Power utilization habit-based power utilization abnormal behavior real-time analysis method and system

Abstract

The invention belongs to the technical field of power system data analysis, and relates to a power utilization habit-based power utilization abnormal behavior real-time analysis method and system, and the method comprises the steps: obtaining a historical power utilization data sample of a charging pile user, and carrying out the calculation to obtain a power utilization behavior habit interval; acquiring real-time power consumption data of the charging pile user according to a preset period, judging whether the real-time power consumption data is in the power consumption behavior habit interval, and if so, not giving an alarm; otherwise, giving an alarm; the advantages of wide coverage, high timeliness and high accuracy of power data are utilized, and the power utilization habit of the user is obtained through data analysis. Real-time power utilization data and historical power utilization habits are compared, abnormal power utilization behaviors are recognized, abnormal power utilization alarms are given out, and a charging pile operator is assisted in effective management, prevention and control; maintenance and upgrade plans of the charging piles are reasonably arranged, and usability of the charging piles is ensured. An electric power company can adjust an electric power supply strategy in advance, optimizes a power grid load, and avoids overlarge power grid pressure caused by a charging peak.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system data analysis, and relates to a real-time analysis method and system for abnormal power consumption behavior based on power consumption habits. Background Art

[0002] With the increasing popularity of electric vehicles, the demand for charging piles, as an important supporting facility for electric vehicles, has also increased dramatically. However, despite the increasing number of charging piles, we currently lack in-depth and comprehensive analysis of users' electricity consumption habits when using charging piles. This lack of analysis not only limits the optimization of the layout of charging facilities, but also affects the improvement of charging efficiency, and it is difficult to provide users with more personalized services. Specifically, the current usage data of charging piles mostly stays at the basic level of charging volume, charging time and charging frequency, while we have not yet conducted sufficient and detailed research on users' deeper behavioral habits such as charging preferences, charging time distribution, and charging location selection. This lack of data collection and analysis makes it impossible for us to accurately predict and grasp users' charging needs, and it is difficult to make scientific and reasonable layout planning for charging facilities. In some areas, charging piles may be too dense, resulting in a waste of resources; in other areas, charging piles may be in short supply, resulting in difficulties for users to charge.

[0003] In summary, there is currently a lack of in-depth analysis of users' electricity consumption habits when using charging piles, which makes it impossible to effectively optimize the layout of charging facilities, improve charging efficiency, reasonably arrange maintenance and upgrade plans for charging piles, and adjust power supply strategies to ensure the availability of charging piles. Optimize grid load and avoid excessive grid pressure caused by charging peaks. Summary of the invention

[0004] The purpose of the present invention is to provide a real-time analysis method and system for abnormal electricity usage behavior based on electricity usage habits, which solves the technical problems in the prior art of lack of in-depth analysis of electricity usage behavior habits, and inability to reasonably optimize the layout and maintenance of charging facilities and provide reasonable power supply.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present application discloses a real-time analysis method for abnormal electricity usage behavior based on electricity usage habits, comprising: Obtain historical electricity consumption data samples of charging pile users according to a preset period, and calculate the electricity consumption behavior habit interval of charging pile users; The real-time electricity consumption data of the charging pile users is obtained according to the preset period, and it is determined whether the real-time electricity consumption data is within the electricity consumption behavior habit range. If so, no alarm is issued; if not, an alarm is issued.

[0006] Preferably, the historical electricity consumption data samples of the charging pile users, the data set involves original tables mainly coming from CMS2.0, a new generation of electricity consumption information collection systems and the like.

[0007] Preferably, the acquiring of historical electricity consumption data samples of charging pile users and the calculation of the electricity consumption behavior habit intervals of charging pile users specifically include: S101: Acquire historical electricity consumption data samples according to a preset period, and pre-process the historical electricity consumption data samples; S102: Calculating the upper and lower bounds of the electricity consumption behavior habit interval based on the preprocessed historical electricity consumption data samples; S103: Based on the calculated upper and lower bounds of the electricity usage behavior habit interval, a line graph of the electricity usage behavior habit is drawn to obtain the electricity usage behavior habit interval of the charging pile user.

[0008] Preferably, in S101, the historical electricity consumption data samples are preprocessed, specifically: S1011: using the Laida criterion to detect discrete values ​​in the historical electricity consumption data sample to obtain discrete values; S1012: deleting or setting to zero the discrete values ​​detected in the historical electricity consumption data sample to obtain missing values; S1013: Fill the missing values ​​in the historical electricity consumption data sample with the value at the same position of the previous sampling point.

[0009] Preferably, the S102 specifically includes: S1021: Determine whether the pre-processed historical electricity consumption data sample conforms to the normal distribution under the set confidence level; S1022: If it is detected that the historical electricity consumption data sample conforms to the normal distribution, the upper and lower bounds of the electricity consumption behavior habit interval are calculated by the following formula:

[0010]

[0011] in: is the mean of the historical electricity consumption data samples; z is the normal distribution table value when the confidence level is 95%; is the standard deviation of historical electricity consumption data samples, and n is the number of sampling points; is the upper bound of the electricity consumption behavior interval; is the lower bound of the electricity consumption behavior habit interval; If it does not conform to the normal distribution, the Bootstrap method is used to calculate the upper and lower bounds of the electricity consumption behavior habit interval.

[0012] Preferably, the real-time power consumption data of the charging pile user is obtained according to a preset period, and it is determined whether the real-time power consumption data is within the power consumption behavior habit interval, if so, no alarm is issued; if not, an alarm is issued, specifically including: S201: acquiring the real-time power consumption data of the charging pile user according to a preset period, and determining whether the real-time power consumption data is 0; if the current real-time power consumption data is 0, determining whether it is a power outage event; if it is not a power outage event, determining it to be an abnormal power outage, and directly issuing the highest level alarm; S202: Determine whether the real-time power consumption data is within the power consumption behavior habit interval, and if so, do not issue an alarm; S203: If the real-time power consumption data is not within the power consumption behavior habit range, determining the abnormal power consumption behavior type; and obtaining the corresponding alarm reason according to the abnormal power consumption behavior type; S204: Obtain an alarm of a corresponding level according to the abnormal type of electricity consumption behavior or the real-time electricity consumption data.

[0013] Preferably, in said S203, determining the abnormal type specifically comprises: determining whether the real-time power consumption data is high load; If the real-time power consumption data is high load, determine whether the previous alarm is high load; if so, it is a continuous high load abnormality; if not, it is a sudden high load abnormality; If the real-time power consumption data is not high load, determine whether the previous alarm is low load; if so, it is a continuous low load abnormality, if not, it is a sudden low load abnormality.

[0014] Preferably, the alarm of corresponding level is obtained according to the real-time power consumption data, specifically: If the current maximum value of real-time electricity consumption data is within ±20% of the electricity consumption behavior habit range, it is a blue warning; if the current maximum value of real-time electricity consumption data is within ±(20%-40%) of the electricity consumption behavior habit range, it is a yellow warning; if the current maximum value of real-time electricity consumption data is within ±(40%-60%) of the electricity consumption behavior habit range, it is an orange warning; if the current maximum value of real-time electricity consumption data is within ±(60%-∞) of the electricity consumption behavior habit range, it is a red warning; the alarm urgency levels are blue, yellow, orange and red from low to high.

[0015] Preferably, obtaining an alarm of a corresponding level according to the type of abnormal power consumption behavior specifically includes: Obtain the alarm duration points corresponding to the abnormal power consumption behavior type; If the number of duration points is between [1,4], it is a blue warning; if the number of duration points is between [4,10], it is a yellow warning; if the number of duration points is between [10,16], it is an orange warning; if the number of duration points is between [16,+∞], it is a red warning; the alarm urgency levels are blue, yellow, orange, and red from low to high.

[0016] In a second aspect, the present application discloses a real-time analysis system for abnormal electricity usage behavior based on electricity usage habits, comprising: A preprocessing unit, used to obtain historical electricity consumption data samples of charging pile users according to a preset period, and calculate the electricity consumption behavior habit interval of the charging pile users; The analysis and judgment unit is used to obtain the real-time power consumption data of the charging pile user according to a preset period, and judge whether the real-time power consumption data is within the power consumption behavior habit range. If so, no alarm is issued; if not, an alarm is issued.

[0017] In a third aspect, the present application discloses an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-mentioned methods for real-time analysis of abnormal electricity usage behavior based on electricity usage habits when executing the computer program.

[0018] In a fourth aspect, the present application discloses a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of real-time analysis of abnormal electricity usage behavior based on electricity usage habits as described in any of the above items.

[0019] Compared with the prior art, the present invention has the following beneficial effects: This paper proposes a real-time analysis method for abnormal electricity consumption behavior based on electricity consumption habits. This method takes advantage of the wide coverage, strong timeliness and high accuracy of electricity data. By analyzing electricity consumption data, it reflects the living conditions of users. By analyzing a large number of users' electricity consumption behavior data, a database of concerned objects is established. Based on the historical electricity consumption data in the data center, the electricity consumption habits of the concerned objects are analyzed and recorded by big data. By comparing the real-time electricity consumption data and historical electricity consumption habits of the concerned objects, abnormal electricity consumption behaviors are identified, and abnormal electricity consumption alarms are issued to assist charging pile operators in effective management and prevention. Charging pile operators can reasonably arrange maintenance and upgrade plans for charging piles according to demand forecasts to ensure the availability of charging piles. Power companies can adjust power supply strategies in advance, optimize grid loads, and avoid excessive grid pressure caused by charging peaks.

[0020] Furthermore, the historical electricity consumption data samples take advantage of the characteristics of electricity data, such as wide coverage, high accuracy, and strong timeliness, and integrate the historical data calculation capabilities of the data center, the quasi-real-time data collection capabilities of the real-time measurement center, and the channel capabilities of the energy big data center's power intranet and government dedicated lines. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of the method of the present invention; Figure 2 Schematic diagram of a flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments 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 part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0024] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0026] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0027] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0028] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0029] The present invention is further described in detail below in conjunction with the accompanying drawings: The present invention utilizes the characteristics of power data, which has wide coverage, high accuracy and strong timeliness, and integrates the historical data calculation capability of the data center, the quasi-real-time data collection capability of the real-time measurement center, and the channel capability of the power intranet and government-related dedicated lines of the energy big data center. Combined with intelligent analysis algorithms, the power consumption data reflects the power consumption behavior and infers the risk of abnormal power consumption. Figure 1 The present application discloses a real-time analysis method of abnormal electricity consumption behavior based on electricity consumption habits, including: S1: Obtain historical electricity consumption data samples of charging pile users according to a preset period, and calculate the electricity consumption behavior habit interval of the charging pile users; S2: Acquire the real-time electricity consumption data of the charging pile users according to the preset period, and determine whether the real-time electricity consumption data is within the electricity consumption behavior habit range. If so, no alarm is issued; if not, an alarm is issued.

[0030] In some embodiments, the historical electricity consumption data samples of the charging pile users, the data set involves original tables mainly coming from CMS2.0, the new generation of electricity consumption information collection systems and other systems.

[0031] In some embodiments, the acquiring of historical electricity usage data samples of charging pile users and the calculation of the electricity usage behavior habit intervals of charging pile users specifically include: S101: Acquire historical electricity consumption data samples according to a preset period, and pre-process the historical electricity consumption data samples; S102: Calculating the upper and lower bounds of the electricity consumption behavior habit interval based on the preprocessed historical electricity consumption data samples; S103: Based on the calculated upper and lower bounds of the electricity usage behavior habit interval, a line graph of the electricity usage behavior habit is drawn to obtain the electricity usage behavior habit interval of the charging pile user.

[0032] In some embodiments, in S101, the historical electricity consumption data samples are preprocessed, specifically: S1011: using the Laida criterion to detect discrete values ​​in the historical electricity consumption data sample to obtain discrete values; S1012: deleting or setting to zero the discrete values ​​detected in the historical electricity consumption data sample to obtain missing values; S1013: Fill the missing values ​​in the historical electricity consumption data sample with the value at the same position of the previous sampling point.

[0033] In some embodiments, the S102 specifically includes: S1021: Determine whether the pre-processed historical electricity consumption data sample conforms to the normal distribution under the set confidence level; S1022: If it is detected that the historical electricity consumption data sample conforms to the normal distribution, the upper and lower bounds of the electricity consumption behavior habit interval are calculated by the following formula:

[0034]

[0035] in: is the mean of the historical electricity consumption data samples; z is the normal distribution table value when the confidence level is 95%; is the standard deviation of historical electricity consumption data samples, and n is the number of sampling points; is the upper bound of the electricity consumption behavior interval; is the lower bound of the electricity consumption behavior habit interval; If it does not conform to the normal distribution, the Bootstrap method is used to calculate the upper and lower bounds of the electricity consumption behavior habit interval.

[0036] In some embodiments, the real-time power consumption data of the charging pile user is obtained according to a preset period, and it is determined whether the real-time power consumption data is within the power consumption behavior habit interval. If so, no alarm is issued; if not, an alarm is issued, specifically including: S201: acquiring the real-time power consumption data of the charging pile user according to a preset period, and determining whether the real-time power consumption data is 0; if the current real-time power consumption data is 0, determining whether it is a power outage event; if it is not a power outage event, determining it to be an abnormal power outage, and directly issuing the highest level alarm; S202: Determine whether the real-time power consumption data is within the power consumption behavior habit interval, and if so, do not issue an alarm; S203: If the real-time power consumption data is not within the power consumption behavior habit range, determining the abnormal power consumption behavior type; and obtaining the corresponding alarm reason according to the abnormal power consumption behavior type; S204: Obtain an alarm of a corresponding level according to the abnormal type of electricity consumption behavior or the real-time electricity consumption data.

[0037] In some embodiments, in S203, determining the abnormal type is specifically: determining whether the real-time power consumption data is high load; If the real-time power consumption data is high load, determine whether the previous alarm is high load; if so, it is a continuous high load abnormality; if not, it is a sudden high load abnormality; If the real-time power consumption data is not high load, determine whether the previous alarm is low load; if so, it is a continuous low load abnormality, if not, it is a sudden low load abnormality.

[0038] In some embodiments, the alarm of corresponding level is obtained according to the real-time power consumption data, specifically: If the current maximum value of real-time electricity consumption data is within ±20% of the electricity consumption behavior habit range, it is a blue warning; if the current maximum value of real-time electricity consumption data is within ±(20%-40%) of the electricity consumption behavior habit range, it is a yellow warning; if the current maximum value of real-time electricity consumption data is within ±(40%-60%) of the electricity consumption behavior habit range, it is an orange warning; if the current maximum value of real-time electricity consumption data is within ±(60%-∞) of the electricity consumption behavior habit range, it is a red warning; the alarm urgency levels are blue, yellow, orange and red from low to high.

[0039] In some embodiments, obtaining an alarm of a corresponding level according to the type of abnormal power consumption behavior specifically includes: Obtain the alarm duration points corresponding to the abnormal power consumption behavior type; If the number of duration points is between [1,4], it is a blue warning; if the number of duration points is between [4,10], it is a yellow warning; if the number of duration points is between [10,16], it is an orange warning; if the number of duration points is between [16,+∞], it is a red warning; the alarm urgency levels are blue, yellow, orange, and red from low to high.

[0040] In some embodiments, a method for real-time analysis of abnormal electricity usage behavior based on electricity usage habits includes: 1. Data traceability: The original meters involved in this data set mainly come from CMS2.0, the new generation of electricity consumption information collection systems and other systems.

[0041] 2. Construct a summary table of charging pile electricity usage habits: Step 1: Calculate the electricity usage behavior interval of charging pile users based on the historical electricity usage data samples of charging pile users. The process is as follows: Step 101: Obtain historical electricity consumption data samples and perform preprocessing.

[0042] Step 102: Determine the electricity usage behavior habit interval.

[0043] Step 103: based on the calculated upper and lower bounds of the electricity usage behavior habit interval, draw an electricity usage behavior habit line graph, which is the electricity usage behavior habit interval of the charging pile user.

[0044] Step 2: Determine whether the current real-time power consumption data of the charging pile user is within the power consumption behavior habit interval obtained in step 1. If it is within the power consumption behavior habit interval, no alarm is required. If it is not within the power consumption behavior habit interval, a current alarm is issued. Figure 1 As shown, the process is as follows: Step 201: Sampling is performed according to the sampling period described in step 1, that is, fifteen minutes, to obtain the current real-time power consumption data of the charging pile user, and determine whether the current real-time power consumption data is zero.

[0045] If the current real-time power consumption data is 0, it is determined whether it is a power outage event; if it is not a power outage event, it is determined to be an abnormal power outage and the highest level alarm is directly issued.

[0046] If the current real-time power consumption data is not 0, the subsequent step 202 is executed.

[0047] Step 202: determine whether the current real-time electricity consumption data of the charging pile user is within the electricity consumption behavior habit range obtained in step 1. If it is within the electricity consumption behavior habit range, no alarm is required; if it is not within the electricity consumption behavior habit range, a current alarm is issued.

[0048] Step 203: After the load type of the current alarm is obtained, the current alarm is compared with the previous adjacent alarm by load type. If both are alarms of the same load type, the current alarm is determined to be a continuous abnormal type; if not, the current alarm is determined to be a sudden abnormal type. Thus, by executing step 203, it can be determined whether the current alarm is a sudden abnormality or a continuous abnormality.

[0049] Step 204: Determine the cause of the alarm based on the type of the current alarm. Specifically: If the current alarm is of abnormally high load type or sudden abnormal type, it is determined whether there was a high load alarm last time. If not, the cause of the alarm is that the minute-level power consumption exceeds the threshold.

[0050] If the current alarm is of abnormally low load type or sudden abnormal type, it is determined whether there was a low load alarm last time. If not, it is determined that the cause of the alarm is a sudden drop in load.

[0051] If the current alarm is of abnormally high load type or continuous abnormal type, determine whether the current time period is at night. If it is at night, the alarm reason is continuous high load at night; if it is not at night, the alarm reason is long-term high load.

[0052] If the current alarm is of abnormally low load type or continuous abnormal load type, then determine whether the current time is in the morning. If it is in the morning, the alarm reason is that there is no fluctuation during breakfast time; if it is not in the morning, then continue to determine whether it is at noon. If it is at noon, the alarm reason is that there is no fluctuation during lunch time; if it is not at noon, then continue to determine whether it is in the evening. If it is in the evening, the alarm reason is that there is no fluctuation during dinner time; if it is not in the evening, then continue to determine whether it is before going to bed. If it is before going to bed, the alarm reason is that there is no fluctuation before going to bed; if it is not in the above time, it is a long-term low load.

[0053] Step 205: Obtain an alarm of a corresponding level according to the real-time power consumption data, specifically: If the current maximum value of real-time electricity consumption data is within ±20% of the electricity consumption behavior habit range, it is a blue warning; if the current maximum value of real-time electricity consumption data is within ±(20%-40%) of the electricity consumption behavior habit range, it is a yellow warning; if the current maximum value of real-time electricity consumption data is within ±(40%-60%) of the electricity consumption behavior habit range, it is an orange warning; if the current maximum value of real-time electricity consumption data is within ±(60%-∞) of the electricity consumption behavior habit range, it is a red warning; the alarm urgency levels are blue, yellow, orange and red from low to high.

[0054] In some embodiments, a method for real-time analysis of abnormal electricity usage behavior based on electricity usage habits includes the following steps: The original meters involved in this data set mainly come from CMS2.0, the new generation of electricity consumption information collection systems and other systems.

[0055] Step 1: Calculate the charging pile user's electricity usage behavior interval based on the charging pile user's historical electricity usage data sample, such as Figure 2 As shown, the process is as follows: Step 101: Obtain historical electricity consumption data samples and perform preprocessing.

[0056] Since the electricity consumption of power users varies greatly in different seasons, this embodiment divides four types of electricity consumption habit season categories based on the four seasons of spring, summer, autumn and winter. And due to the particularity of charging pile users, since holidays may lead to an increase in electricity consumption data, this embodiment divides each type of electricity consumption habit season category into two habit categories, holidays and non-holidays. Therefore, this embodiment constructs a total of eight habit categories (four types of electricity consumption habit season categories multiplied by 2), and it is necessary to obtain historical electricity consumption data samples of charging pile users under each habit category.

[0057] In addition, the historical electricity consumption data samples under each habit category obtained in this embodiment have a sampling period of 15 minutes, so electricity consumption data of 96 sampling points can be obtained in one day. The subsequent electricity consumption behavior habit analysis is also analyzed with 15 minutes as a sampling point.

[0058] In the process of collecting electricity consumption data, it is necessary to go through multiple transmission links. Due to transmission problems, some outliers may appear. Outliers, also known as escape values, refer to one or more values ​​in the data that are significantly different from other values. These outliers will obviously affect the analysis and use of electricity consumption data, so they need to be preprocessed. In this embodiment, the preprocessing process of the historical electricity consumption data samples of eight habitual categories of charging pile users is as follows: Step 1011: First, use the Laida criterion to detect discrete values ​​in the historical electricity consumption data samples.

[0059] The Laida criterion is also known as the 3σ criterion. Its principle is: according to Chebyshev's inequality, for data of any distribution form, at least some of the data fall within k standard deviations of the mean, that is, when k=3, at least 89% of the data fall within the range of the mean plus or minus 3 standard deviations. Therefore, the Laida criterion is: for an independent measurement data of the same accuracy, when its residual error is , the data is considered to be an outlier, where is the mean and is the standard deviation. The calculation formula is as follows:

[0060]

[0061] By substituting the historical electricity consumption data samples obtained in this embodiment into formulas (1) and (2), discrete values ​​can be detected.

[0062] Step 1012: Delete or set to zero the discrete values ​​detected in the historical electricity consumption data samples.

[0063] Step 1013: fill in the missing values ​​in the historical electricity consumption data samples. Specifically, the missing value of each sampling point is filled with the value at the same position of the previous sampling point.

[0064] Thus, the preprocessing of the historical power consumption data samples is completed through steps 1011-1013. In this embodiment, if the discrete values ​​are calculated according to step 1011 and it is found that the discrete values ​​are generated for a long time, it is necessary to diagnose whether the power consumption data transmission system is faulty.

[0065] Step 102: Determine the electricity usage behavior habit interval.

[0066] User behavior habit analysis introduces the concept of confidence interval in statistics. The behavior habit interval of charging pile electricity consumption is obtained by calculating the upper and lower limits of the confidence interval of the electricity consumption data of charging pile users. This embodiment sets the confidence level to 95%, which means that there is a 95% probability that the electricity consumption data of the charging pile falls within the confidence interval, and the data that does not fall within the confidence interval may be abnormal. The specific process is as follows: First, determine whether the preprocessed historical electricity consumption data sample conforms to the normal distribution under the set confidence level. This embodiment uses the improved Shapiro-Wilk test to determine whether it conforms to the normal distribution. The Shapiro-Wilk test is an algorithm based on correlation. A correlation coefficient can be calculated. The closer it is to 1, the better the data fits the normal distribution. The electricity consumption data is a table lookup value, and the calculation formula is:

[0067] The test statistic W is calculated and compared with the limit value Wa, which is obtained by looking up the table. If the W value is less than Wa, the normality hypothesis is abandoned according to the significance level written in the table; if the W value is greater than Wa, the normality hypothesis is accepted.

[0068] When it is detected that the historical electricity consumption data samples conform to the normal distribution, the upper and lower bounds of the electricity consumption behavior habit interval are calculated using the following formula:

[0069]

[0070] Among them: is the mean of the historical electricity consumption data samples; z is the normal distribution lookup value at a confidence level of 95%; is the standard deviation of the historical electricity consumption data samples, n is the number of sampling points; is the upper bound of the electricity consumption behavior habit interval; is the lower bound of the electricity consumption behavior habit interval.

[0071] If it does not conform to the normal distribution, the Bootstrap method is used to calculate the upper and lower bounds of the electricity consumption behavior habit interval. Boostrap, also known as the bootstrap method, is a non-parametric statistical technique widely used in statistics to estimate the variability of a statistic and construct its confidence interval. The core idea of ​​the Bootstrap method is to simulate the sampling distribution of data by repeatedly sampling the original data.

[0072] Step 103: based on the calculated upper and lower bounds of the electricity usage behavior habit interval, draw an electricity usage behavior habit line graph, which is the electricity usage behavior habit interval of the charging pile user.

[0073] Step 2: Determine whether the current real-time power consumption data of the charging pile user is within the power consumption behavior habit interval obtained in step 1. If it is within the power consumption behavior habit interval, no alarm is required. If it is not within the power consumption behavior habit interval, a current alarm is issued. Figure 1 As shown, the process is as follows: Step 201: Sampling is performed according to the sampling period described in step 1, that is, fifteen minutes, to obtain the current real-time power consumption data of the charging pile user, and determine whether the current real-time power consumption data is zero.

[0074] If the current real-time power consumption data is 0, it is determined whether it is a power outage event; if it is not a power outage event, it is determined to be an abnormal power outage and the highest level alarm is directly issued.

[0075] If the current real-time power consumption data is not 0, the subsequent step 202 is executed.

[0076] Step 202: determine whether the current real-time electricity consumption data of the charging pile user is within the electricity consumption behavior habit range obtained in step 1. If it is within the electricity consumption behavior habit range, no alarm is required; if it is not within the electricity consumption behavior habit range, a current alarm is issued.

[0077] In this embodiment, four alarm urgency levels are set for the current alarm, indicating the urgency of the current alarm information. The alarm urgency levels are blue, yellow, orange, and red from low to high. When the alarm is actually issued, the higher alarm level is used as the alarm level. The specific urgency level of the current alarm is determined based on the percentage range of the current real-time power consumption data exceeding the power consumption behavior habit interval, or the number of current alarm duration points, where: When determining the urgency level based on the percentage range of the current real-time electricity consumption data exceeding the electricity consumption habit range, if the maximum value of the current real-time electricity consumption data is within ±20% of the electricity consumption habit range, it is a blue warning; if the maximum value of the current real-time electricity consumption data is within ±(20%-40%) of the electricity consumption habit range, it is a yellow warning; if the maximum value of the current real-time electricity consumption data is within ±(40%-60%) of the electricity consumption habit range, it is an orange warning; if the maximum value of the current real-time electricity consumption data is within ±(60%-∞) of the electricity consumption habit range, it is a red warning.

[0078] When determining the urgency level based on the number of current alarm duration points, if the number of duration points is between [1,4], it is a blue warning; if the number of duration points is between [4,10], it is a yellow warning; if the number of duration points is between [10,16], it is an orange warning; if the number of duration points is between [16,+∞], it is a red warning.

[0079] In this embodiment, if the current alarm is issued, it is further determined whether the current real-time power consumption data is higher than the upper limit of the power consumption behavior habit interval and whether it is lower than the lower limit of the power consumption behavior habit interval. If it is higher than the upper limit, the current alarm is determined to be an abnormally high load type; if it is lower than the lower limit, the current alarm is determined to be an abnormally low load type.

[0080] After step 202 is completed, the subsequent step 203 is executed.

[0081] In step 203, after the load type of the current alarm is obtained, the current alarm is compared with the adjacent last alarm according to the load type. If both are alarms of the same load type, the current alarm is determined to be a continuous abnormal type; if they are not alarms of the same load type, the current alarm is determined to be a sudden abnormal type. Thus, by executing step 203, it can be determined whether the current alarm is a sudden abnormality or a continuous abnormality.

[0082] Step 204: Determine the cause of the alarm based on the type of the current alarm. Specifically: If the current alarm is of a sudden high load abnormal type, it is determined whether there was a high load alarm last time. If not, the alarm cause is that the minute-level power consumption exceeds the threshold.

[0083] If the current alarm is of a sudden low load abnormal type, it is determined whether there was a low load alarm last time. If not, it is determined that the cause of the alarm is a sudden drop in load.

[0084] If the current alarm is of a continuous high load abnormal type, determine whether the current time period is at night. If it is at night, the alarm reason is continuous high load at night; if it is not at night, the alarm reason is long-term high load.

[0085] If the current alarm is of a continuous low load abnormal type, determine whether the current time is in the morning. If it is in the morning, the alarm reason is that there is no fluctuation during breakfast time; if it is not in the morning, continue to determine whether it is at noon. If it is at noon, the alarm reason is that there is no fluctuation during lunch time; if it is not at noon, continue to determine whether it is in the evening. If it is in the evening, the alarm reason is that there is no fluctuation during dinner time; if it is not in the evening, continue to determine whether it is before going to bed. If it is before going to bed, the alarm reason is that there is no fluctuation before going to bed; if it is not in any of the above times, it is a long-term low load.

[0086] Therefore, based on steps 1 and 2, this embodiment can analyze and monitor the electricity usage habits of charging pile users in combination with the current real-time electricity usage data of the currently sampled charging pile users, and issue an alarm when necessary. The next time the real-time electricity usage data of the charging pile users is sampled, the previously sampled real-time electricity usage data is added to the historical electricity usage data sample described in step 1, thereby realizing the continuous updating of the historical electricity usage data sample.

[0087] The present application also discloses a real-time analysis system for abnormal electricity usage behavior based on electricity usage habits, including: A preprocessing unit, used to obtain historical electricity consumption data samples of charging pile users according to a preset period, and calculate the electricity consumption behavior habit interval of the charging pile users; The analysis and judgment unit is used to obtain the real-time power consumption data of the charging pile user according to a preset period, and judge whether the real-time power consumption data is within the power consumption behavior habit range. If so, no alarm is issued; if not, an alarm is issued.

[0088] The present application also discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for real-time analysis of abnormal electricity usage behavior based on electricity usage habits described in any one of the above are implemented.

[0089] The present application also discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of real-time analysis of abnormal electricity usage behavior based on electricity usage habits as described in any of the above items are implemented.

[0090] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A real-time analysis method for abnormal electricity consumption behavior based on electricity consumption habits, characterized in that: include: Obtain historical electricity consumption data samples of charging pile users according to a preset period, and calculate the electricity consumption behavior habit interval of charging pile users; The real-time electricity consumption data of the charging pile users is obtained according to the preset period, and it is determined whether the real-time electricity consumption data is within the electricity consumption behavior habit range. If so, no alarm is issued; if not, an alarm is issued.

2. A real-time analysis method for abnormal electricity consumption behavior based on electricity consumption habits according to claim 1, characterized in that: The obtaining of historical electricity consumption data samples of charging pile users and calculating the electricity consumption behavior habit interval of charging pile users specifically includes: S101: Acquire historical electricity consumption data samples according to a preset period, and pre-process the historical electricity consumption data samples; S102: Calculating the upper and lower bounds of the electricity consumption behavior habit interval based on the preprocessed historical electricity consumption data samples; S103: Based on the calculated upper and lower bounds of the electricity usage behavior habit interval, a line graph of the electricity usage behavior habit is drawn to obtain the electricity usage behavior habit interval of the charging pile user.

3. A real-time analysis method of abnormal electricity consumption behavior based on electricity consumption habits according to claim 2, characterized in that: In S101, the historical electricity consumption data samples are preprocessed, specifically: S1011: using the Laida criterion to detect discrete values ​​in the historical electricity consumption data sample to obtain discrete values; S1012: deleting or setting to zero the discrete values ​​detected in the historical electricity consumption data sample to obtain missing values; S1013: Fill the missing values ​​in the historical electricity consumption data sample with the value at the same position of the previous sampling point.

4. The method for real-time analysis of abnormal electricity consumption behavior based on electricity consumption habits according to claim 2, characterized in that: The S102 specifically includes: S1021: Determine whether the pre-processed historical electricity consumption data sample conforms to the normal distribution under the set confidence level; S1022: If it is detected that the historical electricity consumption data sample conforms to the normal distribution, the upper and lower bounds of the electricity consumption behavior habit interval are calculated by the following formula: in: is the mean of the historical electricity consumption data samples; z is the normal distribution table value when the confidence level is 95%; is the standard deviation of historical electricity consumption data samples, and n is the number of sampling points; is the upper bound of the electricity consumption behavior interval; is the lower bound of the electricity consumption behavior habit interval; If it does not conform to the normal distribution, the Bootstrap method is used to calculate the upper and lower bounds of the electricity consumption behavior habit interval.

5. The method for real-time analysis of abnormal electricity consumption behavior based on electricity consumption habits according to claim 1, characterized in that: The real-time power consumption data of the charging pile user is obtained according to a preset period, and it is determined whether the real-time power consumption data is within the power consumption behavior habit range. If so, no alarm is issued; if not, an alarm is issued, specifically including: S201: acquiring the real-time power consumption data of the charging pile user according to a preset period, and determining whether the real-time power consumption data is 0; if the current real-time power consumption data is 0, determining whether it is a power outage event; if it is not a power outage event, determining it to be an abnormal power outage, and directly issuing the highest level alarm; S202: Determine whether the real-time power consumption data is within the power consumption behavior habit interval, and if so, do not issue an alarm; S203: If the real-time power consumption data is not within the power consumption behavior habit range, determining the abnormal power consumption behavior type; and obtaining the corresponding alarm reason according to the abnormal power consumption behavior type; S204: Obtain an alarm of a corresponding level according to the abnormal type of electricity consumption behavior or the real-time electricity consumption data.

6. A real-time analysis method of abnormal electricity consumption behavior based on electricity consumption habits according to claim 5, characterized in that: In the step S203, determining the abnormal type is specifically: determining whether the real-time power consumption data is high load; If the real-time power consumption data is high load, determine whether the previous alarm is high load; if so, it is a continuous high load abnormality; if not, it is a sudden high load abnormality; If the real-time power consumption data is not high load, determine whether the previous alarm is low load; if so, it is a continuous low load abnormality, if not, it is a sudden low load abnormality.

7. The method for real-time analysis of abnormal electricity usage behavior based on electricity usage habits according to claim 5, characterized in that: The alarm of corresponding level is obtained according to the real-time power consumption data, specifically: If the current maximum value of real-time electricity consumption data is within ±20% of the electricity consumption behavior habit range, it is a blue warning; if the current maximum value of real-time electricity consumption data is within ±(20%-40%) of the electricity consumption behavior habit range, it is a yellow warning; if the current maximum value of real-time electricity consumption data is within ±(40%-60%) of the electricity consumption behavior habit range, it is an orange warning; if the current maximum value of real-time electricity consumption data is within ±(60%-∞) of the electricity consumption behavior habit range, it is a red warning; the alarm urgency levels are blue, yellow, orange and red from low to high.

8. A real-time analysis system for abnormal electricity consumption behavior based on electricity consumption habits, characterized in that: include: A preprocessing unit, used to obtain historical electricity consumption data samples of charging pile users according to a preset period, and calculate the electricity consumption behavior habit interval of the charging pile users; The analysis and judgment unit is used to obtain the real-time power consumption data of the charging pile user according to a preset period, and judge whether the real-time power consumption data is within the power consumption behavior habit range. If so, no alarm is issued; if not, an alarm is issued.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for real-time analysis of abnormal electricity usage behavior based on electricity usage habits as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the method for real-time analysis of abnormal electricity usage behavior based on electricity usage habits as described in any one of claims 1 to 7.

Images