A household-level illegal electricity use detection method, device, equipment and storage medium

Abstract

The application provides a household-level illegal electricity use detection method and device, equipment and a storage medium, and relates to the technical field of electricity detection. The method introduces real-time electricity data of a target user to construct a real-time dimension deviation, introduces historical electricity data of the target user to construct a historical dimension deviation, and introduces real-time electricity data of non-target users under the same power distribution node to construct a spatial dimension characteristic deviation. The real-time dimension deviation, the historical dimension deviation and the spatial dimension characteristic deviation are fused, a double-threshold three-level judgment mechanism is used, sudden illegal loads and regular compliant loads can be more effectively distinguished, common-mode interference of the power grid is inhibited through horizontal comparison, the false positive rate is greatly reduced, and the accuracy and robustness of household-level illegal electricity use detection are improved.

Description

Technical Field

[0001] This application relates to the field of power detection technology, and in particular to a method, device, equipment and storage medium for detecting household-level illegal electricity use. Background Technology

[0002] Non-intrusive load location technology is typically used to monitor unauthorized electrical equipment at the household level. This technology directly identifies the electricity consumption behavior of each user by collecting real-time power data such as the main incoming line at the household level, thereby determining whether a user has illegally connected to a load and which user has used the unauthorized appliance.

[0003] However, in actual operation of identifying illegal loads, the following three interference factors exist: 1. Over-reliance on instantaneous characteristics can easily lead to misjudging compliantly enabled heavy-load devices (such as high-performance computers) as non-compliant electrical devices; 2. Limited to independent analysis of single-household data, when common-mode interference such as overall voltage fluctuations in the power grid occurs, it is impossible to distinguish whether it is a local violation or environmental interference, which can easily lead to misjudgment. 3. The commonly used fixed threshold decision strategy has weak anti-interference ability in complex environments with overlapping and fluctuating base loads, and is prone to misjudgment and missed judgment.

[0004] The above three interference factors reduce the accuracy of illegal load judgment and lead to inaccurate illegal load location. Summary of the Invention

[0005] The main objective of this application is to provide a method, device, equipment, and storage medium for detecting illegal electricity use at the household level, aiming to solve the technical problem of how to improve the accuracy of determining and locating illegal electricity use at the household level.

[0006] To achieve the above objectives, this application provides a method for detecting illegal electricity use at the household level, the steps of which include: Acquire the first real-time electricity consumption data and historical electricity consumption data of the target user under the target power distribution node, and at the same time acquire the second real-time electricity consumption data of at least one non-target user under the target power distribution node; The corresponding real-time dimensional deviation is obtained by using the first real-time electricity consumption data; The historical dimensional deviation is obtained by using the historical electricity consumption data. The spatial dimension feature deviation is obtained by using the second real-time electricity consumption data; Based on the real-time dimensional deviation, the historical dimensional deviation, and the spatial dimensional feature deviation, the overall violation confidence level of the target user is determined; Based on the comprehensive violation confidence level, high confidence threshold, and low confidence threshold, it is determined whether the target user has any illegal electrical equipment.

[0007] In one embodiment, the step of obtaining the corresponding real-time dimensional deviation using the first real-time electricity consumption data includes: The first power mean and the first power standard deviation of the first real-time power consumption data are obtained based on a sliding window. The real-time dimension deviation is determined based on the first power mean, the first power standard deviation, and the first instantaneous power corresponding to the current moment in the first real-time power consumption data.

[0008] In one embodiment, after the step of obtaining the corresponding real-time dimensional deviation using the first real-time electricity consumption data, the method further includes: Based on the first power mean and the first power standard deviation, determine the corresponding real-time adaptive threshold; If the first instantaneous power corresponding to the current moment in the first real-time power consumption data is not greater than the real-time adaptive threshold, the step of obtaining the corresponding historical dimension deviation through the historical power consumption data is stopped, and it is determined that the target user does not have the illegal power consumption equipment.

[0009] In one embodiment, the step of obtaining the corresponding historical dimension deviation using the historical electricity consumption data includes: Based on the historical electricity consumption data, obtain the historical electricity consumption data for the same period that is one historical tracing period apart from the current time; The historical power mean and historical power standard deviation corresponding to the historical electricity consumption data of the same period are obtained based on a sliding window. The historical dimension deviation is determined based on the historical power mean, the historical power standard deviation, and the historical instantaneous power at the corresponding historical time in the historical electricity consumption data.

[0010] In one embodiment, the step of obtaining the corresponding spatial dimension feature deviation using the second real-time electricity consumption data includes: The second power mean and second power standard deviation of the second real-time power consumption data are obtained based on a sliding window. Based on the second power mean, the second power standard deviation, and the second instantaneous power corresponding to the current moment in the second real-time power consumption data, the spatial dimension feature deviation is determined.

[0011] In one embodiment, the step of determining the overall violation confidence level of the target user based on the real-time dimensional deviation, the historical dimensional deviation, and the spatial dimensional feature deviation includes: The collaborative reward value is determined based on the real-time dimensional deviation, the historical dimensional deviation, and the preset collaborative threshold. The comprehensive violation confidence level is determined based on the real-time dimensional deviation, the historical dimensional deviation, the spatial dimensional feature deviation, and the collaborative reward value.

[0012] In one embodiment, the step of determining whether the target user has illegally used electrical equipment based on the comprehensive violation confidence level, the high confidence threshold, and the low confidence threshold includes: When the overall violation confidence level is greater than the high confidence threshold, it is determined that the target user has the violation of the electrical equipment. When the overall violation confidence level is less than the low confidence threshold, it is determined that the target user does not have the violating electrical equipment. When the overall confidence level of the violation is between the high confidence threshold and the low confidence threshold, it is determined that the target user is suspected of having the illegal electrical equipment.

[0013] Furthermore, to achieve the above objectives, this application also provides a household-level illegal electricity use detection device, the household-level illegal electricity use detection device comprising: The data acquisition module is used to acquire the first real-time electricity consumption data and historical electricity consumption data of the target user under the target power distribution node, and at the same time acquire the second real-time electricity consumption data of at least one non-target user under the target power distribution node. The feature extraction module is used to obtain the corresponding real-time dimension deviation through the first real-time electricity consumption data; The feature extraction module is also used to obtain the corresponding historical dimension deviation through the historical electricity consumption data; The feature extraction module is also used to obtain the corresponding spatial dimension feature deviation through the second real-time electricity consumption data; The feature fusion module is used to determine the comprehensive violation confidence level of the target user based on the real-time dimensional deviation, the historical dimensional deviation, and the spatial dimensional feature deviation. The judgment module is used to determine whether the target user has any illegal electrical equipment based on the comprehensive violation confidence level, the high confidence threshold, and the low confidence threshold.

[0014] In addition, to achieve the above objectives, this application also provides a household-level illegal electricity use detection device, which includes: a memory, a processor, and a household-level illegal electricity use detection program stored in the memory and executable on the processor. The household-level illegal electricity use detection program is configured to implement the steps of the household-level illegal electricity use detection method described above.

[0015] In addition, to achieve the above objectives, this application also provides a storage medium, which is a computer-readable storage medium, and stores a household-level illegal electricity use detection program thereon. When the household-level illegal electricity use detection program is executed by a processor, it implements the steps of the household-level illegal electricity use detection method described above.

[0016] This application provides a method, apparatus, device, and storage medium for detecting household-level illegal electricity use. The method includes the following steps: acquiring first real-time electricity consumption data and historical electricity consumption data of a target user under a target distribution node, and simultaneously acquiring second real-time electricity consumption data of at least one non-target user under the target distribution node; obtaining the corresponding real-time dimensional deviation using the first real-time electricity consumption data; obtaining the corresponding historical dimensional deviation using the historical electricity consumption data; obtaining the corresponding spatial dimensional feature deviation using the second real-time electricity consumption data; determining the comprehensive violation confidence level of the target user based on the real-time dimensional deviation, the historical dimensional deviation, and the spatial dimensional feature deviation; and determining whether the target user has any illegal electrical devices based on the comprehensive violation confidence level, a high confidence threshold, and a low confidence threshold.

[0017] By incorporating real-time electricity consumption data from target users to construct real-time dimensional deviation, historical electricity consumption data from target users to construct historical dimensional deviation, and real-time electricity consumption data from non-target users at the same distribution node to construct spatial dimensional feature deviation, this system integrates real-time, historical, and spatial dimensional feature deviations. Based on a dual-threshold, three-level judgment mechanism, it can more effectively distinguish between sudden illegal loads and regular compliant loads. Furthermore, by suppressing common-mode interference from the power grid through horizontal comparison, it significantly reduces the false alarm rate and improves the accuracy and robustness of household-level illegal electricity consumption detection. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the household-level illegal electricity use detection method provided in this application. Figure 2 A schematic diagram showing the power time-series changes of different electrical appliances; Figure 3 This is a flowchart illustrating Embodiment 2 of the household-level illegal electricity use detection method provided in this application; Figure 4 This is a schematic diagram of a sliding window data acquisition method. Figure 5 This is a flowchart illustrating Embodiment 3 of the household-level illegal electricity use detection method provided in this application; Figure 6 This is a diagram illustrating a judgment regarding the illegal use of electrical equipment. Figure 7 This is a schematic diagram of the module structure provided in Embodiment 1 of the household-level illegal electricity use detection device of this application; Figure 8 This is a structural schematic diagram of the first embodiment of the household-level illegal electricity use detection equipment provided in this application.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] This application presents a household-level illegal electricity use detection method according to the first embodiment. Please refer to [link / reference]. Figure 1 as well as Figure 2 The household-level illegal electricity use detection method includes steps S10-S60: Step S10: Obtain the first real-time electricity consumption data and historical electricity consumption data of the target user under the target distribution node, and at the same time obtain the second real-time electricity consumption data of at least one non-target user under the target distribution node. It should be understood that, in this embodiment, the executing entity is a household-level illegal electricity use detection device or equipment, such as a smart meter, edge computing gateway, or cloud server.

[0025] It should be noted that, in this embodiment, the target distribution node can be the power supply range covered by any secondary distribution box in any residential area; the target user refers to a specific electricity user within the power supply range corresponding to the target distribution node who needs to be detected for household-level illegal electricity use; the non-target user refers to other electricity users located under the same target distribution node as the target user; the first real-time electricity consumption data refers to the real-time power time series of the target user collected in real time; the historical electricity consumption data refers to the historical power time series of the target user collected in the past; the second real-time electricity consumption data refers to the real-time power time series of the non-target user located under the same target distribution node as the target user collected in real time.

[0026] It is easy to understand that real-time power time series can be used to reflect the electricity consumption behavior of the target user and non-target users located at the same target distribution node at the current moment, while historical power time series can be used to reflect the electricity consumption behavior of the target user in the past. In this embodiment, the real-time power time series of the target user can be collected in real time by a non-intrusive monitoring device deployed at the main inlet of the target user to obtain the first real-time electricity consumption data. At the same time, the real-time power time series of non-target users can be collected in real time by a non-intrusive monitoring device deployed at at least one main inlet of the non-target user under the same target distribution node to obtain the second real-time electricity consumption data. Historical power time series can also be read from the database to directly obtain historical electricity consumption data. The first real-time electricity consumption data, the second real-time electricity consumption data, and the historical electricity consumption data obtained in the above manner can be used for subsequent analysis of the target user's own electricity consumption patterns and perception of changes in the overall power grid environment.

[0027] Step S20: Obtain the corresponding real-time dimension deviation using the first real-time electricity consumption data; Step S30: Obtain the corresponding historical dimension deviation using the historical electricity consumption data; Step S40: Obtain the corresponding spatial dimension feature deviation using the second real-time electricity consumption data; It should be noted that, in this embodiment, the real-time dimension deviation refers to the data feature used to reflect the target user's current electricity consumption behavior, which can characterize the degree of deviation of the user's current electricity consumption behavior from the short-term electricity consumption behavior fluctuation level; the historical dimension deviation refers to the data feature used to reflect the target user's electricity consumption behavior at the same time in the past, which can characterize the degree of deviation of the user's current electricity consumption behavior from the historical same-time electricity consumption behavior benchmark; the spatial dimension feature deviation refers to the data feature used to reflect the current electricity consumption behavior of non-target users located at the same target distribution node as the target user, which can characterize the degree of deviation of the user's current electricity consumption behavior from the electricity consumption behavior benchmark of the non-target user group under the same distribution node.

[0028] As is easily understood, real-time deviation primarily reflects whether short-term fluctuations in electricity consumption behavior exceed the normal range, used to capture sudden events; historical deviation primarily reflects whether current electricity consumption behavior breaks long-term historical patterns, used to filter periodic compliant loads; spatial feature deviation primarily reflects whether current behavior is unique to the target user, used to suppress common-mode interference from the power grid. In this embodiment, by acquiring real-time deviation, historical deviation, and spatial feature deviation respectively, a multi-faceted and three-dimensional characterization of illegal electricity consumption behavior can be formed, facilitating a comprehensive judgment of illegal electricity consumption behavior in the future.

[0029] Step S50: Based on the real-time dimension deviation, the historical dimension deviation, and the spatial dimension feature deviation, determine the comprehensive violation confidence level of the target user; Step S60: Based on the comprehensive violation confidence level, high confidence threshold, and low confidence threshold, determine whether the target user has any illegal electrical equipment.

[0030] It should be noted that, in this embodiment, the comprehensive violation confidence score is a comprehensive score obtained by weighted fusion of features from three dimensions: real-time, historical, and spatial. It is used to quantify the probability that the current electricity use behavior constitutes a violation. The high confidence threshold and the low confidence threshold are two quantitative indicators used to distinguish the degree to which a user has used illegal electrical equipment (which can be adjusted according to the sensitivity requirements of the actual application scenario). The high confidence threshold and the low confidence threshold are used as the upper boundary thresholds, constructing three confidence levels to determine which level the current comprehensive violation confidence score belongs to (corresponding to different judgment conclusions). Illegal electrical equipment refers to electrical appliances that are prohibited from use in specific electricity use scenarios, such as high-power devices that are prone to causing fires, such as electric kettles, electric stoves, and hair dryers in dormitory scenarios.

[0031] It should be understood that, for ease of understanding the definition of non-compliant electrical equipment, the following explanation is provided. For example, in a school dormitory setting, students may purchase various different electrical devices, such as purely resistive kettles, hybrid resistive and inductive hair dryers, and heavy-duty computers. The power characteristics of the above three types of electrical equipment are as follows: Figure 2 As shown, Figure 2 The horizontal axis represents the time sequence, corresponding to the sampling date and time interval, covering the entire cycle of electrical equipment from startup, operation to shutdown; the vertical axis represents the power axis, in watts, representing the real-time total power value of the applied electrical circuit; the black solid line is the real-time total power curve, representing the real-time power time sequence data collected at the household-level incoming line, reflecting the dynamic change of the power of the electrical circuit over time. According to... Figure 2 As shown in the demonstration, the kettle has the power characteristics of "sharp rise and fall, high power steady state", and the hair dryer has the power characteristics of "high power, high frequency fluctuation", both of which are illegal electrical devices; the computer has the power characteristics of "low power, gradual change", and is a legal electrical device.

[0032] It is easy to understand that in this embodiment, by fusing real-time dimensional deviation, historical dimensional deviation, and spatial dimensional feature deviation into a quantifiable comprehensive violation confidence level, a mapping from multi-dimensional features to a single judgment result can be achieved. Subsequently, a dual-threshold three-level judgment mechanism, constructed from high and low confidence thresholds, grades the comprehensive violation confidence level, thereby obtaining the corresponding judgment conclusion. Based on the combination of the above multi-source fusion mechanism and the dual-threshold three-level judgment mechanism, information from different dimensions can be comprehensively weighed, and the judgment result can be made more reliable through a quantified comprehensive violation confidence level. When the comprehensive violation confidence level is high, it indicates that the judgment result of identifying the presence of illegally used electrical equipment is more reliable, which can minimize the false alarm rate; when the comprehensive violation confidence level is moderate, it indicates that the judgment result of identifying illegally used electrical equipment is not completely reliable; when the comprehensive violation confidence level is low, it indicates that the current user is likely not using any illegally used electrical equipment. Thus, high-precision identification of household-level illegally used electrical equipment can be achieved, thereby enabling high-precision location of household-level illegal electricity use.

[0033] This application provides a household-level illegal electricity use detection method. This method constructs a real-time dimensional deviation by introducing real-time electricity consumption data of the target user, constructs a historical dimensional deviation by introducing historical electricity consumption data of the target user, and constructs a spatial dimensional feature deviation by introducing real-time electricity consumption data of non-target users under the same distribution node. By fusing the real-time dimensional deviation, historical dimensional deviation, and spatial dimensional feature deviation, and based on a dual-threshold, three-level judgment mechanism, it can more effectively distinguish between sudden illegal loads and regular compliant loads. Furthermore, by suppressing common-mode interference from the power grid through horizontal comparison, it significantly reduces the false alarm rate and improves the accuracy and robustness of household-level illegal electricity use detection.

[0034] Based on the first embodiment of the household-level illegal electricity use detection method of this application, the content that is the same as or similar to the first embodiment of the household-level illegal electricity use detection method of this application can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 as well as Figure 4 The step of obtaining the corresponding real-time dimensional deviation through the first real-time electricity consumption data includes: Step S21: Obtain the first power mean and first power standard deviation of the first real-time power consumption data based on a sliding window; Step S22: Determine the real-time dimension deviation based on the first power mean, the first power standard deviation, and the first instantaneous power corresponding to the current moment in the first real-time power consumption data.

[0035] It should be noted that, in this embodiment, the sliding window refers to a time window of fixed length that can be slidable (containing several sampling points), which can be used to extract a segment of continuous power data; the first power mean refers to the arithmetic mean of all power sampling points in the corresponding sliding window at the current time; the first power standard deviation refers to the quantized value used to characterize the dispersion of all power sampling points in the corresponding sliding window at the current time; and the first instantaneous power refers to the real-time power value at the current sampling time.

[0036] It should be understood that the working principle of the sliding window used in this embodiment is as follows: Figure 4 As shown, Figure 4 The horizontal axis represents the time axis, with sampling points as the basic unit, corresponding to the time series of data acquisition; the vertical axis represents the power axis, characterizing the power magnitude collected at the corresponding sampling point. t1, t2, t3, ..., t16 represent the 1st to 16th sampling points, respectively, and the time interval between adjacent sampling points is the sampling period. The total number of sampling points contained in the sliding window is the window size W, which can also be understood as the window length; the number of sampling point intervals in a single slide of the sliding window is the step size S. Figure 4 The blue box shows the sliding window at time t, and the red box shows the sliding window at time t+S. The sliding window moves from a historical time to the current time for sampling along the scrolling direction of the time axis.

[0037] It is easy to understand that, in this embodiment, the first real-time electricity consumption data can be captured by a sliding window, thereby calculating in real time the first power mean and first power standard deviation corresponding to the target user within the sliding window, in order to track the slow changes in the base load (the continuous and relatively stable part of the target user's electricity consumption behavior) in real time. Subsequently, the first power standard deviation can be normalized by the first power mean and the first instantaneous power supplied in the first real-time electricity consumption data, and the result obtained after normalization is nonlinearly mapped to finally obtain the aforementioned real-time dimensional deviation.

[0038] In specific implementation, the formula for calculating the first power average is as follows; ; in, The first power average, The length of the sliding window. For the current moment, This represents the first instantaneous power corresponding to the first real-time electricity consumption data at the current moment. This refers to any sampling time between the starting point of the sliding window and the current time.

[0039] Correspondingly, the formula for calculating the first power standard deviation is as follows: ; in, This represents the first power standard deviation.

[0040] The corresponding formula for calculating real-time dimensional deviation is as follows: ; in, For real-time dimensional deviation, This is a protection constant used to prevent division by zero; its value is extremely small (usually 1). ~ ).

[0041] Furthermore, in this embodiment, after the step of obtaining the corresponding real-time dimensional deviation through the first real-time electricity consumption data, the method further includes: Step S231: Determine the corresponding real-time adaptive threshold based on the first power mean and the first power standard deviation; Step S232: When the first instantaneous power corresponding to the current moment in the first real-time power consumption data is not greater than the real-time adaptive threshold, stop executing the step of obtaining the corresponding historical dimension deviation through the historical power consumption data, and determine that the target user does not have the illegal power consumption equipment.

[0042] It should be noted that, in this embodiment, the real-time adaptive threshold refers to a power threshold calculated based on the dynamic characteristics of the recent base load. Its value is set in relation to the first power mean and the first power standard deviation, and is used to initially screen time periods that may contain violations.

[0043] Specifically, the formula for calculating the real-time adaptive threshold is as follows: ; in, This is a real-time adaptive threshold.

[0044] It is easy to understand that the real-time adaptive threshold is dynamically adjusted as the base load changes. When the base load increases, the threshold also increases accordingly, avoiding in-depth analysis of every minute fluctuation during periods of heavy load. In this embodiment, only when the current power significantly exceeds the recent normal fluctuation range, i.e., when the first instantaneous power in the first real-time power consumption data at the current moment exceeds the real-time adaptive threshold, will subsequent more complex historical dimension deviation and spatial dimension feature deviation extraction and fusion judgment be triggered. If the first instantaneous power at the current moment does not exceed the real-time adaptive threshold, the subsequent steps of historical dimension deviation and spatial dimension feature deviation extraction and fusion judgment can be skipped, and it can be directly determined that the current target user has not connected to any illegal electrical equipment.

[0045] Through the above coarse screening mechanism, the computational overhead can be significantly reduced and the real-time processing capability of the system can be improved while ensuring a high detection rate, thus realizing an efficient event-driven mechanism.

[0046] Furthermore, in this embodiment, the step of obtaining the corresponding historical dimension deviation through the historical electricity consumption data includes: Step S31: Based on the historical electricity consumption data, obtain the historical electricity consumption data for the same period that is one historical tracing cycle apart from the current time; Step S32: Obtain the historical power mean and historical power standard deviation corresponding to the historical electricity consumption data for the same period based on a sliding window; It should be noted that, in this embodiment, the historical tracing period refers to the historical time span used for comparison, such as the same moment a week ago, which is used to reflect the periodic pattern of user electricity consumption behavior; the historical electricity consumption data for the same period refers to the power time series corresponding to the historical tracing period; the historical power mean refers to the arithmetic mean of the power data within the sliding window of the same historical period; and the historical power standard deviation refers to the degree of dispersion of the power data within the sliding window of the same historical period.

[0047] It is easy to understand that user electricity consumption behavior is usually cyclical. In this embodiment, similar to the calculation method of the first power mean and the first power standard deviation mentioned above, historical data (historical power mean and historical standard deviation) separated from the current time by a historical tracing period (such as one week) can be extracted as a benchmark to facilitate subsequent calculation of the corresponding historical dimension deviation and to construct a long-term profile reflecting the target user under normal electricity consumption conditions.

[0048] Step S33: Determine the historical dimension deviation based on the historical power mean, the historical power standard deviation, and the historical instantaneous power at the corresponding historical time in the historical electricity consumption data.

[0049] It is easy to understand that the calculation logic for historical dimension deviation is similar to that for real-time dimension deviation, but its benchmark is the electricity consumption behavior pattern of the same historical period. In this embodiment, the deviation of historical instantaneous power at the same historical period is normalized by using the historical power mean and historical power standard deviation, and the result of the normalization is then nonlinearly mapped to finally obtain the aforementioned historical dimension deviation. The calculation formula for historical dimension deviation is as follows: ; in, For real-time dimensional deviation, This refers to the historical instantaneous power at the corresponding historical time point in the historical electricity consumption data. This is the historical power average. The historical power standard deviation This is a protection constant used to prevent division by zero; its value is extremely small (usually 1). ~ ).

[0050] Based on the historical dimension deviation calculated using the above method, it is possible to accurately identify sudden abnormal behaviors in the long term, that is, to identify that the current electricity consumption behavior has broken the long-term periodic pattern formed by the user.

[0051] Furthermore, in this embodiment, the step of obtaining the corresponding spatial dimension feature deviation through the second real-time electricity consumption data includes: Step S41: Obtain the second power mean and second power standard deviation of the second real-time power consumption data based on a sliding window; Step S42: Determine the spatial dimension feature deviation based on the second power mean, the second power standard deviation, and the second instantaneous power corresponding to the current moment in the second real-time power consumption data.

[0052] It should be noted that, in this embodiment, the second power mean refers to the average power of at least one non-target user (neighbor) under the same target distribution node within the same time window; the second power standard deviation refers to the dispersion of power data of at least one non-target user (neighbor) under the same target distribution node within the same time window.

[0053] It is easy to understand that when the power grid experiences overall voltage fluctuations or is affected by external environmental factors (such as a sudden temperature change causing multiple households' air conditioners to start and stop simultaneously), these disturbances will occur synchronously among all users under the same target distribution node. At this time, although the power change of the target user is significant, non-target users located at the same target distribution node will also show similar trends, resulting in a lower deviation between the target user's power and the neighbor's average. In this embodiment, similar to the calculation method of the first power average and the first power standard value, the calculation target is simply switched from the target user to at least one non-target user under the same target distribution node to obtain the second power average and the second power standard deviation (if there are multiple non-target users, they can be recalculated based on the number of non-target users). Correspondingly, the formula for calculating the spatial dimension characteristic deviation is as follows: ; in, The deviation of spatial dimension features. This represents the second instantaneous power corresponding to the second real-time electricity consumption data at the current moment. The second power average, The second power standard deviation, This is a protection constant used to prevent division by zero; its value is extremely small (usually 1). ~ ).

[0054] By introducing the aforementioned spatial dimension feature deviation, common-mode interference caused by power grid fluctuations can be suppressed, effectively distinguishing power grid environmental interference from individual user violations, and solving the location drift caused by the isolated effect of single-household data.

[0055] Based on the first and / or second embodiments of the household-level illegal electricity use detection method of this application, in the third embodiment of the household-level illegal electricity use detection method of this application, the content that is the same as or similar to the first and second embodiments of the household-level illegal electricity use detection method described above can be referred to the above description and will not be repeated hereafter. Based on this, please refer to... Figure 5 as well as Figure 6 The step of determining the comprehensive violation confidence level of the target user based on the real-time dimensional deviation, the historical dimensional deviation, and the spatial dimensional feature deviation includes: Step S51: Determine the collaborative reward value based on the real-time dimension deviation, the historical dimension deviation, and the preset collaborative threshold. Step S52: Determine the comprehensive violation confidence level based on the real-time dimension deviation, the historical dimension deviation, the spatial dimension feature deviation, and the collaborative reward value.

[0056] It should be noted that, in this embodiment, the collaborative incentive function can reflect the high responsiveness of both real-time and historical dimension deviations, and is used to determine whether the current event is simultaneously captured by short-term fluctuation detection and long-term anomaly detection; the preset collaborative threshold is a pre-set empirical constant used to evaluate whether the current collaborative incentive value can trigger a collaborative reward, and can be adjusted according to the sensitivity requirements of the actual scenario; the collaborative reward value is the final output of the collaborative incentive function, and can also be understood as an additional fixed bonus item, which can further strengthen the comprehensive violation confidence when collaborative responses are generated in the real-time and historical dimensions.

[0057] It is worth noting that, in this embodiment, the expression for the cooperative activation function is as follows: ; in, As an additional bonus item for the overall confidence level of violation, its output value is the collaborative reward value under the corresponding conditions; 0 and 0 represent the collaborative reward values ​​in the two cases, respectively; This is a preset collaboration threshold.

[0058] It is easy to understand that in this embodiment, when both the real-time dimension deviation (reflecting short-term anomalies) and the historical dimension deviation (reflecting the disruption of long-term behavior) are high (both the real-time dimension deviation and the historical dimension deviation exceed the preset coordination threshold), it indicates that the current electricity consumption behavior is both sudden and disrupts the user's long-term behavioral patterns, highly consistent with the typical characteristics of unauthorized electrical equipment access. In this case, a fixed coordination reward value can be provided to strengthen the overall violation confidence. If only one of the real-time dimension deviation and the historical dimension deviation is high, or neither is high (only one of the real-time dimension deviation and the historical dimension deviation exceeds the preset coordination threshold, or neither exceeds the preset coordination threshold), it indicates that the current electricity consumption behavior does not fully conform to the situation of unauthorized electrical equipment access, and there is no need to enhance the overall violation confidence.

[0059] With the introduction of the aforementioned collaborative enhancement judgment mechanism, the final formula for calculating the overall violation confidence level is as follows: ; in, To determine the overall confidence level of the violation, the interval range is [0, 1]. The fusion weights are for real-time dimensional deviation. The fusion weight for the deviation of the historical dimension. The three factors are the fusion weights for the deviation of spatial dimension features, and can be adjusted according to the actual situation. This is an additional bonus point for the overall confidence level of the violation.

[0060] By introducing a collaborative reward-based enhanced judgment mechanism, additional weights can be assigned to the aforementioned dual anomaly cases during multi-source feature fusion. This allows the overall violation confidence to respond more sensitively to genuine violation events, while preventing false alarms triggered by sporadic noise in a single dimension, further improving the robustness of the judgment. Furthermore, in this embodiment, the step of determining whether the target user has illegally used electrical equipment based on the comprehensive violation confidence level, the high confidence threshold, and the low confidence threshold includes: Step S61: When the overall violation confidence level is greater than the high confidence level threshold, it is determined that the target user has the violation of the electrical equipment. Step S62: When the overall violation confidence level is less than the low confidence level threshold, it is determined that the target user does not have the violation equipment. Step S63: When the overall violation confidence level is between the high confidence threshold and the low confidence threshold, it is determined that the target user is suspected of having the illegal electrical equipment.

[0061] It should be noted that, in this embodiment, the high confidence threshold refers to the upper boundary preset value used to determine that "the target user has illegal electrical equipment"; the low confidence threshold refers to the lower boundary threshold used to determine that "the target user has illegal electrical equipment".

[0062] It is easy to understand that in this embodiment, when the overall confidence level of the multi-dimensional violation is greater than the high confidence threshold, it is directly determined that the target user has illegal electrical equipment; when the overall confidence level of the multi-dimensional violation is lower than the low confidence threshold, it is directly determined that the target user does not have illegal electrical equipment; when the overall confidence level of the multi-dimensional violation is between the high confidence threshold and the low confidence threshold, it is considered that there is an abnormal phenomenon but the evidence is insufficient. At this time, the status of "suspected violation" can be output for subsequent manual review, or it can be recorded as a suspicious event for subsequent verification.

[0063] It should be understood that, as an example, please refer to Figure 6 , Figure 6 The horizontal axis represents the time series, and the vertical axis represents the violation confidence level (i.e., the score in the figure), with values ​​ranging from [0, 1]. The combination of these two axes can be used to characterize the probability of a target user's electricity usage violation at a given time. The higher-score dashed line corresponds to the high-confidence threshold, i.e., the alarm threshold in the figure, while the lower-score dashed line corresponds to the low-confidence threshold, i.e., the suspected fluctuation line in the figure. Clearly, the overall violation confidence level of the kettle and hair dryer is consistently higher than the high-confidence threshold during operation, while the overall violation confidence level of the computer is consistently lower than the low-confidence threshold. In cases such as those involving the kettle and hair dryer, it can be directly determined that the target user is using electrical equipment improperly, and an alarm "Violation detected" can be triggered. In cases such as those involving the computer, it can be determined that the target user is not using electrical equipment improperly. Furthermore, if the current overall violation confidence level of the target user remains between the high-confidence threshold and the low-confidence threshold, it can be determined that the target user is suspected of using electrical equipment improperly.

[0064] Based on the above dual-threshold decision mechanism, arbitrary binary decisions at ambiguous boundaries can be avoided, ensuring rapid response to high-confidence events while retaining the traceability capability of low-confidence events, thus greatly improving the availability of the system in practical applications.

[0065] This application also provides a household-level illegal electricity use detection device. Please refer to... Figure 7 The household-level illegal electricity use detection device includes: Data acquisition module 10 is used to acquire the first real-time electricity consumption data and historical electricity consumption data of the target user under the target power distribution node, and at the same time acquire the second real-time electricity consumption data of at least one non-target user under the target power distribution node. The feature extraction module 20 is used to obtain the corresponding real-time dimension deviation through the first real-time electricity consumption data; The feature extraction module 20 is also used to obtain the corresponding historical dimension deviation through the historical electricity consumption data; The feature extraction module 20 is also used to obtain the corresponding spatial dimension feature deviation degree through the second real-time electricity consumption data; The feature fusion module 30 is used to determine the comprehensive violation confidence level of the target user based on the real-time dimension deviation, the historical dimension deviation, and the spatial dimension feature deviation. The judgment module 40 is used to determine whether the target user has any illegal electrical equipment based on the comprehensive violation confidence level, the high confidence threshold, and the low confidence threshold.

[0066] The household-level illegal electricity use detection device provided in this application, employing the household-level illegal electricity use detection method described in the above embodiments, can solve the technical problem of how to improve the accuracy of household-level illegal electricity use determination and location. Compared with the prior art, the beneficial effects of the household-level illegal electricity use detection device provided in this application are the same as those of the household-level illegal electricity use detection method provided in the above embodiments, and other technical features in the household-level illegal electricity use detection device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0067] This application provides a household-level illegal electricity use detection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the household-level illegal electricity use detection method in Embodiment 1 above.

[0068] The following is for reference. Figure 8 The diagram illustrates a structural schematic suitable for implementing a household-level illegal electricity use detection device in the embodiments of this application. The household-level illegal electricity use detection device in the embodiments of this application may include, but is not limited to, fixed terminals such as vehicle-mounted terminals. Figure 8 The household-level illegal electricity use detection device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0069] like Figure 8As shown, the household-level illegal electricity use detection device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the household-level illegal electricity use detection device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following devices can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the residential illegal electricity usage detection device to communicate wirelessly or wiredly with other devices to exchange data. Although a residential illegal electricity usage detection device with various devices is shown in the figure, it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0070] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0071] The household-level illegal electricity use detection device provided in this application, employing the household-level illegal electricity use detection method described in the above embodiments, can solve the technical problem of how to improve the accuracy of household-level illegal electricity use determination and location. Compared with the prior art, the beneficial effects of the household-level illegal electricity use detection device provided in this application are the same as those of the household-level illegal electricity use detection method provided in the above embodiments, and other technical features of this household-level illegal electricity use detection device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0072] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0073] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0074] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the household-level illegal electricity use detection method in the above embodiments.

[0075] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor devices, apparatuses, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution apparatus, device, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0076] The aforementioned computer-readable storage medium may be included in a household-level illegal electricity use detection device; or it may exist independently and not be assembled into a household-level illegal electricity use detection device.

[0077] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by a household-level illegal electricity use detection device, the device causes the following: It acquires first real-time electricity consumption data and historical electricity consumption data of a target user under a target distribution node; simultaneously acquires second real-time electricity consumption data of at least one non-target user under the target distribution node; obtains the corresponding real-time dimensional deviation using the first real-time electricity consumption data; obtains the corresponding historical dimensional deviation using the historical electricity consumption data; obtains the corresponding spatial dimensional feature deviation using the second real-time electricity consumption data; determines the comprehensive illegality confidence level of the target user based on the real-time dimensional deviation, the historical dimensional deviation, and the spatial dimensional feature deviation; and determines whether the target user has any illegal electricity use equipment based on the comprehensive illegality confidence level, a high confidence threshold, and a low confidence threshold.

[0078] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0079] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using dedicated hardware-based apparatus to perform the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0080] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0081] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described household-level illegal electricity use detection method. This solves the technical problem of improving the accuracy of household-level illegal electricity use determination and location. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the household-level illegal electricity use detection method provided in the above embodiments, and will not be repeated here.

[0082] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. A method for detecting household-level illegal electricity use, characterized in that, The steps of the household-level illegal electricity use detection method include: Acquire the first real-time electricity consumption data and historical electricity consumption data of the target user under the target power distribution node, and at the same time acquire the second real-time electricity consumption data of at least one non-target user under the target power distribution node; The corresponding real-time dimensional deviation is obtained by using the first real-time electricity consumption data; The historical dimensional deviation is obtained by using the historical electricity consumption data. The spatial dimension feature deviation is obtained by using the second real-time electricity consumption data; Based on the real-time dimensional deviation, the historical dimensional deviation, and the spatial dimensional feature deviation, the overall violation confidence level of the target user is determined; Based on the comprehensive violation confidence level, high confidence threshold, and low confidence threshold, it is determined whether the target user has any illegal electrical equipment.

2. The household-level illegal electricity use detection method as described in claim 1, characterized in that, The step of obtaining the corresponding real-time dimension deviation through the first real-time electricity consumption data includes: The first power mean and the first power standard deviation of the first real-time power consumption data are obtained based on a sliding window. The real-time dimension deviation is determined based on the first power mean, the first power standard deviation, and the first instantaneous power corresponding to the current moment in the first real-time power consumption data.

3. The household-level illegal electricity use detection method as described in claim 2, characterized in that, After the step of obtaining the corresponding real-time dimensional deviation from the first real-time electricity consumption data, the method further includes: Based on the first power mean and the first power standard deviation, determine the corresponding real-time adaptive threshold; If the first instantaneous power corresponding to the current moment in the first real-time power consumption data is not greater than the real-time adaptive threshold, the step of obtaining the corresponding historical dimension deviation through the historical power consumption data is stopped, and it is determined that the target user does not have the illegal power consumption equipment.

4. The household-level illegal electricity use detection method as described in claim 1, characterized in that, The step of obtaining the corresponding historical dimension deviation through the historical electricity consumption data includes: Based on the historical electricity consumption data, obtain the historical electricity consumption data for the same period that is one historical tracing period apart from the current time; The historical power mean and historical power standard deviation corresponding to the historical electricity consumption data of the same period are obtained based on a sliding window. The historical dimension deviation is determined based on the historical power mean, the historical power standard deviation, and the historical instantaneous power at the corresponding historical time in the historical electricity consumption data.

5. The household-level illegal electricity use detection method as described in claim 1, characterized in that, The step of obtaining the corresponding spatial dimension feature deviation through the second real-time electricity consumption data includes: The second power mean and second power standard deviation of the second real-time power consumption data are obtained based on a sliding window. Based on the second power mean, the second power standard deviation, and the second instantaneous power corresponding to the current moment in the second real-time power consumption data, the spatial dimension feature deviation is determined.

6. The household-level illegal electricity use detection method as described in claim 1, characterized in that, The step of determining the comprehensive violation confidence level of the target user based on the real-time dimensional deviation, the historical dimensional deviation, and the spatial dimensional feature deviation includes: The collaborative reward value is determined based on the real-time dimensional deviation, the historical dimensional deviation, and the preset collaborative threshold. The comprehensive violation confidence level is determined based on the real-time dimensional deviation, the historical dimensional deviation, the spatial dimensional feature deviation, and the collaborative reward value.

7. The household-level illegal electricity use detection method as described in claim 1, characterized in that, The step of determining whether the target user has illegally used electrical equipment based on the comprehensive violation confidence level, the high confidence threshold, and the low confidence threshold includes: When the overall violation confidence level is greater than the high confidence threshold, it is determined that the target user has the violation of the electrical equipment. When the overall violation confidence level is less than the low confidence threshold, it is determined that the target user does not have the violating electrical equipment. When the overall confidence level of the violation is between the high confidence threshold and the low confidence threshold, it is determined that the target user is suspected of having the illegal electrical equipment.

8. A household-level illegal electricity use detection device, characterized in that, The household-level illegal electricity use detection device includes: The data acquisition module is used to acquire the first real-time electricity consumption data and historical electricity consumption data of the target user under the target power distribution node, and at the same time acquire the second real-time electricity consumption data of at least one non-target user under the target power distribution node. The feature extraction module is used to obtain the corresponding real-time dimension deviation through the first real-time electricity consumption data; The feature extraction module is also used to obtain the corresponding historical dimension deviation through the historical electricity consumption data; The feature extraction module is also used to obtain the corresponding spatial dimension feature deviation through the second real-time electricity consumption data; The feature fusion module is used to determine the comprehensive violation confidence level of the target user based on the real-time dimensional deviation, the historical dimensional deviation, and the spatial dimensional feature deviation. The judgment module is used to determine whether the target user has any illegal electrical equipment based on the comprehensive violation confidence level, the high confidence threshold, and the low confidence threshold.

9. A household-level illegal electricity use detection device, characterized in that, The household-level illegal electricity use detection device includes: a memory, a processor, and a household-level illegal electricity use detection program stored in the memory and executable on the processor, wherein the household-level illegal electricity use detection program is configured to implement the steps of the household-level illegal electricity use detection method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and the computer-readable storage medium stores a household-level illegal electricity use detection program. When the household-level illegal electricity use detection program is executed by a processor, it implements the steps of the household-level illegal electricity use detection method as described in any one of claims 1 to 7.

Images