Abnormal power consumption behavior real-time monitoring and positioning method and system

Abstract

The invention relates to the technical field of intelligent power grids, and discloses an abnormal power consumption behavior real-time monitoring and positioning method and system, and the method comprises the steps: carrying out the transformation of an existing collection device at an edge end, achieving the serial communication with the edge collection device, and carrying out the dynamic adjustment according to the collection condition and business demands of a transformer area, and forming a new collection strategy; clustering the electricity meters by using a Pearson's correlation coefficient and a DBSCAN clustering algorithm, dividing electricity meter clusters, and calculating the load condition of each cluster; according to the load condition and the acquisition weight of the electric meter cluster, the acquisition sequence and the acquisition frequency are adjusted, and the acquisition strategy is iterated and optimized periodically; and monitoring ammeter data in real time, identifying an abnormal electricity consumption behavior, and outputting an abnormal prompt. According to the invention, the algorithm is built in the edge computing platform through the big data algorithm analysis of the historical power consumption behaviors of the user, so that the dependence on manual judgment is effectively reduced, and the automation degree in the abnormal power consumption behavior monitoring, analyzing and processing process is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and in particular to a method and system for real-time monitoring and positioning of abnormal electricity consumption behavior. Background Art

[0002] In the power system, with the continuous advancement of science and technology and the widespread application of electrical equipment, power safety and power management have become the focus of attention from all walks of life. Especially in smart homes, industrial automation and daily life, the number and types of electrical equipment have grown exponentially, which has not only greatly improved the convenience of production and life, but also brought new challenges to power supply and use management. Abnormal power consumption behaviors, such as power theft, leakage, overload power consumption, etc., not only threaten the safe and stable operation of the power system, but also seriously interfere with the market order and bring huge economic losses to the country and society. Therefore, it is particularly important to develop efficient and accurate abnormal power consumption behavior detection solutions.

[0003] Electrical safety is an important part of ensuring people's life and production safety. With the popularization of electrical equipment and the continuous increase in electricity consumption, the demand for electrical safety testing is becoming increasingly urgent. Traditional electrical safety testing methods are often based on manual judgment and empirical analysis, and have problems such as high blindness, huge time consumption, and high misjudgment rate. Therefore, it is necessary to introduce new technologies and new methods to improve the efficiency and accuracy of electrical safety testing.

[0004] In the era of big data, data information in various industries is growing explosively. Through big data analysis and mining technology, the laws of users' electricity consumption behavior can be revealed and abnormal electricity consumption behavior can be discovered. However, traditional statistical methods are difficult to deeply mine the information behind the data, resulting in frequent "data disasters" and "data waste". Therefore, it is necessary to use advanced data analysis technology to improve data utilization and provide strong support for abnormal electricity consumption behavior monitoring.

[0005] The development of Internet of Things technology has provided new ideas for electrical safety detection. Through the sensor network, the operating status of electrical equipment, such as power, voltage, current and other parameters, can be monitored in real time, and the data can be transmitted to the monitoring center in real time. Combined with artificial intelligence technology, electrical equipment can be intelligently identified and faults can be predicted to discover potential safety hazards in advance. In addition, artificial intelligence technology can also analyze and process massive electricity consumption data, build abnormal electricity consumption behavior detection models, and improve the accuracy and efficiency of detection.

[0006] As machine learning technology continues to mature, its application in abnormal power consumption behavior detection is becoming more and more widespread. By collecting power consumption data from users' homes or businesses and using machine learning algorithms to preprocess, extract features, and train models, efficient abnormal power consumption detection models can be built. These models can automatically analyze the characteristics of users' power consumption behavior and identify abnormal power consumption patterns. Summary of the invention

[0007] In view of the above existing problems, the present invention is proposed.

[0008] Therefore, the present invention provides a method for real-time monitoring and positioning of abnormal electricity usage behavior, and proposes a solution of adopting different collection strategies for different users and electricity-consuming equipment according to different weights. By distinguishing the collection strategies of different users, the problems of limited data collection scope, insufficient algorithm accuracy, and poor algorithm adaptability in existing algorithms are effectively solved; at the same time, it is proposed to delegate the data processing and analysis links to the edge side, disperse the pressure of data processing and analysis, efficiently and accurately extract information related to abnormal electricity usage behavior, and greatly improve the problems of insufficient data processing capabilities, poor real-time monitoring, and slow response speed in existing algorithms; and, through the big data algorithm analysis of users' historical electricity usage behaviors, the present invention embeds the algorithm into the edge computing platform, effectively reducing the reliance on manual judgment, improving the degree of automation in the abnormal electricity usage behavior monitoring and analysis process, and reducing the requirements for the professional quality of personnel in the process.

[0009] To solve the above technical problems, the present invention provides the following technical solutions: a real-time monitoring and positioning method for abnormal electricity consumption behavior, comprising: modifying the existing collection equipment at the edge, installing an independent monitoring device, and realizing serial communication with the edge collection equipment; dynamically adjusting the collection data items and the collection frequency according to the collection situation of the substation and business needs, and forming a new collection strategy; clustering the electric meters using the Pearson correlation coefficient and the DBSCAN clustering algorithm, dividing the electric meters into clusters, and calculating the load situation of each cluster; adjusting the collection sequence and the collection frequency according to the load situation and collection weight of the electric meter cluster, and periodically iterating and optimizing the collection strategy; real-time monitoring of the zero-to-live current ratio and the power data of the electric meter, identifying abnormal electricity consumption behavior, focusing on monitoring the electric meters with continuous abnormal electricity consumption, and outputting abnormal reminders.

[0010] As a preferred solution of the method for real-time monitoring and positioning of abnormal electricity usage behavior described in the present invention, the implementation of serial port communication with the edge acquisition device includes: the edge monitoring device initiates a request for adjustment of the acquisition strategy configuration to the edge acquisition, and after the edge acquisition device obtains the new acquisition strategy, it collects the user's meter data according to the new acquisition strategy, and the data collected by the new acquisition strategy is synchronized to the edge monitoring device. The edge acquisition device determines whether the collection strategy needs to be updated, and monitors the abnormal electricity usage behavior in real time based on the collected data.

[0011] As a preferred solution of the method for real-time monitoring and positioning of abnormal electricity consumption behavior described in the present invention, wherein: the collection strategy includes a triple sequence of electric meters, collection data items and collection frequencies, expressed as [<electric meter 1, collection data items, collection frequency>, <electric meter 2, collection data items, collection frequency>, <electric meter..., collection data items, collection frequency>, <electric meter n, collection data items, collection frequency>]; the sequence length n is the number of electric meters covered by the edge collection device, and each different electric meter is identified by the electric meter communication address; the collection data items are electric meter-related electrical data, including voltage, electricity, live current, neutral current, power, power factor and other data; the collection frequency is the frequency of the electric meter collection, and the optional range includes 24 points / day, 48 points / day, and 96 points / day; the edge collection device executes the collection strategy in sequence. In the actual collection process, the collection data items and collection frequencies can be adjusted in sections according to the collection situation of the substation and the business requirements, so that the collection situation of the substation and the business requirements are mutually adapted.

[0012] As a preferred solution of the method for real-time monitoring and positioning of abnormal electricity consumption behavior described in the present invention, wherein: the calculation of the load conditions of each cluster includes obtaining the collected voltage data, collecting the voltage data, for each electric meter, collecting the voltage readings within a period of time, performing data cleaning, processing missing values ​​and abnormal values, ensuring the integrity and accuracy of the data, dividing into multiple independent electric meter clusters according to the density clustering process, calculating the Pearson correlation coefficient, and constructing a distance matrix; The DBSCAN clustering algorithm determines the neighborhood size eps and the minimum number of samples min_samples required to form a dense area, and clusters the electricity meters using the DBSCAN algorithm and the distance matrix. When the number of points in the eps neighborhood reaches min_samples, a new cluster is created and the current point is added to the cluster. The points in the eps neighborhood of each point in the cluster are recursively added to the cluster until no new points can be added.

[0013] As a preferred solution of the method for real-time monitoring and positioning of abnormal electricity consumption behavior described in the present invention, the iterating and optimizing the collection strategy includes calculating the load condition of each meter cluster based on the collected electricity data according to the calculated meter cluster, normalizing the load condition by using the maximum and minimum value normalization method, and using the normalized result as the collection weight for collection sorting: The maximum and minimum normalization formulas are as follows: , Among them is Normalized results of each cluster load, is the load condition of each cluster, is the maximum load of each cluster, is the minimum load value of each cluster; Adjust the collection sequence so that the meters in the same cluster are in a similar collection order, and according to the collection weight, put the collection order of the cluster with a high weight at the beginning of the collection sequence; According to the data collection situation in the substation, adjust the data collection frequency of each meter. The maximum value of the adjustment range is the highest frequency that the substation can complete the data collection, and the minimum value is the lowest frequency required for abnormal monitoring. Repeat the above process periodically, randomly repeating according to 300-500 valid points.

[0014] As a preferred solution of the method for real-time monitoring and positioning of abnormal electricity consumption behavior described in the present invention, wherein: the identification of abnormal electricity consumption behavior includes comparing the zero-live current collected by the electric meter, when the ratio of the zero-live current collected by the electric meter for one consecutive hour exceeds a preset interval, or abnormal data appears for 4 hours cumulatively within 24 hours, the abnormal data is allowed to appear discontinuously, that is, the zero-live current of the electric meter is output to be abnormal; When an electric meter has abnormal current, the current meter collection weight is increased to 1, the current meter is collected with the highest priority, and the collection frequency is appropriately increased to focus on monitoring the meter. After the abnormal power consumption continues, the abnormal reminder is continuously output; The electricity data collected within 6 hours is used to conduct a rolling comparison of the Pearson correlation between the electricity data collected by the meter and the line loss data in the substation.

[0015] Another object of the present invention is to provide a real-time monitoring and positioning system for abnormal electricity usage behavior, which can monitor electricity usage behavior in real time, detect abnormal situations in a timely manner, and respond quickly, thereby improving the timeliness of power system monitoring.

[0016] As a preferred solution of the method for real-time monitoring and positioning of abnormal power consumption behavior described in the present invention, it includes: an edge acquisition device transformation module 100, an acquisition strategy configuration and adjustment module 200, a data processing and analysis module 300, an acquisition sequence optimization module 400, an abnormal monitoring and response module 500, a communication and data synchronization module 600, and a data storage and management module 700; The edge acquisition device transformation module 100 implements device upgrades and supports data synchronization and policy adjustments; The acquisition strategy configuration and adjustment module 200 dynamically sets acquisition parameters to adapt to different monitoring requirements; The data processing and analysis module 300 cleans, analyzes and clusters data to identify meter clusters and load conditions; The acquisition sequence optimization module 400 optimizes the acquisition sequence and frequency to improve monitoring efficiency; The abnormal monitoring and response module 500 monitors abnormal power consumption behavior, issues warnings and provides guidance on handling; The communication and data synchronization module 600 ensures real-time data transmission between devices; The data storage and management module 700 stores and manages monitoring data and supports historical query.

[0017] As a preferred solution of the real-time monitoring and positioning system for abnormal power consumption behavior described in the present invention, the modified edge acquisition device is connected to the edge monitoring device through serial communication, and the communication and data synchronization module is responsible for real-time transmission and synchronization of data; The collection strategy configuration and adjustment module generates new collection strategies based on the collection situation in the substation and business needs, and sends them to the edge collection devices through the communication and data synchronization module; The edge acquisition device collects meter data according to the new acquisition strategy. The data processing and analysis module receives the data, cleans it, calculates the Pearson correlation coefficient, builds a distance matrix, and applies the DBSCAN clustering algorithm to cluster the meters. The collection sequence optimization module adjusts the collection sequence and frequency and optimizes the collection strategy according to the meter cluster load and collection weight provided by the data processing and analysis module; The abnormal monitoring and response module receives the meter data provided by the edge acquisition device in real time, monitors the zero-live current ratio and power data, identifies abnormal power consumption behavior, and outputs abnormal reminders; The data storage and management module is responsible for storing the data received from the edge acquisition device, the clustering results of the data processing and analysis module, the policy adjustment records of the acquisition sequence optimization module, and the anomaly records of the anomaly monitoring and response module for subsequent analysis and historical query.

[0018] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, steps of a method for real-time monitoring and positioning of abnormal power consumption behavior are implemented.

[0019] A computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of a method for real-time monitoring and positioning of abnormal electricity consumption behavior.

[0020] Beneficial effects of the present invention: The monitoring method proposed in the present invention can intelligently adjust the key monitoring objects according to the actual load conditions of the substation, and can locate abnormal electricity consumption in the substation more quickly and accurately. At present, due to the complex situation of the substation, the number of substations where all electric meters can achieve high-frequency data collection is limited, and higher-frequency data collection cannot be achieved due to the limited bandwidth of the channel at the edge of the substation. Therefore, by adding personalized data collection items and collection frequencies to different electric meters, high-frequency monitoring of key users and low-frequency monitoring of non-key users can be carried out, which greatly reduces the dependence on the quality of substation collection, and can achieve higher-quality monitoring in substations with relatively poor collection quality. At the same time, the accuracy of the algorithm is further improved based on relatively higher-quality monitoring.

[0021] At the same time, the edge-side data analysis solution proposed in the present invention can advance data collection, analysis and processing to the edge. Compared with the traditional solution of transmitting data to the main station side and then uniformly calculating and analyzing, the solution proposed in the present invention greatly reduces the communication burden between the main station and the substation side. At the same time, the edge-side processing also eliminates the intermediate transmission link compared to returning to the main station for processing, ultimately greatly improving the system response speed.

[0022] Finally, the automatic detection and reporting solution at the edge proposed in the present invention can quickly locate abnormal power usage behavior without human intervention, reducing the workload of manual on-site investigation and disposal of abnormal power usage behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 A flowchart of a method for real-time monitoring and locating abnormal electricity usage behavior provided by an embodiment of the present invention.

[0024] Figure 2 A schematic diagram of the modification of existing data collection equipment for a method for real-time monitoring and positioning of abnormal electricity usage behavior provided by an embodiment of the present invention.

[0025] Figure 3 A collection strategy system topology diagram of a method for real-time monitoring and positioning of abnormal electricity usage behavior provided by an embodiment of the present invention.

[0026] Figure 4 A flow chart of acquisition strategy iteration steps and abnormal power consumption behavior monitoring steps of a method for real-time monitoring and positioning of abnormal power consumption behavior provided by an embodiment of the present invention.

[0027] Figure 5 A schematic diagram of working modules of a real-time monitoring and positioning system for abnormal electricity usage behavior provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0029] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0030] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0031] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0032] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0033] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0034] Example 1, reference Figure 1 - Figure 4 , which is the first embodiment of the present invention, provides a method for real-time monitoring and positioning of abnormal power consumption behavior, including: S1: Modify the existing collection equipment at the edge, install independent monitoring equipment, and realize serial communication with the edge collection equipment. According to the collection situation and business needs of the station area, dynamically adjust the collection data items and collection frequency to form a new collection strategy.

[0035] Furthermore, the implementation of serial communication with the edge acquisition device includes the edge monitoring device initiating a request for adjusting the acquisition strategy configuration to the edge acquisition. After obtaining the new acquisition strategy, the edge acquisition device collects the user's meter data according to the new acquisition strategy, and the data collected by the new acquisition strategy is synchronized to the edge monitoring device. The edge acquisition device determines whether the acquisition strategy needs to be updated, and monitors abnormal power consumption behavior in real time based on the collected data. The results can be synchronously obtained by the handheld mobile terminal. The structure of the system is as follows Figure 3 shown.

[0036] It should be noted that the collection strategy includes a triple sequence of electric meters, collection data items and collection frequencies, expressed as [<electric meter 1, collection data items, collection frequency>, <electric meter 2, collection data items, collection frequency>, <electric meter..., collection data items, collection frequency>, <electric meter n, collection data items, collection frequency>]; the sequence length n is the number of electric meters covered by the edge collection device, and each different electric meter is identified by the electric meter communication address; the collection data items are the electric meter-related electrical data, including voltage, power, live current, neutral current, power, power factor and other data; the collection frequency is the frequency of the electric meter collection, and the optional range includes 24 points / day, 48 points / day, and 96 points / day; the edge collection device executes the collection strategy in sequence. In the actual collection process, the collection data items and collection frequency can be adjusted in sections according to the collection situation of the substation and the business requirements, so that the collection situation of the substation and the business requirements are mutually adapted.

[0037] S2: Use the Pearson correlation coefficient and DBSCAN clustering algorithm to cluster the electricity meters, divide the electricity meters into clusters, and calculate the load of each cluster.

[0038] Furthermore, the calculation of the load condition of each cluster includes obtaining the collected voltage data, dividing it into a plurality of independent meter clusters according to a density clustering process, calculating the Pearson correlation coefficient, and constructing a distance matrix; It should be noted that the formula for calculating the Pearson correlation coefficient is: , in, is the Pearson correlation coefficient between meters A and B. and are the voltage data sequences of meters A and B respectively. is the number of data points. and They are and The mean of represents a data point of meter A, Represents a data point of meter B. n is the number of all meters collected at the edge.

[0039] Construct the distance matrix, convert the correlation coefficient, and use As the distance between the two meters .

[0040] Matrix representation: , For all meter pairs, a distance matrix D is constructed based on the transformed distances, where Represents the distance between meter i and meter j.

[0041] The DBSCAN clustering algorithm determines the neighborhood size eps and the minimum number of samples min_samples required to form a dense area, and clusters the electricity meters using the DBSCAN algorithm and the distance matrix. When the number of points in the eps neighborhood reaches min_samples, a new cluster is created and the current point is added to the cluster. The points in the eps neighborhood of each point in the cluster are recursively added to the cluster until no new points can be added.

[0042] The selection of eps and min_samples has a great influence on the clustering results. Currently, eps uses the 90th percentile value of the correlation distance of the meters in the substation area. If there is data on the number of meters in the meter box in the substation area, the number of meters in the meter box is used. If there is no relevant data, the number value of 2 is used as the value of min_samples.

[0043] S3: According to the load conditions and collection weights of the meter cluster, the collection sequence and frequency are adjusted, and the collection strategy is iterated and optimized periodically.

[0044] Furthermore, the iteration and optimization of the collection strategy includes calculating the load of each meter cluster based on the collected power data according to the calculated meter cluster, normalizing the load using the maximum and minimum value normalization method, and using the normalized result as the collection weight for collection sorting: The maximum and minimum normalization formulas are as follows: , Among them is Normalized results of each cluster load, is the load condition of each cluster, is the maximum load of each cluster, is the minimum load value of each cluster; Adjust the collection sequence so that the meters in the same cluster are in a similar collection order, and according to the collection weight, put the collection order of the cluster with a high weight at the beginning of the collection sequence; According to the data collection situation in the substation, adjust the data collection frequency of each meter. The maximum value of the adjustment range is the highest frequency that the substation can complete the data collection, and the minimum value is the lowest frequency required for abnormal monitoring. Repeat the above process periodically, randomly repeating according to 300-500 valid points.

[0045] S4: Monitor the zero-live current ratio and power data of the electric meter in real time, identify abnormal power consumption behavior, focus on monitoring the electric meter with continuous abnormal power consumption, and output abnormal reminders.

[0046] Furthermore, the identification of abnormal electricity consumption behavior includes comparing the zero-live current collected by the meter, when the ratio of the zero-live current collected by the meter for one consecutive hour exceeds a preset range, or abnormal data appears for 4 hours cumulatively within 24 hours, and the abnormal data is allowed to appear discontinuously, that is, the zero-live current of the meter is output to be abnormal; When an electric meter has abnormal current, the current meter collection weight is increased to 1, the current meter is collected with the highest priority, and the collection frequency is appropriately increased to focus on monitoring the meter. After the abnormal power consumption continues, the abnormal reminder is continuously output; The electricity data collected within 6 hours is used to conduct a rolling comparison of the Pearson correlation between the electricity data collected by the meter and the line loss data in the substation.

[0047] Example 2 is an embodiment of the present invention, which provides a method for real-time monitoring and positioning of abnormal electricity usage behavior. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments. In this experiment, four electric meters in different areas (marked as electric meters A, B, C, and D) were selected to monitor abnormal electricity usage behavior. Before the test, a basic test of the zero-live current ratio was performed on each electric meter to ensure that the electric meter was operating normally. Subsequently, according to the method described in the content of the invention, the electric meter was monitored in the following steps, and the results are shown in Table 1: Compare the zero-live current collected by the meter. If the ratio of the zero-live current collected by the meter for one consecutive hour exceeds the range of 0.8~1.2, or abnormal data appears for 4 hours in total within 24 hours, the abnormal data is allowed to appear discontinuously, that is, the zero-live current of the meter is output as abnormal. If an electric meter has abnormal current, increase the collection weight of the meter to 1, give top priority to collecting the meter, and increase the collection frequency appropriately. Focus on monitoring the meter, and continue to output abnormal reminders after abnormal power consumption continues.

[0048] Use the electricity data collected within 6 hours to conduct a rolling comparison of the Pearson correlation between the electricity data collected by the meter and the line loss data in the substation area. Increase the weight of meters with high correlation (above 0.8) to 0.9; increase the weight of meters with relatively high correlation (above 0.6) to 0.7 and add them to the key monitoring list, and report high correlation anomalies. Output anomaly reminders when there are multiple (5) high correlation anomalies in the collected electricity data.

[0049] Table 1: Abnormal behavior monitoring data , From the above table data, we can clearly see the advantages and innovation of the method of the present invention in monitoring abnormal electricity consumption behavior. The following is a detailed data analysis: Meter A: Although an abnormal current occurred, the abnormal duration did not reach 4 hours, and the Pearson correlation was high (0.85). After the weight was increased to 0.9, the number of abnormal reminders was only 1, indicating that the monitoring method can effectively identify and reduce false alarms.

[0050] Meter B: The current abnormality was as many as 6 times, and the abnormality lasted for 5 hours, indicating that there might be serious power consumption problems. By increasing the weight to 0.7 and adding it to the key monitoring list, the number of abnormal reminders was 3, which effectively improved the monitoring of this meter.

[0051] Meter C: Although the zero-to-live current ratio is slightly higher (0.9), the overall performance is good. Only one current abnormality occurred within 24 hours, and the Pearson correlation is as high as 0.9. No abnormal alert was triggered, which shows the accuracy of the monitoring method.

[0052] Meter D: The abnormal current situation is between meters A and B. The weight is adjusted to 0.8, and the number of abnormal reminders is 2, indicating that the monitoring method can effectively identify and respond to abnormal situations.

[0053] Compared with the prior art, the method of the present invention significantly improves the real-time and accuracy of monitoring by dynamically adjusting the meter weight and collection frequency. In particular, in terms of identifying and responding to current anomalies, the method shows higher efficiency and reliability, reduces false alarms, and improves the monitoring ability of truly abnormal electricity consumption behaviors. In addition, through Pearson correlation analysis, the method can also timely discover potential problems related to line losses in the substation area, thereby providing strong support for the safe and stable operation of the power system.

[0054] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0055] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that: If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0056] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0057] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0058] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0059] Example 4, reference Figure 5 , which is an embodiment of the present invention, provides a real-time monitoring and positioning system for abnormal power consumption behavior, characterized by: comprising an edge acquisition device transformation module 100, an acquisition strategy configuration and adjustment module 200, a data processing and analysis module 300, an acquisition sequence optimization module 400, an abnormal monitoring and response module 500, a communication and data synchronization module 600, and a data storage and management module 700; Edge acquisition equipment transformation module 100, to achieve equipment upgrades, support data synchronization and policy adjustments; The acquisition strategy configuration and adjustment module 200 dynamically sets acquisition parameters to meet different monitoring requirements; Data processing and analysis module 300, cleaning, analyzing and clustering data, identifying meter clusters and load conditions; The acquisition sequence optimization module 400 optimizes the acquisition sequence and frequency to improve monitoring efficiency; The abnormal monitoring and response module 500 monitors abnormal power consumption behavior, issues early warnings and provides guidance for handling; Communication and data synchronization module 600, ensuring real-time data transmission between devices; The data storage and management module 700 stores and manages monitoring data and supports historical query.

[0060] The modified edge acquisition device is connected to the edge monitoring device through serial communication, and the communication and data synchronization module is responsible for real-time transmission and synchronization of data; The collection strategy configuration and adjustment module generates new collection strategies based on the collection situation in the substation and business needs, and sends them to the edge collection devices through the communication and data synchronization module; The edge acquisition device collects meter data according to the new acquisition strategy. The data processing and analysis module receives the data, cleans it, calculates the Pearson correlation coefficient, builds a distance matrix, and applies the DBSCAN clustering algorithm to cluster the meters. The collection sequence optimization module adjusts the collection sequence and frequency and optimizes the collection strategy according to the meter cluster load and collection weight provided by the data processing and analysis module; The abnormal monitoring and response module receives the meter data provided by the edge acquisition device in real time, monitors the zero-live current ratio and power data, identifies abnormal power consumption behavior, and outputs abnormal reminders; The data storage and management module is responsible for storing the data received from the edge acquisition device, the clustering results of the data processing and analysis module, the strategy adjustment records of the acquisition sequence optimization module, and the anomaly records of the anomaly monitoring and response module for subsequent analysis and historical query.

[0061] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for real-time monitoring and positioning of abnormal electricity consumption behavior, characterized in that: include, Modify the existing edge acquisition equipment, install independent monitoring equipment, and realize serial communication with the edge acquisition equipment. According to the acquisition situation and business needs of the station area, dynamically adjust the collection data items and collection frequency to form a new collection strategy; The Pearson correlation coefficient and DBSCAN clustering algorithm are used to cluster the electricity meters, divide the electricity meter clusters, and calculate the load of each cluster; According to the load conditions and collection weights of the meter cluster, the collection sequence and frequency are adjusted, and the collection strategy is iterated and optimized periodically; Monitor the zero-live current ratio and power data of the meter in real time, identify abnormal power usage behavior, focus on monitoring meters that continue to have abnormal power usage, and output abnormal reminders.

2. A method for real-time monitoring and positioning of abnormal power consumption behavior according to claim 1, characterized in that: The implementation of serial port communication with the edge collection device includes: the edge monitoring device initiates a request for edge collection to adjust the collection strategy configuration; after obtaining the new collection strategy, the edge collection device collects user meter data according to the new collection strategy, and synchronizes the data collected by the new collection strategy to the edge monitoring device; the edge collection device determines whether the collection strategy needs to be updated, and monitors abnormal electricity consumption behavior in real time based on the collected data.

3. A method for real-time monitoring and positioning of abnormal power consumption behavior as claimed in claim 2, characterized in that: The collection strategy includes a triple sequence of an electric meter, a collection data item and a collection frequency. The sequence length n is the number of electric meters covered by the edge collection device. Each different electric meter is identified by the electric meter communication address. The edge collection device executes the collection strategy in sequence order, and adjusts the collection data items and the collection frequency in segments according to the collection situation of the substation and the business requirements, so that the collection situation of the substation and the business requirements are adapted to each other.

4. A method for real-time monitoring and positioning of abnormal electricity consumption behavior as claimed in claim 3, characterized in that: The calculation of the load condition of each cluster includes obtaining the collected voltage data, dividing it into a plurality of independent electric meter clusters according to a density clustering process, calculating the Pearson correlation coefficient, and constructing a distance matrix; The DBSCAN clustering algorithm determines the neighborhood size eps and the minimum number of samples min_samples required to form a dense area, and clusters the electricity meters using the DBSCAN algorithm and the distance matrix. When the number of points in the eps neighborhood reaches min_samples, a new cluster is created and the current point is added to the cluster. The points in the eps neighborhood of each point in the cluster are recursively added to the cluster until no new points can be added.

5. A method for real-time monitoring and positioning of abnormal power consumption behavior as claimed in claim 4, characterized in that: The iterating and optimizing the collection strategy includes: calculating the load condition of each electric meter cluster based on the collected power data according to the calculated electric meter cluster, normalizing the load condition by using the maximum and minimum value normalization method, using the normalization result as the collection weight for collection sorting, adjusting the collection sequence so that the electric meters in the same cluster are in a similar collection sequence, and placing the collection sequence of the cluster with a high weight at the beginning of the collection sequence according to the collection weight; According to the data collection situation in the substation, adjust the data collection frequency of each meter. The maximum value of the adjustment range is the highest frequency that the substation can complete the data collection, and the minimum value is the lowest frequency required for abnormal monitoring. Repeat the above process periodically, randomly repeating according to 300-500 valid points.

6. A method for real-time monitoring and positioning of abnormal power consumption behavior according to claim 5, characterized in that: The identification of abnormal electricity consumption behavior includes comparing the zero-live current collected by the meter, when the ratio of the zero-live current collected by the meter for one consecutive hour exceeds a preset range, or abnormal data appears for 4 hours cumulatively within 24 hours, and the abnormal data is allowed to appear discontinuously, that is, the zero-live current of the meter is output to be abnormal; When an electric meter has abnormal current, the current meter collection weight is increased to 1, the current meter is collected with the highest priority, and the collection frequency is appropriately increased to focus on monitoring the meter. After the abnormal power consumption continues, the abnormal reminder is continuously output; The electricity data collected within 6 hours is used to conduct a rolling comparison of the Pearson correlation between the electricity data collected by the meter and the line loss data in the substation.

7. A system using a method for real-time monitoring and positioning of abnormal power consumption behavior as claimed in any one of claims 1 to 6, characterized in that: It includes an edge acquisition device transformation module (100), an acquisition strategy configuration and adjustment module (200), a data processing and analysis module (300), an acquisition sequence optimization module (400), an abnormality monitoring and response module (500), a communication and data synchronization module (600), and a data storage and management module (700); The edge acquisition device transformation module (100) implements device upgrades and supports data synchronization and policy adjustments; The acquisition strategy configuration and adjustment module (200) dynamically sets acquisition parameters to adapt to different monitoring requirements; The data processing and analysis module (300) cleans, analyzes and clusters data to identify meter clusters and load conditions; The acquisition sequence optimization module (400) optimizes the acquisition sequence and frequency to improve monitoring efficiency; The abnormal monitoring and response module (500) monitors abnormal power consumption behavior, issues warnings and provides guidance for handling; The communication and data synchronization module (600) ensures real-time data transmission between devices; The data storage and management module (700) stores and manages monitoring data and supports historical query.

8. The system of the method for real-time monitoring and locating abnormal electricity consumption behavior according to claim 7, characterized in that: The modified edge acquisition device is connected to the edge monitoring device through serial communication, and the communication and data synchronization module is responsible for real-time transmission and synchronization of data; The collection strategy configuration and adjustment module generates new collection strategies based on the collection situation in the substation and business needs, and sends them to the edge collection devices through the communication and data synchronization module; The edge acquisition device collects meter data according to the new acquisition strategy. The data processing and analysis module receives the data, cleans it, calculates the Pearson correlation coefficient, builds a distance matrix, and applies the DBSCAN clustering algorithm to cluster the meters. The collection sequence optimization module adjusts the collection sequence and frequency and optimizes the collection strategy according to the meter cluster load and collection weight provided by the data processing and analysis module; The abnormal monitoring and response module receives the meter data provided by the edge acquisition device in real time, monitors the zero-live current ratio and power data, identifies abnormal power consumption behavior, and outputs abnormal reminders; The data storage and management module is responsible for storing the data received from the edge acquisition device, the clustering results of the data processing and analysis module, the policy adjustment records of the acquisition sequence optimization module, and the anomaly records of the anomaly monitoring and response module for subsequent analysis and historical query.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a method for real-time monitoring and positioning of abnormal electricity usage behavior described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for real-time monitoring and positioning of abnormal electricity usage behavior described in any one of claims 1 to 6 are implemented.

Images