A system and method for identifying abnormal power and energy consumption of large customers

Abstract

The present invention discloses a system for identifying abnormal power and energy consumption of large customers, including a line loss metering module for calculating the daily line loss rate of a line; a user power current metering module for detecting the user's power current; a daily line loss rate abnormality determination module, which is connected to the line loss metering module for determining the abnormal state of the daily line loss rate; an abnormal power current determination module, which is connected to the daily line loss rate abnormality determination module for determining the abnormal state of the power current; and an abnormal power and energy determination module, which is connected to the daily line loss rate abnormality determination module and the power current abnormality determination module for determining the abnormal state of power and energy consumption. The present invention can improve the deficiencies of the prior art and improve the real-time performance of power consumption abnormality identification.

Description

Technical Field

[0001] The invention relates to the technical field of electricity theft and leakage monitoring, in particular to a system and method for identifying abnormal electricity and energy consumption of major customers. Background Art

[0002] With the rapid development of the power system, the detection and identification of abnormal conditions such as power leakage in the power grid plays a key role in the stable operation of the power grid. In the existing technology, it is usually through the collection and comparison analysis of large amounts of user power consumption behavior, and then identification. This method has a large amount of data calculation, is time-consuming, and has poor real-time recognition. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a system and method for identifying abnormal electricity and energy consumption of large customers, which can solve the shortcomings of the existing technology and improve the real-time performance of abnormal electricity consumption identification.

[0004] In order to solve the above technical problems, the technical solutions adopted by the present invention are as follows.

[0005] A system for identifying abnormal power and energy consumption of large customers, comprising:

[0006] Line loss metering module, used to calculate the daily line loss rate of the line;

[0007] User electricity current metering module, used to detect the user's electricity current;

[0008] The daily line loss rate abnormality determination module is connected to the line loss metering module for determining the abnormal state of the daily line loss rate;

[0009] The power current abnormality determination module is connected to the daily line loss rate abnormality determination module for determining the abnormal state of the power current;

[0010] The power and energy consumption abnormality determination module is respectively connected to the daily line loss rate abnormality determination module and the power current abnormality determination module for determining the abnormal state of power and energy consumption.

[0011] A recognition method for a large customer power and energy consumption abnormality recognition system comprises the following steps:

[0012] A. The line loss metering module and the user power current metering module send the collected data to the daily line loss rate abnormality determination module and the power current abnormality determination module respectively;

[0013] B. The daily line loss rate abnormality determination module determines abnormalities in the received data;

[0014] C. The power current abnormality determination module determines abnormality of the received data;

[0015] D. The power and energy consumption abnormality judgment module obtains the customer's power and energy consumption abnormality judgment result based on the judgment results of the daily line loss rate abnormality judgment module and the power current abnormality judgment module.

[0016] Preferably, in step B, the abnormal determination of the daily line loss rate includes the following steps:

[0017] B1. Fit the daily line loss rate data points into a daily line loss rate change curve;

[0018] B2. Set a long sliding window and a short sliding window, and the time span of the long sliding window is 2 to 3 times that of the short sliding window; first, use the long sliding window to traverse the daily line loss rate change curve, extract the features of the daily line loss rate change curve to form a first feature set, and then use the short sliding window to traverse the daily line loss rate change curve, extract the features of the daily line loss rate change curve to form a second feature set;

[0019] B3. Determine the daily line loss rate variation curve area where the second feature set is not linearly correlated with the first feature set as an abnormal area.

[0020] Preferably, in step B2, the characteristics of the daily line loss rate variation curve are composed of a two-dimensional characteristic consisting of an average daily line loss rate variation and a ratio of a maximum daily line loss rate difference to a maximum variation rate.

[0021] Preferably, in step C, the abnormality determination of the power consumption current includes the following steps:

[0022] C1. Collect and form the current curve of each user;

[0023] C2. Segment the power consumption current curve according to the abnormal area obtained in step B, wherein each abnormal area corresponds to a first-class power consumption current curve segment, and the area between adjacent abnormal areas corresponds to a second-class power consumption current curve segment;

[0024] C3, extracting the common feature set of the second type of electricity consumption current curve segments;

[0025] C4. Extract the features of each type of electricity current curve segment, compare the extracted features with the common feature set extracted in step C3, obtain the similarity between each feature and the common feature set, extract linearly correlated feature components from the features whose similarity is lower than a set threshold, and determine the type of electricity current curve segment corresponding to which the ratio of the extracted feature components to the feature is greater than the set threshold as an abnormal area.

[0026] Preferably, in step D, users whose proportion of abnormal power current areas exceeds a set threshold or whose frequency of abnormal power current areas exceeds a set threshold are determined to have abnormal power and energy consumption.

[0027] The beneficial effect brought by adopting the above technical solution is that the present invention uses only two grid parameters, namely daily line loss rate and power current, and realizes accurate identification and positioning of abnormal power users and abnormal power time periods by optimizing the analysis and processing process of the parameters. Since the amount of data involved is greatly reduced, the present invention can quickly identify abnormal power conditions and improve the real-time performance of the identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of a specific implementation mode of the present invention. DETAILED DESCRIPTION

[0029] Reference Figure 1 , a system for identifying abnormal power and energy consumption of large customers, comprising:

[0030] Line loss metering module 1, used to calculate the daily line loss rate of the line;

[0031] User electricity current metering module 2, used to detect the user's electricity current;

[0032] The daily line loss rate abnormality determination module 3 is connected to the line loss metering module 1 for determining the abnormal state of the daily line loss rate;

[0033] The power current abnormality determination module 4 is connected to the daily line loss rate abnormality determination module 3 for determining the abnormal state of the power current;

[0034] The power and energy consumption abnormality determination module 5 is respectively connected to the daily line loss rate abnormality determination module 3 and the power current abnormality determination module 4 for determining the abnormal state of power and energy consumption.

[0035] A recognition method of the above-mentioned large customer power and energy consumption abnormality recognition system includes the following steps:

[0036] A. The line loss metering module 1 and the user power current metering module 2 send the collected data to the daily line loss rate abnormality determination module 3 and the power current abnormality determination module 4 respectively;

[0037] B. The daily line loss rate abnormality determination module 3 determines abnormalities of the received data;

[0038] C. The power current abnormality determination module 4 performs abnormality determination on the received data;

[0039] D. The power and energy consumption abnormality determination module 5 obtains the customer's power and energy consumption abnormality identification result according to the determination results of the daily line loss rate abnormality determination module 3 and the power current abnormality determination module 4.

[0040] In step B, the abnormal determination of the daily line loss rate includes the following steps:

[0041] B1. Fit the daily line loss rate data points into a daily line loss rate change curve;

[0042] B2. Set a long sliding window and a short sliding window, and the time span of the long sliding window is 2 to 3 times that of the short sliding window; first, use the long sliding window to traverse the daily line loss rate change curve, extract the features of the daily line loss rate change curve to form a first feature set, and then use the short sliding window to traverse the daily line loss rate change curve, extract the features of the daily line loss rate change curve to form a second feature set;

[0043] B3. Determine the daily line loss rate variation curve area where the second feature set is not linearly correlated with the first feature set as an abnormal area.

[0044] In step B2, the characteristics of the daily line loss rate change curve are composed of a two-dimensional characteristic consisting of the average change rate of the daily line loss rate and the ratio of the maximum difference of the daily line loss rate to the maximum change rate.

[0045] In step C, the abnormality determination of the power consumption current includes the following steps:

[0046] C1. Collect and form the current curve of each user;

[0047] C2. Segment the power consumption current curve according to the abnormal area obtained in step B, wherein each abnormal area corresponds to a first-class power consumption current curve segment, and the area between adjacent abnormal areas corresponds to a second-class power consumption current curve segment;

[0048] C3, extracting the common feature set of the second type of electricity consumption current curve segments;

[0049] C4. Extract the features of each type of electricity current curve segment, compare the extracted features with the common feature set extracted in step C3, obtain the similarity between each feature and the common feature set, extract linearly correlated feature components from the features whose similarity is lower than a set threshold, and determine the type of electricity current curve segment corresponding to which the ratio of the extracted feature components to the feature is greater than the set threshold as an abnormal area.

[0050] In step D, users whose proportion of abnormal power current areas exceeds a set threshold or whose frequency of abnormal power current areas exceeds a set threshold are determined to have abnormal power and energy consumption.

[0051] Among them, various set thresholds used in the data processing process of the present invention are set and adjusted according to historical experience data, which will not be described in detail here.

[0052] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for identifying abnormal power consumption of a major customer, based on a system for identifying abnormal power consumption of a major customer, wherein the system comprises: A line loss measurement module (1), used to calculate the daily line loss rate of the line; A user electricity current metering module (2), used to detect the user's electricity current; A daily line loss rate abnormality determination module (3), which is in communication connection with the line loss metering module (1) and is used to determine the abnormal state of the daily line loss rate; An abnormal power consumption current determination module (4) is connected in communication with the user power consumption current metering module (2) and is used to determine an abnormal state of the power consumption current; The power consumption and energy abnormality determination module (5) is respectively connected to the daily line loss rate abnormality determination module (3) and the power current abnormality determination module (4) for determining the abnormal state of power consumption and energy consumption; It is characterized by comprising the following steps: A. The line loss metering module (1) and the user power current metering module (2) send the collected data to the daily line loss rate abnormality determination module (3) and the power current abnormality determination module (4) respectively; B. The daily line loss rate abnormality determination module (3) performs abnormality determination on the received data; the abnormality determination of the daily line loss rate includes the following steps: B1. Fit the daily line loss rate data points into a daily line loss rate change curve; B2. Set a long sliding window and a short sliding window, and the time span of the long sliding window is 2 to 3 times that of the short sliding window; first, use the long sliding window to traverse the daily line loss rate change curve, extract the features of the daily line loss rate change curve to form a first feature set, and then use the short sliding window to traverse the daily line loss rate change curve, extract the features of the daily line loss rate change curve to form a second feature set; B3, determining the daily line loss rate change curve area where the second feature set is not linearly related to the first feature set as an abnormal area; C. The power current abnormality determination module (4) performs abnormality determination on the received data; the abnormality determination of the power current includes the following steps: C1. Collect and form the current curve of each user; C2. Segment the power consumption current curve according to the abnormal area obtained in step B, wherein each abnormal area corresponds to a first-class power consumption current curve segment, and the area between adjacent abnormal areas corresponds to a second-class power consumption current curve segment; C3, extracting the common feature set of the second type of electricity consumption current curve segments; C4, extracting the features of each class of electric current curve segments, comparing the extracted features with the common feature set extracted in step C3, obtaining the similarity between each feature and the common feature set, extracting linearly related feature components from the features whose similarity is lower than a set threshold, and determining the class of electric current curve segments corresponding to which the ratio of the extracted feature components to the features is greater than the set threshold as abnormal areas; D. The power and energy consumption abnormality determination module (5) obtains the customer's power and energy consumption abnormality identification result based on the determination results of the daily line loss rate abnormality determination module (3) and the power current abnormality determination module (4).

2. The method for identifying abnormal power consumption of large customers according to claim 1 is characterized by: In step B2, the characteristics of the daily line loss rate change curve are composed of a two-dimensional characteristic consisting of the average change rate of the daily line loss rate and the ratio of the maximum difference of the daily line loss rate to the maximum change rate.

3. The method for identifying abnormal power consumption of large customers according to claim 2 is characterized in that: In step D, users whose proportion of abnormal power current areas exceeds a set threshold or whose frequency of abnormal power current areas exceeds a set threshold are determined to have abnormal power and energy consumption.

Images