Abnormal power consumption site detection method and device, electronic equipment and readable storage medium

Abstract

The application relates to the field of communication, and provides an abnormal power consumption site detection method and device, electronic equipment and a readable storage medium. The abnormal power consumption site detection method comprises the following steps: collecting power consumption data, business data and energy consumption data of a to-be-detected site, determining a first change rate corresponding to the power consumption data, a second change rate corresponding to the business data and a third change rate corresponding to the energy consumption data; in the case that the power consumption data meets a target normal distribution, determining an abnormal time according to the target normal distribution; determining a change rate correlation coefficient and a change rate reverse correlation time according to the first change rate, the second change rate and the third change rate; and determining an abnormal power consumption site in the to-be-detected site according to the abnormal time, the change rate correlation coefficient and the change rate reverse correlation time. The application calculates and detects the abnormal power consumption site through the power consumption data, the business data and the energy consumption data of the to-be-detected site, so that accurate identification of the abnormal power consumption site is realized.

Description

Technical Field

[0001] This application relates to the field of communications, specifically to a method, apparatus, electronic device, and readable storage medium for detecting abnormal power consumption sites. Background Technology

[0002] Telecommunications operators' network equipment rooms are widely distributed. Due to lack of supervision, base stations frequently experience power theft and leakage, which not only infringes on the legitimate rights and interests of telecommunications operators but also causes resource losses. Furthermore, the voltage instability caused by power theft and leakage poses significant safety hazards to the equipment in the equipment rooms. Because of the covert nature of power theft and leakage, it is difficult to detect abnormal power usage in equipment rooms in a timely and accurate manner.

[0003] The existing main solutions for detecting abnormal power consumption in computer rooms include: (1) Installing smart meters inside the computer room, collecting power consumption data of all equipment inside the computer room, and matching it with the power consumption data of the smart meters to obtain abnormal power consumption data. 2. Using the rated power detection of equipment, each piece of equipment in the computer room has its maximum rated power. Normal power consumption of equipment cannot exceed the maximum rated power. Obtain the maximum power value of all equipment in the computer room, compare the monthly power consumption data with the rated power of all equipment in the computer room for the whole month, and mark the site corresponding to the equipment that exceeds the rated power as an abnormal site to obtain abnormal power consumption data. The drawback of solution (1) is that the investment is large, there are computer rooms that are not suitable for installing smart meters, and it is difficult to collect power consumption data of all equipment inside the computer room. The drawback of solution (2) is that the comparison dimension is single, and other factors affecting the power consumption of computer room equipment are not considered. Moreover, the rated power value of computer room equipment is relatively large. Even if there is a phenomenon of electricity theft, it is rare to exceed the rated power. Therefore, the detection accuracy of solution (2) is insufficient. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and readable storage medium for detecting abnormal power consumption sites, in order to solve the above-mentioned problems existing in the existing abnormal power consumption detection schemes for computer rooms.

[0005] In a first aspect, embodiments of this application provide a method for detecting abnormal power consumption sites, including:

[0006] Collect power consumption data, service data and energy consumption data of the site to be tested, and determine the first rate of change corresponding to the power consumption data, the second rate of change corresponding to the service data and the third rate of change corresponding to the energy consumption data;

[0007] If the power consumption data conforms to a target normal distribution, the abnormal time is determined based on the target normal distribution;

[0008] Based on the first rate of change, the second rate of change, and the third rate of change, determine the correlation coefficient of the rate of change and the inverse correlation time of the rate of change;

[0009] Based on the abnormal time, the correlation coefficient of the rate of change, and the inverse correlation time of the rate of change, the abnormal power consumption sites among the sites to be detected are determined.

[0010] In one embodiment, the step of collecting power consumption data, service data, and energy consumption data of the site to be tested is followed by:

[0011] If there is missing data in the power consumption data, determine the first time corresponding to the missing data;

[0012] Obtain the data sequence corresponding to the first time point, and supplement the missing data according to the preset interpolation method and the data sequence.

[0013] In one embodiment, after the step of collecting power consumption data, service data, and energy consumption data of the site to be tested, and determining the first rate of change corresponding to the power consumption data, the second rate of change corresponding to the service data, and the third rate of change corresponding to the energy consumption data, the following steps are included:

[0014] The mean sequence corresponding to the power consumption data is determined according to a preset sampling method;

[0015] The mean sequence is tested according to a preset verification formula to obtain the verification result;

[0016] Based on the test results, determine whether the power consumption data conforms to the target normal distribution.

[0017] In one embodiment, the step of determining the anomalous time based on the target normal distribution includes:

[0018] Based on the standard deviation corresponding to the target normal distribution, the deviation data in the power consumption data is determined;

[0019] The time when the data deviated was collected was determined, and the collection time was designated as the abnormal time.

[0020] In one embodiment, the step of determining the correlation coefficient of the rate of change and the inverse correlation time of the rate of change based on the first rate of change, the second rate of change, and the third rate of change includes:

[0021] The correlation coefficient of the first rate of change is determined based on the first rate of change, the second rate of change, and the preset coefficient calculation formula;

[0022] The second rate of change correlation coefficient is determined based on the first rate of change, the third rate of change, and the preset coefficient calculation formula;

[0023] If the first rate of change correlation coefficient is less than a preset threshold, the first rate of change inverse correlation time is determined based on the first rate of change correlation coefficient.

[0024] If the correlation coefficient of the second rate of change is less than a preset threshold, the second rate of change inverse correlation time is determined based on the correlation coefficient of the second rate of change.

[0025] In one embodiment, the step of determining the abnormal power consumption sites among the sites to be detected based on the abnormal time, the rate of change correlation coefficient, and the rate of change inverse correlation time includes:

[0026] Based on the power consumption data, the abnormal time, the rate of change correlation coefficient, and the rate of change inverse correlation time, the first feature vector corresponding to the site to be detected is determined;

[0027] Obtain the second feature vector corresponding to the preset abnormal site, and calculate the angle in radians between the first feature vector and the second feature vector;

[0028] The stations to be tested are sorted according to the magnitude of the included angle radian value, and the abnormal power consumption stations among the stations to be tested are determined according to the sorting results.

[0029] In one embodiment, the step of determining the first rate of change corresponding to the power consumption data, the second rate of change corresponding to the service data, and the third rate of change corresponding to the energy consumption data includes:

[0030] When the power consumption data, the service data, and the energy consumption data have the same collection time and the same collection period, a first rate of change is calculated based on the power consumption data corresponding to each collection time.

[0031] The second rate of change is calculated based on the business data corresponding to each of the aforementioned collection times, and the third rate of change is calculated based on the energy consumption data corresponding to each of the aforementioned collection times.

[0032] Secondly, embodiments of this application provide an abnormal power consumption site detection device, comprising:

[0033] The rate of change calculation module is used to collect power consumption data, service data and energy consumption data of the site to be tested, and determine the first rate of change corresponding to the power consumption data, the second rate of change corresponding to the service data and the third rate of change corresponding to the energy consumption data.

[0034] An abnormal time determination module is used to determine the abnormal time based on the target normal distribution when the power consumption data conforms to the target normal distribution;

[0035] The correlation coefficient calculation module is used to determine the correlation coefficient of the rate of change and the inverse correlation time of the rate of change based on the first rate of change, the second rate of change and the third rate of change;

[0036] An abnormal power consumption site determination module is used to determine the abnormal power consumption sites among the sites to be detected based on the abnormal time, the correlation coefficient of the rate of change, and the inverse correlation time of the rate of change.

[0037] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory storing a computer program, wherein the processor executes the computer program to implement the steps of the abnormal power station detection method described in the first aspect.

[0038] Fourthly, embodiments of this application provide a readable storage medium including a computer program, which, when executed by a processor, implements the steps of the abnormal power station detection method described in the first aspect.

[0039] The abnormal power consumption site detection method, apparatus, electronic device, and readable storage medium provided in this application collect power consumption data, service data, and energy consumption data of the site to be detected, determine the rate of change corresponding to each data, determine the abnormal time according to the target normal distribution if the power consumption data conforms to the target normal distribution, and then determine the correlation coefficient and inverse correlation time of the rate of change according to the rate of change corresponding to each data. Finally, the abnormal power consumption sites among the sites to be detected are identified based on the abnormal time, the correlation coefficient, and the inverse correlation time of the rate of change. By calculating and detecting abnormal power consumption sites through the power consumption data, service data, and energy consumption data of the site to be detected, the accurate identification of abnormal power consumption sites is achieved. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is one of the flowcharts illustrating the abnormal power consumption site detection method provided in the embodiments of this application;

[0042] Figure 2 This is a second schematic flowchart of the abnormal power consumption site detection method provided in the embodiments of this application;

[0043] Figure 3 This is a schematic diagram of the abnormal power consumption site detection device provided in the embodiments of this application;

[0044] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0046] Reference Figure 1 , Figure 1 This is one of the flowcharts illustrating the abnormal power consumption site detection method in the embodiments of this application. The abnormal power consumption site detection method provided in the embodiments of this application may include:

[0047] Step S100: Collect power consumption data, service data and energy consumption data of the site to be tested, and determine the first rate of change corresponding to the power consumption data, the second rate of change corresponding to the service data and the third rate of change corresponding to the energy consumption data.

[0048] Specifically, telecommunications operators' network equipment rooms are widely distributed across the country. Power consumption in these rooms is often unattended, leading to frequent instances of electricity theft and leakage. Therefore, timely and accurate detection of equipment rooms experiencing electricity theft and leakage has become a pressing technical problem. In this embodiment, the site to be tested refers to the equipment room where electricity theft and leakage are to be detected. Power consumption data, service data, and energy consumption data of the site to be tested are collected using equipment within the equipment room (e.g., electricity meters). The collection period can be 30 or 60 days, and the collection point can be 0:00. The collected power consumption data includes the daily power consumption of the site to be tested within the collection period. Service data and energy consumption data are identical. The power consumption data, service data, and energy consumption data are sorted in chronological order to obtain the power consumption data, service data, and energy consumption data for each site to be tested.

[0049] Taking power consumption data sorted by time as an example, the method for determining the first rate of change corresponding to the power consumption data is: Rate of change on day N = (Power consumption data on day N - Power consumption data on day N-1) × 100 ÷ Power consumption data on day N. The calculation methods for the second rate of change corresponding to business data and the third rate of change corresponding to energy consumption data are the same as those for the first rate of change corresponding to power consumption data.

[0050] Step S200: If the power consumption data conforms to the target normal distribution, determine the abnormal time according to the target normal distribution;

[0051] Specifically, the power consumption data, service data, and energy consumption data are sorted in chronological order to obtain the power consumption data, service data, and energy consumption data for each site to be tested. Then, it is determined whether the power consumption data conforms to the target normal distribution in this embodiment. The specific method is as follows: Each time, power consumption data from multiple different dates is randomly sampled from the total power consumption data, and the average value is calculated. Multiple random samplings are performed, and the average value of each sampling is recorded. The multiple samplings must cover power consumption data from all dates. The average value of each sampling is verified to conform to a normal distribution using the following verification formula: Where n is the number of extractions. Let x be the mean of n samplings. i Let x be the average value of the i-th sampling. j Let be the average value of the j-th sampling, and exp be an exponential function with the natural constant e as the base. Assuming the average value of each sample follows a normal distribution, and the confidence level α is set to 0.05, calculate T. ep If T ep Falling into the rejection domain, {T EP ≥T 1-α,EP If (n)}, then it does not belong to the normal distribution. The rejection region and EP test information are shown in Table 1 below.

[0052]

[0053] Table 1

[0054] If the power consumption data of the site to be tested follows a normal distribution, then the dates on which potential abnormal data are screened according to the standard deviation of the sample mean exceeding 3 times are counted, and the number of days on which potential abnormal data occurs is counted, which is the number of days of abnormal time in this embodiment.

[0055] Step S300: Determine the correlation coefficient of the rate of change and the inverse correlation time of the rate of change based on the first rate of change, the second rate of change and the third rate of change;

[0056] Specifically, in this embodiment, the rate of change correlation coefficient includes a first rate of change correlation coefficient and a second rate of change correlation coefficient, and the rate of change inverse correlation time includes the first rate of change inverse correlation time and the second rate of change inverse correlation time. The method for determining the first rate of change (denoted by E) corresponding to the power consumption data is: Rate of change on day N = (Power consumption data on day N - Power consumption data on day N-1) × 100 ÷ Power consumption data on day N; the method for determining the third rate of change (denoted by C) corresponding to the energy consumption data is: Rate of change on day N = (Energy consumption data on day N - Energy consumption data on day N-1) × 100 ÷ Energy consumption data on day N. Then, based on the first rate of change, the third rate of change, and the preset coefficient calculation formula, the method for determining the second rate of change correlation coefficient r(E, C) is: Cov is used to calculate covariance, and Var is used to calculate variance. The calculation method for the first rate of change correlation coefficient is the same as that for the second rate of change correlation coefficient. After obtaining the first and second rate of change correlation coefficients, if the first rate of change correlation coefficient is less than a preset threshold, the method for determining the first rate of change inverse correlation time based on the first rate of change correlation coefficient is as follows: align the first rate of change corresponding to the power consumption data and the third rate of change corresponding to the energy consumption data in chronological order. If the first and third rates of change aligned in time are opposite in sign, then that day is determined as the second rate of change inverse correlation time. The method for determining the first rate of change inverse correlation time is the same as that for determining the second rate of change inverse correlation time.

[0057] Step S400: Determine the abnormal power consumption sites among the sites to be detected based on the abnormal time, the correlation coefficient of the rate of change, and the inverse correlation time of the rate of change.

[0058] Specifically, after obtaining feature data such as abnormal time, correlation coefficient of rate of change, and inverse correlation time of rate of change, the electricity consumption characteristics of all stations are abstracted into a set of vectors. The vectors contain the following: [mean, variance, kurtosis, skewness statistics of station electricity consumption data, first rate of change correlation coefficient, second rate of change correlation coefficient, number of days of inverse correlation time, and magnitude of inverse correlation deviation]. Through the vector dot product, the angle in radians between the feature vector of the station to be detected and the feature vector of stations known to have electricity theft is calculated. The station with the smallest angle value among the stations to be detected is taken as the detection result. a={x1 x2 ... x n}, b = {y1 y2 ... y n}, 'a' represents the feature vector of the site to be detected, 'b' represents the feature vector of a site known to have engaged in electricity theft, and 'cosθ' represents the angle in radians between the feature vectors of the site to be detected and the site known to have engaged in electricity theft. The angle values ​​are sorted in ascending order, with the site ranked higher being more likely to have engaged in electricity theft; these are then output as the sites with abnormal electricity usage.

[0059] This embodiment collects power consumption data, service data, and energy consumption data of the sites to be tested, determines the rate of change for each data point, and determines the abnormal time based on the target normal distribution when the power consumption data conforms to the target normal distribution. Then, based on the rate of change for each data point, it determines the correlation coefficient and the inverse correlation time of the rate of change. Finally, based on the abnormal time, the correlation coefficient, and the inverse correlation time of the rate of change, it identifies the abnormal power consumption sites among the sites to be tested. By calculating and detecting abnormal power consumption sites through the power consumption data, service data, and energy consumption data of the sites to be tested, the accurate identification of abnormal power consumption sites is achieved.

[0060] In one embodiment, the abnormal power consumption site detection method provided in this application may further include:

[0061] Step S101: If there is missing data in the power consumption data, determine the first time corresponding to the missing data;

[0062] Step S102: Obtain the data sequence corresponding to the first time, and supplement the missing data according to the preset interpolation method and the data sequence.

[0063] Specifically, due to unstable data acquisition, some power consumption data, service data, and energy consumption data of the sites to be tested may be missing. For missing data (e.g., power consumption on a certain day is null), given the relatively stable nature of data over a short period, this embodiment uses a mean-based interpolation method to fill in the missing data. After sorting the power consumption data, service data, and energy consumption data in chronological order (i.e., the data sequence in this embodiment) to obtain the power consumption data, service data, and energy consumption data for each site to be tested, the following mean-based interpolation method (i.e., the preset interpolation method in this embodiment) is used to fill in the missing data. First, the position of the missing data in the time-sorted power consumption data, service data, or energy consumption data is determined. Then, the average value of the data before and after the missing data in the time sequence is calculated. This average value is used as the missing data to fill in the missing data.

[0064] This embodiment supplements missing data by using a preset interpolation method and time sorting, ensuring data integrity and laying a data foundation for the subsequent accurate identification of abnormal power supply points.

[0065] In one embodiment, the abnormal power consumption site detection method provided in this application may further include:

[0066] Step S110: Determine the mean sequence corresponding to the power consumption data according to a preset sampling method;

[0067] Step S120: The mean sequence is tested according to a preset verification formula to obtain the verification result;

[0068] Step S130: Determine whether the power consumption data conforms to the target normal distribution based on the test results.

[0069] Specifically, the power consumption data, service data, and energy consumption data are sorted in chronological order to obtain the power consumption data, service data, and energy consumption data for each site to be tested. Then, it is determined whether the power consumption data conforms to the target normal distribution in this embodiment. The specific method is as follows: Based on a preset sampling method, multiple (e.g., 5-8) power consumption data points from different dates are randomly selected from the total power consumption data each time, and the average value is calculated. This random sampling is repeated multiple times (e.g., 200 times), and the average value of each sampling is recorded to obtain the mean sequence corresponding to the power consumption data. The multiple samplings must cover power consumption data from all dates. The mean sequence corresponding to the power consumption data is verified to conform to a normal distribution. The verification formula (i.e., the preset verification formula in this embodiment) is as follows: Where n is the number of extractions. Let x be the mean of n samplings. i Let x be the average value of the i-th sampling. j Let be the average value of the j-th sampling, and exp be an exponential function with the natural constant e as the base. Assuming the average value of each sample follows a normal distribution, and the confidence level α is set to 0.05, calculate T. ep If T ep Falling into the rejection domain, {T EP ≥T 1-α,EP If the expression (n)} is not normally distributed, then it does not belong to a normal distribution. Assume n = 200, α = 0.05, T 1-α，EP (n) = 0.379, substituting n = 200 and α = 0.05 into the above formula (1), if the obtained T ep ≥T 1-α，EP If (n), then the power consumption data conforms to the target normal distribution.

[0070] This embodiment uses a preset sampling method and a preset verification formula to determine whether the power consumption data conforms to the target normal distribution, and performs preliminary verification of the power consumption data, laying a data foundation for the subsequent accurate identification of abnormal power consumption points.

[0071] In one embodiment, the abnormal power consumption site detection method provided in this application may further include:

[0072] Step S210: Determine the deviation data in the power consumption data based on the standard deviation corresponding to the target normal distribution;

[0073] Step S220: Determine the collection time of the deviation data and treat the collection time as the abnormal time.

[0074] Specifically, if the power consumption data of the site to be tested follows a normal distribution, then the dates on which potential abnormal data (i.e., the deviation data in this embodiment) are screened according to the standard deviation of the deviation from the sample mean by more than 3 times are counted, and the number of days on which potential abnormal data occurs is counted, i.e., the number of days of abnormal time in this embodiment.

[0075] This embodiment uses a target normal distribution to screen potential abnormal data, thus initially filtering power consumption data and laying a data foundation for the subsequent accurate identification of abnormal power consumption points.

[0076] In one embodiment, the abnormal power consumption site detection method provided in this application may further include:

[0077] Step S310: Determine the correlation coefficient of the first rate of change based on the first rate of change, the second rate of change, and the preset coefficient calculation formula;

[0078] Step S320: Determine the correlation coefficient of the second rate of change based on the first rate of change, the third rate of change, and the preset coefficient calculation formula;

[0079] Step S330: If the first rate of change correlation coefficient is less than a preset threshold, determine the first rate of change inverse correlation time based on the first rate of change correlation coefficient;

[0080] Step S340: If the second rate of change correlation coefficient is less than a preset threshold, determine the second rate of change inverse correlation time based on the second rate of change correlation coefficient.

[0081] Specifically, the method for determining the first rate of change (denoted by E) corresponding to the power consumption data is: Rate of change on day N = (Power consumption data on day N - Power consumption data on day N-1) × 100 ÷ Power consumption data on day N; the method for determining the third rate of change (denoted by C) corresponding to the energy consumption data is: Rate of change on day N = (Energy consumption data on day N - Energy consumption data on day N-1) × 100 ÷ Energy consumption data on day N. Then, based on the first rate of change, the third rate of change, and the preset coefficient calculation formula, the method for determining the correlation coefficient r(E, C) of the second rate of change is: Cov is used to calculate covariance, and Var is used to calculate variance. The calculation method for the first rate of change correlation coefficient is the same as that for the second rate of change correlation coefficient. After obtaining the first and second rate of change correlation coefficients, if the first rate of change correlation coefficient is less than a preset threshold, the method for determining the first rate of change inverse correlation time based on the first rate of change correlation coefficient is as follows: align the first rate of change corresponding to the power consumption data and the third rate of change corresponding to the energy consumption data in chronological order. If the first and third rates of change aligned in time are opposite in sign, then that day is determined as the second rate of change inverse correlation time. The method for determining the first rate of change inverse correlation time is the same as that for determining the second rate of change inverse correlation time.

[0082] This embodiment determines the correlation coefficient and inverse correlation time of the rate of change by using the formula for calculating the rate of change and preset coefficients, thereby obtaining data to identify abnormal power consumption sites and achieving accurate identification of abnormal power consumption sites.

[0083] Reference Figure 2 , Figure 2 This is a second flowchart illustrating the abnormal power consumption site detection method in this application. In one embodiment, the abnormal power consumption site detection method provided in this application may further include:

[0084] Step S410: Determine the first feature vector corresponding to the station to be detected based on the power consumption data, the abnormal time, the rate of change correlation coefficient, and the rate of change inverse correlation time.

[0085] Step S420: Obtain the second feature vector corresponding to the preset abnormal site, and calculate the angle in radians between the first feature vector and the second feature vector;

[0086] Step S430: Sort each of the stations to be tested according to the magnitude of the included angle radian value, and determine the abnormal power consumption stations among the stations to be tested according to the sorting results.

[0087] Specifically, after obtaining feature data such as abnormal time, rate of change correlation coefficient, and rate of change inverse correlation time, the electricity consumption characteristics of all stations are abstracted into a set of vectors, namely the first feature vector in this embodiment. The first feature vector contains the following: [station electricity consumption data mean, variance, kurtosis, skewness statistics, first rate of change correlation coefficient, second rate of change correlation coefficient, number of days of rate of change inverse correlation time, and inverse correlation deviation value]. Through the vector dot product, the angle in radians between the feature vector of the station to be detected and the feature vector of the station known to have electricity theft (i.e., the preset abnormal station in this embodiment) (i.e., the second feature vector in this embodiment) is calculated. The station to be predicted corresponding to the smallest radian value among the stations to be detected is taken as the detection result. a={x1 x2 ... x n}, b = {y1 y2 ... y n}, 'a' represents the feature vector of the site to be detected, 'b' represents the feature vector of a site known to have engaged in electricity theft, and 'cosθ' represents the angle in radians between the feature vectors of the site to be detected and the site known to have engaged in electricity theft. The angle values ​​are sorted in ascending order, with the site ranked higher being more likely to have engaged in electricity theft; these are then output as the sites with abnormal electricity usage.

[0088] This embodiment uses feature data such as abnormal time, correlation coefficient of rate of change, and inverse correlation time of rate of change to determine abnormal power consumption sites, thereby achieving accurate identification of abnormal power consumption sites.

[0089] In one embodiment, the abnormal power consumption site detection method provided in this application may further include:

[0090] Step S103: When the power consumption data, the service data, and the energy consumption data have the same collection time and the same collection period, calculate the first rate of change based on the power consumption data corresponding to each collection time.

[0091] Step S104: Calculate the second rate of change based on the business data corresponding to each collection time, and calculate the third rate of change based on the energy consumption data corresponding to each collection time.

[0092] Specifically, when power consumption data, business data, and energy consumption data have the same collection time and collection period, taking a 60-day collection period and a collection time of 0:00 as an example, the method for determining the first rate of change corresponding to the power consumption data is: Rate of change on day N = (Power consumption data on day N - Power consumption data on day N-1) × 100 ÷ Power consumption data on day N. The calculation methods for the second rate of change corresponding to business data and the third rate of change corresponding to energy consumption data are the same as those for the first rate of change corresponding to power consumption data.

[0093] This embodiment calculates the rate of change corresponding to each data point, laying a data foundation for the subsequent accurate identification of abnormal power consumption points.

[0094] refer to Figure 3 , Figure 3 This is a schematic diagram of the abnormal power consumption site detection device in the embodiments of this application. The abnormal power consumption site detection device provided in the embodiments of this application is described below. The abnormal power consumption site detection device described below can be referred to in correspondence with the abnormal power consumption site detection method described above.

[0095] An abnormal power consumption site detection device includes:

[0096] The rate of change calculation module 301 is used to collect power consumption data, service data and energy consumption data of the site to be tested, and determine the first rate of change corresponding to the power consumption data, the second rate of change corresponding to the service data and the third rate of change corresponding to the energy consumption data.

[0097] An abnormal time determination module 302 is used to determine the abnormal time based on the target normal distribution when the power consumption data conforms to the target normal distribution;

[0098] The correlation coefficient calculation module 303 is used to determine the correlation coefficient of the rate of change and the inverse correlation time of the rate of change based on the first rate of change, the second rate of change and the third rate of change;

[0099] The abnormal power consumption site determination module 304 is used to determine the abnormal power consumption sites among the sites to be detected based on the abnormal time, the correlation coefficient of the rate of change, and the inverse correlation time of the rate of change.

[0100] Optionally, the abnormal power station detection device further includes:

[0101] The first-time determination module is used to determine the first time corresponding to the missing data when there is missing data in the power consumption data;

[0102] The missing data supplementation module is used to obtain the data sequence corresponding to the first time, and supplement the missing data according to the preset interpolation method and the data sequence.

[0103] Optionally, the abnormal power station detection device further includes:

[0104] The mean sequence determination module is used to determine the mean sequence corresponding to the power consumption data according to a preset sampling method;

[0105] The verification result determination module is used to verify the mean sequence according to a preset verification formula to obtain the verification result;

[0106] The judgment module is used to determine whether the power consumption data conforms to the target normal distribution based on the test results.

[0107] Optionally, the abnormal time determination module includes:

[0108] The deviation data determination unit is used to determine the deviation data in the power consumption data based on the standard deviation corresponding to the target normal distribution;

[0109] An abnormal time determination unit is used to determine the acquisition time of the deviation data and to designate the acquisition time as the abnormal time.

[0110] Optionally, the correlation coefficient calculation module includes:

[0111] The first rate of change correlation coefficient determination unit is used to determine the first rate of change correlation coefficient based on the first rate of change, the second rate of change, and the preset coefficient calculation formula.

[0112] The second rate of change correlation coefficient determination unit is used to determine the second rate of change correlation coefficient based on the first rate of change, the third rate of change, and the preset coefficient calculation formula.

[0113] The first rate of change inverse correlation time determination unit is used to determine the first rate of change inverse correlation time based on the first rate of change correlation coefficient when the first rate of change correlation coefficient is less than a preset threshold.

[0114] The second rate of change inverse correlation time determination unit is used to determine the second rate of change inverse correlation time based on the second rate of change correlation coefficient when the second rate of change correlation coefficient is less than a preset threshold.

[0115] Optionally, the abnormal power consumption site determination module includes:

[0116] The first feature vector determination unit is used to determine the first feature vector corresponding to the station to be detected based on the power consumption data, the abnormal time, the rate of change correlation coefficient, and the rate of change inverse correlation time.

[0117] Angle radian value calculation unit is used to obtain the second feature vector corresponding to the preset abnormal site and calculate the angle radian value between the first feature vector and the second feature vector;

[0118] An abnormal power consumption site determination unit is used to sort each of the sites to be detected according to the magnitude of the included angle radian value, and to determine the abnormal power consumption sites among the sites to be detected according to the sorting result.

[0119] Optionally, the rate of change calculation module includes:

[0120] The first rate of change calculation unit is used to calculate the first rate of change based on the power consumption data corresponding to each collection time when the power consumption data, the service data and the energy consumption data have the same collection time and the same collection period.

[0121] The third rate of change calculation unit is used to calculate the second rate of change based on the business data corresponding to each of the acquisition times, and to calculate the third rate of change based on the energy consumption data corresponding to each of the acquisition times.

[0122] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 can call the computer program in the memory 430 to execute the steps of the abnormal power station detection method.

[0123] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0124] On the other hand, embodiments of this application also provide a readable storage medium, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the steps of the abnormal power station detection method provided in the above embodiments.

[0125] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0126] 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 abnormal power consumption site detection method described in various embodiments or some parts of embodiments.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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. Such 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 this application.

Claims

1. A method for detecting abnormal power consumption sites, characterized in that, Applications include telecommunications operator network equipment room scenarios, including: Collect power consumption data, service data, and energy consumption data of the site to be tested; wherein, the power consumption data is the daily power consumption of the site to be tested within the collection period, the service data is the daily service volume of the site to be tested within the collection period, and the energy consumption data is the daily energy consumption data of the site to be tested within the collection period. Determine the first rate of change corresponding to the power consumption data, the second rate of change corresponding to the service data, and the third rate of change corresponding to the energy consumption data; If the power consumption data conforms to a target normal distribution, the abnormal time is determined based on the target normal distribution; Based on the first rate of change, the second rate of change, and the third rate of change, determine the correlation coefficient of the rate of change and the inverse correlation time of the rate of change; Based on the abnormal time, the correlation coefficient of the rate of change, and the inverse correlation time of the rate of change, the abnormal power consumption sites among the sites to be detected are determined; The step of determining the correlation coefficient of change rate and the inverse correlation time of change rate based on the first change rate, the second change rate, and the third change rate includes: The correlation coefficient of the first rate of change is determined based on the first rate of change, the second rate of change, and the preset coefficient calculation formula; The second rate of change correlation coefficient is determined based on the first rate of change, the third rate of change, and the preset coefficient calculation formula; If the first rate of change correlation coefficient is less than a preset threshold, the first rate of change inverse correlation time is determined based on the first rate of change correlation coefficient. If the second rate of change correlation coefficient is less than a preset threshold, the second rate of change inverse correlation time is determined based on the second rate of change correlation coefficient. The step of determining the abnormal power consumption sites among the sites to be detected based on the abnormal time, the correlation coefficient of the rate of change, and the inverse correlation time of the rate of change includes: Based on the power consumption data, the abnormal time, the rate of change correlation coefficient, and the rate of change inverse correlation time, the first feature vector corresponding to the site to be detected is determined; Obtain the second feature vector corresponding to the preset abnormal site, and calculate the angle in radians between the first feature vector and the second feature vector; The stations to be tested are sorted according to the magnitude of the included angle radian value, and the abnormal power consumption stations among the stations to be tested are determined according to the sorting results.

2. The method for detecting abnormal power consumption sites according to claim 1, characterized in that, The steps following the collection of power consumption data, service data, and energy consumption data of the site to be tested include: If there is missing data in the power consumption data, determine the first time corresponding to the missing data; Obtain the data sequence corresponding to the first time point, and supplement the missing data according to the preset interpolation method and the data sequence.

3. The method for detecting abnormal power consumption sites according to claim 1, characterized in that, The step of collecting power consumption data, service data, and energy consumption data of the site to be tested, and determining the first rate of change corresponding to the power consumption data, the second rate of change corresponding to the service data, and the third rate of change corresponding to the energy consumption data, is followed by: The mean sequence corresponding to the power consumption data is determined according to a preset sampling method; The mean sequence is tested according to a preset verification formula to obtain the verification result; Based on the verification results, determine whether the power consumption data conforms to the target normal distribution.

4. The method for detecting abnormal power consumption sites according to claim 1, characterized in that, The step of determining the abnormal time based on the target normal distribution includes: Based on the standard deviation corresponding to the target normal distribution, the deviation data in the power consumption data is determined; The time when the data deviated was collected was determined, and the collection time was designated as the abnormal time.

5. The method for detecting abnormal power consumption sites according to claim 1, characterized in that, The step of determining the first rate of change corresponding to the power consumption data, the second rate of change corresponding to the service data, and the third rate of change corresponding to the energy consumption data includes: When the power consumption data, the service data, and the energy consumption data have the same collection time and the same collection period, a first rate of change is calculated based on the power consumption data corresponding to each collection time. The second rate of change is calculated based on the business data corresponding to each of the aforementioned collection times, and the third rate of change is calculated based on the energy consumption data corresponding to each of the aforementioned collection times.

6. An abnormal power consumption site detection device, characterized in that, Applications include telecommunications operator network equipment room scenarios, including: The rate of change calculation module is used to collect power consumption data, service data, and energy consumption data of the site under test; wherein, the power consumption data is the daily power consumption of the site under test within the collection period, the service data is the daily service volume of the site under test within the collection period, and the energy consumption data is the daily energy consumption data of the site under test within the collection period; and determines a first rate of change corresponding to the power consumption data, a second rate of change corresponding to the service data, and a third rate of change corresponding to the energy consumption data; An abnormal time determination module is used to determine the abnormal time based on the target normal distribution when the power consumption data conforms to the target normal distribution; The correlation coefficient calculation module is used to determine the correlation coefficient of the rate of change and the inverse correlation time of the rate of change based on the first rate of change, the second rate of change and the third rate of change; An abnormal power consumption site determination module is used to determine the abnormal power consumption sites among the sites to be detected based on the abnormal time, the correlation coefficient of the rate of change, and the inverse correlation time of the rate of change. The step of determining the correlation coefficient of change rate and the inverse correlation time of change rate based on the first change rate, the second change rate, and the third change rate includes: The correlation coefficient of the first rate of change is determined based on the first rate of change, the second rate of change, and the preset coefficient calculation formula; The second rate of change correlation coefficient is determined based on the first rate of change, the third rate of change, and the preset coefficient calculation formula; If the first rate of change correlation coefficient is less than a preset threshold, the first rate of change inverse correlation time is determined based on the first rate of change correlation coefficient. If the second rate of change correlation coefficient is less than a preset threshold, the second rate of change inverse correlation time is determined based on the second rate of change correlation coefficient. The step of determining the abnormal power consumption sites among the sites to be detected based on the abnormal time, the correlation coefficient of the rate of change, and the inverse correlation time of the rate of change includes: Based on the power consumption data, the abnormal time, the rate of change correlation coefficient, and the rate of change inverse correlation time, the first feature vector corresponding to the site to be detected is determined; Obtain the second feature vector corresponding to the preset abnormal site, and calculate the angle in radians between the first feature vector and the second feature vector; The stations to be tested are sorted according to the magnitude of the included angle radian value, and the abnormal power consumption stations among the stations to be tested are determined according to the sorting results.

7. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the abnormal power station detection method according to any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the abnormal power station detection method as described in any one of claims 1 to 5.

Images