Method for monitoring electricity consumption abnormity of low-voltage user

Abstract

The invention provides a method for monitoring abnormal power utilization of low-voltage users, and the method comprises the following steps: determining a screening time period for a target user in a monitoring range, and obtaining zero line current and live line current data at 24 hourly moments per day in the screening time period; according to the mean square error, measuring the consistency of the null line current and the live line current, and establishing a null line and live line inconsistency identification model: in a # imgabs0 # formula, MSE is the mean square error value of a user in one day, IH (t) is the numerical value of the live line current at the moment t, and IL (t) is the numerical value of the null line current at the moment t; the MSEgt is converted into MSEgt; the data of 1 is defined as zero-fire inconsistency, the number of days of zero-fire inconsistency of all target users in each month is counted, descending sorting is carried out according to the number of days of zero-fire inconsistency, and users with abnormal electricity utilization are determined; acquiring current curve characteristics of the user with the abnormal electricity consumption, and judging the reason of the abnormal electricity consumption according to the current curve characteristics; according to the invention, a digitization technology is used to identify abnormal electricity consumption behaviors of low-voltage users

Description

Technical Field

[0001] The invention relates to the technical field of power consumption monitoring, and in particular to a method for monitoring abnormal power consumption of low-voltage users. Background Art

[0002] In the power system, the power consumption of low-voltage users in the substation is directly related to the quality and reliability of power supply. Effective monitoring of the power consumption of low-voltage users in the substation can timely discover potential problems (such as abnormal user meters, power theft, etc.), ensure the safe and stable operation of the power system, and also ensure the normal power consumption and legal rights of users.

[0003] Traditional manual screening requires a lot of manpower and time. Faced with a large number of low-voltage users in the substation, it is difficult to conduct screening quickly and comprehensively. The staff needs to check the user's meter data one by one or conduct on-site measurements, which is a huge workload. Therefore, manual screening can only be carried out periodically, and it is impossible to monitor the user's electricity consumption in real time. This means that in the time interval between two screenings, some abnormal electricity consumption may occur and cannot be discovered in time, increasing potential risks. At the same time, manual screening is prone to omissions and will be affected by subjective factors, such as the staff's experience and fatigue. Different staff may have different judgment criteria for the same set of data, resulting in unstable accuracy of screening results.

[0004] With the continuous development of information technology, digital identification methods are increasingly being used in the power sector. Advances in sensor technology, data acquisition and transmission technology, and data analysis algorithms have made it possible to automatically identify abnormal power consumption in low-voltage users in substations. Summary of the invention

[0005] In order to overcome the shortcomings of the prior art, the present invention can collect zero-fire current data in real time through the electric energy meter installed at the user end, and transmit it to the power user's electricity consumption information collection system for analysis. Using advanced data analysis algorithms, the inconsistency of zero-fire current can be quickly and accurately identified, greatly improving the monitoring efficiency and accuracy; at the same time, the digital identification method can also realize real-time early warning, promptly notify relevant personnel to handle, and effectively reduce potential risks.

[0006] The present invention adopts the following technical solution:

[0007] A method for monitoring abnormal power consumption of low-voltage users, the method comprising the following steps:

[0008] For target users within the monitoring range, determine the screening time period, and obtain the neutral current and live current data at 24 hours a day during the screening time period;

[0009] The consistency between the neutral current and the live current is measured according to the mean square error, and a zero-live inconsistency identification model is established:

[0010]

[0011] Where: MSE is the mean square error of the user in one day, t is the 24 moments of the day, I H (t) is the value of the live wire current at time t, I L (t) is the value of the neutral line current at time t;

[0012] Define data with MSE>1 as zero-fire inconsistency, count the number of days with zero-fire inconsistency for all target users each month, and sort them in descending order according to the number of zero-fire inconsistency days to identify users with abnormal electricity consumption;

[0013] Obtain the current curve characteristics of users with abnormal power consumption, and determine the cause of the abnormal power consumption based on the current curve characteristics.

[0014] Furthermore, the method of obtaining the current curve characteristics of users with abnormal power consumption and determining the cause of abnormal power consumption according to the current curve characteristics is as follows:

[0015] If the current is constant at 0 or exceeds the meter current range, but the meter power is normal and does not affect the electricity consumption and electricity fee settlement, then the acquisition system or meter is abnormal;

[0016] If the fluctuation trends of the neutral current and live current of the same user are different, but the neutral current of the user is consistent with the live current curve of the adjacent user, then the meter wiring is wrong;

[0017] If the live wire current is always lower than the neutral wire current, it means the user is stealing electricity.

[0018] Furthermore, the method for determining users with abnormal electricity consumption is:

[0019] Users whose number of zero-fire inconsistent days is greater than m are abnormal electricity consumption users, where m is not less than 3.

[0020] Furthermore, before establishing the zero-fire inconsistency identification model, it is necessary to:

[0021] Determine the number of valid points for collecting neutral current and live current for each user every day, and remove and record the data with less than 20 valid points.

[0022] The advantages and positive effects of the present invention are:

[0023] The present invention uses digital technology to identify abnormal electricity consumption behavior of low-voltage users, solving the problems of low operating efficiency and poor result accuracy of traditional manual screening methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of a method for monitoring abnormal power consumption of low-voltage users in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical scheme and advantages of the implementation of the present invention clearer, the technical scheme in the embodiment of the present invention will be described in more detail below in conjunction with the drawings in the embodiment of the present invention. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of the present invention, not all of the embodiments. The embodiments described below with reference to the drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limitations on the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0027] like Figure 1 As shown, a method for monitoring abnormal power consumption of low-voltage users comprises the following steps:

[0028] For the target users within the monitoring range, determine the screening time period, and obtain the neutral current and live current data at 24 hours a day during the screening time period; generally speaking, the screening time period is not less than one natural month;

[0029] The consistency between the neutral current and the live current is measured according to the mean square error, and a zero-live inconsistency identification model is established:

[0030]

[0031] Where: MSE is the mean square error of the user in one day, t is the 24 moments of the day, I H (t) is the value of the live wire current at time t, I L (t) is the value of the neutral line current at time t;

[0032] Define data with MSE>1 as zero-fire inconsistency, count the number of days with zero-fire inconsistency for all target users each month, and sort them in descending order according to the number of zero-fire inconsistency days to identify users with abnormal electricity consumption;

[0033] The current curve characteristics of users with abnormal electricity consumption are obtained, and the causes of abnormal electricity consumption are determined based on the current curve characteristics. It should be noted that the current curve characteristics are obtained through the electricity consumption information collection system of power users.

[0034] Specifically, the method of obtaining the current curve characteristics of users with abnormal power consumption and determining the cause of abnormal power consumption according to the current curve characteristics is as follows:

[0035] If the current is constant at 0 or exceeds the meter current range, but the meter power is normal and does not affect the electricity consumption and electricity fee settlement, then the acquisition system or meter is abnormal;

[0036] If the fluctuation trends of the neutral current and live current of the same user are different, but the neutral current of the user is consistent with the live current curve of the adjacent user, then the meter wiring is wrong;

[0037] If the live wire current is always lower than the neutral wire current, it means the user is stealing electricity.

[0038] In addition, the method for determining users with abnormal electricity consumption is:

[0039] Users with more than m days of zero-live inconsistency are considered abnormal users, where m is not less than 3. This is because the zero-live current of the acquisition system may appear inconsistent due to reasons such as momentary electromagnetic interference, short-term failure of electronic components, and abnormal communication. However, this occasional abnormality usually lasts for a short time, and the meter will soon return to normal measurement. In the process of operation and management, the power department has observed the electricity consumption behavior of different types of users for a long time and handled various abnormal situations. It is found that the majority of normal users generally do not have more than 3 days of inconsistency between the zero and live currents in a month. This threshold can effectively screen out users with possible problems without being too sensitive and causing a large number of misjudgments.

[0040] In addition, before establishing the zero-fire inconsistency identification model, it is necessary to:

[0041] Determine the number of valid points for collecting neutral current and live current for each user every day, and remove and record the data with less than 20 valid points.

[0042] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring abnormal power consumption of low-voltage users, characterized in that: The method comprises the following steps: For target users within the monitoring range, determine the screening time period, and obtain the neutral current and live current data at 24 hours a day during the screening time period; The consistency between the neutral line current and the live line current is measured according to the mean square error, and a zero-live inconsistency identification model is established: Where: MSE is the mean square error of the user in one day, t is the 24 moments of the day, I H (t) is the value of the live wire current at time t, I L (t) is the value of the neutral line current at time t; Define data with MSE>1 as zero-fire inconsistency, count the number of days with zero-fire inconsistency for all target users each month, and sort them in descending order according to the number of zero-fire inconsistency days to identify users with abnormal electricity consumption; Obtain the current curve characteristics of users with abnormal power consumption, and determine the cause of the abnormal power consumption based on the current curve characteristics.

2. A method for monitoring abnormal power consumption of low-voltage users according to claim 1, characterized in that: The method for obtaining the current curve characteristics of users with abnormal power consumption and determining the cause of abnormal power consumption according to the current curve characteristics is as follows: If the current is constant at 0 or exceeds the meter current range, but the meter power is normal and does not affect the electricity consumption and electricity fee settlement, then the acquisition system or meter is abnormal; If the fluctuation trends of the neutral current and live current of the same user are different, but the neutral current of the user is consistent with the live current curve of the adjacent user, then the meter wiring is wrong; If the live wire current is always lower than the neutral wire current, it means the user is stealing electricity.

3. A method for monitoring abnormal power consumption of low-voltage users according to claim 1, characterized in that: The method for determining users with abnormal electricity consumption is as follows: Users whose number of zero-fire inconsistent days is greater than m are abnormal electricity consumption users, where m is not less than 3.

4. A method for monitoring abnormal power consumption of low-voltage users according to claim 1, characterized in that: Before establishing the zero-fire inconsistency identification model, it is necessary to: Determine the number of valid points for collecting neutral current and live current for each user every day, and remove and record the data with less than 20 valid points.

Images