Power terminal equipment safety management and control system based on multi-source data fusion

Abstract

The invention discloses an electric power terminal equipment safety management and control system based on multi-source data fusion, and relates to the technical field of electric power equipment management and control, and the system comprises an electric meter data collection module which is used for collecting the flow characteristic sequence, the electric meter load sequence, the electric power data sequence and the communication characteristic sequence of a plurality of electric meters in a residential area in a preset time zone; the abnormal risk prediction module is used for carrying out network abnormal risk prediction and outputting a plurality of network abnormal risk coefficients; the abnormal ammeter distribution construction module is used for determining a plurality of abnormal ammeters and constructing abnormal ammeter distribution; and the ammeter operation and maintenance management and control module is used for setting an ammeter operation and maintenance scheme according to the abnormal concentration ratio to perform ammeter operation and maintenance management and control. According to the method and the device, the technical problems of poor management and control efficiency, accuracy and safety of the power terminal equipment caused by difficulty in accurately and comprehensively monitoring the state of the power equipment and incapability of predicting the network abnormal risk in advance in the prior art are solved, and the technical effect of improving the management and control efficiency, accuracy and safety of the equipment is achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to power equipment management and control, and specifically to a power terminal equipment safety management and control system based on multi-source data fusion. Background Art

[0002] As the key connection point between the power grid and users, the safe and stable operation of power terminal equipment is crucial for ensuring power supply reliability, improving user experience, and maintaining the overall security of the power grid. Traditional power terminal equipment security management relies primarily on single-source data collection and manual inspections, which have many limitations. First, collecting only power data series makes it difficult to fully reflect the operating status and safety risks of the equipment. For example, relying solely on power data may not promptly detect communication anomalies caused by cyber attacks, thus missing the optimal time to troubleshoot, increasing the risk of equipment failure and grid instability. Second, manual inspections are inefficient and costly, and cannot achieve real-time, dynamic monitoring of equipment and accurate early warnings, making it difficult to meet the high security requirements of smart grids for power terminal equipment. At the same time, the number of electricity meters in residential areas continues to increase, and the operating environment of equipment is becoming increasingly complex. Cybersecurity threats and equipment failure risks are significantly increasing, affecting the accuracy and safety of power terminal equipment anomaly risk prediction.

[0003] Therefore, in the current relevant technologies, there are technical problems such as difficulty in accurately and comprehensively monitoring the status of power equipment and inability to predict network abnormality risks in advance, resulting in poor efficiency, accuracy and safety of power terminal equipment management and control. Summary of the Invention

[0004] This application solves the technical problems in the existing technology that it is difficult to accurately and comprehensively monitor the status of power equipment and cannot predict network abnormality risks in advance, resulting in poor efficiency, accuracy and safety of power terminal equipment management and control, by providing a power terminal equipment safety management and control system based on multi-source data fusion. It achieves the technical effect of improving the efficiency, accuracy and safety of equipment management and control.

[0005] The present application provides a power terminal equipment safety management and control system based on multi-source data fusion, the system comprising: an electricity meter data acquisition module, for collecting flow feature sequences, electricity meter load sequences, electricity data sequences and communication feature sequences of a plurality of electricity meters in a residential area within a preset time zone; an abnormal risk prediction module, for performing network abnormality risk prediction on the plurality of electricity meters based on the flow feature sequences, electricity meter load sequences, electricity data sequences and communication feature sequences, and outputting a plurality of network abnormality risk coefficients; an abnormal electricity meter distribution construction module, for determining a plurality of abnormal electricity meters based on the plurality of network abnormality risk coefficients, and constructing an abnormal electricity meter distribution; an electricity meter operation and maintenance management module, for performing concentration analysis based on the abnormal electricity meter distribution, outputting abnormal concentration, and setting an electricity meter operation and maintenance plan based on the abnormal concentration to perform electricity meter operation and maintenance management.

[0006] In a possible implementation, the power terminal equipment safety management and control system based on multi-source data fusion also performs the following processing: collecting sample data to train the feedforward neural network until convergence, and constructing an abnormal risk predictor, wherein the abnormal risk predictor includes K abnormal risk prediction plug-ins, K is an integer greater than 5; randomly selecting a first electricity meter, and obtaining the first flow feature sequence, the first electricity meter load sequence, the first power data sequence and the first communication feature sequence of the first electricity meter, performing feature fluctuation analysis, and determining the first feature fluctuation scale; multiplying the ratio of the first feature fluctuation scale to the historical maximum feature fluctuation scale by K and rounding it up to obtain the number of plug-in selections P; randomly selecting P abnormal risk prediction plug-ins from the K abnormal risk prediction plug-ins, performing network abnormal risk prediction based on the first flow feature sequence, the first electricity meter load sequence, the first power data sequence and the first communication feature sequence, outputting P prediction risk coefficients, calculating the average to obtain the first network abnormal risk coefficient, and adding it to the several network abnormal risk coefficients.

[0007] In a possible implementation, the power terminal equipment safety management and control system based on multi-source data fusion also performs the following processing: performing characteristic fluctuation analysis on the first flow feature sequence, the first meter load sequence, the first power data sequence and the first communication feature sequence respectively, and outputting multiple characteristic fluctuation coefficients, wherein the characteristic fluctuation coefficient is the ratio of the characteristic standard deviation to the characteristic mean; performing weighted fusion on the multiple characteristic fluctuation coefficients to obtain the first characteristic fluctuation scale.

[0008] In a possible implementation, the power terminal equipment safety management and control system based on multi-source data fusion also performs the following processing: screening the several network abnormality risk coefficients according to a preset risk threshold, determining multiple abnormal meters, and multiple abnormal meter location coordinates; and constructing an abnormal meter distribution based on the multiple abnormal meter location coordinates.

[0009] In a possible implementation, the power terminal equipment safety management and control system based on multi-source data fusion also performs the following processing: performing meter distribution discrete evaluation on the abnormal meter distribution and outputting the meter distribution discreteness; and taking the inverse of the meter distribution discreteness as the abnormal concentration.

[0010] In a possible implementation, the power terminal equipment safety management and control system based on multi-source data fusion also performs the following processing: if the abnormal concentration is less than or equal to the preset concentration threshold, a local operation and maintenance strategy is set, and an electric meter operation and maintenance plan is set based on the local operation and maintenance strategy; if the abnormal concentration is greater than the preset concentration threshold, a global operation and maintenance strategy is set, and an electric meter operation and maintenance plan is set based on the global operation and maintenance strategy.

[0011] In a possible implementation, the power terminal equipment safety management and control system based on multi-source data fusion also performs the following processing: obtaining multiple network abnormality risk coefficients of the multiple abnormal meters, and sorting them from large to small to construct an abnormal meter sequence, wherein each abnormal meter has an order identifier; enumerating operation and maintenance paths according to the location coordinates of the multiple abnormal meters, and determining multiple local operation and maintenance paths; constructing a path evaluation function with the goal of minimizing the operation and maintenance distance and minimizing the operation and maintenance order deviation; using the path evaluation function, evaluating the multiple local operation and maintenance paths respectively, and outputting the local operation and maintenance path with the maximum path fitness as the meter operation and maintenance plan.

[0012] In a possible implementation, the power terminal equipment safety management and control system based on multi-source data fusion further performs the following processing: the expression of the path evaluation function is: ; in, is the path fitness, is the order bias weight, is the operation and maintenance distance weight, M is the number of meters, is the identification order of the mth meter, is the actual operation and maintenance order of the mth meter, is the operation and maintenance distance of the mth meter.

[0013] In a possible implementation, the power terminal equipment safety management and control system based on multi-source data fusion also performs the following processing: obtaining several network abnormality risk coefficients of several electricity meters, and constructing an electricity meter sequence by sorting them from large to small; determining the optimal global operation and maintenance path based on the analysis of the electricity meter sequence, and setting it as the electricity meter operation and maintenance plan.

[0014] In a possible implementation, the power terminal equipment safety management and control system based on multi-source data fusion also performs the following processing: enumerating operation and maintenance paths according to the location coordinates of the several electricity meters to determine multiple global operation and maintenance paths; using the path evaluation function, evaluating the multiple global operation and maintenance paths respectively, and outputting the global operation and maintenance path with the maximum fitness as the optimal global operation and maintenance path.

[0015] The electric power terminal equipment safety management and control system based on multi-source data fusion proposed in this application includes a meter data acquisition module for collecting flow characteristic sequences, meter load sequences, power data sequences, and communication characteristic sequences of several meters in residential areas within a preset time zone; an abnormal risk prediction module for predicting network abnormality risks and outputting several network abnormality risk coefficients; an abnormal meter distribution construction module for determining multiple abnormal meters and constructing abnormal meter distributions; and an electric meter operation and maintenance management module for outputting abnormal concentrations and setting up meter operation and maintenance plans based on abnormal concentrations for meter operation and maintenance management. This solves the technical problems in the prior art of difficulty in accurately and comprehensively monitoring the status of electric power equipment and inability to predict network abnormality risks in advance, resulting in poor efficiency, accuracy, and safety in the management and control of electric power terminal equipment, thereby achieving the technical effect of improving equipment management efficiency, accuracy, and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 Schematic diagram of the structure of the power terminal equipment safety management and control system based on multi-source data fusion provided in an embodiment of the present application.

[0018] Figure 2 A schematic diagram of the execution process of the abnormal risk prediction module in the power terminal equipment safety management and control system based on multi-source data fusion provided in an embodiment of the present application.

[0019] Explanation of the accompanying symbols: meter data collection module 10, abnormal risk prediction module 20, abnormal meter distribution construction module 30, meter operation and maintenance control module 40. DETAILED DESCRIPTION

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0021] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0023] The present application embodiment provides a power terminal equipment security management and control system based on multi-source data fusion, such as Figure 1 As shown, the system includes: The electric meter data collection module 10 is used to collect flow characteristic sequences, electric meter load sequences, power data sequences and communication characteristic sequences of a plurality of electric meters in a residential area within a preset time zone.

[0024] Preferably, the flow characteristic sequence, meter load sequence, power data sequence and communication characteristic sequence of several electricity meters in a residential area within a preset time zone are collected. Specifically, the flow characteristic sequence refers to a sequence formed by chronologically arranging the changes in data flow when the electricity meter interacts with an external system (such as the main station system of the power company) within the preset time zone, mainly including upstream flow and downstream flow, wherein the upstream flow is the flow of data sent by the electricity meter to the main station system, such as the meter readings and equipment status information sent down; the downstream flow is the flow of data sent by the main station system to the electricity meter, such as remote control instructions, parameter configuration information, etc.; by analyzing the flow characteristic sequence, it is possible to understand the activity of the electricity meter's communication with the outside world, the rules of data transmission, and whether there are abnormal data flow fluctuations, and then determine whether the communication of the electricity meter is normal, whether it may be subject to network attacks or there are communication failures.

[0025] Preferably, the meter load sequence refers to a sequence in which the energy consumption of the load equipment connected to the meter (such as various electrical appliances in a house) changes over time within a preset time zone, mainly including information such as the power size, current value, and voltage value of the load. Among them, power is a physical quantity that measures the speed at which the load consumes electrical energy. By monitoring the power changes, the usage of electrical appliances in the house at different time periods can be understood, and whether there are abnormal conditions such as overload and short circuit. Current and voltage are important parameters that reflect the working status of the load. Abnormal current and voltage values ​​may indicate an electrical appliance failure or a line problem. For example, a sudden increase in current may be a short circuit in the appliance, and abnormal voltage fluctuations may affect the normal use of the appliance and the measurement accuracy of the meter.

[0026] Preferably, the power data sequence refers to a sequence formed by chronologically arranging various power-related data recorded by the electric meter within a preset time zone, including active power, reactive power, power factor, etc., wherein active power is the actual electric energy consumed by the user, which is used to measure the total electricity consumption of the user and is the main basis for electricity bill settlement; reactive power reflects the energy exchange between components such as inductance and capacitance in the circuit and the power supply, and has an important impact on the power factor and voltage stability of the power system; power factor is the ratio of active power to apparent power, which reflects the efficiency of electric energy utilization in the power system. A low power factor will lead to increased line loss and reduced equipment utilization. By monitoring the power factor, reactive compensation problems in the power system can be discovered in a timely manner, and the operating efficiency of the power system can be optimized.

[0027] Preferably, the communication characteristic sequence refers to a sequence of various characteristic parameters that change over time during the communication process of the electric meter within a preset time zone, including communication success rate, communication delay, bit error rate, etc., wherein the communication success rate indicates the probability that the electric meter successfully completes a communication task. If the communication success rate is low, it may mean that there is a fault or interference in the communication network, affecting the normal transmission of the electric meter data and the execution of control instructions; communication delay refers to the time interval between sending data and receiving a response. Excessive communication delay may cause data to be updated untimely, affecting the real-time monitoring and scheduling of the power system; the bit error rate refers to the ratio of the number of erroneous code elements to the total number of code elements during the transmission process. A bit error rate that is too high will cause errors in data transmission, resulting in inaccurate information interaction between the electric meter and the master station system, thereby affecting the safe operation and management of the power system.

[0028] The abnormality risk prediction module 20 is used to perform network abnormality risk prediction on the plurality of electricity meters according to the flow feature sequence, the electricity meter load sequence, the power data sequence and the communication feature sequence, and output a plurality of network abnormality risk coefficients.

[0029] Further, such as Figure 2 As shown, the specific configuration of the abnormal risk prediction module 20 also includes collecting sample data to train the feedforward neural network until convergence, and constructing an abnormal risk predictor, wherein the abnormal risk predictor includes K abnormal risk prediction plug-ins, K is an integer greater than 5; randomly selecting a first electricity meter, and obtaining the first flow feature sequence, the first electricity meter load sequence, the first power data sequence and the first communication feature sequence of the first electricity meter, performing feature fluctuation analysis, and determining the first feature fluctuation scale; multiplying the ratio of the first feature fluctuation scale to the historical maximum feature fluctuation scale by K and rounding it up to obtain the number of plug-in selections P; randomly selecting P abnormal risk prediction plug-ins from the K abnormal risk prediction plug-ins, performing network abnormal risk prediction according to the first flow feature sequence, the first electricity meter load sequence, the first power data sequence and the first communication feature sequence, outputting P prediction risk coefficients, calculating the average to obtain the first network abnormal risk coefficient, and adding it to the several network abnormal risk coefficients.

[0030] Preferably, a large amount of meter-related data, including meter flow feature sequences, meter load sequences, power data sequences, and communication feature sequences, is collected from different meters in different time periods as sample data, and a prediction model is constructed based on a feedforward neural network, wherein the feedforward neural network is an artificial neural network model consisting of an input layer, a hidden layer, and an output layer, and information is transmitted unidirectionally from the input layer to the output layer. The prediction model is trained using sample data, and the weights and biases in the network are continuously adjusted so that the output of the network is as close to the actual abnormal risk situation as possible. This process is continued until the performance of the network reaches stability, i.e., convergence, to obtain an abnormal risk predictor, which can predict the network abnormal risk of the meter based on the input meter-related data, wherein the abnormal risk predictor includes K abnormal risk prediction plug-ins, K is an integer greater than 5, and the abnormal risk prediction plug-ins are different prediction sub-models in the predictor, and each plug-in can independently predict the abnormal risk of the meter.

[0031] Preferably, one of the many electricity meters is randomly selected as the first electricity meter, and the first flow characteristic sequence, the first electricity meter load sequence, the first power data sequence and the first communication characteristic sequence of the first electricity meter are obtained, and the changes in various indicators of the electricity meter over a period of time are recorded. Then, characteristic fluctuation analysis is performed on these sequences, that is, the fluctuation of each characteristic sequence over a certain period of time is calculated, for example, the standard deviation, variance and other statistics of each characteristic sequence are calculated to measure the size of the fluctuation. By comprehensively analyzing the fluctuation, the first characteristic fluctuation scale is determined, which reflects the overall fluctuation degree of various characteristics of the electricity meter over a period of time.

[0032] Preferably, the historical maximum characteristic fluctuation scale is the maximum value of the characteristic fluctuation scales of all electricity meters counted through historical data. The first characteristic fluctuation scale is divided by the historical maximum characteristic fluctuation scale to obtain a ratio, and then this ratio is multiplied by K, and the result is rounded to obtain the number of plug-in selections P, so as to dynamically determine how many abnormal risk prediction plug-ins are needed for prediction based on the characteristic fluctuation scale of the first electricity meter. The larger the fluctuation scale, the more plug-ins are selected, that is, the electricity meter with large fluctuation may have more complex abnormal risk situations, and more prediction sub-models are required for prediction.

[0033] Preferably, P plug-ins are randomly selected from the K abnormal risk prediction plug-ins, and the first flow feature sequence, the first meter load sequence, the first power data sequence and the first communication feature sequence of the first meter are input into the selected P abnormal risk prediction plug-ins. Each plug-in performs network abnormal risk prediction based on the input data and outputs a predicted risk coefficient. These P predicted risk coefficients are added together and then divided by P to obtain the mean as the first network abnormal risk coefficient. Finally, the first network abnormal risk coefficient is added to several network abnormal risk coefficients for abnormal meter analysis and operation and maintenance control, etc., thereby ensuring the safety of power terminal equipment.

[0034] Furthermore, the specific configuration of the abnormal risk prediction module 20 also includes performing characteristic fluctuation analysis on the first flow feature sequence, the first meter load sequence, the first power data sequence and the first communication feature sequence, and outputting multiple characteristic fluctuation coefficients, wherein the characteristic fluctuation coefficient is the ratio of the characteristic standard deviation to the characteristic mean; and performing weighted fusion on the multiple characteristic fluctuation coefficients to obtain the first characteristic fluctuation scale.

[0035] Preferably, the flow characteristic sequence may record the electricity flow data of the meter at different times, such as the hourly and minute-by-minute changes in electricity usage. A characteristic fluctuation analysis is performed on it, that is, first calculating the mean of all the data in the sequence, that is, the average flow value, and then calculating the standard deviation of the sequence to reflect the degree of dispersion of the data relative to the mean, that is, the fluctuation of the flow data. The characteristic fluctuation coefficient is the ratio of the characteristic standard deviation to the characteristic mean, which can eliminate the influence of the data dimension and more intuitively reflect the relative fluctuation of the flow data. The meter load sequence records the changes in the load carried by the meter, such as the total power of electrical equipment at different time points. Similarly, a characteristic fluctuation analysis is performed on it, that is, first calculating the mean of the sequence to obtain the average load, then calculating the standard deviation, and finally obtaining the characteristic fluctuation coefficient, which reflects the relative fluctuation of the meter load. If the coefficient is large, it indicates that the load changes are more drastic, and there may be frequent starting and stopping of electrical equipment or the connection of high-power equipment.

[0036] Preferably, the power data sequence includes more comprehensive power-related information, such as voltage, current, and power factor. This is then subjected to characteristic fluctuation analysis. Specifically, the mean and standard deviation of each specific power data subsequence (e.g., voltage sequence, current sequence, etc.) are calculated to obtain a characteristic fluctuation coefficient, thereby understanding the relative degree of fluctuation of each power parameter. The communication characteristic sequence records relevant data related to the meter's communication with the outside world, such as communication frequency, communication packet size, and communication success rate. By calculating its characteristic fluctuation coefficient, the stability of the meter's communication can be understood. A large fluctuation coefficient of the communication characteristic indicates unstable communication with the meter, such as intermittent communication signal strength and high packet loss rate, which may affect the normal transmission of power data and remote monitoring of the equipment.

[0037] Preferably, different characteristic fluctuation coefficients may have different degrees of influence on the overall abnormal risk of the electricity meter. For example, certain parameters in the power data sequence (such as voltage fluctuation) may have a greater impact on the safe operation of the electricity meter, while the fluctuation of the communication characteristic sequence has a relatively small impact on the safety of the electricity meter itself. Then, by analyzing the correlation between different characteristics in the historical data and the abnormal conditions of the electricity meter, the weights are determined and the weighted fusion of each characteristic fluctuation coefficient is performed to obtain the first characteristic fluctuation scale, which comprehensively reflects the overall characteristic fluctuation of the electricity meter in multiple aspects such as flow, load, power data and communication, and is used to measure the stability of the electricity meter's operating status and the potential degree of abnormal risk. If the first characteristic fluctuation scale is large, it means that the operating status of the electricity meter in multiple aspects has large fluctuations, and there may be a high abnormal risk.

[0038] The abnormal electricity meter distribution construction module 30 is configured to determine a plurality of abnormal electricity meters according to the plurality of network abnormality risk coefficients and construct an abnormal electricity meter distribution.

[0039] Furthermore, the specific configuration of the abnormal meter distribution construction module 30 also includes screening the several network abnormality risk coefficients according to a preset risk threshold, determining multiple abnormal meters, and multiple abnormal meter location coordinates; and constructing an abnormal meter distribution based on the multiple abnormal meter location coordinates.

[0040] Preferably, a plurality of network anomaly risk coefficients are screened according to a preset risk threshold, wherein the preset risk threshold is a standard value determined comprehensively based on the operating experience of the power system, safety standards, and analysis of historical data. For example, by statistically analyzing the network anomaly risk coefficients of a large number of normally operating electricity meters, the distribution range of the risk coefficients under normal circumstances is obtained, which is used to determine whether the network anomaly risk level of the electricity meter exceeds the normal range; then, the plurality of network anomaly risk coefficients are compared with the preset risk threshold. If the network anomaly risk coefficient of a certain electricity meter is greater than or equal to the preset risk threshold, the electricity meter is determined to be an abnormal electricity meter, that is, the electricity meter that may have a network anomaly risk is screened out from all the electricity meters; each electricity meter has its corresponding location information, which is usually expressed in the form of coordinates (For example, the specific geographical location of a residential area or the node location in the power network, etc.), if a certain meter is determined to be an abnormal meter, its location coordinates can be obtained so that the distribution of abnormal meters can be analyzed and displayed; then, based on the location coordinates of multiple abnormal meters, they are marked and visualized in the geographic information system (GIS). For example, the location of the abnormal meter is represented on the map with a specific symbol (such as a red dot) to intuitively see the distribution of abnormal meters in the residential area or the entire power system, thereby forming an abnormal meter distribution, which helps power operation and maintenance personnel quickly understand the spatial distribution characteristics of abnormal meters, so as to reasonably arrange maintenance personnel and resources, give priority to checking and processing areas where abnormalities are concentrated, improve operation and maintenance efficiency, and ensure the safe and stable operation of the power system.

[0041] The electric meter operation and maintenance control module 40 is used to perform concentration analysis based on the abnormal electric meter distribution, output abnormal concentration, and set an electric meter operation and maintenance plan according to the abnormal concentration to perform electric meter operation and maintenance control.

[0042] Preferably, a concentration analysis is performed based on the distribution of abnormal meters. This involves quantitatively analyzing the spatial distribution of abnormal meters, such as calculating the distance relationship and degree of clustering between abnormal meters, to assess the concentration of abnormal meters. This results in an abnormal concentration index, which represents the degree of spatial concentration of abnormal meters. A high abnormal concentration index indicates that abnormal meters are primarily concentrated in a few areas, exhibiting a clear clustering phenomenon. Conversely, a low abnormal concentration index indicates that abnormal meters are relatively dispersed across different areas.

[0043] Preferably, the meter operation and maintenance plan is then set up and meter operation and maintenance management is carried out according to the abnormal concentration. When the abnormal concentration is high, the operation and maintenance plan should focus on the concentrated areas, including the centralized deployment of more operation and maintenance personnel and resources to these areas for comprehensive and in-depth inspection and repair. For example, detailed inspections of power lines, transformers and other equipment in concentrated areas are carried out to check whether there are line aging, short circuits, overloads, etc. For situations with low abnormal concentration, the operation and maintenance plan may focus more on comprehensive coverage and remote monitoring, that is, first collect and analyze real-time data of each abnormal meter through remote monitoring, preliminarily judge the nature and severity of the problem, and then, according to the specific situation, dispatch operation and maintenance personnel to some key or more serious locations for on-site processing, and at the same time, conduct regular inspections of other scattered abnormal meters.

[0044] Preferably, according to the operation and maintenance plan, an operation and maintenance work order is created for each abnormal meter or area that needs to be handled, and the operation and maintenance tasks, responsible personnel, time requirements and other information are clearly defined. The operation and maintenance work is tracked and managed through the work order system to ensure that each problem is handled in a timely and effective manner; the quality of the operation and maintenance work is controlled and supervised to ensure that the operation and maintenance personnel operate in accordance with the prescribed procedures and standards. For example, after the maintenance is completed, the maintenance effect is inspected to check whether the abnormal meter has resumed normal operation and whether the relevant indicators meet the standard requirements; various data of the operation and maintenance process are recorded in detail, including the specific problems of the abnormal meter, maintenance measures, data changes before and after maintenance, etc. By analyzing these data, lessons learned are summarized and the operation and maintenance plan is improved.

[0045] Furthermore, the specific configuration of the meter operation and maintenance control module 40 also includes performing meter distribution dispersion evaluation on the abnormal meter distribution and outputting meter distribution dispersion; and taking the inverse of the meter distribution dispersion as the abnormal concentration.

[0046] Preferably, the distribution of abnormal electricity meters is evaluated for meter distribution dispersion. Specifically, the average distance between each abnormal electricity meter and other abnormal electricity meters is calculated to measure the dispersion. If the average distance is large, the dispersion is high, indicating that the electricity meters are distributed more dispersedly. Dispersion and concentration are two opposite aspects that describe the same phenomenon (spatial distribution characteristics of abnormal electricity meters). Dispersion measures the degree of dispersion, while concentration measures the degree of concentration. When the dispersion is high, it means that the electricity meters are distributed dispersedly and their concentration is low. The inverse of the dispersion is then used to represent the abnormal concentration.

[0047] Furthermore, the specific configuration of the electricity meter operation and maintenance control module 40 also includes: if the abnormal concentration is less than or equal to the preset concentration threshold, a local operation and maintenance strategy is set, and an electricity meter operation and maintenance plan is set based on the local operation and maintenance strategy; if the abnormal concentration is greater than the preset concentration threshold, a global operation and maintenance strategy is set, and an electricity meter operation and maintenance plan is set based on the global operation and maintenance strategy.

[0048] Preferably, the preset concentration threshold is a standard value determined based on the actual operating conditions of the power system, historical data, and the configuration of operation and maintenance resources, and is used to classify abnormal concentration situations into different categories so as to adopt different operation and maintenance strategies. Specifically, if the abnormal concentration is less than or equal to the preset concentration threshold, it means that the distribution of abnormal meters is relatively dispersed, and no large-scale concentrated abnormal area has been formed. At this time, a local operation and maintenance strategy is adopted, that is, the operation and maintenance focus is placed on the local area where each dispersed abnormal meter is located, rather than performing large-scale operation and maintenance operations on the entire power system. This allows for more targeted handling of abnormal situations, improved operation and maintenance efficiency, and avoidance of waste of resources. Then, based on the local operation and maintenance strategy, the meter operation and maintenance plan is set up, including determining the key local operation and maintenance areas according to the location coordinates of the abnormal meters, that is, a smaller area where abnormal meters are relatively concentrated, such as the power substation of a certain community or a certain street; for each key operation and maintenance area, reasonably deploy resources such as operation and maintenance personnel, tools and equipment; formulate operation and maintenance processes such as detection, fault diagnosis, repair or replacement of abnormal meters, and collect the operating data and status information of abnormal meters in a timely manner, and establish a feedback mechanism to adjust and optimize the operation and maintenance plan.

[0049] Preferably, if the abnormal concentration is greater than the preset concentration threshold, it indicates that the abnormal meters are highly concentrated in space, and there may be systemic problems that affect the operation of meters in a large range. At this time, a global operation and maintenance strategy is adopted to conduct comprehensive inspection and maintenance of all links in the power system to ensure the safety and reliability of the system. Then, the meter operation and maintenance plan is set based on the global operation and maintenance strategy. Specifically, a comprehensive assessment is conducted on the entire power system, including power generation, transmission, transformation, distribution and other links, to analyze the possible causes of the concentrated occurrence of abnormal meters, such as power grid failure, aging of power equipment, external environmental impact, etc.; operation and maintenance resources are coordinated and allocated on a global scale, including human, material and financial resources, to ensure that there are sufficient forces to deal with large-scale abnormal situations; a systematic meter operation and maintenance plan is formulated, including comprehensive inspection of power equipment, line inspection, meter detection and calibration, etc.; a comprehensive assessment of the risks that may arise during the operation and maintenance process is conducted, and corresponding emergency plans are formulated to ensure the safe and stable operation of the power system.

[0050] Furthermore, the specific configuration of the electricity meter operation and maintenance control module 40 also includes obtaining multiple network abnormality risk coefficients of the multiple abnormal electricity meters, and sorting them from large to small to construct an abnormal electricity meter sequence, wherein each abnormal electricity meter has an order identifier; enumerating operation and maintenance paths according to the location coordinates of the multiple abnormal electricity meters, and determining multiple local operation and maintenance paths; constructing a path evaluation function with the goal of minimizing the operation and maintenance distance and minimizing the operation and maintenance order deviation; using the path evaluation function, respectively evaluating the multiple local operation and maintenance paths, and outputting the local operation and maintenance path with the maximum path fitness as the electricity meter operation and maintenance plan.

[0051] Furthermore, the specific configuration of the electric meter operation and maintenance control module 40 also includes the expression of the path evaluation function: ; in, is the path fitness, is the order bias weight, is the operation and maintenance distance weight, M is the number of meters, is the identification order of the mth meter, is the actual operation and maintenance order of the mth meter, is the operation and maintenance distance of the mth meter.

[0052] Preferably, network anomaly risk coefficients corresponding to multiple abnormal meters are obtained. The larger the value, the higher the abnormal risk of the meter. The obtained multiple network anomaly risk coefficients are sorted from largest to smallest, and meters with higher abnormal risks are processed first. Based on the sorting results of the network anomaly risk coefficients, a sequence of abnormal meters is formed, and each abnormal meter is assigned an order identifier to indicate its position in the sequence. For example, the abnormal meter ranked first has the largest network anomaly risk coefficient and an order identifier of 1; the abnormal meter ranked second has an order identifier of 2, and so on. Then, based on the location coordinates of the abnormal meters, all possible operation and maintenance paths are enumerated to obtain multiple local operation and maintenance paths, that is, operation and maintenance paths within a relatively small area (such as a community or a block).

[0053] Preferably, a path evaluation function is constructed with the goal of minimizing the operation and maintenance distance and minimizing the operation and maintenance order deviation, wherein the operation and maintenance distance refers to the total distance traveled by the operation and maintenance personnel along the operation and maintenance path when performing the operation and maintenance tasks. The operation and maintenance distance is minimized to reduce the time and cost consumption in the operation and maintenance process and improve the operation and maintenance efficiency; the operation and maintenance order deviation refers to the difference between the access order of abnormal meters in the actual operation and maintenance path and the order in the abnormal meter sequence (sorted from large to small according to the network abnormality risk coefficient). The operation and maintenance order deviation is minimized to give priority to processing meters with higher abnormal risks, ensuring that problems with greater impact on the power system are resolved in a timely manner.

[0054] Preferably, the path evaluation function is constructed with the goal of minimizing the operation and maintenance distance and minimizing the operation and maintenance order deviation. , used to evaluate and score each operation and maintenance path. The higher the score, the more the path meets the target requirements. is the path fitness, is the order bias weight, is the operation and maintenance distance weight, M is the number of meters, is the identification order of the mth meter, is the actual operation and maintenance order of the mth meter, is the maintenance distance of the mth meter. Finally, multiple local maintenance paths are input into the path evaluation function, and the evaluation score of each local maintenance path, namely the path fitness, is calculated. This score reflects the degree to which each path satisfies the requirements of minimizing the maintenance distance and minimizing the deviation in the maintenance order. Then, all path fitnesses are compared to determine the local maintenance path with the highest path fitness. This path is then determined as the meter maintenance plan. The maintenance personnel then perform maintenance operations on abnormal meters in sequence according to the path determined by the plan. This improves maintenance efficiency, prioritizes high-risk meters, and ensures the safe and stable operation of the power system.

[0055] Furthermore, the specific configuration of the meter operation and maintenance control module 40 also includes obtaining several network abnormality risk coefficients of several meters, and constructing a meter sequence by sorting them from large to small; determining the optimal global operation and maintenance path based on the meter sequence analysis, and setting it as the meter operation and maintenance plan.

[0056] Preferably, network anomaly risk coefficients corresponding to multiple abnormal meters are obtained, and the obtained multiple network anomaly risk coefficients are arranged in order from large to small, and then meters with higher abnormal risks are processed first. According to the sorting results of the network anomaly risk coefficients, an abnormal meter sequence is formed, and then based on the meter sequence, the distribution location of the meters, the distance between each other, and the actual needs of operation and maintenance, a reasonable sequence and path are found to ensure that the operation and maintenance work is carried out efficiently and orderly, and then the optimal global operation and maintenance path is found from all possible operation and maintenance paths, specifically including the shortest total distance to reduce time and cost consumption; completing the operation and maintenance work of all meters in the shortest time to improve operation and maintenance efficiency; meeting the requirements of giving priority to high-risk meters to the greatest extent to ensure the safety of the power system; determining the optimal balance point of these goals; finally, the optimal global operation and maintenance path is set as the meter operation and maintenance plan, and according to the path and sequence determined by this plan, the meters in the meter sequence are operated and maintained in turn, thereby improving the efficiency of operation and maintenance work, ensuring that high-risk meters are handled in a timely manner, and ensuring the safe and stable operation of the power system.

[0057] Furthermore, the specific configuration of the electricity meter operation and maintenance control module 40 also includes enumerating operation and maintenance paths according to the location coordinates of the several electricity meters to determine multiple global operation and maintenance paths; using the path evaluation function to evaluate the multiple global operation and maintenance paths respectively, and outputting the global operation and maintenance path with the maximum fitness as the optimal global operation and maintenance path.

[0058] Preferably, all possible operation and maintenance paths are enumerated based on the location coordinates of the electricity meters, that is, the routes for accessing each electricity meter in a certain order to perform operation and maintenance operations. For example, assuming there are three electricity meters A, B, and C, there are six possible operation and maintenance paths: ABC, ACB, BAC, BCA, CAB, and CBA. In actual situations, the number of electricity meters is greater and the path combinations are more complex. By enumerating all possible paths, all potential operation and maintenance path options can be obtained; then, paths that meet the global operation and maintenance requirements are screened out to obtain multiple global operation and maintenance paths. Each global operation and maintenance path is substituted into the path evaluation function, and the evaluation score of the path, i.e., the path fitness, is obtained through calculation of the function; finally, the path fitness of all global operation and maintenance paths is compared, and the path with the largest fitness is found, which is determined as the optimal global operation and maintenance path. The electricity meters are then operated and maintained in the order of the paths to achieve efficient meter operation and maintenance management and ensure the safe and stable operation of the power system.

[0059] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0060] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. The power terminal equipment safety management and control system based on multi-source data fusion is characterized by: The power terminal equipment safety management and control system includes: The electric meter data acquisition module is used to collect flow characteristic sequences, electric meter load sequences, power data sequences and communication characteristic sequences of several electric meters in residential areas within a preset time zone; an abnormality risk prediction module, configured to perform network abnormality risk prediction on each of the plurality of electricity meters based on the flow characteristic sequence, the electricity meter load sequence, the power data sequence, and the communication characteristic sequence, and output a plurality of network abnormality risk coefficients; An abnormal electricity meter distribution construction module is used to determine a plurality of abnormal electricity meters according to the plurality of network abnormality risk coefficients and construct an abnormal electricity meter distribution; The electric meter operation and maintenance control module is used to perform concentration analysis based on the abnormal electric meter distribution, output abnormal concentration, and set an electric meter operation and maintenance plan according to the abnormal concentration to perform electric meter operation and maintenance control.

2. The power terminal equipment safety management and control system based on multi-source data fusion according to claim 1 is characterized in that: The steps performed by the abnormal risk prediction module include: Collecting sample data to train a feedforward neural network until convergence, and constructing an abnormality risk predictor, wherein the abnormality risk predictor includes K abnormality risk prediction plug-ins, where K is an integer greater than 5; Randomly selecting a first electricity meter, obtaining a first flow characteristic sequence, a first electricity meter load sequence, a first power data sequence, and a first communication characteristic sequence of the first electricity meter, performing characteristic fluctuation analysis, and determining a first characteristic fluctuation scale; The ratio of the first characteristic fluctuation scale to the historical maximum characteristic fluctuation scale is multiplied by K and rounded to the integer to obtain the number of plug-in selections P; P abnormal risk prediction plug-ins are randomly selected from the K abnormal risk prediction plug-ins, and network abnormal risk prediction is performed according to the first traffic feature sequence, the first meter load sequence, the first power data sequence and the first communication feature sequence. P prediction risk coefficients are output, and the first network abnormal risk coefficient is obtained by averaging and added to the plurality of network abnormal risk coefficients.

3. The power terminal equipment safety management and control system based on multi-source data fusion according to claim 2 is characterized in that: The steps performed by the abnormal risk prediction module include: Performing characteristic fluctuation analysis on the first flow characteristic sequence, the first electric meter load sequence, the first power data sequence, and the first communication characteristic sequence, respectively, and outputting a plurality of characteristic fluctuation coefficients, wherein the characteristic fluctuation coefficient is a ratio of a characteristic standard deviation to a characteristic mean; The plurality of characteristic fluctuation coefficients are weightedly integrated to obtain the first characteristic fluctuation scale.

4. The power terminal equipment safety management and control system based on multi-source data fusion according to claim 1 is characterized in that: The steps performed by the abnormal meter distribution construction module include: Screening the plurality of network abnormality risk coefficients according to a preset risk threshold, determining a plurality of abnormal electricity meters and a plurality of abnormal electricity meter location coordinates; An abnormal electricity meter distribution is constructed according to the plurality of abnormal electricity meter location coordinates.

5. The power terminal equipment safety management and control system based on multi-source data fusion according to claim 1 is characterized in that: The steps performed by the meter operation and maintenance control module include: Performing meter distribution dispersion evaluation on the abnormal meter distribution and outputting meter distribution dispersion; The inverse of the meter distribution dispersion is taken as the abnormal concentration.

6. The power terminal equipment safety management and control system based on multi-source data fusion according to claim 1 is characterized in that: The steps performed by the meter operation and maintenance control module include: If the abnormal concentration is less than or equal to a preset concentration threshold, setting a local operation and maintenance strategy, and setting an electric meter operation and maintenance plan based on the local operation and maintenance strategy; If the abnormal concentration is greater than a preset concentration threshold, a global operation and maintenance strategy is set, and an electric meter operation and maintenance plan is set based on the global operation and maintenance strategy.

7. The power terminal equipment safety management and control system based on multi-source data fusion according to claim 6 is characterized in that: The steps performed by the meter operation and maintenance control module include: Acquire multiple network abnormality risk coefficients of the multiple abnormal electricity meters, sort them from large to small, and construct an abnormal electricity meter sequence, wherein each abnormal electricity meter has a sequence identifier; Enumerate operation and maintenance paths based on the coordinates of multiple abnormal meter locations and determine multiple local operation and maintenance paths; With the goal of minimizing the operation and maintenance distance and minimizing the operation and maintenance order deviation, a path evaluation function is constructed; The path evaluation function is used to evaluate the multiple local operation and maintenance paths respectively, and the local operation and maintenance path with the maximum path fitness is output as the meter operation and maintenance plan.

8. The power terminal equipment safety management and control system based on multi-source data fusion according to claim 7 is characterized in that: The expression of the path evaluation function is: ； in, is the path fitness, is the order bias weight, is the operation and maintenance distance weight, M is the number of meters, is the identification order of the mth meter, is the actual operation and maintenance order of the mth meter, is the operation and maintenance distance of the mth meter.

9. The power terminal equipment safety management and control system based on multi-source data fusion according to claim 8 is characterized in that: The steps performed by the meter operation and maintenance control module include: Obtain several network anomaly risk coefficients of several electricity meters and construct an electricity meter sequence by sorting them from largest to smallest; An optimal global operation and maintenance path is determined based on the meter sequence analysis and is set as the meter operation and maintenance plan.

10. The power terminal equipment safety management and control system based on multi-source data fusion according to claim 9 is characterized in that: The steps performed by the meter operation and maintenance control module include: Enumerating operation and maintenance paths according to the location coordinates of the plurality of electricity meters to determine a plurality of global operation and maintenance paths; The path evaluation function is used to evaluate the multiple global operation and maintenance paths respectively, and the global operation and maintenance path with the maximum fitness is output as the optimal global operation and maintenance path.

Images