Line loss abnormity monitoring method and system based on user behaviors
By collecting and analyzing user power information data, calculating the load fluctuation index and the consistency of electricity consumption patterns, the problem of insufficient adaptability to changes in user behavior in traditional line loss management is solved, enabling accurate identification and location of line loss anomalies, and improving monitoring efficiency and accuracy.
Patent Information
- Application Number
- CN202511713890.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-21
- Publication Date
- 2026-02-13
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional line loss management relies on manual inspections, which makes it difficult to detect line loss anomalies in a timely manner. Especially after the connection of new electrical equipment, the line loss calculation has large deviations and is not adaptable enough to changes in user behavior, leading to misjudgments and omissions.
By collecting user power information data, calculating the load fluctuation index and the consistency of electricity consumption patterns, distinguishing the stability of user electricity consumption behavior, and combining theoretical line loss calculations with actual line loss deviation rates, line loss anomalies are identified and located.
It enables accurate identification of abnormal line loss, improves monitoring efficiency and accuracy, reduces misjudgments and omissions, and significantly improves the accuracy and effectiveness of line loss monitoring.
Smart Images
Figure CN121524847A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application relates to the technical field of power monitoring, in particular to a line loss anomaly monitoring method and system based on user behavior. BACKGROUND
[0002] Line loss anomaly monitoring is a key link in power system monitoring management, aiming to analyze the difference between power supply and power sales to identify abnormal conditions in line loss, such as electricity stealing, metering error, line aging and leakage loss, etc.
[0003] However, traditional line loss management still relies on manual inspection mode. With the widespread application of new power equipment in distribution areas and the access of new user equipment, the power grid operating environment has become more complex, and the manual inspection cycle has been extended, making it difficult to detect line loss anomalies in a timely manner. Even if the theoretical line loss is calculated by analyzing the line parameters and compared, this method is not suitable for new users or users with sudden changes in power consumption behavior, resulting in a large deviation in the calculation of theoretical line loss. Only relying on the parameters of the line itself, it is difficult to distinguish between line loss fluctuations caused by changes in user behavior and real abnormal line loss. SUMMARY
[0004] To solve the above problems, the application provides a line loss anomaly monitoring method based on user behavior, comprising: Collecting power information data of all users in the target area, the power information data including the power consumption type of each user, current period power load data, offline historical period power load data, power meter power supply data and power meter power sales data; merging the preprocessed current period power load data and offline historical period power load data; Based on the merged data of each user, the user power consumption behavior stability is determined, the merged data of a single user is compared with a preset data value, if it is less than the preset data value, it is determined that the user is a power consumption behavior unstable user; if it is greater than the preset data value, the user power consumption feature is extracted according to the merged data, the load fluctuation index and the power consumption rule consistency are calculated, and the power consumption behavior stability is determined according to the load fluctuation index and the power consumption rule consistency; The theoretical line loss of the power consumption behavior stable user and the power consumption behavior unstable user is calculated respectively, and the theoretical line loss of all users is accumulated to obtain the total theoretical line loss of the target area; According to the total power supply of the target area and the sum of the power sales data of all users, the actual line loss value of the target area in the current period is calculated; based on the actual line loss value and the total theoretical line loss, the line loss deviation rate is calculated, and the line loss anomaly is judged; When it is judged that there is line loss abnormality in the target area, the deviation value of the actual line loss value of each user from the theoretical line loss is calculated, the abnormal contribution degree is obtained according to the deviation value proportion, the user abnormality is marked based on the abnormal contribution degree, and the line loss positioning is performed.
[0005] The power consumption behavior stability is determined according to the load fluctuation index and the power consumption regularity consistency, if the load fluctuation index is less than 0.5 and the power consumption regularity consistency is greater than 0.8, the user is determined as a stable power consumption behavior user, otherwise, the user is determined as an unstable power consumption behavior user.
[0006] The calculation formula of the load fluctuation index is: In the formula, P i represents the power consumption power at the dth time point; i represents the average power consumption power; N is the total number of data points; represents the load fluctuation index. LVI
[0007] The calculation formula of the power consumption regularity consistency is: In the formula, P d represents the power consumption curve of the dth day, P d [ P d,1 , P d,2 , P d,i ]; P avg represents the average power consumption curve; ρ represents the Pearson correlation coefficient; D is the total number of days.
[0008] The calculation of the theoretical line loss of the stable user includes establishing a line loss calculation model according to the offline historical period power load data of the user and the line parameters; calculating the management line loss according to the management line loss coefficient corresponding to the power consumption type of the user and the power consumption data; and obtaining the stable single user theoretical line loss according to the line loss calculation model and the management line loss.
[0009] The theoretical line loss of the user with unstable power consumption behavior also includes correcting the theoretical line loss by similar user data, grouping historical load data of other users into a first historical sequence, calculating the noise degree of each data, dividing the first historical sub-sequence according to the length of the current time period, calculating the similarity index with the current load sequence of the target user, and screening the reference historical data sequence with a similarity index greater than or equal to a preset threshold; all users are classified according to each user feature, the similarity index of the user load data in each category is calculated, and the average value of all categories is taken as the correlation degree of the feature and the power consumption behavior; the power consumption similarity is calculated according to the category matching of the similar user and the target user; the reflecting degree of the reference data sequence is obtained by combining the environmental similarity of the reference period and the current period; the theoretical line loss of the similar user is weighted based on the reflecting degree to obtain the corrected theoretical line loss of the user with unstable power consumption behavior.
[0010] The calculation formula of the line loss deviation rate is: Wherein, ΔP user represents the stable single-user theoretical line loss; ΔP user ' represents the corrected theoretical line loss of the user with unstable power consumption behavior; ΔP a is the actual line loss value of the target area in the current period.
[0011] In the specific embodiment, the deviation value of a single user is divided by the sum of the deviation values of all users to obtain the abnormal contribution degree of a single user.
[0012] The user abnormality marking based on the abnormal contribution degree is used for line loss positioning, specifically, the abnormal contribution degree of each user is compared with the contribution reference threshold, if greater than or equal to the contribution reference threshold, the user is marked as abnormal, and the line loss abnormal area is located according to the power information data and line node parameters of the user.
[0013] The application also provides a line loss abnormality monitoring system based on user behavior, comprising: A data processing module is used for collecting power information data of all users in a target area, the power information data including power consumption type, current period power load data, offline historical period power load data, power meter power supply data and power meter power sales data of each user; and the current period power load data and offline historical period power load data are preprocessed and then merged. The behavior analysis module is used for user electricity behavior stability determination based on the merged data of each user, comparing the merged data of a single user with a preset data amount value, if less than the preset data amount value, determining that the user is an electricity behavior unstable user, if greater than the preset data amount value, performing user electricity feature extraction according to the merged data, calculating a load fluctuation index and electricity law consistency, and performing electricity behavior stability determination according to the load fluctuation index and electricity law consistency; The line loss calculation module is used for calculating the theoretical line loss of the electricity behavior stable user and the electricity behavior unstable user respectively, and accumulating the theoretical line loss of all users to obtain the total theoretical line loss of the target station area; The abnormality judgment module is used for calculating the actual line loss value of the target station area in the current period according to the total power supply amount of the target station area and the sum of the electricity sales data of all users, calculating the line loss deviation rate based on the actual line loss value and the total theoretical line loss, and performing line loss abnormality judgment; The marking processing module is used for calculating the deviation value of the actual line loss value and the theoretical line loss of each user when it is judged that the target station area has line loss abnormality, obtaining the abnormal contribution degree according to the deviation value proportion, performing user abnormality marking based on the abnormal contribution degree, and performing line loss positioning.
[0014] Beneficial effects: the present application is a line loss abnormality monitoring method and system based on user behavior, which can more accurately identify line loss abnormality by collecting and analyzing the power information data of the target station area users, marking user abnormality and positioning line loss according to the abnormal contribution degree, effectively solving the limitations of traditional line loss management relying on manual inspection, improving the monitoring efficiency and accuracy; at the same time, considering the stability of user electricity behavior, the load fluctuation index and electricity law consistency are calculated, which can distinguish the line loss fluctuation caused by user behavior change from the real abnormal line loss, thereby reducing the misjudgment and omission, solving the problem of low line loss calculation accuracy and difficult abnormality positioning caused by the insufficient consideration of user behavior difference in traditional line loss monitoring, realizing the accurate portrait and classification of user electricity behavior, and significantly improving the accuracy and effectiveness of line loss monitoring. BRIEF DESCRIPTION OF DRAWINGS
[0015] The scheme and advantages of the present application will become clear to those skilled in the art by reading the detailed description of the preferred embodiments below. The drawings are only for the purpose of illustrating the preferred embodiments and are not considered as limiting the present application.
[0016] Figure 1 It is a flowchart of the line loss abnormality monitoring method based on user behavior. DETAILED DESCRIPTION
[0017] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings.
[0018] Example See Figure 1 This embodiment provides a method for monitoring abnormal line loss based on user behavior, which includes the following steps: Step 1: Collect power information data for all users within the target distribution area. The power information data includes each user's electricity consumption type, current time period power load data, offline historical time period power load data, electricity meter power supply data, and electricity meter sales data. The current time period power load data and offline historical time period power load data are preprocessed and then merged. The power information data of all electricity users in the distribution area is obtained by the distributed power data acquisition system of the distribution area. Based on the acquisition cycle, the power load data of each user in the current time period is obtained in real time. At the same time, the offline historical power load data of each user is collected in parallel. The power supply data and power sales data of the user collected by the smart energy meter are obtained.
[0019] Preprocessing operations are performed on the collected current period power load data and offline historical period power load data, including using median filtering algorithm to remove noise from the data; using linear interpolation to complete missing data; converting all data into labeled mode and retaining their original timestamps.
[0020] The historical data collected from offline historical periods is merged with the real-time data collected in the current period to obtain a merged dataset.
[0021] Step 2: Based on the merged data of each user, determine the stability of the user's electricity consumption behavior. Compare the merged data of a single user with a preset data value. If it is less than the preset data value, the user is determined to be a user with unstable electricity consumption behavior. If it is greater than the preset data value, extract the user's electricity consumption characteristics based on the merged data, calculate the load fluctuation index and the consistency of electricity consumption patterns, and determine the stability of electricity consumption behavior based on the consistency of the load fluctuation index and the electricity consumption patterns. The user's merged data is less than the preset data volume value, which indicates that the user is a new user with less offline historical power load data, and the user's historical data is less than the data volume corresponding to a fixed number of days based on the collection period.
[0022] When the user's merged data exceeds a preset data value, user electricity consumption characteristics are extracted based on the user's electricity load. The calculation formula for the load fluctuation index is as follows: In the formula, P i Indicates the first i Power consumption at a specific time point; This represents the average power consumption; N is the total number of data points. LVI This represents the load volatility index.
[0023] The formula for calculating the consistency of electricity consumption patterns is as follows: in, P d This represents the electricity consumption curve for day d. P d =[ P d,1 , P d,2 , ..., P d,i ]; P avg Represents the average electricity consumption curve; ρ denoted by Pearson correlation coefficient; D represents the total number of days.
[0024] The stability of electricity consumption behavior is determined based on the consistency between the load fluctuation index and the electricity consumption pattern. If the load fluctuation index is less than 0.5 and the consistency of electricity consumption pattern is greater than 0.8, the user is determined to be a user with stable electricity consumption behavior; otherwise, the user is determined to be a user with unstable electricity consumption behavior.
[0025] Step 3: Calculate the theoretical line loss for users with stable electricity consumption and users with unstable electricity consumption separately, and sum the theoretical line losses of all users to obtain the total theoretical line loss of the target transformer area. The specific operation is as follows: Calculating the theoretical line loss for users with stable electricity consumption behavior involves establishing a line loss calculation model based on the user's offline historical power load data and line parameters. The formula is as follows: Where I is the load current; R represents the line resistance; and t represents the duration.
[0026] The management line loss is calculated based on the management line loss coefficient corresponding to the user's electricity consumption type and the electricity sales data. The formula is as follows: Where Psell represents electricity sales data; k represents the management line loss coefficient.
[0027] Based on the line loss calculation model and management line loss, the stable theoretical line loss for a single user is obtained. .
[0028] The theoretical line loss for users with unstable electricity consumption behavior is calculated, and this theoretical line loss is corrected using similar user data. Historical load data from other users are grouped into a first historical sequence, and the noise level of each data point is calculated. The first historical subsequence is divided according to the current time period length, and a similarity index is calculated between it and the current load sequence of the target user. Reference historical data sequences with a similarity index ≥ a preset threshold are selected. All users are classified according to each user characteristic, and the similarity index of user load data under each category is calculated. The average value of all categories is taken as the correlation between that characteristic and electricity consumption behavior. Electricity consumption similarity is calculated based on the category matching between similar users and the target user. The reflectivity of the reference data sequence is obtained by combining the environmental similarity between the reference time period and the current time period. The theoretical line loss of similar users is weighted based on the reflectivity to obtain the corrected theoretical line loss ΔP for users with unstable electricity consumption behavior. user '.
[0029] The total theoretical line loss of the target transformer area is obtained by summing up the theoretical line losses of all users.
[0030] Step 4: Calculate the actual line loss value of the target transformer area for the current time period based on the sum of the total power supply of the target transformer area and the electricity sales data of all users; calculate the line loss deviation rate based on the actual line loss value and the total theoretical line loss, and make a judgment on line loss anomalies. The actual line loss value for the target transformer area during the current time period is calculated based on the sum of the total power supply of the target transformer area and the electricity sales data of all users. The formula is as follows: In the formula, P S The total power supply to the target distribution area; ΔP a This represents the actual line loss value for the current time period.
[0031] The line loss deviation rate is calculated based on the actual line loss value and the total theoretical line loss. The formula is as follows: Line loss anomaly is determined based on the calculated line loss deviation rate. If the line loss deviation rate is greater than or equal to a preset deviation threshold, the target transformer area is judged to have a line loss anomaly; if it is less than the preset deviation threshold, the line loss is judged to be normal.
[0032] Step 5: When it is determined that there is an abnormal line loss in the target area, calculate the deviation between the actual line loss value and the theoretical line loss value for each user, obtain the abnormal contribution rate based on the deviation rate, and mark the user abnormality based on the abnormal contribution rate to locate the line loss. When step four determines that there is an abnormal line loss in the target transformer area based on the line loss deviation rate, the abnormal line loss is located based on the line loss data of each user. The deviation value between the actual line loss value and the theoretical line loss of each user is calculated. The deviation value of a single user is divided by the sum of the deviation values of all users to obtain the abnormal contribution of a single user. The abnormal contribution of each user is compared with the contribution reference threshold. If it is greater than or equal to the contribution reference threshold, the user is marked as abnormal. Based on the power information data and line node parameters of the user, the abnormal line loss area is located. At the same time, the cause of the abnormality is determined based on the changes in the electricity consumption behavior and metering information data of the abnormal user.
[0033] In addition, a line loss anomaly monitoring system based on user behavior is also provided, including: The data processing module is used to collect power information data of all users within the target distribution area. The power information data includes each user's electricity consumption type, current time period power load data, offline historical time period power load data, electricity meter power supply data, and electricity meter sales data. The current time period power load data and offline historical time period power load data are preprocessed and then merged. The behavior analysis module is used to determine the stability of user electricity consumption behavior based on the merged data of each user. It compares the merged data of a single user with a preset data value. If the data is less than the preset data value, the user is determined to be a user with unstable electricity consumption behavior. If the data is greater than the preset data value, the module extracts user electricity consumption characteristics based on the merged data, calculates the load fluctuation index and the consistency of electricity consumption patterns, and determines the stability of electricity consumption behavior based on the consistency of the load fluctuation index and the electricity consumption patterns. The line loss calculation module is used to calculate the theoretical line loss for users with stable electricity consumption behavior and users with unstable electricity consumption behavior respectively, and to sum up the theoretical line losses of all users to obtain the total theoretical line loss of the target transformer area. The anomaly detection module is used to calculate the actual line loss value of the target transformer area in the current time period based on the total power supply of the target transformer area and the sum of the electricity sales data of all users; and to calculate the line loss deviation rate based on the actual line loss value and the total theoretical line loss to make line loss anomaly detection. The marking and processing module is used to calculate the deviation between the actual line loss value and the theoretical line loss value for each user when it is determined that there is an abnormal line loss in the target area. The module obtains the abnormal contribution based on the percentage of the deviation value, marks the user as abnormal based on the abnormal contribution, and locates the line loss.
Claims
1. A method for monitoring abnormal line loss based on user behavior, characterized in that, include: Collect power information data of all users in the target area. The power information data includes each user's electricity consumption type, current time period power load data, offline historical time period power load data, electricity meter power supply data and electricity meter sales data. The current period's power load data and the offline historical period's power load data are preprocessed and then merged. The stability of user electricity consumption behavior is determined based on the merged data of each user. The merged data of a single user is compared with a preset data value. If it is less than the preset data value, the user is determined to be a user with unstable electricity consumption behavior. If the data volume exceeds the preset value, user electricity consumption characteristics are extracted based on the merged data, the load fluctuation index is calculated to match the electricity consumption pattern, and the stability of electricity consumption behavior is determined based on the consistency between the load fluctuation index and the electricity consumption pattern. Calculate the theoretical line loss for users with stable electricity consumption and users with unstable electricity consumption separately, and sum up the theoretical line losses of all users to obtain the total theoretical line loss of the target transformer area; Calculate the actual line loss value of the target transformer area for the current time period based on the sum of the total power supply of the target transformer area and the electricity sales data of all users; The line loss deviation rate is calculated based on the actual line loss value and the total theoretical line loss to determine line loss anomalies. When it is determined that there is an abnormal line loss in the target area, the deviation between the actual line loss value and the theoretical line loss value of each user is calculated. The abnormal contribution is obtained based on the percentage of the deviation value. Based on the abnormal contribution, users are marked as abnormal and the line loss is located.
2. The method for monitoring abnormal line loss based on user behavior according to claim 1, characterized in that, The stability of electricity consumption behavior is determined based on the consistency between the load fluctuation index and the electricity consumption pattern. If the load fluctuation index is less than 0.5 and the consistency of electricity consumption pattern is greater than 0.8, the user is determined to be a user with stable electricity consumption behavior; otherwise, the user is determined to be a user with unstable electricity consumption behavior.
3. The method for monitoring abnormal line loss based on user behavior according to claim 2, characterized in that, The formula for calculating the load volatility index is as follows: In the formula, P i Indicates the first i Power consumption at a specific time point; This represents the average power consumption; N is the total number of data points. LVI This represents the load volatility index.
4. The method for monitoring abnormal line loss based on user behavior according to claim 2, characterized in that, The formula for calculating the consistency of electricity consumption patterns is as follows: in, P d This represents the electricity consumption curve for day d. P d =[ P d,1 , P d,2 , ..., P d,i ]; P avg Represents the average electricity consumption curve; ρ denoted by Pearson correlation coefficient; D represents the total number of days.
5. The method for monitoring abnormal line loss based on user behavior according to claim 1, characterized in that, The calculation of theoretical line loss for users with stable electricity consumption behavior includes establishing a line loss calculation model based on the user's offline historical power load data and line parameters; and calculating the management line loss based on the management line loss coefficient corresponding to the user's electricity consumption type and electricity sales data. Based on the line loss calculation model and management line loss, the stable theoretical line loss for a single user is obtained.
6. The method for monitoring abnormal line loss based on user behavior according to claim 1, characterized in that, The theoretical line loss for users with unstable electricity consumption behavior also includes correcting the theoretical line loss using similar user data. This involves forming a first historical sequence from the historical load data of other users and calculating the noise level of each data point; dividing the first historical subsequence according to the current time period length and calculating a similarity index with the current load sequence of the target user; filtering reference historical data sequences with a similarity index ≥ a preset threshold; classifying all users according to each user characteristic, calculating a similarity index for the user load data under each category, and taking the average value of all categories as the degree of correlation between the characteristic and the electricity consumption behavior. Calculate electricity consumption similarity based on the category matching between similar users and the target user; By combining the environmental similarity between the reference period and the current period, the reflectivity of the reference data sequence is obtained; based on the theoretical line loss of similar users weighted by the reflectivity, the corrected theoretical line loss for users with unstable electricity consumption behavior is obtained.
7. The method for monitoring abnormal line loss based on user behavior according to claim 1, characterized in that, The formula for calculating the line loss deviation rate is: Wherein, ΔP user Indicates the stable theoretical line loss for a single user; ΔP user 'Indicates the theoretical line loss after correction for users with unstable electricity consumption behavior; ΔP a This represents the actual line loss value for the target transformer area during the current time period.
8. The method for monitoring abnormal line loss based on user behavior according to claim 1, characterized in that, Divide the deviation value of a single user by the sum of the deviation values of all users to obtain the abnormal contribution of a single user.
9. The method for monitoring abnormal line loss based on user behavior according to claim 8, characterized in that, The method of using abnormal contribution degree to mark users as abnormal and locate line loss specifically involves comparing the abnormal contribution degree of each user with a contribution reference threshold. If the abnormal contribution degree is greater than or equal to the contribution reference threshold, the user is marked as abnormal, and the abnormal line loss area is located based on the user's power information data and line node parameters.
10. A line loss anomaly monitoring system based on user behavior, characterized in that, include: The data processing module is used to collect power information data of all users in the target distribution area. The power information data includes each user's electricity consumption type, current time period power load data, offline historical time period power load data, electricity meter power supply data, and electricity meter sales data. The current period's power load data and the offline historical period's power load data are preprocessed and then merged. The behavior analysis module is used to determine the stability of user electricity consumption behavior based on the merged data of each user. It compares the merged data of a single user with a preset data value. If the data is less than the preset data value, the user is determined to be a user with unstable electricity consumption behavior. If the data volume exceeds the preset value, user electricity consumption characteristics are extracted based on the merged data, the load fluctuation index is calculated to match the electricity consumption pattern, and the stability of electricity consumption behavior is determined based on the consistency between the load fluctuation index and the electricity consumption pattern. The line loss calculation module is used to calculate the theoretical line loss for users with stable electricity consumption behavior and users with unstable electricity consumption behavior respectively, and to sum up the theoretical line losses of all users to obtain the total theoretical line loss of the target transformer area. The anomaly detection module is used to calculate the actual line loss value of the target transformer area in the current time period based on the sum of the total power supply of the target transformer area and the electricity sales data of all users. The line loss deviation rate is calculated based on the actual line loss value and the total theoretical line loss to determine line loss anomalies. The marking and processing module is used to calculate the deviation between the actual line loss value and the theoretical line loss value for each user when it is determined that there is an abnormal line loss in the target area. The module obtains the abnormal contribution based on the percentage of the deviation value, marks the user as abnormal based on the abnormal contribution, and locates the line loss.