Collection master station intelligent monitoring method and system based on autonomous configuration technology

Abstract

The invention discloses an acquisition master station intelligent monitoring method and system based on an autonomous configuration technology, and belongs to the technical field of data processing, and the method comprises the steps: carrying out the data integrity identification processing of a multi-dimensional acquisition service matrix, and obtaining a terminal acquisition configuration sequence in combination with a communication redundancy check rule; performing real-time monitoring processing on the terminal acquisition configuration sequence, and obtaining a terminal load feature vector in combination with the data interaction state of the intelligent electric meter; carrying out intelligent diagnosis processing on the terminal load feature vector, and obtaining collection link abnormal identification data in combination with electricity collection time sequence features; and performing dynamic optimization processing on the abnormal identification data of the acquisition link, and obtaining an autonomous configuration optimization strategy in combination with historical performance indexes of the acquisition master station. According to the invention, through real-time monitoring and intelligent diagnosis, operation abnormity is found and solved in time, and the reliability and stability of the system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, and particularly relates to a collection master station intelligent monitoring method and system based on autonomous configuration technology. BACKGROUND

[0002] At present, the power consumption information collection system in the construction of smart grid mainly manages and monitors terminal devices through the collection master station. The collection master station communicates with the terminal device through the object-oriented 698 protocol and 376.1 protocol to realize data collection, parameter configuration and other functions. The traditional configuration method of the collection terminal device mainly includes two kinds: one is to issue configuration parameters one by one through the collection master station, and the other is to configure by default when the terminal device leaves the factory. With the rapid development of new business such as distributed photovoltaic, orderly power consumption and demand response, the demand for power consumption data collection is increasingly diversified, and higher requirements are put forward for the function configuration and monitoring of terminal devices.

[0003] However, the existing collection master station monitoring method has obvious deficiencies: first, the configuration process lacks flexibility, and the terminal device needs to be reconfigured after restoring the factory settings, which consumes a lot of manpower; second, the configuration parameter issuing method is inefficient, and issuing one by one is easy to cause configuration failure or parameter missing; third, the terminal function configuration needs to be upgraded frequently, which not only increases the maintenance cost, but also easily leads to system instability; finally, there is a lack of intelligent monitoring and diagnosis mechanism for the running state of the terminal, which makes it difficult to find and solve abnormal problems in time. SUMMARY

[0004] The present application provides a collection master station intelligent monitoring method and system based on autonomous configuration technology, which is used to realize efficient autonomous configuration and intelligent monitoring of collection terminal devices, so that the terminal device can adaptively adjust the configuration parameters according to the business demand, and at the same time, through real-time monitoring and intelligent diagnosis, it can find and solve the running abnormity in time, improve the reliability and stability of the system. TECHNICAL SCHEME

[0005] A collection master station intelligent monitoring method based on autonomous configuration technology, comprising the following steps: The parameter set of the collection protocol communication frame is subjected to hierarchical decoupling processing to obtain a power terminal function mapping table; the power terminal function mapping table is subjected to service scenario evaluation processing to obtain a multi-dimensional collection service matrix in combination with a distributed energy collection strategy; the multi-dimensional collection service matrix is subjected to data integrity identification processing to obtain a terminal collection configuration sequence in combination with a communication redundancy check rule; the terminal collection configuration sequence is subjected to real-time monitoring processing to obtain a terminal load feature vector in combination with an intelligent electric meter data interaction state; the terminal load feature vector is subjected to intelligent diagnosis processing to obtain collection link abnormality identification data in combination with a power consumption collection timing feature; and the collection link abnormality identification data is subjected to dynamic optimization processing to obtain a self-configuring optimization strategy in combination with a collection master station historical performance index.

[0006] A collection master station intelligent detection system based on a self-configuring technology comprises the following modules: A decoupling module for subjecting a parameter set of a collection protocol communication frame to hierarchical decoupling processing to obtain a power terminal function mapping table; An evaluation module for subjecting the power terminal function mapping table to service scenario evaluation processing to obtain a multi-dimensional collection service matrix in combination with a distributed energy collection strategy; A processing module for subjecting the multi-dimensional collection service matrix to data integrity identification processing to obtain a terminal collection configuration sequence in combination with a communication redundancy check rule; A monitoring module for subjecting the terminal collection configuration sequence to real-time monitoring processing to obtain a terminal load feature vector in combination with an intelligent electric meter data interaction state; A diagnosis module for subjecting the terminal load feature vector to intelligent diagnosis processing to obtain collection link abnormality identification data in combination with a power consumption collection timing feature; An optimization module for subjecting the collection link abnormality identification data to dynamic optimization processing to obtain a self-configuring optimization strategy in combination with a collection master station historical performance index.

[0007] Beneficial effects: The parameter set of the collection protocol communication frame is subjected to hierarchical decoupling processing to obtain a power terminal function mapping table, realizing structured management of collection terminal configuration parameters and improving flexibility and maintainability of parameter configuration.

[0008] The power terminal function mapping table is subjected to service scenario evaluation processing in combination with a distributed energy collection strategy to obtain a multi-dimensional collection service matrix, thereby realizing precise matching of configuration parameters and actual service requirements and enhancing pertinence and adaptability of a configuration scheme.

[0009] By performing data integrity identification processing on the multi-dimensional acquisition service matrix and combining it with communication redundancy verification rules, a terminal acquisition configuration sequence is obtained, which ensures the integrity and validity of the configuration parameters and reduces the risk of configuration errors.

[0010] By performing real-time monitoring and processing of the terminal's collected configuration sequence and combining it with the smart meter's data interaction status, a terminal load feature vector is obtained, enabling real-time control of the terminal's operating status and improving the efficiency of anomaly detection.

[0011] By performing intelligent diagnostic processing on the terminal load feature vector and combining it with the power consumption collection timing features, abnormal identification data of the collection link is obtained, which enables accurate location and cause analysis of abnormal situations, and improves the accuracy and efficiency of fault handling.

[0012] By dynamically optimizing the abnormal identification data of the acquisition link and combining it with the historical performance indicators of the acquisition master station, an autonomous configuration optimization strategy is obtained, which realizes the adaptive optimization of configuration parameters and improves the stability and reliability of system operation.

[0013] The entire solution organically combines six stages: hierarchical decoupling, scenario evaluation, integrity verification, real-time monitoring, intelligent diagnosis, and dynamic optimization. This constructs a complete closed-loop optimization mechanism, significantly improving the configuration efficiency and operational quality of the data acquisition terminal. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the method steps of the present invention; Figure 2 This is a schematic diagram of the modules of the present invention. Detailed Implementation

[0015] The present invention will now be described in further detail with reference to the accompanying drawings. It should be noted that this is only for the purpose of more clearly illustrating and explaining the present invention.

[0016] like Figure 1 As shown, this embodiment discloses an intelligent monitoring method for a data acquisition master station based on autonomous configuration technology. The execution subject of this invention can be an intelligent detection system for a data acquisition master station based on autonomous configuration technology, or it can be a terminal or a server; the specific implementation is not limited here. This embodiment uses a server as the execution subject for illustration.

[0017] Step S101: Perform hierarchical decoupling processing on the parameter set of the acquisition protocol communication frame to obtain the power terminal function mapping table.

[0018] In this embodiment, the process of executing step S101 may specifically include the following steps: (1) Classify and statistically process the functional code segments in the acquisition protocol communication frames to obtain the terminal functional code feature set, and perform parameter attribute parsing processing on the terminal functional code feature set to obtain the original data of functional parameters; (2) Standardize the data format of the original data of the function parameters to obtain the standard set of function parameters, and perform hierarchical association processing on the standard set of function parameters to obtain the parameter hierarchical association table; (3) Perform functional grouping and clustering on the parameter hierarchical association table to obtain functional module grouping data, and perform dependency analysis on the functional module grouping data to obtain the module dependency chain list; (4) Perform business type mapping on the module dependency list to obtain a business function reference table, and perform parameter integrity verification on the business function reference table to obtain a parameter verification result set; (5) The parameter verification result set is recursively traversed by the depth traversal algorithm to obtain the function mapping relationship tree, and the function mapping relationship tree is integrated to obtain the power terminal function mapping table.

[0019] Specifically, the meaning of function codes is analyzed. Under the 698 protocol framework, function code segments include different types such as data acquisition, parameter configuration, and control commands. Classification and statistical processing categorizes function codes based on their frequency of occurrence and usage scenarios, establishing a correspondence between function codes and terminal functions, generating a terminal function code feature set. Parameter attribute parsing of the terminal function code feature set involves extracting the parameter attributes corresponding to each function code, including data type, length, and value range, forming the raw function parameter data. The raw function parameter data contains parameter information in different formats, requiring standardized data format processing. Standardization converts different types of parameters, such as floating-point, integer, and character types, into a unified data structure, ensuring that parameters can be compared and operated on, thus obtaining a standard set of function parameters. When performing hierarchical association processing on the standard set of function parameters, a hierarchical structure between parameters is first constructed, with upper-level parameters as parent nodes and lower-level parameters as child nodes, forming a hierarchical parameter association table.

[0020] Parameters in the parameter hierarchy association table are grouped and clustered according to functional similarity, grouping parameters with similar functions into the same functional module to obtain functional module grouping data. Dependency analysis is then performed on the functional module grouping data to determine the calling relationships and data flow between functional modules, generating a module dependency list describing the dependencies between modules. This module dependency list is then mapped to functional modules with actual business requirements through business type mapping, generating a business function lookup table. Parameter integrity verification is performed on the business function lookup table to check whether the parameters required for each business function are complete and valid, ultimately generating a parameter verification result set.

[0021] A depth-first traversal algorithm is used to recursively traverse the parameter verification result set. Starting from the root node, the depth-first traversal visits all nodes to construct a complete functional mapping tree. The functional mapping tree is then processed to integrate the data, organizing the node relationships and parameter information within the tree structure, ultimately generating a power terminal functional mapping table.

[0022] Taking a certain power terminal equipment as an example, its function code segment includes 100 function codes such as voltage acquisition (0x01), current acquisition (0x02), and power acquisition (0x03). Classification and statistical processing categorizes these function codes into 40 data acquisition categories, 35 parameter configuration categories, and 25 control command categories. Parameter attribute parsing determines that the voltage acquisition data type is float32, and the range is 0-380V. Data format standardization converts electrical parameters from different units to the International System of Units (SI). Hierarchical association processing establishes a three-level parameter structure of voltage-current-power. Functional grouping and clustering divides these parameters into three functional modules: basic measurement, load management, and power quality. Dependency analysis shows that the load management module depends on the data input from the basic measurement module. Business mapping maps these functional modules to business scenarios such as daily data acquisition, demand response, and orderly power consumption. Finally, through deep traversal and data integration, a complete terminal function mapping table is formed to guide subsequent data acquisition and monitoring work.

[0023] Step S102: Perform business scenario evaluation processing on the power terminal function mapping table, and combine it with the distributed energy acquisition strategy to obtain a multi-dimensional acquisition business matrix.

[0024] In this embodiment, the process of executing step S102 may specifically include the following steps: (1) The power terminal function mapping table is divided into business types to obtain a business function classification list, and the business function classification list is processed to identify the collection requirements to obtain a business collection feature table. (2) Divide the service collection feature table into collection frequency intervals to obtain a collection frequency interval set, and mark the collection frequency interval set with service priority to obtain a service weight sequence; (3) The business weight sequence is processed in layers by correlation analysis algorithm to obtain layered business weight data, and the layered business weight data is processed by scenario matching to obtain a scenario adaptation table. (4) Perform energy acquisition strategy analysis on the scene adaptation table to obtain the energy acquisition scheme table, and perform acquisition parameter association processing on the energy acquisition scheme table to obtain the parameter association matrix; (5) Perform business cross-validation on the parameter correlation matrix to obtain the business cross matrix, and perform data integration on the business cross matrix to obtain the multidimensional acquisition business matrix.

[0025] Specifically, when classifying the power terminal function mapping table by business type, functions are categorized into basic data acquisition, load monitoring, power quality monitoring, distributed photovoltaic monitoring, and demand response based on their nature, generating a business function classification list. The business function classification list is then processed to identify data acquisition requirements, labeling each business type with its data acquisition requirements, including acquisition items, acquisition accuracy, and data timeliness, forming a business acquisition characteristic table. The business acquisition characteristic table is then divided into acquisition frequency ranges, setting the acquisition frequency range according to the real-time requirements of the business. The basic data acquisition frequency range is 15 minutes / time, the load monitoring frequency range is 5 minutes / time, and the power quality monitoring frequency range is 1 minute / time, resulting in a set of acquisition frequency ranges. Finally, the acquisition frequency range set is processed to mark business priorities, assigning weight values ​​to each business based on its importance and data timeliness requirements, generating a business weight sequence.

[0026] When using a correlation analysis algorithm to stratify the business weight sequence, the degree of correlation between businesses is calculated. The correlation between businesses is assessed using the Pearson correlation coefficient. Businesses with a correlation coefficient greater than 0.8 are classified as strongly correlated, those between 0.5 and 0.8 as moderately correlated, and those less than 0.5 as weakly correlated, resulting in stratified business weight data. Scenario matching processing is then performed on the stratified business weight data to establish a correspondence between different levels of businesses and actual application scenarios, generating a scenario adaptation table. Energy collection strategy analysis is then performed on the scenario adaptation table, and a collection plan is formulated based on the characteristics of distributed energy access. For photovoltaic power generation users, a collection frequency of 5 minutes / time for power generation and 1 minute / time for voltage and current is set, forming an energy collection plan table. The energy collection plan table undergoes parameter correlation processing to establish the correlation between collection parameters, generating a parameter correlation matrix.

[0027] The parameter correlation matrix undergoes cross-validation to check for overlaps or conflicts in the collected parameters across different services, generating a cross-validation matrix. This cross-validation matrix is ​​then integrated with the data, comprehensively processing information such as collection requirements, frequency requirements, and priorities for various services to ultimately form a multi-dimensional data collection service matrix. Taking the power load monitoring of a certain distribution area as an example, the service type is divided into three categories: daily power consumption monitoring, peak-valley load analysis, and power factor assessment. The collection requirement identifier specifies that daily power consumption monitoring requires the collection of voltage and current, peak-valley load analysis requires the collection of active power, and power factor assessment requires the collection of reactive power. The collection frequency intervals are set as follows: daily monitoring 15 minutes / time, peak-valley analysis 5 minutes / time, and power factor 1 hour / time. The service weights are set to 0.6, 0.8, and 0.4, respectively. Correlation analysis shows that the correlation coefficient between peak-valley load analysis and daily monitoring is 0.85, classifying it as a strongly correlated layer. In scenario adaptation, the strongly correlated layer services are placed in key load monitoring scenarios. The energy collection scheme sets a collection frequency of 5 minutes / time for key loads. Parameter correlation analysis revealed a direct relationship between active power and voltage / current. Cross-validation of services showed that voltage and current parameters were repeatedly collected across multiple services. By integrating the data, the collection frequency was standardized to 5 minutes per instance, forming the final multi-dimensional data collection service matrix.

[0028] Step S103: Perform data integrity identification processing on the multi-dimensional acquisition service matrix, and combine it with communication redundancy verification rules to obtain the terminal acquisition configuration sequence.

[0029] In this embodiment, the process of executing step S103 may specifically include the following steps: (1) Perform data item integrity scanning on the multidimensional acquisition business matrix to obtain a data item missing identifier table, and perform anomaly point location processing on the data item missing identifier table to obtain an abnormal data item set; (2) Perform data completion processing on the abnormal data item set to obtain a candidate data item table, and perform data validity verification processing on the candidate data item table to obtain a valid data item sequence; (3) The valid data item sequence is subjected to redundancy check processing by the cyclic check algorithm to obtain the check code sequence, and the check code sequence is segmented to obtain the check segment table. (4) Perform data frame encapsulation on the verification segment table to obtain a communication data frame set, and perform frame sequence encoding on the communication data frame set to obtain an encoding sequence table; (5) Perform task matching processing on the encoding sequence table to obtain the task sequence, and perform configuration integration processing on the task sequence to obtain the terminal acquisition configuration sequence.

[0030] Specifically, a data item integrity scan is performed on the multi-dimensional data acquisition matrix. This involves traversing the acquisition parameter values ​​of each data item in the matrix and recording the location and type of null and outlier values. The data item integrity scan checks the numerical integrity of acquisition parameters such as voltage, current, and power, marking the locations of missing or abnormal data and generating a data item missing identifier table. Anomaly point localization processing is then performed on the data item missing identifier table to pinpoint the specific location and cause of the data anomaly, such as data acquisition interruption or communication failure, forming a set of abnormal data items. Data completion processing is then performed on the abnormal data item set, using methods such as nearest-neighbor interpolation and historical data backfilling for data repair. During data completion, linear interpolation is used to complete missing values ​​for voltage parameters, and previous value backfilling is used for current parameters, generating a candidate data item table. Finally, the candidate data item table undergoes data validity verification to check whether the completed data meets physical constraints, business rules, and other requirements. Data items that meet the requirements are selected to form a valid data item sequence.

[0031] Redundancy checks are performed on the valid data item sequence using a cyclic redundancy check algorithm, and the checksum is calculated using CRC. The data sequence is divided into fixed-length segments, and a 16-bit CRC checksum is calculated for each segment to generate a checksum sequence. The checksum sequence is then segmented, and the checksums are organized according to the correspondence between data segments to form a checksum segment table. The checksum segment table is then encapsulated into data frames, and communication data frames are constructed according to the 698 protocol requirements. Each data frame contains a frame start flag, address field, control field, data field, and checksum. The data from the checksum segment table is filled into the corresponding fields to generate a communication data frame set. The communication data frame set is then encoded, and a unique sequence number is assigned to each data frame to ensure the orderliness of data transmission, generating an encoded sequence table.

[0032] The encoded sequence table is matched with acquisition tasks to establish a correspondence between encoded data frames and specific acquisition tasks. Based on data acquisition time requirements, priorities, and other information, the data frames are organized into acquisition task sequences. These acquisition task sequences are then configured and integrated, incorporating execution strategies, parameter settings, and other information into a configuration file to ultimately generate the terminal acquisition configuration sequence.

[0033] Taking a power distribution terminal as an example, a data integrity scan revealed 3 missing voltage data points and 2 abnormal current data points out of 96 data collection points within a day. Anomaly location showed that the missing voltage data occurred between 10:15 and 10:45, while the abnormal current values ​​appeared at 14:30 and 15:45. Data completion processing used linear interpolation to fill in the missing values ​​between 220V at 10:15 and 225V at 10:45, filling them in as 221.5V, 223V, and 224.5V respectively. Data validity verification confirmed that the filled values ​​were within the allowable deviation range. Cyclic verification calculated a CRC16 checksum for every 256 bytes of data. Data frame encapsulation organized the voltage and current data and their checksums into a 512-byte data frame using the 698 protocol format. Data acquisition task matching configured the terminal with a regular acquisition task every 15 minutes, generating a configuration sequence containing the acquisition time, data items, and communication parameters.

[0034] Step S104: Perform real-time monitoring and processing on the terminal's collected configuration sequence, and combine it with the smart meter's data interaction status to obtain the terminal load feature vector.

[0035] In this embodiment, the process of executing step S104 may specifically include the following steps: (1) Perform task execution status scanning processing on the terminal acquisition configuration sequence to obtain the task execution status table, and perform acquisition success rate statistical processing on the task execution status table to obtain the acquisition success rate dataset; (2) The data acquisition success rate dataset is segmented into time windows to obtain a time period acquisition feature table, and the data delay calculation is performed on the time period acquisition feature table to obtain the acquisition delay sequence; (3) The data sampling process of the acquisition delay sequence is performed by the sliding window algorithm to obtain the real-time sampling dataset, and the communication quality evaluation process of the real-time sampling dataset is performed to obtain the communication quality index table; (4) Perform resource occupancy rate calculation on the communication quality index table to obtain the resource occupancy dataset, and perform load status analysis on the resource occupancy dataset to obtain the load status table. (5) Perform feature extraction processing on the load status table to obtain the load feature dataset, and perform vector mapping processing on the load feature dataset to obtain the terminal load feature vector.

[0036] Specifically, the terminal acquisition configuration sequence undergoes a data acquisition task execution status scan, requiring monitoring of the execution status of each acquisition task. The scan process records task start time, completion time, data return status, and other information, generating a task execution status table. The task execution status table is then processed to statistically analyze the acquisition success rate, calculating the success rate of each acquisition task and compiling success rate indicators for different time periods and task types, forming an acquisition success rate dataset. This dataset is then segmented into time windows. For daily data acquisition, a 1-hour window is used for segmentation, recording acquisition characteristics within each time window, including the number of acquisitions, the number of successes, and the number of failures, generating a time-period acquisition characteristic table. Finally, the time-period acquisition characteristic table is processed to calculate the time interval from sending to receiving for each acquisition task, analyzing data transmission delays and generating an acquisition delay sequence.

[0037] Data sampling of the acquired delay sequence is performed using a sliding window algorithm. The sampling window size is set to 10 minutes, and the window sliding step is 1 minute. Delay data is collected within each window to form a real-time sampling dataset. Communication quality assessment is performed on the real-time sampling dataset, calculating reliability indicators of the communication link, including data packet loss rate, signal strength, and bit error rate, generating a communication quality indicator table. Resource utilization is calculated on the communication quality indicator table, statistically analyzing the CPU, memory, and storage space usage of the acquisition task on the terminal device, generating a resource utilization dataset. Load status analysis is performed on the resource utilization dataset to assess the load level of the terminal device, determine whether resource usage is reasonable, and generate a load status table.

[0038] Feature extraction is performed on the load status table to extract key feature indicators reflecting the terminal's operating status, such as average load rate, peak load rate, and resource utilization efficiency, generating a load feature dataset. Vector mapping is then applied to this load feature dataset to convert the multi-dimensional feature data into a standardized feature vector form, ultimately yielding the terminal load feature vector.

[0039] Taking a power distribution terminal as an example, the data acquisition task execution status scan showed that 60 data acquisition tasks were executed between 8:00 and 9:00, of which 57 were successfully completed, resulting in a success rate of 95%. After segmenting the time window, the success rate dropped to 85% between 9:00 and 10:00. Data latency calculation showed that the normal acquisition latency was between 0.5 and 1 second, while the average latency increased to 2.5 seconds between 9:00 and 10:00. Sliding window sampling detected a decline in communication quality at 9:30, with the packet loss rate increasing from 0.1% to 1.5%. Resource usage calculation showed that CPU utilization reached 75% and memory utilization reached 80% during this period. Load status analysis determined that the terminal was under high load, and the load feature vector obtained from feature extraction showed that the load level during this period was significantly higher than in other periods, requiring load optimization adjustments.

[0040] Step S105: Perform intelligent diagnostic processing on the terminal load feature vector, and combine it with the power consumption collection timing characteristics to obtain the collection link anomaly identification data.

[0041] In this embodiment, the process of executing step S105 may specifically include the following steps: (1) Perform load threshold comparison processing on the terminal load feature vector to obtain the load over-limit identification table, and perform time-series association processing on the load over-limit identification table to obtain the load abnormal time-series table. (2) Extract key feature points from the load anomaly time series table to obtain anomaly feature sequences, and perform fluctuation pattern analysis on the anomaly feature sequences to obtain fluctuation feature datasets; (3) The periodic analysis of the fluctuation feature dataset is performed by time series analysis algorithm to obtain the periodic feature table, and the abnormal pattern recognition is performed on the periodic feature table to obtain the abnormal pattern set. (4) Perform link node localization processing on the abnormal pattern set to obtain an abnormal node identification table, and perform fault impact range analysis processing on the abnormal node identification table to obtain a fault impact dataset. (5) Perform anomaly level classification on the fault impact dataset to obtain an anomaly level table, and perform identification data integration on the anomaly level table to obtain the acquisition link anomaly identification data.

[0042] Specifically, the terminal load feature vector is compared with load thresholds, and load thresholds are set according to the performance indicators of the terminal devices. The CPU load threshold is set to 80%, the memory load threshold to 85%, and the communication load threshold to 90%. Load points exceeding the thresholds are marked to generate a load overload identification table. The load overload identification table is then subjected to time-series correlation processing to analyze the temporal patterns of load overload occurrences, recording information such as continuous overload duration and frequency to form a load anomaly time-series table. Key feature points are extracted from the load anomaly time-series table to identify abrupt changes, inflection points, and peak points of load anomalies. The start time, duration, and peak level of each anomaly time sequence are extracted to generate an anomaly feature sequence. The anomaly feature sequence is then subjected to fluctuation pattern analysis to study the changing trends of load anomalies, including the rate of increase, rate of decrease, and fluctuation amplitude, forming a fluctuation feature dataset.

[0043] The fluctuation feature dataset is processed periodically using time-series analysis algorithms, and autocorrelation analysis is employed to identify the periodic patterns of load anomalies. Periodic characteristics at different time scales, including daily, weekly, and monthly cycles, are calculated to generate a periodic feature table. Anomaly pattern recognition is performed on the periodic feature table, clustering similar anomaly patterns to summarize typical anomaly pattern characteristics and form an anomaly pattern set. Link node localization processing is performed on the anomaly pattern set to trace the specific node location where the anomaly occurred. Analysis of the acquisition terminals, communication modules, and master station system in the communication link identifies key nodes where anomalies occur, generating an anomaly node identifier table. The anomaly node identifier table is then processed for fault impact range analysis to assess the degree of impact of the anomaly on data acquisition services, including the number of affected acquisition points and the types of data affected, forming a fault impact dataset.

[0044] The fault impact dataset is processed to classify anomalies into levels based on their severity and scope. Anomalies are categorized into three levels: urgent, important, and minor, generating an anomaly level table. This table then undergoes data integration processing, combining information such as anomaly node information, scope of impact, and processing priority to ultimately form the data acquisition link anomaly identification data.

[0045] Taking a power distribution terminal device as an example, load threshold comparison revealed that between 9:00 and 10:00, the CPU load exceeded 80% of the threshold for 30 consecutive minutes, reaching a peak of 85%. Time-series correlation analysis showed that the memory load also rose to 87% during this period. Key feature point extraction revealed that the load anomaly began at 9:05, peaked at 9:20, and continued until 9:50. Fluctuation pattern analysis showed that the load increase rate was 2% / minute, and the decrease rate was 1% / minute. Periodic analysis revealed that this type of load anomaly was more frequent on Monday mornings. Link node location determined that the anomaly occurred in the data processing module of the terminal device. Fault impact analysis showed that the anomaly affected data acquisition at 15 collection points, involving basic data such as voltage and current. Based on the scope of impact, the anomaly was classified as critical and required to be resolved within 30 minutes.

[0046] Step S106: Dynamically optimize the abnormal identification data of the acquisition link, and obtain the autonomous configuration optimization strategy by combining the historical performance indicators of the acquisition master station.

[0047] In this embodiment, the process of executing step S106 may specifically include the following steps: (1) Classify the abnormal identification data of the acquisition link to obtain an abnormal classification table, and perform historical data association processing on the abnormal classification table to obtain a historical association dataset; (2) The historical associated dataset is compared with the performance indicators to obtain a performance difference table, and the key parameters of the performance difference table are extracted to obtain the parameter adjustment sequence. (3) The parameter adjustment sequence is constrained by the parameter optimization algorithm to obtain the parameter constraint table, and the parameter constraint table is processed to generate configuration rules to obtain the configuration rule set; (4) Perform collection efficiency evaluation processing on the configuration rule set to obtain an efficiency evaluation data table, and perform adjustment scheme generation processing on the efficiency evaluation data table to obtain a configuration adjustment scheme; (5) Perform strategy integration processing on the configuration adjustment scheme to obtain a strategy combination table, and perform priority sorting processing on the strategy combination table to obtain the self-configuration optimization strategy.

[0048] Specifically, the abnormal identification data of the acquisition link is classified into four categories based on its nature: communication abnormalities, data quality abnormalities, resource usage abnormalities, and business execution abnormalities. Communication abnormalities include communication interruptions, communication delays, and data frame errors; data quality abnormalities include missing data, data out-of-bounds errors, and discontinuous data; resource usage abnormalities include high CPU usage, high memory usage, and insufficient storage space; and business execution abnormalities include acquisition task timeouts, incomplete acquisition data, and acquisition frequency deviations. An abnormality classification table is established to record the specific manifestations, occurrence times, durations, and impact ranges of each type of abnormality. When performing historical data association processing on the abnormality classification table, the acquisition master station retrieves processing records of similar abnormal situations from the historical database. In the historical association dataset, each abnormal record includes information such as the terminal configuration parameters, operating environment parameters, processing solutions, and processing effects at the time of the abnormality. For example, when an abnormal communication delay is found in a terminal in a certain area, by querying historical data, it can be found that the terminal has experienced similar situations many times in the past three months, and all of them are related to the sampling frequency being set too high. These historical processing experiences will provide important references for subsequent parameter optimization.

[0049] When comparing performance metrics of historical correlated datasets, the focus is on analyzing changes in key performance indicators before and after anomalies. Performance metrics include multiple dimensions such as data acquisition success rate, communication response time, resource utilization, and data quality score. Comparative analysis yields a performance difference table, clearly showing the trends of each indicator. Further analysis of the performance difference table extracts key parameters, identifying configuration parameters closely related to performance changes, such as acquisition frequency, number of retries, and timeout, forming a parameter adjustment sequence. A genetic algorithm is used as the parameter optimization algorithm to constrain the parameter adjustment sequence. The genetic algorithm continuously optimizes parameter combinations by simulating natural selection and genetic processes. Each individual in the population represents a set of possible parameter configuration schemes, and the merits of each scheme are evaluated using a fitness function. The fitness function comprehensively considers multiple indicators such as acquisition efficiency, resource consumption, and data quality. Through selection, crossover, and mutation operations, the algorithm evolves generation by generation to produce better parameter combinations, ultimately yielding a parameter constraint table that clarifies the value range of each parameter.

[0050] When generating configuration rules for the parameter constraint table, the main data acquisition station formulates corresponding configuration rules based on the characteristics of the business scenario and the capabilities of the terminal. These rules include the dependencies between parameters, the priority of parameter adjustments, and the step size control for parameter changes. These rules ensure that the parameter adjustment process can resolve anomalies without introducing new stability risks. The final generated configuration rule set provides a basis for parameter optimization decisions. When evaluating the collection efficiency of the configuration rule set, the main data acquisition station constructs an evaluation index system to assess the effectiveness of the configuration scheme from multiple dimensions, including collection success rate, collection latency, and resource consumption. The evaluation results are recorded in the efficiency evaluation data table, including the expected improvement effect of each index. Based on the evaluation results, a specific configuration adjustment scheme is generated, clarifying the adjustment direction and magnitude of each parameter.

[0051] When integrating configuration adjustment schemes, the main data collection station considers the synergistic effects between multiple configuration schemes, combining complementary schemes to form a complete strategy combination table. Finally, based on factors such as anomaly level, scope of business impact, and execution difficulty, the strategy combinations are prioritized to obtain the final autonomous configuration optimization strategy.

[0052] Specifically, a hierarchical decoupling process is performed on the parameter set of the acquisition protocol communication frames. The acquisition protocol communication frame is the basic unit for data transmission based on the 698 protocol framework, containing information such as function code segments, data field segments, and check code segments. The hierarchical decoupling process classifies and statistically analyzes the function codes in the communication frames to form a terminal function code feature set. Then, the parameter attributes of the function code feature set are parsed to generate raw function parameter data. This raw function parameter data is standardized and converted into a standard set of function parameters. Then, a hierarchical association process is used to establish relationships between parameters, generating a parameter hierarchical association table. Based on this, the parameter hierarchical association table is functionally grouped and clustered to obtain functional module group data. A depth-first traversal algorithm is used to recursively traverse the parameter verification result set, ultimately forming a power terminal function mapping table. After obtaining the power terminal function mapping table, a business scenario evaluation process is performed. The business scenario evaluation first classifies the function mapping table by business type, distinguishing different types of business functions, such as electricity data acquisition, load monitoring, and power quality monitoring, forming a business function classification list. Through acquisition requirement identification processing, the data acquisition requirements for each business function are determined, generating a business acquisition feature table. The data collection feature table is divided into frequency ranges, and different service collection frequency requirements are set. Service priorities are also marked to form a service weight sequence. A correlation analysis algorithm is used to perform hierarchical processing of the service weight sequence, and combined with distributed energy collection strategies, a multi-dimensional data collection service matrix is ​​generated.

[0053] When performing data integrity identification processing on the multi-dimensional acquisition service matrix, the process begins by scanning data items to identify missing data and generating a missing data item identifier table. Anomalies in the missing item identifier table are located, forming a set of abnormal data items. A candidate data item table is generated through data completion processing, and its validity is verified to obtain a sequence of valid data items. A cyclic verification algorithm is used for redundancy verification, generating a checksum sequence, which is then segmented into a checksum segment table. This checksum segment table is then encapsulated and encoded into data frames to ultimately generate the terminal acquisition configuration sequence. During the real-time monitoring phase, the acquisition task execution status of the terminal acquisition configuration sequence is scanned, recording the task execution status and generating a task execution status table. Acquisition success rate statistics are processed to form an acquisition success rate dataset. The dataset is segmented into time windows to obtain a time-period acquisition feature table, and acquisition delay is calculated to generate an acquisition delay sequence. A sliding window algorithm is used to sample the acquisition delay sequence, generating a real-time sampling dataset to evaluate communication quality and form a communication quality index table. Resource utilization is calculated, load status is analyzed, and finally, through feature extraction and vector mapping, a terminal load feature vector is obtained.

[0054] The intelligent diagnostic process compares the terminal load feature vectors with load thresholds to generate a load over-limit identifier table, and then uses time-series correlation processing to form a load anomaly time-series table. Key feature points are extracted from the anomaly time-series table, fluctuation patterns are analyzed, and a fluctuation feature dataset is obtained. Time-series analysis algorithms are then used for periodic analysis to identify anomaly patterns, locate abnormal link nodes, analyze the scope of fault impact, and finally generate collected link anomaly identifier data.

[0055] During the dynamic optimization phase, anomaly identification data from the acquisition link are categorized by anomaly type to create an anomaly classification table. This table is then used to perform correlation analysis with historical data, generating a historical correlation dataset. Performance metrics are compared, and key parameters are extracted to create a parameter adjustment sequence. A parameter optimization algorithm is used to constrain parameter ranges, generating a configuration rule set. The efficiency of this configuration rule set is evaluated, and adjustment schemes are generated, ultimately forming a self-configuration optimization strategy.

[0056] Taking a distributed photovoltaic (PV) user in a certain area as an example, parameters such as voltage, current, and power in the acquisition protocol communication frames were classified through hierarchical decoupling processing, forming a feature set containing 100 function codes. After parameter attribute parsing and standardization, grouped data of 15 functional modules were established. In the business scenario evaluation phase, the PV power generation data acquisition frequency was set to 5 minutes / time, and the load data acquisition frequency was set to 15 minutes / time, with acquisition task weights of 0.8 and 0.6 respectively. Data integrity identification processing revealed 32 missing data points during the daily data acquisition process, and 28 valid data points were recovered through completion processing. Real-time monitoring showed that the terminal executed 288 acquisition tasks with a success rate of 96.5% and an average acquisition delay of 1.2 seconds. Intelligent diagnosis found 3 acquisition anomalies between 14:00 and 15:00, which were determined to be caused by communication link fluctuations through time series analysis. Finally, an optimization strategy was generated to adjust the acquisition tasks during this period to avoid peak times, improving the acquisition success rate to 98.2%.

[0057] In this embodiment, by performing hierarchical decoupling processing on the parameter set of the acquisition protocol communication frames, a power terminal function mapping table is obtained, realizing structured management of acquisition terminal configuration parameters and improving the flexibility and maintainability of parameter configuration. The power terminal function mapping table is then subjected to business scenario evaluation processing and combined with distributed energy acquisition strategies to obtain a multi-dimensional acquisition service matrix. This achieves accurate matching between configuration parameters and actual business needs, enhancing the pertinence and adaptability of the configuration scheme. By performing data integrity identification processing on the multi-dimensional acquisition service matrix and combining it with communication redundancy verification rules, a terminal acquisition configuration sequence is obtained, ensuring the integrity and validity of configuration parameters and reducing configuration costs. To mitigate error risks, real-time monitoring and processing of the terminal's configuration sequence, combined with smart meter data interaction status, yields a terminal load feature vector. This enables real-time control of the terminal's operational status, improving the efficiency of anomaly detection. Intelligent diagnostic processing of the terminal load feature vector, combined with electricity consumption collection timing characteristics, generates anomaly identification data for the collection link, enabling accurate anomaly location and root cause analysis, thus improving the accuracy and efficiency of fault handling. Finally, dynamic optimization of the collection link anomaly identification data, combined with historical performance indicators of the main collection station, yields an autonomous configuration optimization strategy, achieving adaptive optimization of configuration parameters and improving system stability and reliability. The entire solution organically combines six stages—layered decoupling, scenario evaluation, integrity verification, real-time monitoring, intelligent diagnosis, and dynamic optimization—to construct a complete closed-loop optimization mechanism, significantly improving the configuration efficiency and operational quality of the collection terminals.

[0058] For example, a data acquisition delay anomaly occurred in a certain distribution area's concentrator during operation. Anomaly classification categorized it as a acquisition delay type within communication anomalies. Records showed that the anomaly lasted for more than 2 hours, affecting 85% of the acquisition terminals in that area. Historical data correlation analysis revealed that the concentrator experienced five similar anomalies in the past month, all occurring during peak electricity consumption periods. Performance indicator comparison showed that during the anomaly, the acquisition response time increased from the normal 3 seconds to 12 seconds, the acquisition success rate decreased from 98% to 75%, and CPU utilization reached 85%. Key parameter extraction identified three key optimization parameters: acquisition frequency, number of concurrent tasks, and communication timeout. After 50 generations of evolution using a genetic algorithm, the optimized parameter combination was obtained: the acquisition frequency was adjusted from once every 5 minutes to once every 8 minutes, the number of concurrent tasks decreased from 10 to 6, and the communication timeout was extended from 5 seconds to 8 seconds. Acquisition efficiency assessment predicted that this parameter combination could control the acquisition response time to within 4 seconds, increase the acquisition success rate to over 95%, and reduce CPU utilization to around 65%. The final optimization strategy takes this set of parameter adjustments as the preferred solution, and combines it with auxiliary measures such as adding a retry mechanism and optimizing the data caching strategy to form a complete optimization solution.

[0059] like Figure 2 As shown, this embodiment discloses an intelligent monitoring system for a data acquisition master station based on autonomous configuration technology, including: The decoupling module is used to perform hierarchical decoupling processing on the parameter set of the acquisition protocol communication frames to obtain the power terminal function mapping table. The evaluation module is used to perform business scenario evaluation processing on the power terminal function mapping table and, in combination with the distributed energy acquisition strategy, obtain a multi-dimensional acquisition business matrix. The processing module is used to perform data integrity identification processing on the multi-dimensional acquisition service matrix and, in conjunction with communication redundancy verification rules, obtain the terminal acquisition configuration sequence. The monitoring module is used to monitor and process the configuration sequence collected by the terminal in real time, and obtain the terminal load feature vector by combining the data interaction status of the smart meter. The diagnostic module is used to perform intelligent diagnostic processing on the terminal load feature vector and, in combination with the power consumption collection timing features, obtain the collection link anomaly identification data. The optimization module is used to dynamically optimize the abnormal identification data of the acquisition link and obtain an autonomous configuration optimization strategy by combining the historical performance indicators of the acquisition master station.

[0060] Through the collaborative efforts of the aforementioned components, and by performing hierarchical decoupling processing on the parameter set of the acquisition protocol communication frames, a power terminal function mapping table is obtained. This enables structured management of the acquisition terminal configuration parameters, improving the flexibility and maintainability of parameter configuration. By performing business scenario evaluation processing on the power terminal function mapping table and combining it with distributed energy acquisition strategies, a multi-dimensional acquisition service matrix is ​​obtained. This achieves precise matching between configuration parameters and actual business needs, enhancing the relevance and adaptability of the configuration scheme. Furthermore, by performing data integrity identification processing on the multi-dimensional acquisition service matrix and combining it with communication redundancy verification rules, a terminal acquisition configuration sequence is obtained, ensuring the integrity and validity of the configuration parameters and reducing costs. This approach reduces the risk of configuration errors by performing real-time monitoring and processing of the terminal's configuration sequence and combining it with the smart meter's data interaction status to obtain the terminal load feature vector. This enables real-time control of the terminal's operating status and improves the efficiency of anomaly detection. Intelligent diagnostic processing of the terminal load feature vector, combined with electricity consumption collection time-series characteristics, yields collection link anomaly identification data, enabling accurate anomaly location and cause analysis, thus improving the accuracy and efficiency of fault handling. Finally, dynamic optimization processing of the collection link anomaly identification data, combined with historical performance indicators of the collection master station, yields an autonomous configuration optimization strategy, achieving adaptive optimization of configuration parameters and improving system stability and reliability. The entire solution organically combines six stages—layered decoupling, scenario evaluation, integrity verification, real-time monitoring, intelligent diagnosis, and dynamic optimization—to construct a complete closed-loop optimization mechanism, significantly improving the configuration efficiency and operational quality of the collection terminals.

[0061] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for intelligent monitoring of a data acquisition master station based on autonomous configuration technology, characterized in that, Includes the following steps: The parameter set of the acquisition protocol communication frames is subjected to hierarchical decoupling processing to obtain the power terminal function mapping table; The power terminal function mapping table is subjected to business scenario evaluation processing, and combined with the distributed energy acquisition strategy, a multi-dimensional acquisition business matrix is ​​obtained. The multi-dimensional acquisition service matrix is ​​subjected to data integrity identification processing, and combined with communication redundancy verification rules, the terminal acquisition configuration sequence is obtained; The terminal's configuration sequence is monitored and processed in real time, and combined with the smart meter's data interaction status, a terminal load feature vector is obtained. The terminal load feature vector is intelligently diagnosed and processed, and combined with the power consumption collection timing features, to obtain the collection link anomaly identification data; The abnormal identification data of the acquisition link is dynamically optimized, and an autonomous configuration optimization strategy is obtained by combining the historical performance indicators of the acquisition master station.

2. The intelligent monitoring method for the data acquisition master station based on autonomous configuration technology according to claim 1, characterized in that, The hierarchical decoupling process of the parameter set of the acquisition protocol communication frames to obtain the power terminal function mapping table includes: The functional code segments in the acquisition protocol communication frames are classified and statistically processed to obtain the terminal functional code feature set, and the terminal functional code feature set is parsed for parameter attributes to obtain the original functional parameter data. The original data of the functional parameters are processed to standardize the data format to obtain a standard set of functional parameters, and the standard set of functional parameters is processed to perform hierarchical association processing to obtain a parameter hierarchical association table. The parameter hierarchical association table is subjected to functional grouping and clustering processing to obtain functional module grouping data, and the functional module grouping data is subjected to dependency relationship analysis processing to obtain module dependency linked list; The module dependency list is processed by business type mapping to obtain a business function lookup table, and the business function lookup table is processed by parameter integrity verification to obtain a parameter verification result set. The parameter verification result set is recursively traversed using a depth-first search algorithm to obtain a function mapping tree. The function mapping tree is then integrated to obtain the power terminal function mapping table.

3. The intelligent monitoring method for the data acquisition master station based on autonomous configuration technology according to claim 1, characterized in that, The process of evaluating business scenarios in the power terminal function mapping table, combined with distributed energy acquisition strategies, yields a multi-dimensional acquisition business matrix, including: The power terminal function mapping table is processed to classify business types to obtain a business function classification list, and the business function classification list is processed to identify collection requirements to obtain a business collection feature table. The service collection feature table is divided into collection frequency intervals to obtain a collection frequency interval set, and the collection frequency interval set is marked with service priority to obtain a service weight sequence. The business weight sequence is processed hierarchically using a correlation analysis algorithm to obtain hierarchical business weight data, and then the hierarchical business weight data is processed for scenario matching to obtain a scenario adaptation table. The scenario adaptation table is subjected to energy acquisition strategy analysis and processing to obtain an energy acquisition scheme table, and the energy acquisition scheme table is subjected to acquisition parameter association processing to obtain a parameter association matrix. The parameter correlation matrix is ​​subjected to business cross-validation processing to obtain a business cross matrix, and the business cross matrix is ​​subjected to data integration processing to obtain the multidimensional acquisition business matrix.

4. The intelligent monitoring method for the data acquisition master station based on autonomous configuration technology according to claim 1, characterized in that, The process of performing data integrity identification on the multi-dimensional acquisition service matrix, combined with communication redundancy verification rules, yields the terminal acquisition configuration sequence, including: The multidimensional acquisition service matrix is ​​subjected to data item integrity scanning processing to obtain a data item missing identifier table, and the data item missing identifier table is subjected to anomaly point location processing to obtain an abnormal data item set. The abnormal data item set is subjected to data completion processing to obtain a candidate data item table, and the candidate data item table is subjected to data validity verification processing to obtain a valid data item sequence; The valid data item sequence is subjected to redundancy check processing by a cyclic check algorithm to obtain a check code sequence, and the check code sequence is segmented to obtain a check segment table. The verification segment table is encapsulated into data frames to obtain a communication data frame set, and the communication data frame set is encoded into a frame sequence to obtain an encoding sequence table. The encoding sequence table is subjected to acquisition task matching processing to obtain an acquisition task sequence, and the acquisition task sequence is subjected to configuration integration processing to obtain the terminal acquisition configuration sequence.

5. The intelligent monitoring method for the data acquisition master station based on autonomous configuration technology according to claim 1, characterized in that, The real-time monitoring and processing of the terminal's collected configuration sequence, combined with the smart meter's data interaction status, yields a terminal load feature vector, including: The terminal acquisition configuration sequence is subjected to acquisition task execution status scanning processing to obtain a task execution status table, and the acquisition success rate is statistically processed on the task execution status table to obtain an acquisition success rate dataset. The data acquisition success rate dataset is segmented into time windows to obtain a time period acquisition feature table, and the data delay calculation is performed on the time period acquisition feature table to obtain an acquisition delay sequence. The acquisition delay sequence is sampled using a sliding window algorithm to obtain a real-time sampling dataset. The real-time sampling dataset is then subjected to communication quality evaluation to obtain a communication quality index table. The resource utilization rate of the communication quality index table is calculated to obtain a resource utilization dataset, and the load status of the resource utilization dataset is analyzed to obtain a load status table. The load status table is subjected to feature extraction processing to obtain a load feature dataset, and the load feature dataset is subjected to vector mapping processing to obtain the terminal load feature vector.

6. The intelligent monitoring method for the data acquisition master station based on autonomous configuration technology according to claim 1, characterized in that, The intelligent diagnostic processing of the terminal load feature vector, combined with the power consumption collection time sequence characteristics, yields the collection link anomaly identification data, including: The load threshold comparison process is performed on the terminal load feature vector to obtain the load over-limit identification table, and the load over-limit identification table is subjected to time-series correlation processing to obtain the load anomaly time-series table. The load anomaly time series table is processed by extracting key feature points to obtain an anomaly feature sequence, and the anomaly feature sequence is processed by fluctuation pattern analysis to obtain a fluctuation feature dataset. The fluctuation feature dataset is subjected to periodic analysis processing using a time series analysis algorithm to obtain a periodic feature table, and the periodic feature table is subjected to abnormal pattern recognition processing to obtain an abnormal pattern set. The abnormal pattern set is processed to locate the link node to obtain an abnormal node identification table, and the abnormal node identification table is processed to analyze the scope of the fault impact to obtain a fault impact dataset. The fault impact dataset is subjected to anomaly level classification to obtain an anomaly level table, and the anomaly level table is further processed by identification data integration to obtain the acquisition link anomaly identification data.

7. The intelligent monitoring method for the data acquisition master station based on autonomous configuration technology according to claim 1, characterized in that, The dynamic optimization processing of the abnormal identification data of the acquisition link, combined with the historical performance indicators of the acquisition master station, yields a self-configurable optimization strategy, including: The abnormal identification data of the acquisition link is classified into abnormal types to obtain an abnormal classification table, and the abnormal classification table is associated with historical data to obtain a historical associated dataset. The historical associated dataset is subjected to performance index comparison processing to obtain a performance difference table, and the performance difference table is subjected to key parameter extraction processing to obtain a parameter adjustment sequence; The parameter adjustment sequence is subjected to parameter range constraint processing by a parameter optimization algorithm to obtain a parameter constraint table, and the parameter constraint table is subjected to configuration rule generation processing to obtain a configuration rule set. The configuration rule set is subjected to collection efficiency evaluation processing to obtain an efficiency evaluation data table, and the efficiency evaluation data table is subjected to adjustment scheme generation processing to obtain a configuration adjustment scheme. The configuration adjustment scheme is integrated to obtain a strategy combination table, and the strategy combination table is sorted by priority to obtain the autonomous configuration optimization strategy.

8. A data acquisition master station intelligent detection system based on autonomous configuration technology, used to implement the data acquisition master station intelligent monitoring method based on autonomous configuration technology as described in any one of claims 1-7, characterized in that, include: The decoupling module is used to perform hierarchical decoupling processing on the parameter set of the acquisition protocol communication frames to obtain the power terminal function mapping table. The evaluation module is used to perform business scenario evaluation processing on the power terminal function mapping table and, in combination with the distributed energy acquisition strategy, obtain a multi-dimensional acquisition business matrix. The processing module is used to perform data integrity identification processing on the multi-dimensional acquisition service matrix and, in conjunction with communication redundancy verification rules, obtain the terminal acquisition configuration sequence. The monitoring module is used to monitor and process the configuration sequence collected by the terminal in real time, and obtain the terminal load feature vector by combining the data interaction status of the smart meter. The diagnostic module is used to perform intelligent diagnostic processing on the terminal load feature vector and, in combination with the power consumption collection timing features, obtain the collection link anomaly identification data. The optimization module is used to dynamically optimize the abnormal identification data of the acquisition link and obtain an autonomous configuration optimization strategy by combining the historical performance indicators of the acquisition master station.

Images