Household electric power measurement data security risk early warning method and system
By generating calibration coefficients and calculating power change index, the problem of smart meter being unable to sense circuit aging leakage and inaccurate measurement of electricity consumption data in advance is solved, and refined and real-time monitoring of household power metering data is realized, reducing power stealing and Risk of leakage.
Patent Information
- Application Number
- CN202411516967.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-29
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing smart meters cannot sense the aging leakage of household electrical circuits in advance, resulting in inaccurate measurement of electricity consumption data and ineffective early warning of peak and valley electricity consumption, which may lead to electricity stealing or leakage, and the load cannot be accurately monitored under temperature and holiday changes. power.
By collecting load power timing data and temperature data from the past seven days, generating calibration coefficients, dividing the time interval and calculating the reference average, maximum and minimum power, combining real-time data to calculate the power change index, comparing with preset thresholds to judge abnormal power metering data, issuing Early warning.
It realizes refined and real-time monitoring of household power metering data, reduces the difference in load power caused by temperature and holiday changes, improves sensitivity, promptly detects electricity stealing or leakage, and reduces user losses.
Smart Images

Figure CN119047846A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of household electrical appliance power consumption risk early warning, and in particular to a household electricity metering data security risk early warning method and system. Background Art
[0002] With the rapid expansion of the power grid and the emergence of new household appliances, household electricity is facing more serious nonlinearity and randomness in electricity consumption. In addition, the reform of the power market and the management of electricity demand also require electricity metering to be accurate and real-time. Therefore, a household electricity metering data security risk warning method and system are needed to judge, measure and record electricity usage, provide users with accurate electricity usage data, and help users use electricity reasonably and save energy.
[0003] In the existing technology, the publication number is CN114088998A, which uses smart meters to measure household electricity data to achieve safety risk warning. By analyzing the trend of residual current changes and combining multiple factors such as line temperature rise, current and voltage original waveforms, the circuit risk trend is obtained. Combined with the software platform to display the trend chart in real time, it can better warn of risks. Therefore, the present invention functionally meets the premise of prepayment and electrical risk warning and greatly reduces the false alarm rate. Its working principle is to measure the user's electricity consumption and output digital or electronic pulse information about the user's electricity consumption data. It can accurately measure the electricity consumption and process various information in a timely manner, and record the electricity consumption within a week as well as the peak and valley electricity consumption and the low peak and valley electricity consumption.
[0004] The shortcomings of existing technologies are: The risk warning of existing smart meters is aimed at overload conditions of electrical equipment. Generally, this is caused by aging and leakage of household appliance circuits, which are greatly affected by temperature. Smart meters cannot sense it in advance. Once the total current exceeds the overload protection current, a "tripping" phenomenon will occur.
[0005] There are big differences in household electricity metering data between weekdays and weekends, and smart meters cannot accurately measure the actual electricity consumption data of peak and valley electricity consumption and low peak and valley electricity consumption during the day, which will lead to electricity theft without the user's detection, causing the user to suffer losses.
[0006] Therefore, it is necessary to provide a household electricity metering data security risk early warning method and system to solve the above problem.
[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention
[0008] The object of the present invention is to provide a household electricity metering data security risk early warning method and system to solve the problems raised in the above background technology.
[0009] To achieve the above object, the present invention provides the following technical solutions: A household electricity metering data security risk early warning method, the specific steps include: Step 1: Collect the user's daily load power time series data and daily average temperature and holiday situation data in the past seven days, generate a first calibration coefficient based on the holiday situation data and temperature data, and use the first calibration coefficient to calibrate the load power time series data of each day; Step 2: Divide the calibrated load power time series data into multiple time intervals in chronological order, collect the average power, maximum power and minimum power in each time interval, set the weight coefficient of each time interval, and generate the reference average power, reference maximum power and reference minimum power of each time interval according to the load power time series data fragments of each time interval every day;
[0010] Step 3: Collect the real-time power value at the current moment, determine the time interval to which the current moment belongs, collect the load power time series data of the time interval corresponding to the current moment, calibrate it as the monitoring load power time series data, collect the current temperature and holiday situation data, and generate the second calibration coefficient; Step 4: Use the second calibration coefficient to calibrate the monitoring load power time series data, calculate the average power value and the power growth rate through the calibrated monitoring load power time series data, and comprehensively generate the power change index based on the average power value and the power growth rate of the calibrated monitoring load power time series data, and the reference average power, reference maximum power and reference minimum power of the corresponding time interval in the historical data; Step 5: Compare the power change index with the preset threshold value, and determine whether the power metering data is abnormal based on the comparison result. If it is abnormal, issue an early warning; According to the holiday data, the calibration is performed based on whether the day is a holiday. The method is as follows: If the day is a holiday, the holiday data for that day is If it is not a holiday, the holiday data for that day is ,and , the first calibration coefficient is generated based on the following logic: ; in, Indicates the first The average temperature of the day, Indicated in The first calibration factor of the day, Indicated in Days of holiday data, is a positive integer, and ; The second calibration coefficient is generated based on the method: If the day is a holiday, the holiday data for that day is If it is not a holiday, the holiday data for that day is ,and ,The logic for generating the second calibration coefficient is: ; in, represents the second calibration coefficient, Indicates the holiday data for the current day. Indicates the collected current temperature data.
[0011] The formula for the comprehensive generation power variation index is: ; in, Indicates the load power timing data after calibration in this time interval at the current moment. Indicates the load power of the time interval at the current moment, The formula for calculating the average power value and the power growth rate is based on the second calibration coefficient: ; ; in, represents the average power value, , Represents the value of the monitoring time interval at the current moment. represents the power growth rate; The power change index is generated comprehensively based on the average power value and power growth rate of the calibrated monitoring load power time series data, and the reference average power, reference maximum power and reference minimum power of the corresponding time interval in the historical data. The formula is as follows: ; in, represents the average power, represents the reference average power, , Represents the reference maximum power and reference minimum power, Represents the power growth rate.
[0012] Furthermore, the first calibration coefficient is used to calibrate the load power time series data of each day, and the formula based on it is: ; In the formula, Indicates the calibration Daily load power time series data, Indicates Daily load power time series data,
[0013] Furthermore, the calibrated load power time series data is divided into multiple time intervals in chronological order, and the average power, maximum power and minimum power in each time interval are collected, and the weight coefficient of each time interval is set, and the method based on which is: Divide into multiple time intervals according to time sequence The first time interval and the second time interval Set the third time interval to the peak period of electricity consumption. and the fourth time interval Set to low-peak hours, and , generates the average power, based on the formula: ; In the formula Indicates user Tiandi The average power consumption in a time interval, , Respectively The lower and upper limits corresponding to the time intervals, Indicates Tiandi Load power timing data within a time period.
[0014] The maximum power and minimum power in each time interval are based on the formula: ; ; In the formula, Represents the Tiandi The maximum power in a time period, Represents the Tiandi The minimum power in a time period.
[0015] Furthermore, based on the load power time series data fragments of each time interval every day, the reference average power, reference maximum power and reference minimum power of each time interval are generated, and the formula based on them is: ; ; ; In the formula, Representative The reference average power in the time interval is Representative The reference maximum power in a time interval is Representative The reference minimum power within a time interval.
[0016] Furthermore, the real-time power value at the current moment is collected, the time interval to which the current moment belongs is determined, and the load power time series data of the time interval corresponding to the current moment is collected and calibrated as the monitoring load power time series data. The method is as follows: At each time point, the real-time power value of the current moment is collected. According to the time interval provided, the peak period is marked as "peak" and the low peak period is marked as "low peak". Then, according to the timestamp of the current moment, the timestamp boundary moment is compared with the The size of the moment to determine the time segment to which it belongs. If the timestamp is less than , then the current time belongs to the first time interval; if the timestamp is greater than , but less than , then the current time belongs to the second time interval; if the timestamp is greater than or equal to , but less than , then the current time belongs to the third time interval; if the timestamp is greater than or equal to , then the current moment belongs to the last interval.
[0017] Furthermore, the power variation index is compared with a preset threshold value, and the power metering data is judged to be abnormal according to the comparison result. If it is abnormal, an early warning is issued, and the method is based on: Compare the power change index with the preset threshold and set the upper limit of the risk warning threshold , Risk warning threshold lower limit ,and , the comprehensive power variation index and risk warning threshold , For comparison, if , it indicates that the household electricity metering data is normal; if or , it indicates that there is an abnormality in the household electricity metering data, there is leakage or electricity theft, and a risk warning signal is issued to remind users to check the meter data and the operation of the overall circuit.
[0018] The present invention also provides a household electricity metering data security risk early warning system, the early warning system is used to execute any of the household electricity metering data security risk early warning methods described above, comprising: The historical data collection module is used to collect the user's daily load power time series data and the daily average temperature and holiday situation data in the past seven days, generate a first calibration coefficient according to the holiday situation data and temperature data, and use the first calibration coefficient to calibrate the load power time series data of each day; The data calibration processing module is used to divide the calibrated load power time series data into multiple time intervals in chronological order, collect the average power, maximum power and minimum power in each time interval, set the weight coefficient of each time interval, and generate the reference average power, reference maximum power and reference minimum power of each time interval according to the load power time series data fragments of each time interval every day;
[0019] A real-time data acquisition module is used to collect the real-time power value at the current moment, determine the time interval to which the current moment belongs, collect the load power time series data of the time interval corresponding to the current moment, calibrate it as monitoring load power time series data, collect the current temperature and holiday situation data, and generate a second calibration coefficient; An index generating module is used to calibrate the monitoring load power time series data using a second calibration coefficient, calculate the average power value and the power growth rate through the calibrated monitoring load power time series data, and comprehensively generate a power change index based on the average power value and the power growth rate of the calibrated monitoring load power time series data, and the reference average power, reference maximum power and reference minimum power of the corresponding time interval in the historical data; The risk warning module is used to compare the power change index with the preset threshold value, and judge whether the power metering data is abnormal based on the comparison result. If it is abnormal, an early warning is issued.
[0020] Compared with the prior art, the present invention has the following beneficial effects: The present invention monitors the load power data in real time by generating a comprehensive power change index, thereby avoiding the situation where household appliances are damaged due to aging and leakage caused by temperature changes or different power consumption during holidays, and generates reference average power, reference maximum power and reference minimum power for each time interval based on the load power time series data fragments of each time interval every day. If "power theft" occurs, the average power, maximum power and minimum power in the load power time series data monitored in real time will be different from the reference average power, reference maximum power and reference minimum power data of each time interval every day, so that users can be aware of the "power theft" in time. By setting up a risk threshold and comparing it with the comprehensive power change index, the situation of users "tripping" during peak power consumption is effectively reduced. The present invention reduces the differences in load power on different days caused by temperature environment and holidays. By comparing the comprehensive power change index with the risk warning threshold, it is convenient to monitor power changes, greatly improves the sensitivity, and achieves refined and real-time monitoring of electricity consumption. In each time period, load power changes caused by power theft or leakage can be discovered in time. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Figure 1 It is a schematic diagram of the overall method flow of the present invention.
[0022] Figure 2 It is a schematic diagram of the system module flow of the present invention. DETAILED DESCRIPTION
[0023] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.
[0024] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0025] Example: See also Figure 1 , a household electricity metering data security risk early warning method, comprising: Step 1: Collect the user's daily load power time series data and daily average temperature and holiday situation data in the past seven days, generate a first calibration coefficient based on the holiday situation data and temperature data, and use the first calibration coefficient to calibrate the load power time series data of each day; Step 2: Divide the calibrated load power time series data into multiple time intervals in chronological order, collect the average power, maximum power and minimum power in each time interval, set the weight coefficient of each time interval, and generate the reference average power, reference maximum power and reference minimum power of each time interval according to the load power time series data fragments of each time interval every day;
[0026] Step 3: Collect the real-time power value at the current moment, determine the time interval to which the current moment belongs, collect the load power time series data of the time interval corresponding to the current moment, calibrate it as the monitoring load power time series data, collect the current temperature and holiday situation data, and generate the second calibration coefficient; Step 4: Use the second calibration coefficient to calibrate the monitoring load power time series data, calculate the average power value and the power growth rate through the calibrated monitoring load power time series data, and comprehensively generate the power change index based on the average power value and the power growth rate of the calibrated monitoring load power time series data, and the reference average power, reference maximum power and reference minimum power of the corresponding time interval in the historical data; Step 5: Compare the power change index with the preset threshold value, and determine whether the power metering data is abnormal based on the comparison result. If it is abnormal, issue an early warning; According to the holiday data, the calibration is performed based on whether the day is a holiday. The method is as follows: If the day is a holiday, the holiday data for that day is If it is not a holiday, the holiday data for that day is ,and , the first calibration coefficient is generated based on the following logic: ; in, Indicates the first The average temperature of the day, Indicated in The first calibration factor of the day, Indicated in Day holiday data, is a positive integer, and .
[0027] The second calibration coefficient is generated based on the method: If the day is a holiday, the holiday data for that day is If it is not a holiday, the holiday data for that day is ,and ,The logic for generating the second calibration coefficient is: ; in, represents the second calibration coefficient, Indicates the holiday data for the current day. Indicates the collected current temperature data.
[0028] The formula for the comprehensive generation power variation index is: ; in, Indicates the load power timing data after calibration in this time interval at the current moment. Indicates the load power of the time interval at the current moment, The formula for calculating the average power value and the power growth rate is based on the second calibration coefficient: ; ; in, represents the average power value, , Represents the value of the monitoring time interval at the current moment. represents the power growth rate; The power change index is generated comprehensively based on the average power value and power growth rate of the calibrated monitoring load power time series data, and the reference average power, reference maximum power and reference minimum power of the corresponding time interval in the historical data. The formula is as follows: ; in, represents the average power, represents the reference average power, , Represents the reference maximum power and reference minimum power, Represents the power growth rate.
[0029] It should be noted that by using the first calibration coefficient, the load power timing data can be adjusted to more accurately reflect the actual battery charging or usage. The calibration coefficient is usually generated based on historical data, system performance standards or experimental results, and it can correct the system deviation, measurement error or other influencing factors in the data, thereby improving the accuracy of the data.
[0030] Therefore, it is necessary to use the generated first calibration coefficient to calibrate the user's daily load power time series in the past seven days, based on the following logic: ; in, Indicates the calibration Daily load power time series data, Indicates Daily load power time series data, It can be seen from the above formula that the size of the first calibration coefficient is determined by the temperature and whether the day is a holiday. It can be seen from the formula that the size of the first calibration coefficient is proportional to the temperature, and the load power timing data is inversely proportional to the first calibration coefficient, which reflects the extent to which the user's seven-day load power timing data needs to be calibrated to the standard load power timing data under the influence of holiday situation data and temperature data. Using the first calibration coefficient to calibrate the user's load power timing data can reduce the impact of holiday situation data and temperature.
[0031] It should be noted that the division of time intervals can divide the continuous power time series data into discrete parts, each of which can be analyzed separately. Because only collecting the user's load power time series data for one week is not representative, it is necessary to set a reference average power, reference maximum power and reference minimum power that can be used for reference and comparison in each time interval. The purpose of this is to facilitate real-time monitoring of load power changes.
[0032] Therefore, it is necessary to divide the calibrated load power time series data into multiple time intervals in chronological order, collect the average power, maximum power and minimum power in each time interval, and set the weight coefficient of each time interval. The method is as follows: Divide into multiple time intervals according to time sequence The first time interval and the second time interval Set the third time interval to the peak period of electricity consumption. and the fourth time interval Set as low-peak electricity consumption period, the first peak electricity consumption time interval Take every day of the week The second peak period Take every day of the week The second low-peak period is every day in a week. and , generates the average power, based on the formula: ; in, Indicates user Tiandi The average power consumption in a time interval, , Respectively The lower and upper limits corresponding to the time intervals, Indicates Tiandi The load power time series data in each time period, the maximum power and minimum power in each time interval, are based on the formula: ; ; in, Represents the Tiandi The maximum power in a time period, Represents the Tiandi The minimum power in a time period; From the above formula, we can know that for the Load power time series data for the day ] to obtain the average power in any time period, and to determine the exact range of maximum power and minimum power by comparing the average power at the same time of the day. ], after determining the interval, select the maximum and minimum load power data within this time interval.
[0033] It should be noted that by calculating the reference average power, maximum power and minimum power, a performance benchmark can be established for each time interval. These benchmark values help determine the normal operating range, thereby identifying load conditions that do not meet expectations, and thus help monitor the performance and stability of the battery charging cabinet.
[0034] Therefore, it is necessary to generate the reference average power, reference maximum power and reference minimum power of each time interval based on the load power time series data fragments in the same time interval every day. The formula is as follows: ; ; ; in, Representative The reference average power in the time interval is Representative The reference maximum power in a time interval is Representative The reference minimum power in the time interval; in the above formula, by The load power time series data fragments of the same time interval on the same day are summed to obtain the reference average power, and then Tiandi The maximum value and the minimum value of the load power time series in the time interval are taken as the reference maximum power and the reference minimum power.
[0035] It should be noted that by collecting the real-time power value at the current moment and calibrating the load power time series data of the corresponding time interval, real-time monitoring, dynamic performance analysis, accurate load prediction, improved decision quality, abnormal detection and early warning, and optimized energy efficiency management can be achieved. These measures ensure the efficient, stable and reliable operation of the system.
[0036] Therefore, it is necessary to collect the real-time power value at the current moment, determine the time interval to which the current moment belongs, collect the load power time series data of the time interval corresponding to the current moment, and calibrate it as the monitoring load power time series data. The method is as follows: At each time point, the real-time power value of the current moment is collected. According to the time interval provided, the peak period is marked as "peak" and the low peak period is marked as "low peak". Then, according to the timestamp of the current moment, the timestamp boundary moment is compared with the The size of the moment to determine the time segment to which it belongs. If the timestamp is less than , then the current time belongs to the first time interval; if the timestamp is greater than , but less than , then the current time belongs to the second time interval; if the timestamp is greater than or equal to , but less than , then the current time belongs to the third time interval; if the timestamp is greater than or equal to , then the current moment belongs to the last interval.
[0037] It should be noted that comparing the power change index with the preset threshold can detect whether the power metering data is abnormal in real time. This real-time performance is very critical, as it can immediately detect and take necessary measures when a problem occurs, avoiding potential losses or expanding the problem.
[0038] Therefore, it is necessary to compare the power variation index with a preset threshold value, and the method is as follows: Set the upper limit of risk warning threshold , Risk warning threshold lower limit ,and , the comprehensive power variation index and risk warning threshold , For comparison, if , it indicates that the household electricity metering data is normal; if or , it indicates that there is an abnormality in the household electricity metering data, there is leakage or electricity theft, and a risk warning signal is issued to remind users to check the meter data and the operation of the overall circuit.
[0039] See also Figure 2 The present invention also provides a household electricity metering data security risk early warning system, comprising: The historical data collection module is used to collect the user's daily load power time series data and the daily average temperature and holiday situation data in the past seven days, generate a first calibration coefficient according to the holiday situation data and temperature data, and use the first calibration coefficient to calibrate the load power time series data of each day; The data calibration module is used to divide the calibrated load power time series data into multiple time intervals in chronological order, collect the average power, maximum power and minimum power in each time interval, and set the weight coefficient of each time interval; A preprocessing module, used to generate a reference average power, a reference maximum power and a reference minimum power for each time interval according to the load power time series data fragments of each time interval every day;
[0040] A real-time data acquisition module is used to collect the real-time power value at the current moment, determine the time interval to which the current moment belongs, collect the load power time series data of the time interval corresponding to the current moment, calibrate it as monitoring load power time series data, collect the current temperature and holiday situation data, and generate a second calibration coefficient; A data processing module, used to calibrate the monitoring load power time series data using a second calibration coefficient, and calculate an average power value and a power growth rate through the calibrated monitoring load power time series data; A monitoring and adjustment module is used to comprehensively generate a power change index based on the average power value and power growth rate of the calibrated monitoring load power time series data, and the reference average power, reference maximum power and reference minimum power of the corresponding time interval in the historical data; The risk warning module is used to compare the power change index with the preset threshold value, and judge whether the power metering data is abnormal based on the comparison result. If it is abnormal, an early warning is issued.
[0041] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0042] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.
[0043] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0044] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.
Claims
1. A household electricity metering data security risk early warning method, characterized in that: The specific steps include: Step 1: Collect the user's daily load power time series data and daily average temperature and holiday situation data in the past seven days, generate a first calibration coefficient based on the holiday situation data and temperature data, and use the first calibration coefficient to calibrate the load power time series data of each day; Step 2: Divide the calibrated load power time series data into multiple time intervals in chronological order, collect the average power, maximum power and minimum power in each time interval, set the weight coefficient of each time interval, and generate the reference average power, reference maximum power and reference minimum power of each time interval according to the load power time series data fragments of each time interval every day; Step 3: Collect the real-time power value at the current moment, determine the time interval to which the current moment belongs, collect the load power time series data of the time interval corresponding to the current moment, calibrate it as the monitoring load power time series data, collect the current temperature and holiday situation data, and generate the second calibration coefficient; Step 4: Use the second calibration coefficient to calibrate the monitoring load power time series data, calculate the average power value and the power growth rate through the calibrated monitoring load power time series data, and comprehensively generate the power change index based on the average power value and the power growth rate of the calibrated monitoring load power time series data, and the reference average power, reference maximum power and reference minimum power of the corresponding time interval in the historical data; Step 5: Compare the power change index with the preset threshold value, and determine whether the power metering data is abnormal based on the comparison result. If it is abnormal, issue an early warning; According to the holiday data, the calibration is performed based on whether the day is a holiday. The method is as follows: If the day is a holiday, the holiday data for that day is If it is not a holiday, the holiday data for that day is ,and , the first calibration coefficient is generated based on the following logic: ; in, Indicates the first The average temperature of the day, Indicated in The first calibration factor of the day, Indicated in Days of holiday data, is a positive integer, and ; The second calibration coefficient is generated based on the method: If the day is a holiday, the holiday data for that day is If it is not a holiday, the holiday data for that day is ,and ,The logic for generating the second calibration coefficient is: ; in, represents the second calibration coefficient, Indicates the holiday data for the current day. Indicates the data of the current temperature collected; The formula for the comprehensive generation power variation index is: ; in, Indicates the load power timing data after calibration in this time interval at the current moment. Indicates the load power of the time interval at the current moment, The formula for calculating the average power value and the power growth rate is based on the second calibration coefficient: ; ; in, represents the average power value, , Represents the value of the monitoring time interval at the current moment. represents the power growth rate; The power change index is generated comprehensively based on the average power value and power growth rate of the calibrated monitoring load power time series data, and the reference average power, reference maximum power and reference minimum power of the corresponding time interval in the historical data. The formula is as follows: ; in, represents the average power, represents the reference average power, , Represents the reference maximum power and reference minimum power, Represents the power growth rate.
2. A household electricity metering data security risk early warning method according to claim 1, characterized in that: The generated first calibration coefficient is used to calibrate the user's daily load power time series data in the past seven days, based on the following logic: ; in, Indicates the calibration Daily load power time series data, Indicates Daily load power time series data, Represents a time variable.
3. A household electricity metering data security risk early warning method according to claim 1, characterized in that: The calibrated load power time series data is divided into multiple time intervals in chronological order, and the average power, maximum power and minimum power in each time interval are collected, and the weight coefficient of each time interval is set. The method is based on: Divide into multiple time intervals according to time sequence The first time interval and the second time interval Set it as the peak period of electricity consumption, and set the third time interval and the fourth time interval Set to low-peak hours, and , the formula for generating average power is: ; in, Indicates user Tiandi The average power consumption in a time interval, , Respectively The lower and upper limits corresponding to the time intervals, Indicates Tiandi The load power time series data in each time period, the maximum power and minimum power in each time interval, are based on the formula: ; ; in, Represents the Tiandi The maximum power in a time period, Represents the Tiandi The minimum power in a time period.
4. A household electricity metering data security risk early warning method according to claim 1, characterized in that: Based on the load power time series data fragments in the same time interval every day, the reference average power, reference maximum power and reference minimum power of each time interval are generated according to the following formula: ; ; ; in, Representative The reference average power in the time interval is Representative The reference maximum power in a time interval is Representative The reference minimum power within a time interval.
5. A household electricity metering data security risk early warning method according to claim 1, characterized in that: Collect the real-time power value at the current moment, determine the time interval to which the current moment belongs, collect the load power time series data of the time interval at the current moment, and calibrate it as the monitoring load power time series data. The method is based on: According to the time interval provided, the peak period is marked as "peak" and the off-peak period is marked as "off-peak", and then the timestamp boundary moment is compared with the current time stamp. The size of the moment to determine the time segment to which it belongs. If the timestamp is less than , then the current time belongs to the first time interval; if the timestamp is greater than , but less than , then the current moment belongs to the second time interval; If the timestamp is greater than or equal to , but less than , then the current moment belongs to the third time interval; If the timestamp is greater than or equal to , then the current moment belongs to the last interval.
6. A household electricity metering data security risk early warning method according to claim 1, characterized in that: The power change index is compared with the preset threshold value, and the power metering data is judged to be abnormal based on the comparison result. If it is abnormal, an early warning is issued. The method is based on: Compare the power change index with the preset threshold and set the upper limit of the risk warning threshold , Risk warning threshold lower limit ,and , the comprehensive power variation index and risk warning threshold , For comparison, if , it indicates that the household electricity metering data is normal; if or , it indicates that there is an abnormality in the household electricity metering data, there is leakage or electricity theft, and a risk warning signal is issued to remind users to check the meter data and the operation of the overall circuit.
7. A household electricity metering data security risk early warning system, the early warning system is used to execute the household electricity metering data security risk early warning method according to any one of claims 1 to 6, comprising: The historical data collection module is used to collect the user's daily load power time series data and the daily average temperature and holiday situation data in the past seven days, generate a first calibration coefficient according to the holiday situation data and temperature data, and use the first calibration coefficient to calibrate the load power time series data of each day; The data calibration processing module is used to divide the calibrated load power time series data into multiple time intervals in chronological order, collect the average power, maximum power and minimum power in each time interval, set the weight coefficient of each time interval, and generate the reference average power, reference maximum power and reference minimum power of each time interval according to the load power time series data fragments of each time interval every day; A real-time data acquisition module is used to collect the real-time power value at the current moment, determine the time interval to which the current moment belongs, collect the load power time series data of the time interval corresponding to the current moment, calibrate it as monitoring load power time series data, collect the current temperature and holiday situation data, and generate a second calibration coefficient; An index generating module is used to calibrate the monitoring load power time series data using a second calibration coefficient, calculate the average power value and the power growth rate through the calibrated monitoring load power time series data, and comprehensively generate a power change index based on the average power value and the power growth rate of the calibrated monitoring load power time series data, and the reference average power, reference maximum power and reference minimum power of the corresponding time interval in the historical data; The risk warning module is used to compare the power change index with the preset threshold value, and judge whether the power metering data is abnormal based on the comparison result. If it is abnormal, an early warning is issued.
Citation Information
Patent Citations
Monitoring and early warning method for abnormal electricity utilization behaviors of elderly people living alone based on electric power big data
CN114493918A
Reactive compensation method of power distribution system
CN116231675A
Residential electricity consumption abnormity monitoring method and intelligent electric meter thereof
CN116449284A
Power supply state monitoring and early warning system and method for 5G communication equipment
CN117676685A
Power consumption monitoring method and system for intelligent electric meter
CN117990976A
Cited By
Power utilization safety monitoring method based on daily power utilization characteristics
CN119628236A
Power failure risk early warning system and method based on real-time state of power grid
CN119809321A
Fault online monitoring and analysis electric energy meter based on multi-source data fusion
CN121933803A
