A method and system for analyzing abnormal electricity consumption data

Abstract

This invention discloses a method and system for analyzing abnormal electricity consumption data. The method includes: determining whether the sequence deviation between a first target electricity consumption data subsequence and a second target electricity consumption data subsequence is greater than a preset deviation threshold; if it is greater than the preset deviation threshold, they are defined as a first suspicious electricity consumption data subsequence and a second suspicious electricity consumption data subsequence, respectively, and performing electricity consumption data anomaly analysis on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence according to a preset first data analysis strategy; and based on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence, using a preset second data analysis strategy to perform abnormal electricity consumption data anomaly analysis on a first non-target electricity consumption data subsequence adjacent to the first suspicious electricity consumption data subsequence and a second non-target electricity consumption data subsequence adjacent to the second suspicious electricity consumption data subsequence. This method can accurately identify abnormal electricity consumption data.

Description

Technical Field

[0001] This invention belongs to the field of electricity consumption data analysis technology, and in particular relates to a method and system for analyzing abnormal electricity consumption data. Background Technology

[0002] In the field of power equipment monitoring, accurate identification of abnormal power consumption data is crucial for preventing equipment failures, reducing fire risks, and ensuring power safety. Currently, mainstream anomaly detection methods mainly suffer from the following technical bottlenecks:

[0003] Existing technologies generally rely on single-dimensional power consumption thresholds for judgment (such as setting fixed thresholds or statistical models based on historical data). However, during equipment state switching, both normal load fluctuations (such as motor starting, material feeding into processing equipment) and actual anomalies (such as short circuits, current surges caused by insulation aging) will manifest as increased power consumption. Due to the lack of dynamic correlation analysis of the real-time thermal state of the equipment, existing methods have the following shortcomings:

[0004] High false alarm rate: Normal state transitions (such as cold start current) are falsely reported as abnormal;

[0005] High risk of missed detection: When abnormal current does not exceed the static threshold but has already caused the equipment temperature to accumulate rapidly (such as due to poor local contact), there is no timely warning.

[0006] Of particular concern is the higher sensitivity of equipment temperature changes to current anomalies—according to Joule's law (Q=I²Rt), the rate of temperature rise caused by abnormal current is much higher than that of normal load changes. However, current technologies fail to effectively utilize the temporal abrupt changes in temperature data to accurately pinpoint suspicious intervals in power consumption data, resulting in low analysis efficiency. Summary of the Invention

[0007] This invention provides a method and system for analyzing abnormal electricity consumption data, which addresses the technical problem of low analysis efficiency caused by the inability to effectively utilize the temporal abrupt change characteristics of temperature data to accurately locate suspicious intervals in electricity consumption data.

[0008] In a first aspect, the present invention provides a method for analyzing abnormal electricity consumption data, comprising:

[0009] Acquire a sequence of power consumption data and a sequence of equipment temperature data within a preset time period, wherein the power consumption data sequence contains power consumption data at different time points, and the equipment temperature data sequence contains equipment temperature data at different time points;

[0010] Based on the changing trend of the temperature data of each device, at least one abrupt change in device temperature data is selected from the device temperature data sequence. Based on the time node of the at least one abrupt change in device temperature data, at least one target power consumption data subsequence and at least one non-target power consumption data subsequence are extracted from the power consumption data sequence aligned with the device temperature data sequence according to the preset data extraction rules.

[0011] Determine whether the sequence deviation between the first target electricity consumption data subsequence and the second target electricity consumption data subsequence is greater than a preset deviation threshold, wherein the first target electricity consumption data subsequence and the second target electricity consumption data subsequence are two adjacent target electricity consumption data subsequences;

[0012] If the deviation exceeds the preset deviation threshold, the first target electricity consumption data subsequence and the second target electricity consumption data subsequence are defined as the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence, respectively, and an anomaly analysis of electricity consumption data is performed on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence according to the preset first data analysis strategy.

[0013] Based on the first suspected electricity consumption data subsequence and the second suspected electricity consumption data subsequence, a preset second data analysis strategy is used to perform abnormal electricity consumption data analysis on the first non-target electricity consumption data subsequence adjacent to the first suspected electricity consumption data subsequence and the second non-target electricity consumption data subsequence adjacent to the second suspected electricity consumption data subsequence.

[0014] Secondly, the present invention provides an electricity consumption data anomaly analysis system, comprising:

[0015] The acquisition module is configured to acquire a sequence of power consumption data and a sequence of device temperature data within a preset time period, wherein the power consumption data sequence includes power consumption data at different time points, and the device temperature data sequence includes device temperature data at different time points.

[0016] The interception module is configured to select at least one abruptly changing device temperature data in the device temperature data sequence according to the changing trend of each device temperature data, and based on the time node of the at least one abruptly changing device temperature data, intercept at least one target power consumption data subsequence and at least one non-target power consumption data subsequence in the power consumption data sequence aligned with the device temperature data sequence according to a preset data interception rule.

[0017] The judgment module is configured to determine whether the sequence deviation between the first target electricity consumption data subsequence and the second target electricity consumption data subsequence is greater than a preset deviation threshold, wherein the first target electricity consumption data subsequence and the second target electricity consumption data subsequence are two adjacent target electricity consumption data subsequences;

[0018] The first analysis module is configured to, if the deviation exceeds a preset deviation threshold, define the first target electricity consumption data subsequence and the second target electricity consumption data subsequence as the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence, respectively, and perform electricity consumption data anomaly analysis on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence according to a preset first data analysis strategy.

[0019] The second analysis module is configured to perform abnormal electricity consumption data analysis on the first non-target electricity consumption data subsequence adjacent to the first suspected electricity consumption data subsequence and the second non-target electricity consumption data subsequence adjacent to the second suspected electricity consumption data subsequence, based on the first suspected electricity consumption data subsequence and the second suspected electricity consumption data subsequence, using a preset second data analysis strategy.

[0020] Thirdly, an electronic device is provided, comprising: 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, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the power consumption data anomaly analysis method according to any embodiment of the present invention.

[0021] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the steps of the power consumption data anomaly analysis method according to any embodiment of the present invention.

[0022] The electricity consumption data anomaly analysis method and system of this application determines temperature mutation points based on dynamically preset temperature thresholds, extracts key electricity consumption windows based on temperature mutation points, and adaptively focuses on abnormal electricity consumption related time periods; then, it quantifies the differences in electricity consumption trajectory patterns by the degree of sequence deviation, distinguishing normal load fluctuations from real faults as much as possible; and, combined with the first data analysis strategy, it performs precise positioning of suspicious areas and non-target areas, that is, dynamically selects full-domain marking or selective marking mode according to the maximum electricity consumption change, thereby effectively accelerating the speed of electricity consumption data anomaly identification while maximizing the accuracy of abnormal electricity consumption data identification. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1A flowchart of a method for analyzing abnormal electricity consumption data provided in an embodiment of the present invention;

[0025] Figure 2 This is a structural block diagram of an electricity consumption data anomaly analysis system provided in an embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] Please see Figure 1 The diagram shows a flowchart of a method for analyzing abnormal electricity consumption data according to this application.

[0029] like Figure 1 As shown, the method for analyzing abnormal electricity consumption data specifically includes the following steps:

[0030] Step S101: Obtain the power consumption data sequence and the equipment temperature data sequence of the electrical equipment within a preset time period, wherein the power consumption data sequence contains power consumption data at different time points, and the equipment temperature data sequence contains equipment temperature data at different time points.

[0031] In this step, a high-precision smart meter (e.g., 0.5S accuracy) is installed in the power supply circuit of the electrical equipment, supporting millisecond-level current / power sampling. The high-precision smart meter acquires the electrical consumption data of the equipment within a preset time period, and the data is arranged chronologically to obtain a sequence of consumption data.

[0032] Infrared temperature sensors (accuracy ±1℃) or fiber optic temperature sensors (anti-electromagnetic interference) should be deployed at key heat-generating parts of the equipment (such as motor windings and terminals). The sensor distribution points should cover Joule's law hotspot areas (such as locations prone to poor contact). The temperature data of the electrical equipment should be acquired through the temperature sensors within a preset time period and arranged in chronological order to obtain a sequence of equipment temperature data.

[0033] Step S102: Select at least one abrupt change in device temperature data from the device temperature data sequence according to the changing trend of each device temperature data, and based on the time node of the at least one abrupt change in device temperature data, extract at least one target power consumption data subsequence and at least one non-target power consumption data subsequence from the power consumption data sequence aligned with the device temperature data sequence according to a preset data extraction rule.

[0034] In this step, constructing a dynamic preset temperature threshold specifically includes: setting an initial preset temperature threshold, which corresponds to a first temperature difference, wherein the first temperature difference is the difference between the first device temperature data at the first position and the second device temperature data at the second position in the device temperature data sequence; determining whether the first temperature difference is greater than the initial preset temperature threshold; if the first temperature difference is greater than the initial preset temperature threshold, then adding the first temperature difference to the initial preset temperature threshold to obtain an updated first preset temperature threshold, wherein the first preset temperature threshold corresponds to a second temperature difference, wherein the second temperature difference is the difference between the second device temperature data at the second position and the third device temperature data at the third position in the device temperature data sequence; determining whether the second temperature difference is greater than the first preset temperature threshold; if the second temperature difference is greater than the first preset temperature threshold, then adding the second temperature difference to the initial preset temperature threshold to obtain an updated second preset temperature threshold, wherein the second preset temperature threshold corresponds to a third temperature difference, wherein the third temperature difference is the difference between the third device temperature data at the third position and the fourth device temperature data at the fourth position in the device temperature data sequence.

[0035] In one specific embodiment, after determining whether the first temperature difference is greater than the initial preset temperature threshold, if the first temperature difference is not greater than the initial preset temperature threshold, the initial preset temperature threshold is directly defined as the first preset temperature threshold; if the second temperature difference is not greater than the first preset temperature threshold, the first preset temperature threshold is directly defined as the second preset temperature threshold.

[0036] In a specific application scenario, the equipment is: a transformer in a substation;

[0037] Data acquisition frequency: 1Hz (1 data point per second);

[0038] Initial preset temperature threshold: 5℃ (set based on historical data);

[0039] The temperature data sequence is (66, 67, 68, 70, 78, 84, 95, 103).

[0040] The first temperature difference is ΔT1=T1-T0=67-66=1℃. Since the first temperature difference of 1℃ is not greater than the initial preset temperature threshold, the initial preset temperature threshold (5℃) is defined as the first preset temperature threshold.

[0041] The second temperature difference is ΔT2=T2-T1=68-67=1℃. Since the second temperature difference of 1℃ is not greater than the first preset temperature threshold, the first preset temperature threshold (5℃) is defined as the second preset temperature threshold.

[0042] The third temperature difference is ΔT3=T3-T2=70-68=2℃. Since the third temperature difference of 2℃ is not greater than the second preset temperature threshold, the second preset temperature threshold (5℃) is defined as the third preset temperature threshold.

[0043] The fourth temperature difference is ΔT4 = T4 - T3 = 78 - 70 = 8℃. Since the fourth temperature difference of 8℃ is greater than the third preset temperature threshold, the third temperature difference (2℃) is added to the initial preset temperature threshold (5℃) to obtain the fifth preset temperature threshold (7℃).

[0044] The fifth temperature difference is ΔT5 = T5 - T4 = 84 - 78 = 6℃. Since the fifth temperature difference of 6℃ is not greater than the fifth preset temperature threshold (7℃), the fifth preset temperature threshold is defined as the sixth preset temperature threshold.

[0045] The sixth temperature difference is ΔT6=T6-T5=95-84=11℃. Since the sixth temperature difference of 11℃ is greater than the sixth preset temperature threshold (7℃), the third temperature difference (6℃) is added to the initial preset temperature threshold (5℃) to obtain the seventh preset temperature threshold (11℃).

[0046] The seventh temperature difference is ΔT7=T7-T6=103-95=8℃. Since the seventh temperature difference of 8℃ is not greater than the seventh preset temperature threshold (11℃), the seventh preset temperature threshold is defined as the eighth preset temperature threshold.

[0047] Furthermore, the temperature difference between two adjacent equipment temperature data in the equipment temperature data sequence is compared with the corresponding dynamic preset temperature threshold, and the comparison results are used to determine whether there is at least one abrupt change in equipment temperature data in the equipment temperature data sequence. If there is no abrupt change in equipment temperature data, it is directly determined that each power consumption data in the power consumption data sequence corresponding to the equipment temperature data sequence is normal. If there is at least one abrupt change in equipment temperature data, at least one abrupt change in equipment temperature data is selected in the equipment temperature data sequence.

[0048] In one specific embodiment, the temperature data sequence is (66, 67, 68, 70, 78, 84, 95, 103), where the difference between 78℃ and 70℃ is greater than the corresponding third preset temperature threshold, therefore 78℃ is defined as the temperature data of the abruptly changing device. Similarly, the difference between 95℃ and 84℃ is greater than the corresponding sixth preset temperature threshold, therefore 95℃ is also defined as the temperature data of the abruptly changing device. Therefore, the first fault and the second fault may have occurred at the time points corresponding to 78℃ and 95℃, respectively.

[0049] In this embodiment, by setting a dynamic preset temperature threshold, the system becomes more sensitive to subsequent temperature rises, thereby accurately capturing the starting point of temperature changes that are not caused by the normal load operation of the electrical equipment. Since temperature changes lag behind changes in power consumption when a fault occurs, the time point corresponding to the sudden change in equipment temperature data cannot be directly defined as the time point of power consumption anomaly. Therefore, it is necessary to perform "based on preset data interception rules, intercept at least one target power consumption data subsequence and at least one non-target power consumption data subsequence from the power consumption data sequence aligned with the equipment temperature data sequence" and other subsequent steps to further analyze the time point of power consumption anomaly. Thus, this embodiment can achieve the effect of determining the time interval of power consumption anomaly relatively quickly.

[0050] It should be noted that, based on the time node of at least one abrupt change in device temperature data, and according to preset data extraction rules, at least one target power consumption data subsequence and at least one non-target power consumption data subsequence are extracted from the power consumption data sequence aligned with the device temperature data sequence, including:

[0051] Align the equipment temperature data sequence with the power consumption data sequence, and select power consumption data in the power consumption data sequence that is at the same time node as at least one abruptly changing equipment temperature data, and define it as abruptly changing power consumption data; take the position point of a certain abruptly changing power consumption data as the center point, and extract a certain power consumption data subsequence of a preset length from the power consumption data sequence; based on the time sequence, determine whether the absolute difference in power consumption between any two adjacent power consumption data in a certain power consumption data subsequence is greater than a preset power consumption threshold; if the absolute difference in power consumption between any two adjacent power consumption data in a certain power consumption data subsequence is not greater than the preset power consumption threshold, then directly define the certain power consumption data subsequence as the target power consumption data subsequence; if the first power consumption data in a certain power consumption data subsequence is greater than the target power consumption threshold, then the target power consumption data subsequence is defined as the target power consumption data subsequence. If the absolute difference in electricity consumption between the first electricity consumption data and the second electricity consumption data is greater than a preset electricity consumption threshold, then the location of the first electricity consumption data is defined as the first cutoff point. The time node corresponding to the first electricity consumption data is earlier than the time node corresponding to the second electricity consumption data, and the first and second electricity consumption data are two adjacent electricity consumption data that are the first to exceed the preset electricity consumption threshold based on their time sequence. A second cutoff point symmetrical to the first cutoff point is obtained with the center point as the symmetrical point. The electricity consumption data between the first cutoff point and the second cutoff point is extracted from a certain electricity consumption data subsequence to obtain a target electricity consumption data subsequence. Each target electricity consumption data subsequence is extracted from the electricity consumption data sequence to obtain at least one target electricity consumption data subsequence and at least one non-target electricity consumption data subsequence.

[0052] For example, obtain the electricity consumption data at the corresponding time points of 78℃ and 95℃, and define the electricity consumption data at these two time points as sudden change electricity consumption data.

[0053] In this embodiment, the key window of electricity consumption data is anchored by temperature mutation points (such as 78℃, 95℃) to eliminate interference from steady-state data and focus on the fault-related time period; and the symmetrical interception mechanism automatically adjusts the analysis window: when the electricity consumption mutation is significant (> preset electricity consumption threshold), the analysis range is narrowed to the mutation interval; when the electricity consumption change is gradual (≤ preset electricity consumption threshold), the complete preset window is retained to avoid the problem of the preset window length not matching the fault characteristics.

[0054] Step S103: Determine whether the sequence deviation between the first target power consumption data subsequence and the second target power consumption data subsequence is greater than a preset deviation threshold, wherein the first target power consumption data subsequence and the second target power consumption data subsequence are two adjacent target power consumption data subsequences.

[0055] In this step, before determining whether the sequence deviation between the first target electricity consumption data subsequence and the second target electricity consumption data subsequence is greater than a preset deviation threshold, the first target electricity consumption data subsequence and the second target electricity consumption data subsequence are aligned based on the center point of the target electricity consumption data subsequence; the target electricity consumption data located at the first center point of the first target electricity consumption data subsequence is defined as the first center target electricity consumption data, and the target electricity consumption data located at the second center point of the second target electricity consumption data subsequence is defined as the first center target electricity consumption data; the first absolute difference in electricity consumption between the first other target electricity consumption data and the first center target electricity consumption data is obtained, wherein the first other target electricity consumption data is the first target electricity consumption data. The first target power consumption data is obtained from the subsequence excluding the first central target power consumption data; the second absolute difference in power consumption between the second other target power consumption data and the second central target power consumption data is obtained, wherein the second other target power consumption data is the second target power consumption data excluding the second central target power consumption data in the second target power consumption data subsequence; the first absolute difference in power consumption between the first other target power consumption data and the second absolute difference in power consumption between the aligned first other target power consumption data and the second other target power consumption data is subtracted again, and the absolute value is taken to obtain the degree of deviation of each absolute difference in power consumption, and the degree of deviation is added together to obtain the degree of sequence deviation between the first target power consumption data subsequence and the second target power consumption data subsequence.

[0056] Specifically, the absolute difference in electricity consumption is the absolute value of the difference in electricity consumption, that is, the first absolute difference in electricity consumption is the absolute value of the first difference in electricity consumption, and the second absolute difference in electricity consumption is the absolute value of the second difference in electricity consumption.

[0057] In a specific application scenario, the electricity consumption data is the amount of electricity consumed, in kW·h. The first target electricity consumption data subsequence is [475, 480, 483, 485 (center), 492, 505, 510], with the first center point being 485;

[0058] The second target electricity consumption data subsequence is: [505, 520, 545, 565 (center), 575, 580, 578], second center point: 565;

[0059] Align the first center point 485 of the first target power consumption data subsequence with the second center point 565 of the second target power consumption data subsequence on the time axis;

[0060] First-order difference (differences between each point and the center point):

[0061] The difference result of the first target electricity consumption data subsequence: [10,5,2,7,20,25];

[0062] The difference result of the first target electricity consumption data subsequence: [60,45,20,10,15,13];

[0063] Second difference (second difference at aligned positions):

[0064] Position 1: 60 - 10 = 50;

[0065] Position 2: 45 - 5 = 40;

[0066] Position 3: 20 - 2 = 18;

[0067] Position 4: 10-7=3;

[0068] Position 5: 20-15=5;

[0069] Position 6: 25-13=12.

[0070] Sequence deviation degree=50+40+18+3+5+12=128.

[0071] In this embodiment, by determining whether the sequence deviation of adjacent target power consumption data subsequences exceeds a preset deviation threshold, it is possible to distinguish between normal load fluctuations (such as the smooth symmetrical trajectory of motor starting and stopping) and real faults (such as sudden changes in power consumption caused by faults), which facilitates further anomaly analysis of power consumption data in subsequent steps S104 and S105.

[0072] Step S104: If the deviation exceeds a preset threshold, the first target electricity consumption data subsequence and the second target electricity consumption data subsequence are defined as the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence, respectively. An abnormal electricity consumption data analysis is performed on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence according to a preset first data analysis strategy.

[0073] In this step, the first maximum change in electricity consumption in the first suspected electricity consumption data subsequence and the second maximum change in electricity consumption in the second suspected electricity consumption data subsequence are obtained, and it is determined whether the first maximum change in electricity consumption and the second maximum change in electricity consumption are greater than a preset electricity consumption change threshold. If the first maximum change in electricity consumption is not greater than the preset electricity consumption change threshold, each first suspected electricity consumption data in the first suspected electricity consumption data subsequence is defined as abnormal electricity consumption data; otherwise, the first suspected electricity consumption data in the first suspected electricity consumption data subsequence that is greater than the first suspected average electricity consumption value is defined as abnormal electricity consumption data. If the second maximum change in electricity consumption is not greater than the preset electricity consumption change threshold, each second suspected electricity consumption data in the second suspected electricity consumption data subsequence is defined as abnormal electricity consumption data; otherwise, the second suspected electricity consumption data in the second suspected electricity consumption data subsequence that is greater than the second suspected average electricity consumption value is defined as abnormal electricity consumption data.

[0074] In this embodiment, if the first maximum change in power consumption is greater than a preset threshold for change in power consumption, then a significant change in power consumption has occurred in the first suspected power consumption data subsequence. This suggests that the fault likely occurred within the time interval corresponding to the first suspected power consumption data subsequence. Therefore, the first suspected power consumption data in the first suspected power consumption data subsequence that is greater than the first suspected average power consumption value is defined as abnormal power consumption data. The first suspected average power consumption value is the average value of each first suspected power consumption data in the first suspected power consumption data subsequence. If the first maximum change in power consumption is not greater than the preset threshold for change in power consumption, then it suggests that the fault likely occurred outside the time interval corresponding to the first suspected power consumption data subsequence, but before that time interval, causing the first suspected power consumption data in the first suspected power consumption data subsequence to remain abnormal.

[0075] When the maximum change in electricity consumption in a suspicious subsequence does not exceed a preset threshold (indicating a gradual and sustained accumulation of anomalies), the entire suspicious subsequence is classified as a global anomaly, avoiding partial missed detections of progressive faults. Conversely, when the maximum change exceeds the preset threshold (representing sudden and drastic fluctuations), only data points with electricity consumption above the average are defined as anomalies, effectively eliminating normal fluctuation segments. This strategy, by dynamically switching between "overall marking" and "selective marking" modes, can achieve pixel-level localization of electricity consumption data anomalies with relatively high accuracy.

[0076] Step S105: Based on the first suspected electricity consumption data subsequence and the second suspected electricity consumption data subsequence, a preset second data analysis strategy is used to perform abnormal electricity consumption data analysis on the first non-target electricity consumption data subsequence adjacent to the first suspected electricity consumption data subsequence and the second non-target electricity consumption data subsequence adjacent to the second suspected electricity consumption data subsequence.

[0077] In this step, when the first maximum change in electricity consumption is greater than the preset threshold for change in electricity consumption, each of the first non-target electricity consumption data in the first non-target electricity consumption data subsequence is directly determined to be normal electricity consumption data.

[0078] If the first maximum change in electricity consumption is not greater than the preset threshold for change in electricity consumption, then the first non-target electricity consumption data in the first non-target electricity consumption data subsequence that is greater than the first non-target average electricity consumption value is defined as abnormal electricity consumption data.

[0079] When the second maximum change in electricity consumption is greater than the preset threshold for change in electricity consumption, then each of the second non-target electricity consumption data in the second non-target electricity consumption data subsequence is directly determined to be normal electricity consumption data.

[0080] If the second maximum change in electricity consumption is not greater than the preset threshold for change in electricity consumption, then the second non-target electricity consumption data in the second non-target electricity consumption data subsequence that is greater than the second non-target average electricity consumption value is defined as abnormal electricity consumption data.

[0081] In this embodiment, a second data analysis strategy is adopted, which can achieve accurate ripple diagnosis of non-target electricity consumption data subsequences as much as possible: when the maximum change in electricity consumption of a suspicious subsequence exceeds a preset threshold (indicating a sudden local fault), the adjacent non-target subsequences are determined to be normal as a whole, which can better diagnose over-diagnosis of non-abnormal time intervals; while when the maximum change in electricity consumption of a suspicious subsequence does not exceed the threshold (indicating a persistent latent fault), the data points in the non-target subsequence with electricity consumption higher than the average are marked as abnormal, thereby more accurately determining abnormal electricity consumption data.

[0082] In summary, the method of this application determines temperature mutation points based on dynamically preset temperature thresholds, extracts key electricity consumption windows based on temperature mutation points, and adaptively focuses on abnormal electricity consumption related time periods; then, it quantifies the differences in electricity consumption trajectory patterns by the degree of sequence deviation, distinguishing normal load fluctuations from actual faults as much as possible; and, combined with the first data analysis strategy, it performs precise positioning of suspicious areas and non-target areas, that is, dynamically selects full-domain marking or selective marking mode according to the maximum electricity consumption change, thereby effectively accelerating the speed of abnormal electricity consumption data identification while maximizing the accuracy of abnormal electricity consumption data identification.

[0083] Please see Figure 2 The diagram shows a structural block diagram of an electricity consumption data anomaly analysis system according to this application.

[0084] like Figure 2 As shown, the electricity data anomaly analysis system 200 includes an acquisition module 210, an interception module 220, a judgment module 230, a first analysis module 240, and a second analysis module 250.

[0085] The acquisition module 210 is configured to acquire a sequence of power consumption data and a sequence of equipment temperature data within a preset time period. The power consumption data sequence includes power consumption data at different time points, and the equipment temperature data sequence includes equipment temperature data at different time points. The extraction module 220 is configured to select at least one abruptly changing equipment temperature data from the equipment temperature data sequence based on the changing trends of each equipment temperature data, and, based on the time point of the at least one abruptly changing equipment temperature data, extract at least one target power consumption data subsequence and at least one non-target power consumption data subsequence from the power consumption data sequence aligned with the equipment temperature data sequence, according to a preset data extraction rule. The judgment module 230 is configured to judge whether the sequence deviation between the first target power consumption data subsequence and the second target power consumption data subsequence is greater than a preset deviation threshold. The first target electricity consumption data subsequence and the second target electricity consumption data subsequence are two adjacent target electricity consumption data subsequences; the first analysis module 240 is configured to, if the deviation exceeds a preset threshold, define the first target electricity consumption data subsequence and the second target electricity consumption data subsequence as the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence, respectively, and perform electricity consumption data anomaly analysis on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence according to a preset first data analysis strategy; the second analysis module 250 is configured to, based on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence, perform abnormal electricity consumption data anomaly analysis on the first non-target electricity consumption data subsequence adjacent to the first suspicious electricity consumption data subsequence and the second non-target electricity consumption data subsequence adjacent to the second suspicious electricity consumption data subsequence using a preset second data analysis strategy.

[0086] It should be understood that Figure 2 The modules and references described in the document Figure 1 The steps described in the text correspond to those in the method described above. Therefore, the operations, features, and corresponding technical effects described above also apply to the method described in the text. Figure 2 The various modules in the document will not be described in detail here.

[0087] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the power consumption data anomaly analysis method in any of the above method embodiments.

[0088] In one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, which are configured as follows:

[0089] Acquire a sequence of power consumption data and a sequence of equipment temperature data within a preset time period, wherein the power consumption data sequence contains power consumption data at different time points, and the equipment temperature data sequence contains equipment temperature data at different time points;

[0090] Based on the changing trend of the temperature data of each device, at least one abrupt change in device temperature data is selected from the device temperature data sequence. Based on the time node of the at least one abrupt change in device temperature data, at least one target power consumption data subsequence and at least one non-target power consumption data subsequence are extracted from the power consumption data sequence aligned with the device temperature data sequence according to the preset data extraction rules.

[0091] Determine whether the sequence deviation between the first target electricity consumption data subsequence and the second target electricity consumption data subsequence is greater than a preset deviation threshold, wherein the first target electricity consumption data subsequence and the second target electricity consumption data subsequence are two adjacent target electricity consumption data subsequences;

[0092] If the deviation exceeds the preset deviation threshold, the first target electricity consumption data subsequence and the second target electricity consumption data subsequence are defined as the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence, respectively, and an anomaly analysis of electricity consumption data is performed on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence according to the preset first data analysis strategy.

[0093] Based on the first suspected electricity consumption data subsequence and the second suspected electricity consumption data subsequence, a preset second data analysis strategy is used to perform abnormal electricity consumption data analysis on the first non-target electricity consumption data subsequence adjacent to the first suspected electricity consumption data subsequence and the second non-target electricity consumption data subsequence adjacent to the second suspected electricity consumption data subsequence.

[0094] Computer-readable storage media may include a stored program area and a stored data area, wherein the stored program area may store an operating system and an application program required for at least one function; the stored data area may store data created based on the use of the power consumption data anomaly analysis system, etc. Furthermore, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include memory remotely disposed relative to the processor, and these remote memories may be connected to the power consumption data anomaly analysis system via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0095] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 3As shown, the device includes a processor 310 and a memory 320. The electronic device may also include an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 can be connected via a bus or other means. Figure 3 Taking a bus connection as an example, the memory 320 is the computer-readable storage medium described above. The processor 310 executes various server functions and data processing by running non-volatile software programs, instructions, and modules stored in the memory 320, thereby implementing the power consumption data anomaly analysis method described in the above embodiment. The input device 330 can receive input digital or character information and generate key signal inputs related to user settings and function control of the power consumption data anomaly analysis system. The output device 340 may include a display screen or other display device.

[0096] The aforementioned electronic device can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0097] In one implementation, the above-described electronic device is used in an electricity consumption data anomaly analysis system for a client, comprising: 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, the instructions being executed by the at least one processor to enable the at least one processor to:

[0098] Acquire a sequence of power consumption data and a sequence of equipment temperature data within a preset time period, wherein the power consumption data sequence contains power consumption data at different time points, and the equipment temperature data sequence contains equipment temperature data at different time points;

[0099] Based on the changing trend of the temperature data of each device, at least one abrupt change in device temperature data is selected from the device temperature data sequence. Based on the time node of the at least one abrupt change in device temperature data, at least one target power consumption data subsequence and at least one non-target power consumption data subsequence are extracted from the power consumption data sequence aligned with the device temperature data sequence according to the preset data extraction rules.

[0100] Determine whether the sequence deviation between the first target electricity consumption data subsequence and the second target electricity consumption data subsequence is greater than a preset deviation threshold, wherein the first target electricity consumption data subsequence and the second target electricity consumption data subsequence are two adjacent target electricity consumption data subsequences;

[0101] If the deviation exceeds the preset deviation threshold, the first target electricity consumption data subsequence and the second target electricity consumption data subsequence are defined as the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence, respectively, and an anomaly analysis of electricity consumption data is performed on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence according to the preset first data analysis strategy.

[0102] Based on the first suspected electricity consumption data subsequence and the second suspected electricity consumption data subsequence, a preset second data analysis strategy is used to perform abnormal electricity consumption data analysis on the first non-target electricity consumption data subsequence adjacent to the first suspected electricity consumption data subsequence and the second non-target electricity consumption data subsequence adjacent to the second suspected electricity consumption data subsequence.

[0103] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing anomalies in electricity consumption data, characterized in that, include: Acquire the power consumption data sequence and equipment temperature data sequence of electrical equipment within a preset time period; Based on the changing trend of temperature data of each device, at least one abrupt change in device temperature data is selected from the device temperature data sequence. Based on the time node of the at least one abrupt change in device temperature data, at least one target power consumption data subsequence and at least one non-target power consumption data subsequence are extracted from the power consumption data sequence aligned with the device temperature data sequence according to a preset data extraction rule. The step of selecting at least one temperature data point of a sudden change in the temperature data sequence of each device based on the changing trend of the temperature data of each device includes: Construct a dynamic preset temperature threshold, specifically as follows: An initial preset temperature threshold is set, which corresponds to a first temperature difference. Determine whether the first temperature difference is greater than the initial preset temperature threshold; If the first temperature difference is greater than the initial preset temperature threshold, then the first temperature difference is added to the initial preset temperature threshold to obtain an updated first preset temperature threshold, wherein the first preset temperature threshold corresponds to the second temperature difference. Determine whether the second temperature difference is greater than the first preset temperature threshold; If the second temperature difference is greater than the first preset temperature threshold, then the second temperature difference is added to the initial preset temperature threshold to obtain an updated second preset temperature threshold, wherein the second preset temperature threshold corresponds to the third temperature difference. The temperature difference between two adjacent equipment temperature data in the equipment temperature data sequence is compared with the corresponding dynamic preset temperature threshold, and the comparison results are used to determine whether there is at least one abrupt change in equipment temperature data in the equipment temperature data sequence. If there is no temperature data of at least one device that changes abruptly, then it is directly determined that each power consumption data in the power consumption data sequence corresponding to the device temperature data sequence is normal; If at least one temperature data point of a mutated device exists, then the at least one temperature data point of a mutated device is selected from the device temperature data sequence; Determine whether the sequence deviation between the first target electricity consumption data subsequence and the second target electricity consumption data subsequence is greater than a preset deviation threshold; If the deviation exceeds the preset deviation threshold, the first target electricity consumption data subsequence and the second target electricity consumption data subsequence are defined as the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence, respectively, and an anomaly analysis of electricity consumption data is performed on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence according to the preset first data analysis strategy. Based on the first suspected electricity consumption data subsequence and the second suspected electricity consumption data subsequence, a preset second data analysis strategy is used to perform abnormal electricity consumption data analysis on the first non-target electricity consumption data subsequence adjacent to the first suspected electricity consumption data subsequence and the second non-target electricity consumption data subsequence adjacent to the second suspected electricity consumption data subsequence.

2. The method for analyzing abnormal electricity consumption data according to claim 1, characterized in that, in, The electricity consumption data sequence contains electricity consumption data at different time points, and the equipment temperature data sequence contains equipment temperature data at different time points; The first temperature difference is: the difference between the first device temperature data at the first position and the second device temperature data at the second position in the device temperature data sequence; The second temperature difference is the difference between the second device temperature data at the second position and the third device temperature data at the third position in the device temperature data sequence. The third temperature difference is the difference between the third device temperature data at the third position and the fourth device temperature data at the fourth position in the device temperature data sequence.

3. The method for analyzing abnormal electricity consumption data according to claim 1, characterized in that, in, The first target electricity consumption data subsequence and the second target electricity consumption data subsequence are two adjacent target electricity consumption data subsequences; After determining whether the first temperature difference is greater than the initial preset temperature threshold, the method further includes: If the first temperature difference is not greater than the initial preset temperature threshold, then the initial preset temperature threshold is directly defined as the first preset temperature threshold. If the second temperature difference is not greater than the first preset temperature threshold, then the first preset temperature threshold is directly defined as the second preset temperature threshold.

4. The method for analyzing abnormal electricity consumption data according to claim 1, characterized in that, The step of extracting at least one target electricity consumption data subsequence and at least one non-target electricity consumption data subsequence from the electricity consumption data sequence aligned with the equipment temperature data sequence based on the time node of the at least one abruptly changed equipment temperature data and a preset data extraction rule includes: Align the equipment temperature data sequence with the power consumption data sequence, and select power consumption data in the power consumption data sequence that is at the same time node as the at least one abruptly changed equipment temperature data, and define it as abruptly changed power consumption data; Using the location of a certain sudden change in electricity consumption data as the center point, a certain electricity consumption data subsequence of a preset length is extracted from the electricity consumption data sequence; Based on the chronological order, determine whether the absolute difference in electricity consumption between two adjacent electricity consumption data in a certain electricity consumption data subsequence is greater than a preset electricity consumption threshold. If the absolute difference in electricity consumption between any two adjacent electricity consumption data in a certain electricity consumption data subsequence is not greater than a preset electricity consumption threshold, then the certain electricity consumption data subsequence is directly defined as the target electricity consumption data subsequence. If the absolute difference in electricity consumption between the first electricity consumption data and the second electricity consumption data in a certain electricity consumption data subsequence is greater than a preset electricity consumption threshold, then the position point where the first electricity consumption data is located is defined as the first cutoff point. Here, the time node corresponding to the first electricity consumption data is earlier than the time node corresponding to the second electricity consumption data, and the first electricity consumption data and the second electricity consumption data are two adjacent electricity consumption data that are greater than the preset electricity consumption threshold for the first time based on the time sequence. Using the center point as a symmetrical point, obtain a second cutoff point that is symmetrical to the first cutoff point. Extract the electricity consumption data between the first cutoff point and the second cutoff point from a certain electricity consumption data subsequence to obtain the target electricity consumption data subsequence. Each target electricity consumption data subsequence is extracted from the electricity consumption data sequence to obtain at least one target electricity consumption data subsequence and at least one non-target electricity consumption data subsequence.

5. The method for analyzing abnormal electricity consumption data according to claim 1, characterized in that, Before determining whether the sequence deviation between the first target electricity consumption data subsequence and the second target electricity consumption data subsequence is greater than a preset deviation threshold, the method further includes: Align the first target electricity consumption data subsequence and the second target electricity consumption data subsequence based on the center point of the target electricity consumption data subsequence; The target electricity consumption data located at the first center point of the first target electricity consumption data subsequence is defined as the first center target electricity consumption data, and the target electricity consumption data located at the second center point of the second target electricity consumption data subsequence is defined as the second center target electricity consumption data. Obtain the first absolute difference in electricity consumption between the first other target electricity consumption data and the first central target electricity consumption data, wherein the first other target electricity consumption data is the first target electricity consumption data excluding the first central target electricity consumption data in the first target electricity consumption data subsequence; Obtain the second absolute difference in electricity consumption between the second other target electricity consumption data and the second central target electricity consumption data, wherein the second other target electricity consumption data is the second target electricity consumption data excluding the second central target electricity consumption data in the second target electricity consumption data subsequence; The absolute difference of the first electricity consumption of the first other target electricity consumption data that are aligned and in the same position is subtracted again from the absolute difference of the second electricity consumption of the second other target electricity consumption data to obtain the degree of deviation of each absolute difference of electricity consumption. The degree of deviation of each deviation is added together to obtain the degree of sequence deviation between the first target electricity consumption data subsequence and the second target electricity consumption data subsequence.

6. The method for analyzing abnormal electricity consumption data according to claim 1, characterized in that, After determining whether the sequence deviation between the first target electricity consumption data subsequence and the second target electricity consumption data subsequence is greater than a preset deviation threshold, the method further includes: If the deviation is not greater than the preset deviation threshold, then the first target electricity consumption data subsequence is subjected to electricity consumption data anomaly analysis according to the first data analysis strategy, wherein the sequence length in the first target electricity consumption data subsequence is greater than the sequence length in the second target electricity consumption data subsequence; The analysis results of each first target electricity consumption data in the first target electricity consumption data subsequence are directly assigned to each second target electricity consumption data in the second target electricity consumption data subsequence that is in the same position.

7. The method for analyzing abnormal electricity consumption data according to claim 1, characterized in that, The step of performing electricity consumption anomaly analysis on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence according to a preset first data analysis strategy includes: Obtain the first maximum change in electricity consumption in the first suspected electricity consumption data subsequence and the second maximum change in electricity consumption in the second suspected electricity consumption data subsequence, and determine whether the first maximum change in electricity consumption and the second maximum change in electricity consumption are greater than a preset electricity consumption change threshold. If the first maximum change in electricity consumption is not greater than the preset threshold for change in electricity consumption, then each of the first suspected electricity consumption data in the first suspected electricity consumption data subsequence is defined as abnormal electricity consumption data; otherwise, the first suspected electricity consumption data in the first suspected electricity consumption data subsequence that is greater than the first suspected average electricity consumption value is defined as abnormal electricity consumption data. If the second maximum change in electricity consumption is not greater than the preset threshold for change in electricity consumption, then each second suspected electricity consumption data in the second suspected electricity consumption data subsequence is defined as abnormal electricity consumption data; otherwise, the second suspected electricity consumption data in the second suspected electricity consumption data subsequence that is greater than the second suspected average electricity consumption value is defined as abnormal electricity consumption data.

8. The method for analyzing abnormal electricity consumption data according to claim 7, characterized in that, The step of performing abnormal electricity consumption data analysis on the first non-target electricity consumption data subsequence adjacent to the first suspicious electricity consumption data subsequence and the second non-target electricity consumption data subsequence adjacent to the second suspicious electricity consumption data subsequence using a preset second data analysis strategy includes: When the first maximum change in electricity consumption is greater than the preset change in electricity consumption threshold, it is directly determined that each of the first non-target electricity consumption data in the first non-target electricity consumption data subsequence is normal electricity consumption data. If the first maximum change in electricity consumption is not greater than the preset change in electricity consumption threshold, then the first non-target electricity consumption data in the first non-target electricity consumption data subsequence that is greater than the first non-target average electricity consumption value is defined as abnormal electricity consumption data. When the second maximum change in electricity consumption is greater than the preset change in electricity consumption threshold, then each of the second non-target electricity consumption data in the second non-target electricity consumption data subsequence is directly determined to be normal electricity consumption data. If the second maximum change in electricity consumption is not greater than the preset threshold for change in electricity consumption, then the second non-target electricity consumption data in the second non-target electricity consumption data subsequence that is greater than the second non-target average electricity consumption value is defined as abnormal electricity consumption data.

9. A power consumption data anomaly analysis system, characterized in that, include: The acquisition module is configured to acquire the power consumption data sequence and the equipment temperature data sequence of the electrical equipment within a preset time period; The interception module is configured to select at least one abruptly changing device temperature data in the device temperature data sequence according to the changing trend of each device temperature data, and based on the time node of the at least one abruptly changing device temperature data, intercept at least one target power consumption data subsequence and at least one non-target power consumption data subsequence in the power consumption data sequence aligned with the device temperature data sequence according to a preset data interception rule. The step of selecting at least one temperature data point of a sudden change in the temperature data sequence of each device based on the changing trend of the temperature data of each device includes: Construct a dynamic preset temperature threshold, specifically as follows: An initial preset temperature threshold is set, which corresponds to a first temperature difference. Determine whether the first temperature difference is greater than the initial preset temperature threshold; If the first temperature difference is greater than the initial preset temperature threshold, then the first temperature difference is added to the initial preset temperature threshold to obtain an updated first preset temperature threshold, wherein the first preset temperature threshold corresponds to the second temperature difference. Determine whether the second temperature difference is greater than the first preset temperature threshold; If the second temperature difference is greater than the first preset temperature threshold, then the second temperature difference is added to the initial preset temperature threshold to obtain an updated second preset temperature threshold, wherein the second preset temperature threshold corresponds to the third temperature difference. The temperature difference between two adjacent equipment temperature data in the equipment temperature data sequence is compared with the corresponding dynamic preset temperature threshold, and the comparison results are used to determine whether there is at least one abrupt change in equipment temperature data in the equipment temperature data sequence. If there is no temperature data of at least one device that changes abruptly, then it is directly determined that each power consumption data in the power consumption data sequence corresponding to the device temperature data sequence is normal; If at least one temperature data point of a mutated device exists, then the at least one temperature data point of a mutated device is selected from the device temperature data sequence; The judgment module is configured to determine whether the sequence deviation between the first target electricity consumption data subsequence and the second target electricity consumption data subsequence is greater than a preset deviation threshold. The first analysis module is configured to, if the deviation exceeds a preset deviation threshold, define the first target electricity consumption data subsequence and the second target electricity consumption data subsequence as the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence, respectively, and perform electricity consumption data anomaly analysis on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence according to a preset first data analysis strategy. The second analysis module is configured to perform abnormal electricity consumption data analysis on the first non-target electricity consumption data subsequence adjacent to the first suspected electricity consumption data subsequence and the second non-target electricity consumption data subsequence adjacent to the second suspected electricity consumption data subsequence, based on the first suspected electricity consumption data subsequence and the second suspected electricity consumption data subsequence, using a preset second data analysis strategy.

Images