of feeders and real-time data of substations is the starting point of the data processing chain of the entire system, ensuring the source of real-time monitoring data. Technical means include extracting real-time data streams from various sensors and measuring devices, including current sensors, voltage sensors, power meters, etc., which involve current intensity, voltage level, power factor and load conditions. The acquired data is timely and dynamic, which requires the system to be able to process and store a large amount of high-frequency data. Data preprocessing is a key step in converting raw data into useful information. Specific technical means include data cleaning, missing value filling and outlier detection. In the data cleaning process, first of all, it is necessary to identify and eliminate erroneous or inconsistent data records, such as abnormal data points caused by sensor failure or communication problems. Missing value filling technology includes using interpolation methods (such as linear interpolation or polynomial interpolation) or statistical models (such as mean filling or nearest neighbor filling) to process missing values ​​in the data to ensure the integrity and consistency of the data. Outlier detection involves identifying and processing data points that deviate from the normal range. This is achieved through statistical analysis methods such as Z-score or machine learning-based anomaly detection algorithms, which can effectively identify values ​​that significantly deviate from the normal data distribution. The process of generating a feeder processing data set relies on integrating and standardizing the processed data, unifying data from different sources into a consistent format and scale for subsequent data analysis and processing. This process involves data integration techniques such as data fusion and data transformation, which combine different data sources (feeder and station data) to form a comprehensive processing data set, thereby providing a comprehensive view. This data set includes not only real-time monitoring data, but also pre-processed historical data to provide richer contextual information.

[0070] Step S2: Acquire a historical data set of the power grid; perform a two-dimensional curve fitting analysis on the historical data set of the power grid and the processed data set of the feeder line in the substation area to generate two-dimensional fitting data of the feeder line in the substation area; perform abnormal and disharmonious area determination on the two-dimensional fitting data of the feeder line in the substation area to generate abnormal load fluctuation voltage data;

[0071] In an embodiment of the present invention, obtaining a historical data set of the power grid is to provide necessary basic data for subsequent analysis. These data sets include parameters such as current, voltage, power factor, etc. of historical records, reflecting the state of the power grid at different time points. Technical means involve extracting these historical data from a power grid management system, a data acquisition system, or a storage device, and these data can come from different time periods and different parts of the power grid to provide a comprehensive historical background. Two-dimensional curve fitting analysis is an important step in comprehensively analyzing the historical data set of the power grid and the feeder processing data set of the substation area. Specific technical means include fusing historical data with real-time processing data, and establishing a relationship model between data by a two-dimensional curve fitting method. The curve fitting here uses linear regression, polynomial regression, or more complex nonlinear regression models, which can capture the relationship pattern between data and generate a fitting curve. This fitting analysis enables trend information to be extracted from a complex data set to form two-dimensional fitting data of the substation feeder, thereby helping to understand the changing trend of the power grid state over time. After generating the two-dimensional fitting data of the substation feeder, it is a key step to determine the abnormal and disharmonious area. Technical means include using statistical detection methods or machine learning-based anomaly detection algorithms, which can identify parts of the fitting data that do not conform to the expected trend. Specific methods include residual analysis (i.e., the difference between actual data and fitted curves) or anomaly detection algorithms (such as isolation forests, support vector machines, etc.) to identify and mark areas that deviate significantly from the fitted model. This process generates load fluctuation voltage anomaly data, which indicates abnormal fluctuation areas in the power grid, which are related to uneven load, equipment failure, or other factors that affect the stability of the power grid.

[0072] Step S3: obtaining a maximum switching frequency range of the switch device; constructing an empirical model for the power grid historical data set based on the maximum switching frequency range of the switch device, and generating a switching frequency-equipment life empirical model;

[0073] In an embodiment of the present invention, the maximum switching times range of the switch device is obtained. This data comes from the technical specifications of the device or the technical manual provided by the manufacturer, and includes the maximum number of operations allowed by the device during its life cycle. This data is crucial for the subsequent model construction. The technical means include extracting these parameters from the equipment manufacturer, the equipment operation record or the relevant equipment standard document, and sorting and confirming them to ensure the accuracy and completeness of the data. Based on the maximum switching times range of the switch device, the process of constructing an empirical model for the power grid historical data set involves several key technical steps. First, it is necessary to extract relevant operating data from the power grid historical data set, which includes the actual switching times of the switch device, the operating time of the equipment, the fault records and other relevant parameters that affect the life of the equipment. This process is completed using database query, data extraction tools or data management systems. The empirical model is constructed by combining the maximum switching times range of the switch device with the switching times data in the power grid historical data set. The core of the model is to establish the relationship between the switching times of the equipment and the life of the equipment based on statistical analysis or machine learning technology. The specific technical means include modeling the data using linear regression, nonlinear regression or multivariate regression analysis methods. These models can reveal the dependency between the switching times of the equipment and its life. For example, regression analysis can be used to obtain a quantitative relationship between the life of an equipment and its switching times, forming a prediction formula or function. During the construction process, the empirical model also needs to take into account the influence of other factors, such as the equipment's load conditions, operating environment, maintenance records, etc. These factors can be comprehensively considered through multivariate regression analysis. The empirical model obtained by fitting the data can predict the expected life of the equipment under a given number of switching times. This process requires the use of statistical tools and software, such as SPSS, MATLAB, etc., for model training, parameter estimation, and result verification.

[0074] Step S4: Use the real-time feeder data and the real-time substation data as input into the switching times-equipment life empirical model to generate real-time medium-voltage switching-equipment life data; use the preset load voltage threshold to perform load voltage judgment on the real-time medium-voltage switching-equipment life data and load fluctuation voltage abnormality data to generate a transfer operation judgment result; perform a transfer operation based on the transfer operation judgment result, thereby completing the medium-voltage distribution network transfer operation.

[0075] In an embodiment of the present invention, the real-time data of the feeder and the real-time data of the substation are input into the switching times-equipment life empirical model to generate real-time medium voltage switching-equipment life data. This process involves the following specific technical means. First, it is necessary to obtain the real-time operation data of the feeder and the substation from the real-time data acquisition system. These data are collected by sensors, monitoring systems or automatic data recorders, including key indicators such as current, voltage, and power factor. After obtaining these data, they need to be input into the previously constructed switching times-equipment life empirical model. This model is established based on the maximum switching times range of the switchgear and the historical data set of the power grid. Through regression analysis and other methods, a mathematical model is formed to predict the life of the equipment. The real-time data is matched with the input variables of the model, and the real-time medium voltage switching-equipment life data is calculated. This process is implemented through a programming interface (API) or a data processing system to ensure that the real-time data can be imported into the model in a timely and accurate manner and generate the expected output data. The next technical step is to perform load voltage judgment on the generated real-time medium voltage switching-equipment life data and load fluctuation voltage abnormality data. This process requires a preset load voltage threshold, which is a voltage range determined according to the grid design standards and actual operating experience to distinguish between normal operating conditions and abnormal conditions. By comparing the real-time medium voltage switching-equipment life data with the load fluctuation voltage abnormality data, and combining the load voltage threshold, the data is analyzed using conditional judgment and logic algorithms. Specific technical means include threshold detection algorithms and anomaly detection algorithms, which can identify situations where the voltage exceeds the normal range and generate corresponding transfer operation judgment results. Common methods include using statistical methods such as Z-score or machine learning methods such as classification algorithms to ensure the accuracy and reliability of the judgment results. The process of performing a transfer operation based on the transfer operation judgment result involves an automated control system. Based on the load voltage judgment result, the automated control system will perform the transfer operation. Specific operations include switching power sources, adjusting voltage settings, or reconfiguring the grid structure to ensure system stability and power supply quality. The process of executing the transfer operation is completed by the control system and the execution device, and the real-time adjustment and optimization of the grid are achieved through preset logical rules and control instructions.

[0076] The beneficial effect of the present invention is that by acquiring and preprocessing the real-time data of feeders and real-time data of substations, a high-quality substation feeder processing data set is generated to ensure the reliability of subsequent analysis. By performing a two-dimensional curve fitting analysis on the historical data of the power grid and the feeder data of the substation, the potential patterns and correlations in the data are extracted, and then the abnormal and disharmonious areas are effectively judged. The generated load fluctuation voltage abnormality data provides key basic information for the subsequent power supply transfer judgment. By obtaining the maximum switching frequency range of the switchgear and combining the historical data of the power grid, an empirical model of switching frequency-equipment life is constructed. The model can predict the consumption of equipment life in a complex power grid environment and provide a data-driven basis for real-time operation. The feeder data acquired in real time is combined with the empirical model to generate real-time medium voltage switching-equipment life data. The load voltage is judged on the data and the load fluctuation voltage abnormality data by a preset load voltage threshold, and finally an accurate power supply transfer operation judgment result is generated. This process realizes an intelligent response to voltage abnormalities and ensures the rationality and executability of the operation at the data level. Therefore, the present invention solves the problems of reliance on manual experience and delayed response in traditional power grid transfer operations through a data-driven multi-level analysis and judgment method, and improves the intelligence level and decision-making accuracy of medium-voltage distribution network transfer operations.

[0077] Preferably, step S1 comprises the following steps:

[0078] Step S11: Acquire real-time data of feeder lines and substations;

[0079] Step S12: Process missing values ​​on the feeder real-time data and the substation real-time data to generate feeder missing value processed data and substation missing value processed data; use Z-score to detect and remove outliers on the feeder missing value processed data and substation missing value processed data to generate feeder outlier processed data and substation outlier processed data;

[0080] Step S13: performing interpolation time alignment processing on the feeder abnormal value processing data and the substation abnormal value processing data to generate feeder time alignment data and substation time alignment data; performing data standardization processing on the feeder time alignment data and the substation time alignment data to generate feeder standardization data and substation standardization data;

[0081] Step S14: constructing a data set for the feeder standardization data and the substation area standardization data to generate a substation area feeder processing data set.

[0082] In an embodiment of the present invention, the obtained feeder real-time data and substation real-time data are collected in real time by sensors, monitoring systems or automatic data recorders. These data include key parameters of power grid operation such as current, voltage, and power. The technical means at this stage mainly involve the configuration of the data acquisition system and the data transmission protocol to ensure the real-time and accuracy of the data. Perform missing value processing. This process uses interpolation to fill the missing values ​​in the data. Common methods include linear interpolation, spline interpolation or polynomial interpolation. Selecting a suitable interpolation method can maximize the original characteristics of the data while ensuring data integrity. The processed data generates feeder missing value processing data and substation missing value processing data. Subsequently, the Z-score method is used to detect outliers on the processed data. Z-score is an outlier detection method based on standard deviation, which identifies outliers by calculating the degree of deviation of each data point from the mean. In the specific operation, the Z-score value of each data point is calculated, and a threshold is set to eliminate data points whose Z-score exceeds the preset range, thereby generating feeder outlier processing data and substation outlier processing data. The data after outlier processing is interpolated and time aligned. Since the actual data collection time is not completely consistent, it is necessary to use interpolation technology to align the data time. Common methods include linear interpolation or time series interpolation to ensure the consistency of the data in the time dimension. After completing the time alignment, the data is standardized. Data standardization is to eliminate the influence of different dimensions and scales by converting the data into a standard normal distribution form. Common standardization methods include Z-score standardization and Min-Max standardization to generate feeder standardized data and substation standardized data. The processed data is used for data set construction. The process of data set construction includes integrating the standardized feeder data and substation data into a unified data set, which can be used for subsequent analysis and modeling. Through data set construction, the consistency, completeness and applicability of the data are ensured, providing a high-quality data foundation for subsequent data analysis and decision-making.

[0083] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0084] Step S21: Acquire power grid historical data set;

[0085] Step S22: calibrate the time coordinate axis of the power grid historical data set to generate the power grid time correlation axis; use the power grid time correlation axis to perform two-dimensional curve fitting analysis on the substation feeder processing data set to generate substation feeder two-dimensional fitting data; perform local spatial smoothing detection processing on the substation feeder two-dimensional fitting data to generate substation feeder spatial smoothing detection data;

[0086] Step S23: determining the abnormal and disharmonious area of ​​the two-dimensional fitting data of the feeder in the substation area, and generating load fluctuation voltage abnormality data.

[0087] In the embodiment of the present invention, the time series information of the power system is extracted from the historical data set of the power grid, and the time coordinate axis of these data is calibrated. This process aims to establish a unified time base for the historical data at different time points to form a power grid time correlation axis. This time correlation axis, as a time base framework, provides a reference system for subsequent data analysis. By cross-comparing the time correlation axis with the data set of the feeder processing in the substation area, the data set is analyzed using a two-dimensional curve fitting method. This analysis method compares the power data at each time point with the historical trend, aims to find the data fluctuation characteristics at different times, and generates two-dimensional fitting data of the feeder in the substation area. In order to further improve the accuracy and reliability of the data, local spatial smoothing detection processing is required on the basis of the generated two-dimensional fitting data. This step analyzes the spatial distribution of the power data, smoothes the local abnormal fluctuations, thereby eliminating noise and errors, and generates smoother spatial smoothing detection data of the feeder in the substation area. Finally, the data after spatial smoothing is used to judge the abnormal areas therein, especially to identify those areas that are inconsistent with the historical trend and are not harmonious. Such abnormal areas are manifested as significant deviations from load fluctuations and voltage changes. Through this judgment, the voltage anomaly caused by load fluctuation can be accurately identified, and finally the load fluctuation voltage anomaly data can be generated.

[0088] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0089] Step S31: obtaining the maximum switching frequency range of the switch device;

[0090] Step S32: extracting the operating life and switching times of the power grid historical data set to generate operating life data and switching times data of the medium-voltage distribution network; performing linear analysis on the operating life data and switching times data of the medium-voltage distribution network to generate operating life-switching times data of the medium-voltage distribution network;

[0091] Step S33: constructing an empirical model for the medium voltage distribution network operation life-switching number data based on the maximum switching number range of the switch device, and generating a switching number-equipment life empirical model.

[0092] In the embodiment of the present invention, by obtaining the maximum switching times range of the switch device, the maximum number of operations theoretically allowed by the device is established, which lays the foundation for subsequent analysis. Data related to the operating life of the equipment and the actual switching times of the equipment are extracted from the historical data set of the power grid. This process involves complex time series data mining and filtering to ensure that the extracted data has a high degree of accuracy and completeness. By performing linear analysis on the extracted operating life data and the corresponding switching times data of the medium-voltage distribution network, a correlation relationship between the two is established. This linear analysis can not only reveal the life change trend of the equipment under different switching times, but also quantify this relationship through a regression model, thereby generating the operating life-switching times data of the medium-voltage distribution network. The maximum switching times range of the switch device is used to construct an empirical model for the above-generated life-switching times data. The model forms an empirical formula for predicting the life of the equipment by fitting the operating life data of the equipment under different switching times. In the process of model construction, the discrete and nonlinear characteristics of the data are taken into account, and the extreme values ​​are processed to improve the robustness and accuracy of the model. The switching times-equipment life empirical model is finally generated.

[0093] Preferably, step S32 includes the following steps:

[0094] Step S321: extracting the operating life and switching times of the power grid historical data set to generate operating life data and switching times data of the medium voltage distribution network;

[0095] Step S322: performing operation frequency interval analysis on the operation life data and the switching times data of the medium voltage distribution network to generate operation frequency interval data of the medium voltage distribution network; performing equipment status operation degree analysis on the operation frequency interval data of the medium voltage distribution network to generate equipment health degree data of the medium voltage distribution network;

[0096] Step S323: Use the Pearson correlation coefficient to perform equipment times-life linear analysis on the medium-voltage distribution network equipment health data, operating life data and medium-voltage distribution network switching times data to generate medium-voltage distribution network operating life-switching times data.

[0097] In an embodiment of the present invention, by extracting the operating life and switching times of the power grid historical data set, the operating life data and the switching times data of the medium-voltage distribution network are generated respectively. This process requires screening the operating life records and corresponding operation times of the equipment from the original data set to ensure the accuracy and consistency of the data. The extracted data is subjected to operation frequency interval analysis. The core of this step is to calculate the time interval between each switching operation to generate the operation frequency interval data of the medium-voltage distribution network. The data reflects the operation density and frequency change trend of the equipment in different time periods. Based on the operation frequency interval data, the state operation degree of the equipment is deeply analyzed to generate the health data of the medium-voltage distribution network equipment. This analysis process involves the evaluation of the equipment operation status, including evaluating the performance changes of the equipment under different load conditions to determine the current health status of the equipment. The Pearson correlation coefficient is used to perform linear correlation analysis on the health data, operating life data and switching times data of the medium-voltage distribution network equipment, aiming to explore the relationship between these data. The Pearson correlation coefficient can quantify the linear relationship between the health of the equipment and its operating life and switching times, and then generate the linear relationship data between the operating life and switching times of the medium-voltage distribution network.

[0098] Preferably, step S33 includes the following steps:

[0099] Step S331: Acquire equipment operation frequency interval data; construct a life and switching frequency model based on the health data of medium voltage distribution network equipment to generate a preliminary life and switching frequency model;

[0100] Step S332: performing differential identification on the output data of the preliminary model of life and switching times to generate switching times differential data; performing critical value prediction on the switching times differential data to generate switching times critical value data;

[0101] Step S333: Based on the critical value data of the switching number, a nonlinear fitting analysis is performed on the equipment operation frequency interval data and the preliminary model of life and switching number to generate a multi-dimensional nonlinear fitting result; the preliminary model of life and switching number is tested and corrected using the multi-dimensional nonlinear fitting result to generate an empirical model of switching number-equipment life.

[0102] In the embodiment of the present invention, by obtaining the equipment operation frequency interval data, basic data is provided for the construction of the model. Subsequently, based on the health data of the medium-voltage distribution network equipment, a life and switching number model is preliminarily constructed to generate a preliminary model of life and switching number. This process relies on a deep understanding of the health of the equipment, and the life of the equipment under different switching times is preliminarily modeled to capture its basic linear or nonlinear relationship. The data output by the preliminary model is differentiated to generate switching number differentiated data. Differential identification aims to distinguish the life changes of the equipment under different operating frequencies, and by analyzing the differences between various types of data, abnormal or extreme value phenomena under specific conditions are identified. This step can provide reliable input data for subsequent critical value prediction. Critical value prediction is performed on these differentiated data to generate critical value data of the switching number. Critical value prediction determines at what operating frequency the life of the equipment will be significantly reduced by calculating the critical point of the switching number, which is crucial for risk assessment and preventive maintenance of the equipment. Based on the critical value data of the switching number, nonlinear fitting analysis is performed on the equipment operation frequency interval data and the preliminary model to generate multi-dimensional nonlinear fitting results. Nonlinear fitting analysis uses complex mathematical algorithms to integrate data of different dimensions into the model to capture more complex relationships between data. Through these multi-dimensional nonlinear fitting results, the preliminary model can be tested and corrected, and ultimately a more accurate and practical switching times-equipment life empirical model can be generated.

[0103] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0104] Step S41: using the real-time data of feeder lines and the real-time data of substations as inputs into the switching times-equipment life empirical model to generate real-time medium voltage switching-equipment life data;

[0105] Step S42: performing voltage fluctuation severity priority judgment on the load fluctuation voltage abnormality data, and generating power transfer operation priority data;

[0106] Step S43: Use the preset load voltage threshold to perform load voltage judgment on the real-time medium voltage switching-equipment life data and the transfer operation priority data to generate a transfer operation judgment result; perform a transfer operation based on the transfer operation judgment result, thereby completing the medium voltage distribution network transfer operation.

[0107] In an embodiment of the present invention, the real-time data of the feeder and the real-time data of the substation are input into the switching times-equipment life empirical model to generate real-time medium voltage switching-equipment life data. This step first involves the acquisition and model input of real-time data, the data of the feeder and the substation are input as time series, the data are parsed and inferred through the empirical model, and dynamic data reflecting the impact of the current operation on the equipment life is generated. Combined with the load fluctuation voltage abnormality data, the serious priority of the voltage fluctuation is judged. By analyzing the frequency and amplitude of the load fluctuation and its impact on the stability of the power grid, a judgment result that can reflect the priority of the voltage fluctuation on the equipment operation is generated. This result is technically realized by weighted calculation and comparison of the historical records and current data of different voltage fluctuation events, and the dynamic judgment of the voltage fluctuation priority is realized. The preset load voltage threshold is used to judge the load voltage of the real-time medium voltage switching-equipment life data and the transfer operation priority data. The technical core of this step is to use the preset threshold standard to compare the deviation between the real-time data and the threshold to determine whether the transfer operation needs to be performed. To ensure the accuracy and effectiveness of the judgment, this process establishes a relationship model between voltage fluctuations and equipment life, conducts a quantitative assessment of the equipment life reduction under abnormal voltage conditions, and combines the power transfer operation priority data to form the final power transfer operation judgment result.

[0108] Preferably, step S43 includes the following steps:

[0109] Step S431: cross-check the real-time medium voltage switching-equipment life data with the transfer operation priority data to generate a priority-life matching coefficient; perform fluctuation coupling analysis on the priority-life matching coefficient and the real-time medium voltage switching-equipment life data based on a preset load voltage threshold to generate voltage-matching coefficient data;

[0110] Step S432: using a multi-level decision-making technique to perform load voltage judgment on the voltage-matching coefficient data, and generating a power transfer operation judgment result, wherein the power transfer operation judgment result includes a high necessity for power transfer operation and a low necessity for power transfer result;

[0111] Step S433: when the power transfer operation judgment result is that the power transfer operation is highly necessary, the load fluctuation voltage abnormality data is forcibly transferred through a preset response time window using an automated execution algorithm, and equipment switch closing data is generated;

[0112] Step S434: When the result of the power transfer operation is that the power transfer result is of low necessity, the load fluctuation voltage abnormality data is marked as to be observed, and low power transfer marking data is generated; based on the low power transfer marking data, the power transfer operation priority data is increased in priority, and low power transfer processing marking data is generated, thereby completing the medium voltage distribution network power transfer identification and operation.

[0113] In an embodiment of the present invention, the real-time medium voltage switching-equipment life data and the transfer operation priority data are cross-matched by correlation to generate a priority-life matching coefficient. This technical means first calculates the correlation between the two sets of data, and uses statistical methods to find the linear or nonlinear relationship between them, thereby forming a matching coefficient. This coefficient reflects the degree of coupling between the priority of a specific transfer operation and its impact on the life of the equipment. Subsequently, this matching coefficient is combined with the real-time medium voltage switching-equipment life data through fluctuation coupling analysis, and based on the preset load voltage threshold, how the voltage fluctuation affects the change of this coefficient is analyzed, thereby generating voltage-matching coefficient data. The technical core of this step is to use data mining and dynamic fluctuation analysis technology, combined with actual voltage fluctuation conditions, to construct a multidimensional data set that can reflect the impact of voltage fluctuations on equipment operation priority and life in real time. The voltage-matching coefficient data is used to judge the load voltage through multi-level decision-making technology to generate a transfer operation judgment result. Multi-level decision-making technology is mainly used in the decision-making process of complex systems. By hierarchically processing the voltage-matching coefficient data and comprehensively considering multiple factors, the necessity of the transfer operation is determined. This decision-making process includes two results: high necessity and low necessity, providing clear execution guidance for subsequent operations. When the judgment result of the transfer operation shows high necessity, the system will trigger the automatic execution algorithm, use the preset response time window to forcibly transfer the load fluctuation voltage abnormality data, and generate the equipment switch shutdown data. This process involves the rapid identification and processing of abnormal data. Through the set response time window, the data transfer operation is completed in a very short time to ensure the stability of the power grid and the safety of the equipment. The automatic execution algorithm in this step relies on the synergy of the fast response mechanism and the real-time monitoring system to achieve automatic protection of equipment under abnormal voltage conditions. When the judgment result of the transfer operation shows low necessity, the load fluctuation voltage abnormality data is marked as to be observed, and low transfer marking data is generated. This step puts the abnormal data into the monitoring state by marking it for subsequent processing. Based on these marking data, the priority data of the transfer operation is raised to generate low transfer processing marking data. This processing method dynamically adjusts the priority so that the system can respond more quickly when voltage fluctuations occur again.

[0114] In this specification, a medium-voltage distribution network transfer operation identification system is provided, which is used to execute the above-mentioned medium-voltage distribution network transfer operation identification method, and the medium-voltage distribution network transfer operation identification system includes:

[0115] Data acquisition and preprocessing module: acquire feeder real-time data and substation real-time data; perform data preprocessing on feeder real-time data and substation real-time data to generate substation feeder processing data set;

[0116] Historical data fitting and anomaly detection module: obtain the historical data set of the power grid; perform two-dimensional curve fitting analysis on the historical data set of the power grid and the feeder processing data set of the substation area to generate the two-dimensional fitting data of the feeder area; determine the abnormal and disharmonious areas of the two-dimensional fitting data of the feeder area to generate load fluctuation voltage abnormality data;

[0117] Empirical model building module: obtain the maximum switching times range of the switchgear; construct an empirical model for the historical data set of the power grid based on the maximum switching times range of the switchgear, and generate an empirical model of switching times-equipment life;

[0118] Real-time data judgment and transfer operation module: The real-time data of the feeder and the real-time data of the substation are used as input into the switching times-equipment life empirical model to generate real-time medium-voltage switching-equipment life data; the preset load voltage threshold is used to judge the load voltage of the real-time medium-voltage switching-equipment life data and the load fluctuation voltage abnormality data to generate the transfer operation judgment result; the transfer operation is performed based on the transfer operation judgment result, thereby completing the medium-voltage distribution network transfer operation.

[0119] The beneficial effect of the present invention is that the data acquisition and preprocessing module collects the data of the feeder and the substation in real time, performs data preprocessing on the data, and generates the substation feeder processing data set. This process ensures the integrity and accuracy of the data through efficient data acquisition and processing, and provides a reliable basis for subsequent analysis. The optimization operations in the data preprocessing stage, such as missing value processing and outlier detection, provide a clean and consistent data source for the establishment of subsequent analysis models, and effectively reduce the interference of noise and errors. The historical data fitting and anomaly detection module uses two-dimensional curve fitting analysis to comprehensively analyze the power grid historical data set and the substation feeder processing data set to generate two-dimensional fitting data of the substation feeder. This step reveals the potential relationship between the data through fitting analysis, and determines the abnormal and disharmonious areas to generate load fluctuation voltage abnormal data. This process enables the identification of abnormal patterns and trends based on historical data, provides an effective prediction basis for real-time monitoring, and can warn potential voltage fluctuation problems in advance. The empirical model construction module constructs an empirical model for the power grid historical data set based on the maximum switching number range of the switchgear, and generates a switching number-equipment life empirical model. By modeling the relationship between the number of switching times and the life of the equipment, this module provides a quantitative reference standard for the evaluation and decision-making of real-time data. This empirical model not only reveals the relationship between the life of the equipment and the number of switching times, but also provides theoretical support for the subsequent real-time data judgment. The real-time data judgment and transfer operation module takes the real-time feeder data and the substation data as input, and uses the switching times-equipment life empirical model to generate real-time medium voltage switching-equipment life data. Through the preset load voltage threshold, the real-time data and the load fluctuation voltage abnormality data are comprehensively judged to generate the judgment result of the transfer operation. This module dynamically adjusts the power grid operation strategy according to the changes in real-time data through an intelligent decision support system, thereby realizing efficient transfer operation and ensuring the stability and reliability of power grid operation. The high-speed data acquisition module is responsible for obtaining sensor acquisition instructions and calling feeder and substation data for high-speed data sensors based on these instructions. The collected data is transmitted to the processing system through a high-speed flow network, realizing high-speed update and transmission of real-time data. The design of this module ensures the real-time and transmission efficiency of the data and provides timely data information support for the system. In summary, the system has significantly improved the intelligence level of the power grid system through efficient data collection, processing, analysis and decision-making modules. The accurate processing and dynamic adjustment capabilities at the data level have effectively improved the stability and response efficiency of power grid operation, solved the delay and inaccuracy problems in traditional power grid management methods, and provided advanced technical solutions for modern power grid management.

[0120] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0121] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for identifying a medium voltage distribution network power transfer operation, characterized in that: The following steps are involved: Step S1: acquiring feeder real-time data and substation real-time data; performing data preprocessing on the feeder real-time data and substation real-time data to generate a substation feeder processing data set; Step S2: Acquire a historical data set of the power grid; perform a two-dimensional curve fitting analysis on the historical data set of the power grid and the processed data set of the feeder line in the substation area to generate two-dimensional fitting data of the feeder line in the substation area; perform abnormal and disharmonious area determination on the two-dimensional fitting data of the feeder line in the substation area to generate abnormal load fluctuation voltage data; Step S3: obtaining a maximum switching frequency range of the switch device; constructing an empirical model for the power grid historical data set based on the maximum switching frequency range of the switch device, and generating a switching frequency-equipment life empirical model; Step S4: Use the real-time feeder data and the real-time substation data as input into the switching times-equipment life empirical model to generate real-time medium-voltage switching-equipment life data; use the preset load voltage threshold to perform load voltage judgment on the real-time medium-voltage switching-equipment life data and load fluctuation voltage abnormality data to generate a transfer operation judgment result; perform a transfer operation based on the transfer operation judgment result, thereby completing the medium-voltage distribution network transfer operation.

2. The method for identifying the transfer operation of a medium voltage distribution network according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire real-time data of feeder lines and substations; Step S12: Process missing values ​​on the feeder real-time data and the substation real-time data to generate feeder missing value processed data and substation missing value processed data; use Z-score to detect and remove outliers on the feeder missing value processed data and substation missing value processed data to generate feeder outlier processed data and substation outlier processed data; Step S13: performing interpolation time alignment processing on the feeder abnormal value processing data and the substation abnormal value processing data to generate feeder time alignment data and substation time alignment data; performing data standardization processing on the feeder time alignment data and the substation time alignment data to generate feeder standardization data and substation standardization data; Step S14: constructing a data set for the feeder standardization data and the substation area standardization data to generate a substation area feeder processing data set.

3. The method for identifying the transfer operation of a medium voltage distribution network according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Acquire power grid historical data set; Step S22: calibrate the time coordinate axis of the power grid historical data set to generate the power grid time correlation axis; use the power grid time correlation axis to perform two-dimensional curve fitting analysis on the substation feeder processing data set to generate substation feeder two-dimensional fitting data; perform local spatial smoothing detection processing on the substation feeder two-dimensional fitting data to generate substation feeder spatial smoothing detection data; Step S23: determining the abnormal and disharmonious area of ​​the two-dimensional fitting data of the feeder in the substation area, and generating load fluctuation voltage abnormality data.

4. The method for identifying the transfer operation of a medium voltage distribution network according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: obtaining the maximum switching frequency range of the switch device; Step S32: extracting the operating life and switching times of the power grid historical data set to generate operating life data and switching times data of the medium-voltage distribution network; performing linear analysis on the operating life data and switching times data of the medium-voltage distribution network to generate operating life-switching times data of the medium-voltage distribution network; Step S33: constructing an empirical model for the medium voltage distribution network operating life-switching number data based on the maximum switching number range of the switch device, and generating a switching number-equipment life empirical model.

5. The method for identifying the transfer operation of a medium voltage distribution network according to claim 4, characterized in that: Step S32 includes the following steps: Step S321: extracting the operating life and switching times of the power grid historical data set to generate operating life data and switching times data of the medium voltage distribution network; Step S322: performing operation frequency interval analysis on the operation life data and the switching times data of the medium voltage distribution network to generate operation frequency interval data of the medium voltage distribution network; performing equipment status operation degree analysis on the operation frequency interval data of the medium voltage distribution network to generate equipment health degree data of the medium voltage distribution network; Step S323: Use the Pearson correlation coefficient to perform equipment times-life linear analysis on the medium-voltage distribution network equipment health data, operating life data and medium-voltage distribution network switching times data to generate medium-voltage distribution network operating life-switching times data.

6. The method for identifying the transfer operation of a medium voltage distribution network according to claim 4, characterized in that: Step S33 includes the following steps: Step S331: Acquire equipment operation frequency interval data; construct a life and switching frequency model based on the health data of medium voltage distribution network equipment to generate a preliminary life and switching frequency model; Step S332: performing differential identification on the output data of the preliminary model of life and switching times to generate switching times differential data; performing critical value prediction on the switching times differential data to generate switching times critical value data; Step S333: Based on the critical value data of the switching number, a nonlinear fitting analysis is performed on the equipment operation frequency interval data and the preliminary model of life and switching number to generate a multi-dimensional nonlinear fitting result; the preliminary model of life and switching number is tested and corrected using the multi-dimensional nonlinear fitting result to generate an empirical model of switching number-equipment life.

7. The method for identifying the transfer operation of a medium voltage distribution network according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: using the real-time data of feeder lines and the real-time data of substations as inputs into the switching times-equipment life empirical model to generate real-time medium voltage switching-equipment life data; Step S42: performing voltage fluctuation severity priority judgment on the load fluctuation voltage abnormality data, and generating power transfer operation priority data; Step S43: Use the preset load voltage threshold to perform load voltage judgment on the real-time medium voltage switching-equipment life data and the transfer operation priority data to generate a transfer operation judgment result; perform a transfer operation based on the transfer operation judgment result, thereby completing the medium voltage distribution network transfer operation.

8. The method for identifying the transfer operation of a medium voltage distribution network according to claim 7, characterized in that: Step S43 includes the following steps: Step S431: cross-check the real-time medium voltage switching-equipment life data with the transfer operation priority data to generate a priority-life matching coefficient; perform fluctuation coupling analysis on the priority-life matching coefficient and the real-time medium voltage switching-equipment life data based on a preset load voltage threshold to generate voltage-matching coefficient data; Step S432: using a multi-level decision-making technique to perform load voltage judgment on the voltage-matching coefficient data, and generating a power transfer operation judgment result, wherein the power transfer operation judgment result includes a high necessity for power transfer operation and a low necessity for power transfer result; Step S433: when the power transfer operation judgment result is that the power transfer operation is highly necessary, the load fluctuation voltage abnormality data is forcibly transferred through a preset response time window using an automated execution algorithm, and equipment switch closing data is generated; Step S434: When the result of the power transfer operation is that the power transfer result is of low necessity, the load fluctuation voltage abnormality data is marked as to be observed, and low power transfer marking data is generated; based on the low power transfer marking data, the power transfer operation priority data is increased in priority, and low power transfer processing marking data is generated, thereby completing the medium voltage distribution network power transfer identification and operation.

9. A medium voltage distribution network transfer operation identification system, characterized in that: Used to execute the medium voltage distribution network transfer operation identification method according to claim 1, the medium voltage distribution network transfer operation identification system comprises: Data acquisition and preprocessing module: used to acquire real-time feeder data and substation area data; perform data preprocessing on real-time feeder data and substation area data to generate substation area feeder processing data set; Historical data fitting and anomaly detection module: used to obtain the historical data set of the power grid; perform two-dimensional curve fitting analysis on the historical data set of the power grid and the feeder processing data set of the substation area to generate the two-dimensional fitting data of the feeder area; determine the abnormal and disharmonious areas of the two-dimensional fitting data of the feeder area to generate load fluctuation voltage abnormality data; Empirical model building module: used to obtain the maximum switching times range of the switchgear; based on the maximum switching times range of the switchgear, an empirical model is built for the historical data set of the power grid to generate an empirical model of switching times-equipment life; Real-time data judgment and transfer operation module: used to input the real-time data of feeder lines and real-time data of substations into the switching times-equipment life empirical model to generate real-time medium-voltage switching-equipment life data; use the preset load voltage threshold to perform load voltage judgment on the real-time medium-voltage switching-equipment life data and load fluctuation voltage abnormality data to generate a transfer operation judgment result; perform a transfer operation based on the transfer operation judgment result, thereby completing the medium-voltage distribution network transfer operation.

10. A medium voltage distribution network transfer operation identification device, characterized in that: It includes an identification controller for executing the medium voltage distribution network transfer operation identification method as described in claim 1.

Images