A method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data

Abstract

A method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data belongs to the field of electricity. Collect the electricity consumption data of residents, clean the collected raw data, and remove noise and invalid data; calculate the average electricity consumption and electricity consumption time distribution of users based on historical electricity consumption data; classify users in the first step according to the average electricity consumption obtained in step two; and sub-classify users classified in step three based on the electricity consumption time distribution under the first classification; set corresponding thresholds for each classification in step three and step four according to local actual conditions; compare the electricity consumption data collected in step one with the corresponding thresholds; and identify abnormal data. The present invention aims to use electricity consumption information collection data to develop a method for identifying abnormal electricity consumption of residents that does not rely on complex model training, so as to achieve fast and efficient anomaly detection and improve the management efficiency and service quality of power companies.

Description

Technical Field

[0001] The invention relates to a method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data, and belongs to the field of electricity. Background Art

[0002] With the popularization of smart grids, the power consumption information collection system has become an important part of the power system. At present, most of the commonly used power consumption abnormality monitoring systems are put into use after model training. Although the operation is simple, the early model training takes a long time and the maintenance of the system in the later stage is also troublesome. Therefore, it is necessary to improve it. Summary of the invention

[0003] The purpose of the present invention is to solve the above-mentioned problems existing in the background technology and to provide a method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data.

[0004] The present invention achieves the above-mentioned purpose by adopting the following technical solutions:

[0005] A method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data, the identification method comprising the following steps:

[0006] Step 1: Collect residents’ electricity consumption data, clean the collected raw data, and remove noise and invalid data;

[0007] Step 2: Calculate the user's average power consumption and power consumption time distribution based on historical power consumption data;

[0008] Step 3: Classify users according to the average power consumption obtained in step 2;

[0009] Step 4: Based on the users classified in step 3, further sub-classify them based on the electricity usage time distribution;

[0010] Step 5: Set corresponding thresholds for each category in Step 3 and Step 4 according to local actual conditions;

[0011] Step 6: Compare the power consumption data collected in step 1 with the corresponding threshold value;

[0012] Step 7: Identify abnormal data.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention aims to utilize electricity consumption information to collect data and develop a method for identifying abnormalities in residential electricity consumption that does not rely on complex model training, so as to achieve fast and efficient anomaly detection and improve the management efficiency and service quality of power companies. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1It is a schematic diagram of a method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data of the present invention;

[0015] Figure 2 It is a flow chart of a method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data of the present invention;

[0016] Figure 3 It is a user classification schematic diagram of a method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data of the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the invention, rather than all of the embodiments. Based on the embodiments of 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.

[0018] Specific implementation method 1: Figure 1-3 As shown, this embodiment describes a method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data, and the identification method includes the following steps:

[0019] Step 1: Collect residents’ electricity consumption data, clean the collected raw data, and remove noise and invalid data;

[0020] Step 2: Calculate the user's average power consumption and power consumption time distribution based on historical power consumption data;

[0021] Step 3: Classify the users according to the average power consumption obtained in step 2; classify them according to their historical average power consumption, for example, if the average power consumption is below X, they are classified into Class A; if the average power consumption is between X and Y, they are classified into Class B; if the average power consumption is between Y and Z, they are classified into Class C, and so on;

[0022] Step 4: Based on the users classified in step 3, further sub-classify them under the first classification based on the distribution of electricity consumption time; further classify them under category A, category B, and category C based on the distribution of electricity consumption time, for example, users with 80%-90% electricity consumption data between 0-4 o'clock are classified into category I, and users with 80%-90% electricity consumption data between 4-8 o'clock are classified into category II. . . Similarly, the time interval of classification can be 4h, 6h or 12h, and can also be adaptively adjusted according to the local longitude;

[0023] Step 5: Set corresponding thresholds for each category in Step 3 and Step 4 according to local actual conditions; the threshold setting in Step 3 should be within the range of 30%-50% upward fluctuation of the average power consumption of the corresponding category; the threshold setting in Step 4 should be based on the power consumption in the non-classified time period accounting for 50%-70% of the power consumption of the day or month;

[0024] Step 6: Compare the power consumption data collected in step 1 with the corresponding threshold value;

[0025] Step 7: Identify abnormal data. Users who exceed the threshold in step 3 but not in step 4 or users who exceed the threshold in step 4 but not in step 3 will be identified. If the data of a user at 5-7 consecutive monitoring points are abnormal, staff can be sent to check the meter on site or visit the user. After eliminating the abnormal electricity consumption, adjust the user's electricity consumption data to the corresponding classification of step 3 or step 4;

[0026] If both step three and step four exceed the threshold, staff can be sent directly to check the electricity meter on site or visit the user. After eliminating the abnormal electricity consumption, the user's electricity consumption data will be adjusted to the corresponding step three and step four categories.

[0027] In the step 1, the smart meter and the concentrator are used to collect the electricity consumption data of the residential users in real time.

[0028] The invalid data in step 1 includes non-operating equipment and terminal types that do not perform monitoring.

[0029] The average power consumption data in step 2 and step 3 is obtained by dividing the sum of the power consumption data collected in real time on the day and the power consumption data of the previous 29 days by the number of power consumption days, and is made into a line graph.

[0030] It should be noted that when there is a large-scale abnormal electricity consumption due to seasonal changes or other non-human reasons, the staff needs to adjust the threshold adaptively in a timely manner, and then adjust the threshold back after the electricity consumption returns to normal.

[0031] In the step 4, the electricity consumption time distribution is classified into 6 categories, 4 categories or 2 categories with 4h, 6h or 12h as the interval.

[0032] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other forms of assembly without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations within the meaning and range of equivalents of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0033] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data, characterized in that: The identification method comprises the following steps: Step 1: Collect residents’ electricity consumption data, clean the collected raw data, and remove noise and invalid data; Step 2: Calculate the user's average power consumption and power consumption time distribution based on historical power consumption data; Step 3: Classify users according to the average power consumption obtained in step 2; Step 4: Based on the users classified in step 3, further sub-classify them based on the electricity usage time distribution; Step 5: Set corresponding thresholds for each category in Step 3 and Step 4 according to local actual conditions; Step 6: Compare the power consumption data collected in step 1 with the corresponding threshold value; Step 7: Identify abnormal data.

2. A method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data according to claim 1, characterized in that: In the step 1, the smart meter and the concentrator are used to collect the electricity consumption data of the residential users in real time.

3. A method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data according to claim 2, characterized in that: The invalid data in step 1 includes non-operating equipment and terminal types that do not perform monitoring.

4. The method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data according to claim 1, characterized in that: The average power consumption data in step 2 and step 3 is obtained by dividing the sum of the power consumption data collected in real time on the day and the power consumption data of the previous 29 days by the number of power consumption days, and is made into a line graph.

5. The method for identifying abnormal electricity consumption of residents based on electricity consumption information collection data according to claim 1 is characterized in that: In the step 4, the electricity consumption time distribution is classified into 6 categories, 4 categories or 2 categories with 4h, 6h or 12h as the interval.

Images